2100 lines
269 KiB
Plaintext
2100 lines
269 KiB
Plaintext
{
|
||
"nbformat": 4,
|
||
"nbformat_minor": 0,
|
||
"metadata": {
|
||
"colab": {
|
||
"provenance": [],
|
||
"authorship_tag": "ABX9TyODEXOKOlfyD42Q6UHAhHN8",
|
||
"include_colab_link": true
|
||
},
|
||
"kernelspec": {
|
||
"name": "python3",
|
||
"display_name": "Python 3"
|
||
},
|
||
"language_info": {
|
||
"name": "python"
|
||
}
|
||
},
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "view-in-github",
|
||
"colab_type": "text"
|
||
},
|
||
"source": [
|
||
"<a href=\"https://colab.research.google.com/github/casualcomputer/llm_google_colab/blob/main/setup_crewai_agents_google_colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"# Analyst agents to auto-explore datasets"
|
||
],
|
||
"metadata": {
|
||
"id": "LV3nP_sr3jMC"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"**Motivation**\n",
|
||
"\n",
|
||
"Data analysts live by joins. Combining multiple tables – customer details, sales figures, inventory levels – is fundamental to uncovering deeper business insights. But this process is fragile. The final analysis is only as strong as its weakest data link.\n",
|
||
"\n",
|
||
"Introduce just one dataset with quality issues into your sequence of joins, and the entire result becomes suspect. The more tables you bring into the mix, the higher the odds that at least one of them is flawed. Suddenly, that five-table join feels much riskier than a simple two-table lookup. This compounding risk underscores a crucial, often time-consuming step: rigorous data quality assessment before merging.\n",
|
||
"\n",
|
||
"So, how do we typically combat this risk? Before diving into complex joins or modeling, the diligent data analyst performs crucial exploratory data analysis (EDA) and quality checks on each input dataset. This isn't just a single step, but a well-trodden path involving several standard procedures.\n",
|
||
"\n"
|
||
],
|
||
"metadata": {
|
||
"id": "9P93UoEe4OzO"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
""
|
||
],
|
||
"metadata": {
|
||
"id": "WShWG64Du6tF"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"source": [
|
||
"!pip install summarytools langchain-google-genai crewai -q"
|
||
],
|
||
"metadata": {
|
||
"id": "O4_y09ytn-aK"
|
||
},
|
||
"execution_count": 5,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"**Establishing a Data Understanding Baseline**\n",
|
||
"\n",
|
||
"Before complex analysis, understanding each input dataset is crucial. While experienced analysts develop diverse techniques, a common baseline approach guides most initial data quality checks and exploration. This foundational process typically involves:\n",
|
||
"\n",
|
||
"1. Missing Values: Calculating the count and percentage of nulls per variable.\n",
|
||
"2. Continuous Distributions: Examining key statistics (mean, median, min, max, std dev) and outliers, often visualized with histograms.\n",
|
||
"3. Categorical Frequencies: Identifying unique values, their counts, and potential anomalies in categorical fields.\n",
|
||
"4. Trend analysis: Tracking key metrics over time (if applicable) to spot patterns or shifts.\n",
|
||
"5. etc.\n",
|
||
"\n",
|
||
"The example belows demonstrates using \"summarytools\" package in Python to summarize the famous titanic dataset."
|
||
],
|
||
"metadata": {
|
||
"id": "69rF3egFtNAu"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 32,
|
||
"metadata": {
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/",
|
||
"height": 1000
|
||
},
|
||
"id": "Tptn3IAGl513",
|
||
"outputId": "6c170613-bda4-4a85-f200-aff5594bd4c1"
|
||
},
|
||
"outputs": [
|
||
{
|
||
"output_type": "execute_result",
|
||
"data": {
|
||
"text/plain": [
|
||
"<pandas.io.formats.style.Styler at 0x7ec00e5c8390>"
|
||
],
|
||
"text/html": [
|
||
"<style type=\"text/css\">\n",
|
||
"#T_b42c0 thead>tr>th {\n",
|
||
" text-align: left;\n",
|
||
"}\n",
|
||
"#T_b42c0_row0_col0, #T_b42c0_row1_col0, #T_b42c0_row2_col0, #T_b42c0_row3_col0, #T_b42c0_row4_col0, #T_b42c0_row5_col0, #T_b42c0_row6_col0, #T_b42c0_row7_col0, #T_b42c0_row8_col0, #T_b42c0_row9_col0, #T_b42c0_row10_col0, #T_b42c0_row11_col0 {\n",
|
||
" text-align: left;\n",
|
||
" font-size: 12px;\n",
|
||
" vertical-align: middle;\n",
|
||
" width: 5%;\n",
|
||
" max-width: 50px;\n",
|
||
" min-width: 20px;\n",
|
||
"}\n",
|
||
"#T_b42c0_row0_col1, #T_b42c0_row1_col1, #T_b42c0_row2_col1, #T_b42c0_row3_col1, #T_b42c0_row4_col1, #T_b42c0_row5_col1, #T_b42c0_row6_col1, #T_b42c0_row7_col1, #T_b42c0_row8_col1, #T_b42c0_row9_col1, #T_b42c0_row10_col1, #T_b42c0_row11_col1 {\n",
|
||
" text-align: left;\n",
|
||
" font-size: 12px;\n",
|
||
" vertical-align: middle;\n",
|
||
" width: 15%;\n",
|
||
" max-width: 200px;\n",
|
||
" min-width: 100px;\n",
|
||
" word-break: break-word;\n",
|
||
"}\n",
|
||
"#T_b42c0_row0_col2, #T_b42c0_row1_col2, #T_b42c0_row2_col2, #T_b42c0_row3_col2, #T_b42c0_row4_col2, #T_b42c0_row5_col2, #T_b42c0_row6_col2, #T_b42c0_row7_col2, #T_b42c0_row8_col2, #T_b42c0_row9_col2, #T_b42c0_row10_col2, #T_b42c0_row11_col2 {\n",
|
||
" text-align: left;\n",
|
||
" font-size: 12px;\n",
|
||
" vertical-align: middle;\n",
|
||
" width: 30%;\n",
|
||
" min-width: 100px;\n",
|
||
"}\n",
|
||
"#T_b42c0_row0_col3, #T_b42c0_row1_col3, #T_b42c0_row2_col3, #T_b42c0_row3_col3, #T_b42c0_row4_col3, #T_b42c0_row5_col3, #T_b42c0_row6_col3, #T_b42c0_row7_col3, #T_b42c0_row8_col3, #T_b42c0_row9_col3, #T_b42c0_row10_col3, #T_b42c0_row11_col3 {\n",
|
||
" text-align: left;\n",
|
||
" font-size: 12px;\n",
|
||
" vertical-align: middle;\n",
|
||
" width: 25%;\n",
|
||
" min-width: 100px;\n",
|
||
"}\n",
|
||
"#T_b42c0_row0_col4, #T_b42c0_row1_col4, #T_b42c0_row2_col4, #T_b42c0_row3_col4, #T_b42c0_row4_col4, #T_b42c0_row5_col4, #T_b42c0_row6_col4, #T_b42c0_row7_col4, #T_b42c0_row8_col4, #T_b42c0_row9_col4, #T_b42c0_row10_col4, #T_b42c0_row11_col4 {\n",
|
||
" text-align: left;\n",
|
||
" font-size: 12px;\n",
|
||
" vertical-align: middle;\n",
|
||
" width: 20%;\n",
|
||
" min-width: 150px;\n",
|
||
"}\n",
|
||
"#T_b42c0_row0_col5, #T_b42c0_row1_col5, #T_b42c0_row2_col5, #T_b42c0_row3_col5, #T_b42c0_row4_col5, #T_b42c0_row5_col5, #T_b42c0_row6_col5, #T_b42c0_row7_col5, #T_b42c0_row8_col5, #T_b42c0_row9_col5, #T_b42c0_row10_col5, #T_b42c0_row11_col5 {\n",
|
||
" text-align: left;\n",
|
||
" font-size: 12px;\n",
|
||
" vertical-align: middle;\n",
|
||
" width: 10%;\n",
|
||
"}\n",
|
||
"</style>\n",
|
||
"<table id=\"T_b42c0\" class=\"dataframe\">\n",
|
||
" <caption><strong>Data Frame Summary</strong><br>titanic<br>Dimensions: 891 x 12<br>Duplicates: 0</caption>\n",
|
||
" <thead>\n",
|
||
" <tr>\n",
|
||
" <th id=\"T_b42c0_level0_col0\" class=\"col_heading level0 col0\" >No</th>\n",
|
||
" <th id=\"T_b42c0_level0_col1\" class=\"col_heading level0 col1\" >Variable</th>\n",
|
||
" <th id=\"T_b42c0_level0_col2\" class=\"col_heading level0 col2\" >Stats / Values</th>\n",
|
||
" <th id=\"T_b42c0_level0_col3\" class=\"col_heading level0 col3\" >Freqs / (% of Valid)</th>\n",
|
||
" <th id=\"T_b42c0_level0_col4\" class=\"col_heading level0 col4\" >Graph</th>\n",
|
||
" <th id=\"T_b42c0_level0_col5\" class=\"col_heading level0 col5\" >Missing</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row0_col0\" class=\"data row0 col0\" >1</td>\n",
|
||
" <td id=\"T_b42c0_row0_col1\" class=\"data row0 col1\" ><strong>PassengerId</strong><br>[int64]</td>\n",
|
||
" <td id=\"T_b42c0_row0_col2\" class=\"data row0 col2\" >Mean (sd) : 446.0 (257.4)<br>min < med < max:<br>1.0 < 446.0 < 891.0<br>IQR (CV) : 445.0 (1.7)</td>\n",
|
||
" <td id=\"T_b42c0_row0_col3\" class=\"data row0 col3\" >891 distinct values</td>\n",
|
||
" <td id=\"T_b42c0_row0_col4\" class=\"data row0 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row0_col5\" class=\"data row0 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row1_col0\" class=\"data row1 col0\" >2</td>\n",
|
||
" <td id=\"T_b42c0_row1_col1\" class=\"data row1 col1\" ><strong>Survived</strong><br>[int64]</td>\n",
|
||
" <td id=\"T_b42c0_row1_col2\" class=\"data row1 col2\" >1. 0<br>2. 1</td>\n",
|
||
" <td id=\"T_b42c0_row1_col3\" class=\"data row1 col3\" >549 (61.6%)<br>342 (38.4%)</td>\n",
|
||
" <td id=\"T_b42c0_row1_col4\" class=\"data row1 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row1_col5\" class=\"data row1 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row2_col0\" class=\"data row2 col0\" >3</td>\n",
|
||
" <td id=\"T_b42c0_row2_col1\" class=\"data row2 col1\" ><strong>Pclass</strong><br>[int64]</td>\n",
|
||
" <td id=\"T_b42c0_row2_col2\" class=\"data row2 col2\" >1. 3<br>2. 1<br>3. 2</td>\n",
|
||
" <td id=\"T_b42c0_row2_col3\" class=\"data row2 col3\" >491 (55.1%)<br>216 (24.2%)<br>184 (20.7%)</td>\n",
|
||
" <td id=\"T_b42c0_row2_col4\" class=\"data row2 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row2_col5\" class=\"data row2 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row3_col0\" class=\"data row3 col0\" >4</td>\n",
|
||
" <td id=\"T_b42c0_row3_col1\" class=\"data row3 col1\" ><strong>Name</strong><br>[object]</td>\n",
|
||
" <td id=\"T_b42c0_row3_col2\" class=\"data row3 col2\" >1. Dooley, Mr. Patrick<br>2. Braund, Mr. Owen Harris<br>3. Cumings, Mrs. John Bradley (Fl<br>4. Heikkinen, Miss. Laina<br>5. Futrelle, Mrs. Jacques Heath (<br>6. Allen, Mr. William Henry<br>7. Moran, Mr. James<br>8. McCarthy, Mr. Timothy J<br>9. Palsson, Master. Gosta Leonard<br>10. Johnson, Mrs. Oscar W (Elisabe<br>11. other</td>\n",
|
||
" <td id=\"T_b42c0_row3_col3\" class=\"data row3 col3\" >1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>881 (98.9%)</td>\n",
|
||
" <td id=\"T_b42c0_row3_col4\" class=\"data row3 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row3_col5\" class=\"data row3 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row4_col0\" class=\"data row4 col0\" >5</td>\n",
|
||
" <td id=\"T_b42c0_row4_col1\" class=\"data row4 col1\" ><strong>Sex</strong><br>[object]</td>\n",
|
||
" <td id=\"T_b42c0_row4_col2\" class=\"data row4 col2\" >1. male<br>2. female</td>\n",
|
||
" <td id=\"T_b42c0_row4_col3\" class=\"data row4 col3\" >577 (64.8%)<br>314 (35.2%)</td>\n",
|
||
" <td id=\"T_b42c0_row4_col4\" class=\"data row4 col4\" ><img src = \"data:image/png;base64, iVBORw0KGgoAAAANSUhEUgAAAJsAAAAuCAYAAAA/ZmtKAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAATlJREFUeJzt28Fpw0AURdE3QZhko0EIVIyKSLEpQt0IoVnExpvJwpAO/MbzfU8F3/hibKOXaq0CHJKkL0mX1ofg373Wem19xDMM8zx/j+M4tT4ED6WUI6X0EzG4YRzHaV3Xa8751vqYd3ee5+e2bdO+7xdJ8WKTpJzzbVmW39bHQNLja01IH60PwPsgNtgQG2yIDTbEBhtigw2xwYbYYENssCE22BAbbIgNNsQGG2KDDbHBZpAeD+21PgTx34ehlHJs2zYp8EN7PSmlHJLure94BgYvryfs4CUx5YNL9E+2sJ8SPQo95Ys8i+tR2Clf9Flcj6JP+fiF/UL4Uxc2xAYbYoMNscGG2GBDbLAhNtgQG2yIDTbEBhtigw2xwYbYYENssCE22ISd8kV8Tb0LPeWLPIvrEYMX2PwBCltq38NzG/wAAAAASUVORK5CYII=\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row4_col5\" class=\"data row4 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row5_col0\" class=\"data row5 col0\" >6</td>\n",
|
||
" <td id=\"T_b42c0_row5_col1\" class=\"data row5 col1\" ><strong>Age</strong><br>[float64]</td>\n",
|
||
" <td id=\"T_b42c0_row5_col2\" class=\"data row5 col2\" >Mean (sd) : 29.7 (14.5)<br>min < med < max:<br>0.4 < 28.0 < 80.0<br>IQR (CV) : 17.9 (2.0)</td>\n",
|
||
" <td id=\"T_b42c0_row5_col3\" class=\"data row5 col3\" >88 distinct values</td>\n",
|
||
" <td id=\"T_b42c0_row5_col4\" class=\"data row5 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row5_col5\" class=\"data row5 col5\" >177<br>(19.9%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row6_col0\" class=\"data row6 col0\" >7</td>\n",
|
||
" <td id=\"T_b42c0_row6_col1\" class=\"data row6 col1\" ><strong>SibSp</strong><br>[int64]</td>\n",
|
||
" <td id=\"T_b42c0_row6_col2\" class=\"data row6 col2\" >1. 0<br>2. 1<br>3. 2<br>4. 4<br>5. 3<br>6. 8<br>7. 5</td>\n",
|
||
" <td id=\"T_b42c0_row6_col3\" class=\"data row6 col3\" >608 (68.2%)<br>209 (23.5%)<br>28 (3.1%)<br>18 (2.0%)<br>16 (1.8%)<br>7 (0.8%)<br>5 (0.6%)</td>\n",
|
||
" <td id=\"T_b42c0_row6_col4\" class=\"data row6 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row6_col5\" class=\"data row6 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row7_col0\" class=\"data row7 col0\" >8</td>\n",
|
||
" <td id=\"T_b42c0_row7_col1\" class=\"data row7 col1\" ><strong>Parch</strong><br>[int64]</td>\n",
|
||
" <td id=\"T_b42c0_row7_col2\" class=\"data row7 col2\" >1. 0<br>2. 1<br>3. 2<br>4. 5<br>5. 3<br>6. 4<br>7. 6</td>\n",
|
||
" <td id=\"T_b42c0_row7_col3\" class=\"data row7 col3\" >678 (76.1%)<br>118 (13.2%)<br>80 (9.0%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>1 (0.1%)</td>\n",
|
||
" <td id=\"T_b42c0_row7_col4\" class=\"data row7 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row7_col5\" class=\"data row7 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row8_col0\" class=\"data row8 col0\" >9</td>\n",
|
||
" <td id=\"T_b42c0_row8_col1\" class=\"data row8 col1\" ><strong>Ticket</strong><br>[object]</td>\n",
|
||
" <td id=\"T_b42c0_row8_col2\" class=\"data row8 col2\" >1. 347082<br>2. 1601<br>3. CA. 2343<br>4. 3101295<br>5. CA 2144<br>6. 347088<br>7. 382652<br>8. S.O.C. 14879<br>9. 113760<br>10. 19950<br>11. other</td>\n",
|
||
" <td id=\"T_b42c0_row8_col3\" class=\"data row8 col3\" >7 (0.8%)<br>7 (0.8%)<br>7 (0.8%)<br>6 (0.7%)<br>6 (0.7%)<br>6 (0.7%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>4 (0.4%)<br>834 (93.6%)</td>\n",
|
||
" <td id=\"T_b42c0_row8_col4\" class=\"data row8 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row8_col5\" class=\"data row8 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row9_col0\" class=\"data row9 col0\" >10</td>\n",
|
||
" <td id=\"T_b42c0_row9_col1\" class=\"data row9 col1\" ><strong>Fare</strong><br>[float64]</td>\n",
|
||
" <td id=\"T_b42c0_row9_col2\" class=\"data row9 col2\" >Mean (sd) : 32.2 (49.7)<br>min < med < max:<br>0.0 < 14.5 < 512.3<br>IQR (CV) : 23.1 (0.6)</td>\n",
|
||
" <td id=\"T_b42c0_row9_col3\" class=\"data row9 col3\" >248 distinct values</td>\n",
|
||
" <td id=\"T_b42c0_row9_col4\" class=\"data row9 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row9_col5\" class=\"data row9 col5\" >0<br>(0.0%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row10_col0\" class=\"data row10 col0\" >11</td>\n",
|
||
" <td id=\"T_b42c0_row10_col1\" class=\"data row10 col1\" ><strong>Cabin</strong><br>[object]</td>\n",
|
||
" <td id=\"T_b42c0_row10_col2\" class=\"data row10 col2\" >1. nan<br>2. G6<br>3. C23 C25 C27<br>4. B96 B98<br>5. F2<br>6. D<br>7. E101<br>8. C22 C26<br>9. F33<br>10. C83<br>11. other</td>\n",
|
||
" <td id=\"T_b42c0_row10_col3\" class=\"data row10 col3\" >687 (77.1%)<br>4 (0.4%)<br>4 (0.4%)<br>4 (0.4%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>2 (0.2%)<br>175 (19.6%)</td>\n",
|
||
" <td id=\"T_b42c0_row10_col4\" class=\"data row10 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row10_col5\" class=\"data row10 col5\" >687<br>(77.1%)</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <td id=\"T_b42c0_row11_col0\" class=\"data row11 col0\" >12</td>\n",
|
||
" <td id=\"T_b42c0_row11_col1\" class=\"data row11 col1\" ><strong>Embarked</strong><br>[object]</td>\n",
|
||
" <td id=\"T_b42c0_row11_col2\" class=\"data row11 col2\" >1. S<br>2. C<br>3. Q<br>4. nan</td>\n",
|
||
" <td id=\"T_b42c0_row11_col3\" class=\"data row11 col3\" >644 (72.3%)<br>168 (18.9%)<br>77 (8.6%)<br>2 (0.2%)</td>\n",
|
||
" <td id=\"T_b42c0_row11_col4\" class=\"data row11 col4\" ><img src = \"data:image/png;base64, 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\"></img></td>\n",
|
||
" <td id=\"T_b42c0_row11_col5\" class=\"data row11 col5\" >2<br>(0.2%)</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"execution_count": 32
|
||
}
|
||
],
|
||
"source": [
|
||
"import pandas as pd # load example dataset\n",
|
||
"from summarytools import dfSummary\n",
|
||
"titanic = pd.read_csv('https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv')\n",
|
||
"df_summary_info = dfSummary(titanic)\n",
|
||
"df_summary_info"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"We are removing the image tags that visualize categorical variable distributions (under the \"graph\" column) from the dataset summary. This step ensures the remaining results can be saved purely as text in a .txt file, making it suitable for processing by an LLM."
|
||
],
|
||
"metadata": {
|
||
"id": "Yeu-WyXsvq7H"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"source": [
|
||
"print(\"Original Text:\")\n",
|
||
"print(df_summary_info.to_string())\n",
|
||
"\n",
|
||
"import re\n",
|
||
"\n",
|
||
"def remove_img_texts(html_text: str) -> str:\n",
|
||
" \"\"\"\n",
|
||
" Removes any text between <img ... </img> tags (including the tags)\n",
|
||
" from the given text.\n",
|
||
" \"\"\"\n",
|
||
" # This pattern matches an <img> tag with any attributes, followed by any content until a </img> tag.\n",
|
||
" pattern = re.compile(r'<img[^>]*>.*?</img>', re.DOTALL | re.IGNORECASE)\n",
|
||
" cleaned_text = pattern.sub('', html_text)\n",
|
||
" return cleaned_text\n",
|
||
"\n",
|
||
"# Example usage:\n",
|
||
"result = remove_img_texts(df_summary_info.to_string())\n",
|
||
"print(\"\\nCleaned Text:\")\n",
|
||
"print(result)\n",
|
||
"\n",
|
||
"# Optionally, save the cleaned text to a text file.\n",
|
||
"with open(\"df_summary_text.txt\", \"w\") as f:\n",
|
||
" f.write(result)\n",
|
||
"\n",
|
||
"# TODO: apply custom instructions on each row of text. instruct-fine tune, error rate analysis with custom dashboards or just version control of prompts and results like latitude"
|
||
],
|
||
"metadata": {
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/"
|
||
},
|
||
"id": "Z4rjQE548hZ7",
|
||
"outputId": "fda66e4d-1a27-4a6c-ff5f-a339939c3a1c"
|
||
},
|
||
"execution_count": 33,
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"Original Text:\n",
|
||
"No Variable Stats / Values Freqs / (% of Valid) Graph Missing\n",
|
||
"1 <strong>PassengerId</strong><br>[int64] Mean (sd) : 446.0 (257.4)<br>min < med < max:<br>1.0 < 446.0 < 891.0<br>IQR (CV) : 445.0 (1.7) 891 distinct values <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"2 <strong>Survived</strong><br>[int64] 1. 0<br>2. 1 549 (61.6%)<br>342 (38.4%) <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"3 <strong>Pclass</strong><br>[int64] 1. 3<br>2. 1<br>3. 2 491 (55.1%)<br>216 (24.2%)<br>184 (20.7%) <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"4 <strong>Name</strong><br>[object] 1. Dooley, Mr. Patrick<br>2. Braund, Mr. Owen Harris<br>3. Cumings, Mrs. John Bradley (Fl<br>4. Heikkinen, Miss. Laina<br>5. Futrelle, Mrs. Jacques Heath (<br>6. Allen, Mr. William Henry<br>7. Moran, Mr. James<br>8. McCarthy, Mr. Timothy J<br>9. Palsson, Master. Gosta Leonard<br>10. Johnson, Mrs. Oscar W (Elisabe<br>11. other 1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>881 (98.9%) <img src = \"data:image/png;base64, iVBORw0KGgoAAAANSUhEUgAAAJsAAAD+CAYAAAAtWHdlAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAA1xJREFUeJzt3MFpG2EURtE3Rjj2RkIYXELSg4tIsSlCRaQHYzyL2PFmskgWKSDcAeWcCv7FhYdgPi3btg0UbvZ+AP8PsZERGxmxkREbGbGRERsZsZERGxmxkblZluXLsix3ez+E63czM59n5tPeD+H6OaNkxEZGbGTERkZsZMRGRmxkxEZGbGTERkZsZMRGRmxkxEZGbGTERuZmZr7PzM+9H8L1W/yLERVnlIzYyFhXkbGuIuOMkhEbGbGRERsZsZERGxmxkREbGbGRERsZsZERGxmxkREbGbGRMXghY/BCxhklIzYyBi9kDF7IOKNkxEZGbGTERkZsZMRGRmxkxEZGbGTERkZsZMRGRmxkxEZGbGQMXsgYvJBxRsmIjYzYyFhXkbGuIuOMkhEbGbGRERsZsZERGxmxkREbGbGRERsZsZERGxmxkREbGbGRsa4iY11FxhklIzYyBi9kDF7IOKNkxEZGbGTERkZsZMRGRmxkxEZGbGTERkZsZMRGRmxkxEZGbGQMXsgYvJBxRsmIjYzBCxmDFzLOKBmxkREbGbGRERsZsZERGxmxkREbGbGRERsZsZERGxmxkREbGbGRsa4iY11FxhklIzYy1lVkrKvIOKNkxEZGbGTERkZsZMRGRmxkxEZGbGTERkZsZMRGRmxkxEZGbGQMXsgYvJBxRsmIjYzBCxmDFzLOKBmxkREbGbGRERsZsZERGxmxkREbGbGRERsZsZERGxmxkREbGYMXMgYvZJxRMmIjIzYy1lVkrKvIOKNkxEZGbGTERkZsZMRGRmxkxEZGbGTERkZsZMRGRmxkxEZGbGSsq8hYV5FxRsmIjYzBCxmDFzLOKBmxkREbGbGRERsZsZERGxmxkREbGbGRERsZsZERGxmxkREbGYMXMgYvZJxRMsvM3M/M7d4P4ap9bNv2dnh4ePh6PB7Pe7+G67Wu68uyLN8Ox+Px/PT09HY6nd73fhTX5/X19e5yuZyfn59vDzMzp9Pp/fHx8cfeD+Nq3c/4gUBIbGTERkZsZMRGRmxkxEZGbGTERkZsZMRGRmxkxEbmMPP7M5C9H8J1+rutw7quL5fL5Tx/PgOBf21d15eZ+fBZOIWPbdverKvI+IFARmxkxEZGbGTERkZsZMRGRmxkxEbmF8IHaTn++fMrAAAAAElFTkSuQmCC\"></img> 0<br>(0.0%)\n",
|
||
"5 <strong>Sex</strong><br>[object] 1. male<br>2. female 577 (64.8%)<br>314 (35.2%) <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"6 <strong>Age</strong><br>[float64] Mean (sd) : 29.7 (14.5)<br>min < med < max:<br>0.4 < 28.0 < 80.0<br>IQR (CV) : 17.9 (2.0) 88 distinct values <img src = \"data:image/png;base64, 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\"></img> 177<br>(19.9%)\n",
|
||
"7 <strong>SibSp</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 4<br>5. 3<br>6. 8<br>7. 5 608 (68.2%)<br>209 (23.5%)<br>28 (3.1%)<br>18 (2.0%)<br>16 (1.8%)<br>7 (0.8%)<br>5 (0.6%) <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"8 <strong>Parch</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 5<br>5. 3<br>6. 4<br>7. 6 678 (76.1%)<br>118 (13.2%)<br>80 (9.0%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>1 (0.1%) <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"9 <strong>Ticket</strong><br>[object] 1. 347082<br>2. 1601<br>3. CA. 2343<br>4. 3101295<br>5. CA 2144<br>6. 347088<br>7. 382652<br>8. S.O.C. 14879<br>9. 113760<br>10. 19950<br>11. other 7 (0.8%)<br>7 (0.8%)<br>7 (0.8%)<br>6 (0.7%)<br>6 (0.7%)<br>6 (0.7%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>4 (0.4%)<br>834 (93.6%) <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"10 <strong>Fare</strong><br>[float64] Mean (sd) : 32.2 (49.7)<br>min < med < max:<br>0.0 < 14.5 < 512.3<br>IQR (CV) : 23.1 (0.6) 248 distinct values <img src = \"data:image/png;base64, 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\"></img> 0<br>(0.0%)\n",
|
||
"11 <strong>Cabin</strong><br>[object] 1. nan<br>2. G6<br>3. C23 C25 C27<br>4. B96 B98<br>5. F2<br>6. D<br>7. E101<br>8. C22 C26<br>9. F33<br>10. C83<br>11. other 687 (77.1%)<br>4 (0.4%)<br>4 (0.4%)<br>4 (0.4%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>2 (0.2%)<br>175 (19.6%) <img src = \"data:image/png;base64, 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\"></img> 687<br>(77.1%)\n",
|
||
"12 <strong>Embarked</strong><br>[object] 1. S<br>2. C<br>3. Q<br>4. nan 644 (72.3%)<br>168 (18.9%)<br>77 (8.6%)<br>2 (0.2%) <img src = \"data:image/png;base64, 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\"></img> 2<br>(0.2%)\n",
|
||
"\n",
|
||
"\n",
|
||
"Cleaned Text:\n",
|
||
"No Variable Stats / Values Freqs / (% of Valid) Graph Missing\n",
|
||
"1 <strong>PassengerId</strong><br>[int64] Mean (sd) : 446.0 (257.4)<br>min < med < max:<br>1.0 < 446.0 < 891.0<br>IQR (CV) : 445.0 (1.7) 891 distinct values 0<br>(0.0%)\n",
|
||
"2 <strong>Survived</strong><br>[int64] 1. 0<br>2. 1 549 (61.6%)<br>342 (38.4%) 0<br>(0.0%)\n",
|
||
"3 <strong>Pclass</strong><br>[int64] 1. 3<br>2. 1<br>3. 2 491 (55.1%)<br>216 (24.2%)<br>184 (20.7%) 0<br>(0.0%)\n",
|
||
"4 <strong>Name</strong><br>[object] 1. Dooley, Mr. Patrick<br>2. Braund, Mr. Owen Harris<br>3. Cumings, Mrs. John Bradley (Fl<br>4. Heikkinen, Miss. Laina<br>5. Futrelle, Mrs. Jacques Heath (<br>6. Allen, Mr. William Henry<br>7. Moran, Mr. James<br>8. McCarthy, Mr. Timothy J<br>9. Palsson, Master. Gosta Leonard<br>10. Johnson, Mrs. Oscar W (Elisabe<br>11. other 1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>881 (98.9%) 0<br>(0.0%)\n",
|
||
"5 <strong>Sex</strong><br>[object] 1. male<br>2. female 577 (64.8%)<br>314 (35.2%) 0<br>(0.0%)\n",
|
||
"6 <strong>Age</strong><br>[float64] Mean (sd) : 29.7 (14.5)<br>min < med < max:<br>0.4 < 28.0 < 80.0<br>IQR (CV) : 17.9 (2.0) 88 distinct values 177<br>(19.9%)\n",
|
||
"7 <strong>SibSp</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 4<br>5. 3<br>6. 8<br>7. 5 608 (68.2%)<br>209 (23.5%)<br>28 (3.1%)<br>18 (2.0%)<br>16 (1.8%)<br>7 (0.8%)<br>5 (0.6%) 0<br>(0.0%)\n",
|
||
"8 <strong>Parch</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 5<br>5. 3<br>6. 4<br>7. 6 678 (76.1%)<br>118 (13.2%)<br>80 (9.0%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>1 (0.1%) 0<br>(0.0%)\n",
|
||
"9 <strong>Ticket</strong><br>[object] 1. 347082<br>2. 1601<br>3. CA. 2343<br>4. 3101295<br>5. CA 2144<br>6. 347088<br>7. 382652<br>8. S.O.C. 14879<br>9. 113760<br>10. 19950<br>11. other 7 (0.8%)<br>7 (0.8%)<br>7 (0.8%)<br>6 (0.7%)<br>6 (0.7%)<br>6 (0.7%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>4 (0.4%)<br>834 (93.6%) 0<br>(0.0%)\n",
|
||
"10 <strong>Fare</strong><br>[float64] Mean (sd) : 32.2 (49.7)<br>min < med < max:<br>0.0 < 14.5 < 512.3<br>IQR (CV) : 23.1 (0.6) 248 distinct values 0<br>(0.0%)\n",
|
||
"11 <strong>Cabin</strong><br>[object] 1. nan<br>2. G6<br>3. C23 C25 C27<br>4. B96 B98<br>5. F2<br>6. D<br>7. E101<br>8. C22 C26<br>9. F33<br>10. C83<br>11. other 687 (77.1%)<br>4 (0.4%)<br>4 (0.4%)<br>4 (0.4%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>2 (0.2%)<br>175 (19.6%) 687<br>(77.1%)\n",
|
||
"12 <strong>Embarked</strong><br>[object] 1. S<br>2. C<br>3. Q<br>4. nan 644 (72.3%)<br>168 (18.9%)<br>77 (8.6%)<br>2 (0.2%) 2<br>(0.2%)\n",
|
||
"\n"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"# Agent to mimic data analyst and other roles"
|
||
],
|
||
"metadata": {
|
||
"id": "pzocdLs5xUUQ"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"## Input the Gemini API from Google AI Studio"
|
||
],
|
||
"metadata": {
|
||
"id": "1nYi2X0Jxe9s"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"source": [
|
||
"api_key = input(\"Please enter your API key: \")\n",
|
||
"os.environ[\"GEMINI_API_KEY\"] = api_key\n",
|
||
"print(\"API key has been set.\")"
|
||
],
|
||
"metadata": {
|
||
"id": "wKwptGcfxo6e"
|
||
},
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"## Create three agents that analyze the dataset"
|
||
],
|
||
"metadata": {
|
||
"id": "FLk2Tisd1G0N"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"source": [
|
||
"We demonstrate how to automate the preliminary steps of understanding a new dataset, specifically the Titanic dataset, using the CrewAI framework and Google's Gemini Flash model. Instead of manual exploration, we orchestrate a team of specialized AI agents – a Data Quality Analyst, a Statistical Analyst, and a Predictive Modeling Advisor – to examine a comprehensive summary of the data. This method allows for a quick and insightful assessment of potential data quality issues like missing values. It highlights statistical anomalies such as outliers, and even suggests which features might be most valuable for future predictive modeling efforts, all without writing extensive exploratory code."
|
||
],
|
||
"metadata": {
|
||
"id": "TQA6uFNt1nXy"
|
||
}
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"source": [
|
||
"import os\n",
|
||
"import pandas as pd\n",
|
||
"from crewai import Agent, Task, Crew, Process\n",
|
||
"from langchain_google_genai import ChatGoogleGenerativeAI\n",
|
||
"from summarytools import dfSummary\n",
|
||
"from crewai import Agent, Task, Crew, LLM\n",
|
||
"\n",
|
||
"clean_summary = remove_img_texts(df_summary_info.to_string())\n",
|
||
"llm = LLM(model=\"gemini/gemini-2.0-flash\")\n",
|
||
"\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"# 2) Load the Titanic dataset and generate a text summary using summarytools.\n",
|
||
"#\n",
|
||
"# The dfSummary() output (a pandas Styler) is converted to plain text with .to_string().\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"titanic = pd.read_csv(\"https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv\")\n",
|
||
"df_summary_info = dfSummary(titanic).to_string()\n",
|
||
"\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"# 3) Create AI team agents in a CrewAI style.\n",
|
||
"#\n",
|
||
"# Each agent is provided with a role, goal, and backstory. They use Gemini Pro via llm.\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"data_quality_agent = Agent(\n",
|
||
" role=\"Data Quality Analyst\",\n",
|
||
" goal=\"Identify columns with data quality issues such as those with more than 20% missing values.\",\n",
|
||
" backstory=\"An experienced data analyst who excels at detecting data quality issues and anomalies in datasets.\",\n",
|
||
" verbose=True,\n",
|
||
" allow_delegation=False,\n",
|
||
" llm=llm\n",
|
||
")\n",
|
||
"\n",
|
||
"statistical_agent = Agent(\n",
|
||
" role=\"Statistical Analyst\",\n",
|
||
" goal=\"Examine numeric columns for potential outliers where maximum values greatly exceed the mean.\",\n",
|
||
" backstory=\"A meticulous statistician with expertise in numeric data distributions and anomaly detection.\",\n",
|
||
" verbose=True,\n",
|
||
" allow_delegation=False,\n",
|
||
" llm=llm\n",
|
||
")\n",
|
||
"\n",
|
||
"insight_agent = Agent(\n",
|
||
" role=\"Predictive Modeling Advisor\",\n",
|
||
" goal=\"Recommend which columns appear most informative for predictive modeling.\",\n",
|
||
" backstory=\"A seasoned machine learning consultant skilled in feature engineering and predictive analysis.\",\n",
|
||
" verbose=True,\n",
|
||
" allow_delegation=True,\n",
|
||
" llm=llm\n",
|
||
")\n",
|
||
"\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"# 4) Create tasks for each agent by embedding the dataset summary (as text).\n",
|
||
"#\n",
|
||
"# Note: We now include an 'expected_output' field as required by the Task model.\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"task1 = Task(\n",
|
||
" description=f\"\"\"Data Quality Task:\n",
|
||
"Examine the dataset summary below and identify columns with significant data quality issues or concerns.\n",
|
||
"Focus primarily on those columns with more than 20% missing values, and consider columns with unusual uniqueness metrics.\n",
|
||
"Provide detailed insights including the percentage of missing data and any recommendations for cleaning.\n",
|
||
"Dataset Summary:\n",
|
||
"{clean_summary}\"\"\",\n",
|
||
" expected_output=\"A detailed list of column names with significant missing data issues along with insights and recommendations for data cleaning.\",\n",
|
||
" agent=data_quality_agent\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"task2 = Task(\n",
|
||
" description=f\"\"\"Statistical Analysis Task:\n",
|
||
"Review the dataset summary below and identify any numeric columns that exhibit potential outlier behavior.\n",
|
||
"Specifically, look for columns where the maximum value far exceeds the mean (e.g., max > 3 × mean) and any unusual spread in the data.\n",
|
||
"Include a brief explanation of why each identified column may be problematic. Provide any recommendations for further investigation.\n",
|
||
"Dataset Summary:\n",
|
||
"{clean_summary}\"\"\",\n",
|
||
" expected_output=\"A detailed list of numeric columns with potential outlier issues, including a brief explanation for each.\",\n",
|
||
" agent=statistical_agent\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"task3 = Task(\n",
|
||
" description=f\"\"\"Predictive Modeling Insight Task:\n",
|
||
"Based on the dataset summary below, recommend which columns might be most informative for building a predictive model.\n",
|
||
"Dataset Summary:\n",
|
||
"{clean_summary}\"\"\",\n",
|
||
" expected_output=\"A list of column names that are likely to be most informative for predictive modeling.\",\n",
|
||
" agent=insight_agent\n",
|
||
")\n",
|
||
"\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"# 5) Assemble the Crew and execute the tasks sequentially.\n",
|
||
"#\n",
|
||
"# The Crew (ManagerAgent) runs the tasks one by one.\n",
|
||
"# -----------------------------------------------------------------------------\n",
|
||
"crew = Crew(\n",
|
||
" agents=[data_quality_agent, statistical_agent, insight_agent],\n",
|
||
" tasks=[task1, task2, task3],\n",
|
||
" verbose=True,\n",
|
||
" process=Process.sequential,\n",
|
||
")\n",
|
||
"\n",
|
||
"crew_output = crew.kickoff()\n",
|
||
"\n",
|
||
"print(\"\\nCrew Output:\")\n",
|
||
"print(crew_output)\n"
|
||
],
|
||
"metadata": {
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/",
|
||
"height": 1000
|
||
},
|
||
"id": "UDmAXJ6EhaCQ",
|
||
"outputId": "1bdccf3f-9f70-4b1e-9e23-e4ea3a4bd77b"
|
||
},
|
||
"execution_count": 35,
|
||
"outputs": [
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[36m╭─\u001b[0m\u001b[36m───────────────────────────────────────────\u001b[0m\u001b[36m Crew Execution Started \u001b[0m\u001b[36m────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
|
||
"\u001b[36m│\u001b[0m \u001b[36m│\u001b[0m\n",
|
||
"\u001b[36m│\u001b[0m \u001b[1;36mCrew Execution Started\u001b[0m \u001b[36m│\u001b[0m\n",
|
||
"\u001b[36m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[36mcrew\u001b[0m \u001b[36m│\u001b[0m\n",
|
||
"\u001b[36m│\u001b[0m \u001b[37mID: \u001b[0m\u001b[36m29f787f1-e6ba-4749-8b57-97e51a2c4aa5\u001b[0m \u001b[36m│\u001b[0m\n",
|
||
"\u001b[36m│\u001b[0m \u001b[36m│\u001b[0m\n",
|
||
"\u001b[36m│\u001b[0m \u001b[36m│\u001b[0m\n",
|
||
"\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭──────────────────────────────────────────── Crew Execution Started ─────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">Crew Execution Started</span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #008080; text-decoration-color: #008080\">crew</span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">ID: </span><span style=\"color: #008080; text-decoration-color: #008080\">29f787f1-e6ba-4749-8b57-97e51a2c4aa5</span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
|
||
"<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mData Quality Analyst\u001b[00m\n",
|
||
"\u001b[95m## Task:\u001b[00m \u001b[92mData Quality Task:\n",
|
||
"Examine the dataset summary below and identify columns with significant data quality issues or concerns.\n",
|
||
"Focus primarily on those columns with more than 20% missing values, and consider columns with unusual uniqueness metrics.\n",
|
||
"Provide detailed insights including the percentage of missing data and any recommendations for cleaning.\n",
|
||
"Dataset Summary:\n",
|
||
"No Variable Stats / Values Freqs / (% of Valid) Graph Missing\n",
|
||
"1 <strong>PassengerId</strong><br>[int64] Mean (sd) : 446.0 (257.4)<br>min < med < max:<br>1.0 < 446.0 < 891.0<br>IQR (CV) : 445.0 (1.7) 891 distinct values 0<br>(0.0%)\n",
|
||
"2 <strong>Survived</strong><br>[int64] 1. 0<br>2. 1 549 (61.6%)<br>342 (38.4%) 0<br>(0.0%)\n",
|
||
"3 <strong>Pclass</strong><br>[int64] 1. 3<br>2. 1<br>3. 2 491 (55.1%)<br>216 (24.2%)<br>184 (20.7%) 0<br>(0.0%)\n",
|
||
"4 <strong>Name</strong><br>[object] 1. Dooley, Mr. Patrick<br>2. Braund, Mr. Owen Harris<br>3. Cumings, Mrs. John Bradley (Fl<br>4. Heikkinen, Miss. Laina<br>5. Futrelle, Mrs. Jacques Heath (<br>6. Allen, Mr. William Henry<br>7. Moran, Mr. James<br>8. McCarthy, Mr. Timothy J<br>9. Palsson, Master. Gosta Leonard<br>10. Johnson, Mrs. Oscar W (Elisabe<br>11. other 1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>881 (98.9%) 0<br>(0.0%)\n",
|
||
"5 <strong>Sex</strong><br>[object] 1. male<br>2. female 577 (64.8%)<br>314 (35.2%) 0<br>(0.0%)\n",
|
||
"6 <strong>Age</strong><br>[float64] Mean (sd) : 29.7 (14.5)<br>min < med < max:<br>0.4 < 28.0 < 80.0<br>IQR (CV) : 17.9 (2.0) 88 distinct values 177<br>(19.9%)\n",
|
||
"7 <strong>SibSp</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 4<br>5. 3<br>6. 8<br>7. 5 608 (68.2%)<br>209 (23.5%)<br>28 (3.1%)<br>18 (2.0%)<br>16 (1.8%)<br>7 (0.8%)<br>5 (0.6%) 0<br>(0.0%)\n",
|
||
"8 <strong>Parch</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 5<br>5. 3<br>6. 4<br>7. 6 678 (76.1%)<br>118 (13.2%)<br>80 (9.0%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>1 (0.1%) 0<br>(0.0%)\n",
|
||
"9 <strong>Ticket</strong><br>[object] 1. 347082<br>2. 1601<br>3. CA. 2343<br>4. 3101295<br>5. CA 2144<br>6. 347088<br>7. 382652<br>8. S.O.C. 14879<br>9. 113760<br>10. 19950<br>11. other 7 (0.8%)<br>7 (0.8%)<br>7 (0.8%)<br>6 (0.7%)<br>6 (0.7%)<br>6 (0.7%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>4 (0.4%)<br>834 (93.6%) 0<br>(0.0%)\n",
|
||
"10 <strong>Fare</strong><br>[float64] Mean (sd) : 32.2 (49.7)<br>min < med < max:<br>0.0 < 14.5 < 512.3<br>IQR (CV) : 23.1 (0.6) 248 distinct values 0<br>(0.0%)\n",
|
||
"11 <strong>Cabin</strong><br>[object] 1. nan<br>2. G6<br>3. C23 C25 C27<br>4. B96 B98<br>5. F2<br>6. D<br>7. E101<br>8. C22 C26<br>9. F33<br>10. C83<br>11. other 687 (77.1%)<br>4 (0.4%)<br>4 (0.4%)<br>4 (0.4%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>2 (0.2%)<br>175 (19.6%) 687<br>(77.1%)\n",
|
||
"12 <strong>Embarked</strong><br>[object] 1. S<br>2. C<br>3. Q<br>4. nan 644 (72.3%)<br>168 (18.9%)<br>77 (8.6%)<br>2 (0.2%) 2<br>(0.2%)\n",
|
||
"\u001b[00m\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mData Quality Analyst\u001b[00m\n",
|
||
"\u001b[95m## Final Answer:\u001b[00m \u001b[92m\n",
|
||
"**Data Quality Analysis and Recommendations**\n",
|
||
"\n",
|
||
"Based on the provided dataset summary, the following columns exhibit data quality issues that warrant attention:\n",
|
||
"\n",
|
||
"1. **Age:**\n",
|
||
"\n",
|
||
"* **Missing Values:** 177 missing values (19.9%). While this is close to the 20% threshold, it's still a substantial amount of missing data that could bias analyses.\n",
|
||
"* **Recommendation:**\n",
|
||
" * **Imputation:** Consider using imputation techniques to fill in the missing age values. Simple methods like mean or median imputation could be used, but more sophisticated methods like regression imputation or using machine learning models to predict age based on other features (e.g., Pclass, Sex, SibSp, Parch) might be more appropriate. The choice of imputation method should be guided by the nature of the data and the goals of the analysis.\n",
|
||
" * **Consider creating a new feature:** Create a new feature 'Age_Missing' that indicates whether the age was originally missing. This allows the model to capture any potential information encoded in the missingness itself.\n",
|
||
"\n",
|
||
"2. **Cabin:**\n",
|
||
"\n",
|
||
"* **Missing Values:** 687 missing values (77.1%). This is a very high percentage of missing data.\n",
|
||
"* **Recommendation:**\n",
|
||
" * **Drop the column:** Given the high percentage of missing values, the simplest approach would be to drop the column entirely. However, this might result in loss of potentially useful information.\n",
|
||
" * **Imputation with caution:** If you suspect the cabin information is important, you could attempt to impute the missing values. A common approach is to create a new category for missing values (e.g., \"Unknown\"). However, be aware that this could introduce bias if the missingness is not random.\n",
|
||
" * **Feature Engineering:** It might be more useful to extract the first letter of the cabin to represent the cabin type (e.g., A, B, C). Then, create a separate binary variable indicating whether the cabin information was missing. This would help to retain some information from the 'Cabin' column while addressing the large number of missing entries.\n",
|
||
" * **Investigate Missingness:** Determine if the missingness of the 'Cabin' column is related to other variables (e.g. Pclass). Perhaps passengers in certain classes were less likely to have cabin information recorded.\n",
|
||
"\n",
|
||
"3. **Embarked:**\n",
|
||
"\n",
|
||
"* **Missing Values:** 2 missing values (0.2%). This is a small percentage of missing data.\n",
|
||
"* **Recommendation:**\n",
|
||
" * **Imputation:** Since only 2 values are missing, simple imputation is feasible. You could impute with the most frequent value (mode), which is 'S' in this case. Alternatively, you could investigate the passengers with missing 'Embarked' values and try to determine their port of embarkation based on other information (e.g., ticket number, name).\n",
|
||
"\n",
|
||
"**Summary Table**\n",
|
||
"\n",
|
||
"| Column | Missing Values (%) | Recommendation |\n",
|
||
"|------------|--------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n",
|
||
"| Age | 19.9% | Imputation (mean, median, regression, or ML-based). Consider creating a new 'Age_Missing' feature. |\n",
|
||
"| Cabin | 77.1% | Consider dropping the column, imputing with a new category (e.g., \"Unknown\"), or feature engineering to extract cabin type and create a missingness indicator. Investigate relationship between missingness and other features. |\n",
|
||
"| Embarked | 0.2% | Impute with the mode ('S') or investigate the specific passengers to determine their port of embarkation. |\n",
|
||
"\n",
|
||
"By addressing these data quality issues, you can improve the reliability and validity of your analyses and models. The specific cleaning approach should be chosen based on the context of the analysis and the potential impact on the results.\u001b[00m\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"└── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
" \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"└── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[32m╭─\u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m Task Completion \u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m─╮\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[1;32mTask Completed\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[32m27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mAgent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000\">╭──────────────────────────────────────────────── Task Completion ────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">Task Completed</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #008000; text-decoration-color: #008000\">27b3e8e5-4f73-4516-8113-ca44b6419eb4</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mStatistical Analyst\u001b[00m\n",
|
||
"\u001b[95m## Task:\u001b[00m \u001b[92mStatistical Analysis Task:\n",
|
||
"Review the dataset summary below and identify any numeric columns that exhibit potential outlier behavior.\n",
|
||
"Specifically, look for columns where the maximum value far exceeds the mean (e.g., max > 3 × mean) and any unusual spread in the data.\n",
|
||
"Include a brief explanation of why each identified column may be problematic. Provide any recommendations for further investigation.\n",
|
||
"Dataset Summary:\n",
|
||
"No Variable Stats / Values Freqs / (% of Valid) Graph Missing\n",
|
||
"1 <strong>PassengerId</strong><br>[int64] Mean (sd) : 446.0 (257.4)<br>min < med < max:<br>1.0 < 446.0 < 891.0<br>IQR (CV) : 445.0 (1.7) 891 distinct values 0<br>(0.0%)\n",
|
||
"2 <strong>Survived</strong><br>[int64] 1. 0<br>2. 1 549 (61.6%)<br>342 (38.4%) 0<br>(0.0%)\n",
|
||
"3 <strong>Pclass</strong><br>[int64] 1. 3<br>2. 1<br>3. 2 491 (55.1%)<br>216 (24.2%)<br>184 (20.7%) 0<br>(0.0%)\n",
|
||
"4 <strong>Name</strong><br>[object] 1. Dooley, Mr. Patrick<br>2. Braund, Mr. Owen Harris<br>3. Cumings, Mrs. John Bradley (Fl<br>4. Heikkinen, Miss. Laina<br>5. Futrelle, Mrs. Jacques Heath (<br>6. Allen, Mr. William Henry<br>7. Moran, Mr. James<br>8. McCarthy, Mr. Timothy J<br>9. Palsson, Master. Gosta Leonard<br>10. Johnson, Mrs. Oscar W (Elisabe<br>11. other 1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>881 (98.9%) 0<br>(0.0%)\n",
|
||
"5 <strong>Sex</strong><br>[object] 1. male<br>2. female 577 (64.8%)<br>314 (35.2%) 0<br>(0.0%)\n",
|
||
"6 <strong>Age</strong><br>[float64] Mean (sd) : 29.7 (14.5)<br>min < med < max:<br>0.4 < 28.0 < 80.0<br>IQR (CV) : 17.9 (2.0) 88 distinct values 177<br>(19.9%)\n",
|
||
"7 <strong>SibSp</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 4<br>5. 3<br>6. 8<br>7. 5 608 (68.2%)<br>209 (23.5%)<br>28 (3.1%)<br>18 (2.0%)<br>16 (1.8%)<br>7 (0.8%)<br>5 (0.6%) 0<br>(0.0%)\n",
|
||
"8 <strong>Parch</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 5<br>5. 3<br>6. 4<br>7. 6 678 (76.1%)<br>118 (13.2%)<br>80 (9.0%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>1 (0.1%) 0<br>(0.0%)\n",
|
||
"9 <strong>Ticket</strong><br>[object] 1. 347082<br>2. 1601<br>3. CA. 2343<br>4. 3101295<br>5. CA 2144<br>6. 347088<br>7. 382652<br>8. S.O.C. 14879<br>9. 113760<br>10. 19950<br>11. other 7 (0.8%)<br>7 (0.8%)<br>7 (0.8%)<br>6 (0.7%)<br>6 (0.7%)<br>6 (0.7%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>4 (0.4%)<br>834 (93.6%) 0<br>(0.0%)\n",
|
||
"10 <strong>Fare</strong><br>[float64] Mean (sd) : 32.2 (49.7)<br>min < med < max:<br>0.0 < 14.5 < 512.3<br>IQR (CV) : 23.1 (0.6) 248 distinct values 0<br>(0.0%)\n",
|
||
"11 <strong>Cabin</strong><br>[object] 1. nan<br>2. G6<br>3. C23 C25 C27<br>4. B96 B98<br>5. F2<br>6. D<br>7. E101<br>8. C22 C26<br>9. F33<br>10. C83<br>11. other 687 (77.1%)<br>4 (0.4%)<br>4 (0.4%)<br>4 (0.4%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>2 (0.2%)<br>175 (19.6%) 687<br>(77.1%)\n",
|
||
"12 <strong>Embarked</strong><br>[object] 1. S<br>2. C<br>3. Q<br>4. nan 644 (72.3%)<br>168 (18.9%)<br>77 (8.6%)<br>2 (0.2%) 2<br>(0.2%)\n",
|
||
"\u001b[00m\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mStatistical Analyst\u001b[00m\n",
|
||
"\u001b[95m## Final Answer:\u001b[00m \u001b[92m\n",
|
||
"Here's a detailed analysis of the numeric columns, highlighting potential outlier issues and recommendations for further investigation:\n",
|
||
"\n",
|
||
"**Numeric Columns with Potential Outliers:**\n",
|
||
"\n",
|
||
"1. **PassengerId:**\n",
|
||
"\n",
|
||
"* **Stats:** Mean: 446.0, Max: 891.0\n",
|
||
"* **Analysis:** While the maximum is exactly double the mean, this is not necessarily an outlier issue for an index column. PassengerId is simply an identifier and doesn't represent a measured quantity. The values are also evenly distributed with a regular IQR.\n",
|
||
"* **Recommendation:** No action needed.\n",
|
||
"\n",
|
||
"2. **Survived:**\n",
|
||
"\n",
|
||
"* **Stats:** Values: 0, 1\n",
|
||
"* **Analysis:** This is a binary categorical variable encoded numerically. Outlier analysis is not relevant here.\n",
|
||
"* **Recommendation:** No action needed.\n",
|
||
"\n",
|
||
"3. **Pclass:**\n",
|
||
"\n",
|
||
"* **Stats:** Values: 1, 2, 3\n",
|
||
"* **Analysis:** This is an ordinal categorical variable encoded numerically. Outlier analysis is not relevant here.\n",
|
||
"* **Recommendation:** No action needed.\n",
|
||
"\n",
|
||
"4. **Age:**\n",
|
||
"\n",
|
||
"* **Stats:** Mean: 29.7, Max: 80.0\n",
|
||
"* **Analysis:** The maximum age (80) is significantly higher than the mean (29.7), although not exceeding three times the mean. Given the context of the data (passengers on the Titanic), an age of 80 is plausible, but it's still at the upper end of the distribution. The presence of missing values should be dealt with first, as described in the previous response, as this will change the distribution and summary statistics.\n",
|
||
"* **Recommendation:** Further investigation may be warranted, but after addressing the missing values, visualizations (boxplots, histograms) can clarify the distribution and the effect of imputation on the apparent outliers.\n",
|
||
"\n",
|
||
"5. **SibSp:**\n",
|
||
"\n",
|
||
"* **Stats:** Values range from 0 to 8.\n",
|
||
"* **Analysis:** The values range from 0 to 8 siblings/spouses aboard. The mean is not provided in the summary, however it is expected that the max of 8 will greatly exceed the mean, given the distribution.\n",
|
||
"* **Recommendation:** Examine the distribution of SibSp. Values of 5 and 8 are relatively rare, so these could be considered outliers, and investigated further.\n",
|
||
"\n",
|
||
"6. **Parch:**\n",
|
||
"\n",
|
||
"* **Stats:** Values range from 0 to 6.\n",
|
||
"* **Analysis:** The values range from 0 to 6 parents/children aboard. The mean is not provided in the summary, however it is expected that the max of 6 will greatly exceed the mean, given the distribution.\n",
|
||
"* **Recommendation:** Examine the distribution of Parch. Values of 4, 5, and 6 are very rare, so these could be considered outliers, and investigated further.\n",
|
||
"\n",
|
||
"7. **Fare:**\n",
|
||
"\n",
|
||
"* **Stats:** Mean: 32.2, Max: 512.3\n",
|
||
"* **Analysis:** The maximum fare (512.3) is significantly higher than the mean (32.2). In fact, it's more than 15 times the mean. This suggests the presence of outliers, representing passengers who paid significantly more than the average fare.\n",
|
||
"* **Recommendation:** This column clearly warrants further investigation. Boxplots or histograms will help visualize the distribution and confirm the presence of outliers. Consider transformations (e.g., log transformation) to reduce the impact of outliers or capping extreme values.\n",
|
||
"\n",
|
||
"**Summary Table**\n",
|
||
"\n",
|
||
"| Column | Potential Outliers | max > 3*mean? | Recommendation |\n",
|
||
"|------------|--------------------|----------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n",
|
||
"| Age | Yes | Possibly | Investigate after imputing missing values; visualize the distribution. |\n",
|
||
"| SibSp | Yes | Unknown | Visualize distribution with boxplot and histogram, and investigate values 5 and 8. |\n",
|
||
"| Parch | Yes | Unknown | Visualize distribution with boxplot and histogram, and investigate values 4, 5 and 6. |\n",
|
||
"| Fare | Yes | Yes | Visualize distribution; consider transformations or capping. |\u001b[00m\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
" \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[32m╭─\u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m Task Completion \u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m─╮\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[1;32mTask Completed\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[32m133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mAgent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000\">╭──────────────────────────────────────────────── Task Completion ────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">Task Completed</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #008000; text-decoration-color: #008000\">133ee44e-4b91-4802-8f23-e5d38d410e32</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mPredictive Modeling Advisor\u001b[00m\n",
|
||
"\u001b[95m## Task:\u001b[00m \u001b[92mPredictive Modeling Insight Task:\n",
|
||
"Based on the dataset summary below, recommend which columns might be most informative for building a predictive model.\n",
|
||
"Dataset Summary:\n",
|
||
"No Variable Stats / Values Freqs / (% of Valid) Graph Missing\n",
|
||
"1 <strong>PassengerId</strong><br>[int64] Mean (sd) : 446.0 (257.4)<br>min < med < max:<br>1.0 < 446.0 < 891.0<br>IQR (CV) : 445.0 (1.7) 891 distinct values 0<br>(0.0%)\n",
|
||
"2 <strong>Survived</strong><br>[int64] 1. 0<br>2. 1 549 (61.6%)<br>342 (38.4%) 0<br>(0.0%)\n",
|
||
"3 <strong>Pclass</strong><br>[int64] 1. 3<br>2. 1<br>3. 2 491 (55.1%)<br>216 (24.2%)<br>184 (20.7%) 0<br>(0.0%)\n",
|
||
"4 <strong>Name</strong><br>[object] 1. Dooley, Mr. Patrick<br>2. Braund, Mr. Owen Harris<br>3. Cumings, Mrs. John Bradley (Fl<br>4. Heikkinen, Miss. Laina<br>5. Futrelle, Mrs. Jacques Heath (<br>6. Allen, Mr. William Henry<br>7. Moran, Mr. James<br>8. McCarthy, Mr. Timothy J<br>9. Palsson, Master. Gosta Leonard<br>10. Johnson, Mrs. Oscar W (Elisabe<br>11. other 1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>1 (0.1%)<br>881 (98.9%) 0<br>(0.0%)\n",
|
||
"5 <strong>Sex</strong><br>[object] 1. male<br>2. female 577 (64.8%)<br>314 (35.2%) 0<br>(0.0%)\n",
|
||
"6 <strong>Age</strong><br>[float64] Mean (sd) : 29.7 (14.5)<br>min < med < max:<br>0.4 < 28.0 < 80.0<br>IQR (CV) : 17.9 (2.0) 88 distinct values 177<br>(19.9%)\n",
|
||
"7 <strong>SibSp</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 4<br>5. 3<br>6. 8<br>7. 5 608 (68.2%)<br>209 (23.5%)<br>28 (3.1%)<br>18 (2.0%)<br>16 (1.8%)<br>7 (0.8%)<br>5 (0.6%) 0<br>(0.0%)\n",
|
||
"8 <strong>Parch</strong><br>[int64] 1. 0<br>2. 1<br>3. 2<br>4. 5<br>5. 3<br>6. 4<br>7. 6 678 (76.1%)<br>118 (13.2%)<br>80 (9.0%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>1 (0.1%) 0<br>(0.0%)\n",
|
||
"9 <strong>Ticket</strong><br>[object] 1. 347082<br>2. 1601<br>3. CA. 2343<br>4. 3101295<br>5. CA 2144<br>6. 347088<br>7. 382652<br>8. S.O.C. 14879<br>9. 113760<br>10. 19950<br>11. other 7 (0.8%)<br>7 (0.8%)<br>7 (0.8%)<br>6 (0.7%)<br>6 (0.7%)<br>6 (0.7%)<br>5 (0.6%)<br>5 (0.6%)<br>4 (0.4%)<br>4 (0.4%)<br>834 (93.6%) 0<br>(0.0%)\n",
|
||
"10 <strong>Fare</strong><br>[float64] Mean (sd) : 32.2 (49.7)<br>min < med < max:<br>0.0 < 14.5 < 512.3<br>IQR (CV) : 23.1 (0.6) 248 distinct values 0<br>(0.0%)\n",
|
||
"11 <strong>Cabin</strong><br>[object] 1. nan<br>2. G6<br>3. C23 C25 C27<br>4. B96 B98<br>5. F2<br>6. D<br>7. E101<br>8. C22 C26<br>9. F33<br>10. C83<br>11. other 687 (77.1%)<br>4 (0.4%)<br>4 (0.4%)<br>4 (0.4%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>3 (0.3%)<br>2 (0.2%)<br>175 (19.6%) 687<br>(77.1%)\n",
|
||
"12 <strong>Embarked</strong><br>[object] 1. S<br>2. C<br>3. Q<br>4. nan 644 (72.3%)<br>168 (18.9%)<br>77 (8.6%)<br>2 (0.2%) 2<br>(0.2%)\n",
|
||
"\u001b[00m\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
"\u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mStatistical Analyst\u001b[00m\n",
|
||
"\u001b[95m## Task:\u001b[00m \u001b[92mBased on the dataset summary provided and considering potential outliers in 'SibSp' and 'Parch' columns, do you recommend combining these features into a 'FamilySize' feature? Also, considering the high cardinality of 'Name' and 'Ticket' columns, do you think it's worth investing time in extracting titles from 'Name' or prefixes from 'Ticket' columns, or are these likely to introduce more noise than signal?\u001b[00m\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mStatistical Analyst\u001b[00m\n",
|
||
"\u001b[95m## Final Answer:\u001b[00m \u001b[92m\n",
|
||
"Combining 'SibSp' and 'Parch' into 'FamilySize' is recommended to address outliers and create a more informative feature. Extracting titles from the 'Name' column should be explored as a potentially valuable signal reflecting social status, age, and gender. However, I advise against investing significant time in extracting prefixes from the 'Ticket' column due to the high risk of introducing noise without a clear, meaningful relationship to survival. Prioritize feature engineering efforts on 'Name' given the limited time.\u001b[00m\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mPredictive Modeling Advisor\u001b[00m\n",
|
||
"\u001b[95m## Thought:\u001b[00m \u001b[92mOkay, based on the dataset summary and the additional analyses, I need to identify the columns that are most likely to be informative for predictive modeling. Here's my plan:\n",
|
||
"1. **Target Variable:** 'Survived' is the target variable, so it's obviously important.\n",
|
||
"2. **Categorical Features:** 'Pclass', 'Sex', and 'Embarked' seem potentially informative, representing passenger class, gender, and port of embarkation respectively.\n",
|
||
"3. **Continuous Features:** 'Age' and 'Fare' could also be strong predictors, but I need to consider the missing values and potential outliers.\n",
|
||
"4. **Family Size Features:** 'SibSp' and 'Parch' represent the number of siblings/spouses and parents/children aboard, respectively. These could be informative individually or combined into a \"FamilySize\" feature.\n",
|
||
"5. **Name and Ticket:** 'Name' and 'Ticket' are less obvious. 'Name' might contain titles that could be indicative of social status or age. 'Ticket' is a mix of alphanumeric values that are hard to interpret.\n",
|
||
"6. **Cabin:** 'Cabin' has too many missing values to be directly useful, but feature engineering (extracting the deck letter) might salvage some information.\n",
|
||
"7. **PassengerId:** 'PassengerId' is just an identifier and should not be used in the model.\n",
|
||
"Before making a final decision, I want to get a statistical analyst's opinion on whether combining `SibSp` and `Parch` is recommended, given the potential outlier values. Also, I want to get their opinion on `Name` and `Ticket`, especially if the effort to extract titles from names and/or the ticket prefixes is worth it.\u001b[00m\n",
|
||
"\u001b[95m## Using tool:\u001b[00m \u001b[92mAsk question to coworker\u001b[00m\n",
|
||
"\u001b[95m## Tool Input:\u001b[00m \u001b[92m\n",
|
||
"\"{\\\"question\\\": \\\"Based on the dataset summary provided and considering potential outliers in 'SibSp' and 'Parch' columns, do you recommend combining these features into a 'FamilySize' feature? Also, considering the high cardinality of 'Name' and 'Ticket' columns, do you think it's worth investing time in extracting titles from 'Name' or prefixes from 'Ticket' columns, or are these likely to introduce more noise than signal?\\\", \\\"context\\\": \\\"The goal is to identify the most informative columns for predicting passenger survival on the Titanic. The dataset summary contains information on each column, including data type, value frequencies, and missing values. 'SibSp' and 'Parch' have potential outlier values. 'Name' and 'Ticket' have high cardinality.\\\", \\\"coworker\\\": \\\"Statistical Analyst\\\"}\"\u001b[00m\n",
|
||
"\u001b[95m## Tool Output:\u001b[00m \u001b[92m\n",
|
||
"Combining 'SibSp' and 'Parch' into 'FamilySize' is recommended to address outliers and create a more informative feature. Extracting titles from the 'Name' column should be explored as a potentially valuable signal reflecting social status, age, and gender. However, I advise against investing significant time in extracting prefixes from the 'Ticket' column due to the high risk of introducing noise without a clear, meaningful relationship to survival. Prioritize feature engineering efforts on 'Name' given the limited time.\u001b[00m\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"\u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;34m🧠 \u001b[0m\u001b[34mThinking...\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">🧠 </span><span style=\"color: #000080; text-decoration-color: #000080\">Thinking...</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"\u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"\u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[31m╭─\u001b[0m\u001b[31m─────────────────────────────────────────────────\u001b[0m\u001b[31m Tool Error \u001b[0m\u001b[31m──────────────────────────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[1;31mTool Usage Failed\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[31mDelegate work to coworker\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[37mError: \u001b[0m\u001b[31mArguments validation failed: 2 validation errors for DelegateWorkToolSchema\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31mtask\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type':\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m'str'}, input_type=dict]\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m For further information visit https://errors.pydantic.dev/2.11/v/string_type\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31mcontext\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type':\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m'str'}, input_type=dict]\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m For further information visit https://errors.pydantic.dev/2.11/v/string_type\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800000; text-decoration-color: #800000\">╭────────────────────────────────────────────────── Tool Error ───────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">Tool Usage Failed</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #800000; text-decoration-color: #800000\">Delegate work to coworker</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Error: </span><span style=\"color: #800000; text-decoration-color: #800000\">Arguments validation failed: 2 validation errors for DelegateWorkToolSchema</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">task</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type':</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">'str'}, input_type=dict]</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> For further information visit https://errors.pydantic.dev/2.11/v/string_type</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">context</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type':</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">'str'}, input_type=dict]</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> For further information visit https://errors.pydantic.dev/2.11/v/string_type</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[31m╭─\u001b[0m\u001b[31m─────────────────────────────────────────────────\u001b[0m\u001b[31m Tool Error \u001b[0m\u001b[31m──────────────────────────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[1;31mTool Usage Failed\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[31mDelegate work to coworker\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[37mError: \u001b[0m\u001b[31mArguments validation failed: 2 validation errors for DelegateWorkToolSchema\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31mtask\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type':\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m'str'}, input_type=dict]\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m For further information visit https://errors.pydantic.dev/2.11/v/string_type\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31mcontext\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type':\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m'str'}, input_type=dict]\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m For further information visit https://errors.pydantic.dev/2.11/v/string_type\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800000; text-decoration-color: #800000\">╭────────────────────────────────────────────────── Tool Error ───────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">Tool Usage Failed</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #800000; text-decoration-color: #800000\">Delegate work to coworker</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Error: </span><span style=\"color: #800000; text-decoration-color: #800000\">Arguments validation failed: 2 validation errors for DelegateWorkToolSchema</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">task</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type':</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">'str'}, input_type=dict]</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> For further information visit https://errors.pydantic.dev/2.11/v/string_type</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">context</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type':</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">'str'}, input_type=dict]</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> For further information visit https://errors.pydantic.dev/2.11/v/string_type</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[31m╭─\u001b[0m\u001b[31m─────────────────────────────────────────────────\u001b[0m\u001b[31m Tool Error \u001b[0m\u001b[31m──────────────────────────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[1;31mTool Usage Failed\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[31mDelegate work to coworker\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[37mError: \u001b[0m\u001b[31mArguments validation failed: 2 validation errors for DelegateWorkToolSchema\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31mtask\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type':\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m'str'}, input_type=dict]\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m For further information visit https://errors.pydantic.dev/2.11/v/string_type\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31mcontext\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type':\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m'str'}, input_type=dict]\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m For further information visit https://errors.pydantic.dev/2.11/v/string_type\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||
"\u001b[31m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800000; text-decoration-color: #800000\">╭────────────────────────────────────────────────── Tool Error ───────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">Tool Usage Failed</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #800000; text-decoration-color: #800000\">Delegate work to coworker</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Error: </span><span style=\"color: #800000; text-decoration-color: #800000\">Arguments validation failed: 2 validation errors for DelegateWorkToolSchema</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">task</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type':</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">'str'}, input_type=dict]</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> For further information visit https://errors.pydantic.dev/2.11/v/string_type</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">context</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type':</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">'str'}, input_type=dict]</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\"> For further information visit https://errors.pydantic.dev/2.11/v/string_type</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||
"<span style=\"color: #800000; text-decoration-color: #800000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[91m \n",
|
||
"\n",
|
||
"I encountered an error while trying to use the tool. This was the error: Arguments validation failed: 2 validation errors for DelegateWorkToolSchema\n",
|
||
"task\n",
|
||
" Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type': 'str'}, input_type=dict]\n",
|
||
" For further information visit https://errors.pydantic.dev/2.11/v/string_type\n",
|
||
"context\n",
|
||
" Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type': 'str'}, input_type=dict]\n",
|
||
" For further information visit https://errors.pydantic.dev/2.11/v/string_type.\n",
|
||
" Tool Delegate work to coworker accepts these inputs: Tool Name: Delegate work to coworker\n",
|
||
"Tool Arguments: {'task': {'description': 'The task to delegate', 'type': 'str'}, 'context': {'description': 'The context for the task', 'type': 'str'}, 'coworker': {'description': 'The role/name of the coworker to delegate to', 'type': 'str'}}\n",
|
||
"Tool Description: Delegate a specific task to one of the following coworkers: Data Quality Analyst, Statistical Analyst\n",
|
||
"The input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolutely everything you know, don't reference things but instead explain them.\n",
|
||
"\u001b[00m\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mPredictive Modeling Advisor\u001b[00m\n",
|
||
"\u001b[95m## Thought:\u001b[00m \u001b[92mThought: I now have enough information to make a recommendation.\n",
|
||
"I will include the following columns:\n",
|
||
"* **Survived:** (Target variable)\n",
|
||
"* **Pclass:** (Categorical feature)\n",
|
||
"* **Sex:** (Categorical feature)\n",
|
||
"* **Age:** (Continuous feature, needs imputation)\n",
|
||
"* **Fare:** (Continuous feature, potential outliers)\n",
|
||
"* **Embarked:** (Categorical feature, minimal missing values)\n",
|
||
"* **FamilySize:** (Combined 'SibSp' and 'Parch')\n",
|
||
"* **Title:** (Extracted from 'Name')\u001b[00m\n",
|
||
"\u001b[95m## Using tool:\u001b[00m \u001b[92mDelegate work to coworker\u001b[00m\n",
|
||
"\u001b[95m## Tool Input:\u001b[00m \u001b[92m\n",
|
||
"\"{\\\"task\\\": {\\\"description\\\": \\\"Perform exploratory data analysis (EDA) focusing on the 'Age', 'Fare', and 'FamilySize' features. Specifically: 1. Impute missing values in 'Age' using an appropriate method (e.g., mean, median, or regression imputation). 2. Analyze the distribution of 'Fare' and address potential outliers (e.g., using transformations or capping). 3. Combine 'SibSp' and 'Parch' into 'FamilySize'.\\\", \\\"type\\\": \\\"str\\\"}, \\\"context\\\": {\\\"description\\\": \\\"The goal is to prepare the data for predictive modeling of Titanic passenger survival. 'Age' has missing values, 'Fare' has potential outliers, and 'SibSp' and 'Parch' can be combined into a more useful feature. The task should include data exploration to justify any decisions made.\\\", \\\"type\\\": \\\"str\\\"}, \\\"coworker\\\": \\\"Data Quality Analyst\\\"}\"\u001b[00m\n",
|
||
"\u001b[95m## Tool Output:\u001b[00m \u001b[92m\n",
|
||
"\n",
|
||
"I encountered an error while trying to use the tool. This was the error: Arguments validation failed: 2 validation errors for DelegateWorkToolSchema\n",
|
||
"task\n",
|
||
" Input should be a valid string [type=string_type, input_value={'description': \"Perform ...ySize'.\", 'type': 'str'}, input_type=dict]\n",
|
||
" For further information visit https://errors.pydantic.dev/2.11/v/string_type\n",
|
||
"context\n",
|
||
" Input should be a valid string [type=string_type, input_value={'description': \"The goal...s made.\", 'type': 'str'}, input_type=dict]\n",
|
||
" For further information visit https://errors.pydantic.dev/2.11/v/string_type.\n",
|
||
" Tool Delegate work to coworker accepts these inputs: Tool Name: Delegate work to coworker\n",
|
||
"Tool Arguments: {'task': {'description': 'The task to delegate', 'type': 'str'}, 'context': {'description': 'The context for the task', 'type': 'str'}, 'coworker': {'description': 'The role/name of the coworker to delegate to', 'type': 'str'}}\n",
|
||
"Tool Description: Delegate a specific task to one of the following coworkers: Data Quality Analyst, Statistical Analyst\n",
|
||
"The input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolutely everything you know, don't reference things but instead explain them..\n",
|
||
"Moving on then. I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. When responding, I must use the following format:\n",
|
||
"\n",
|
||
"```\n",
|
||
"Thought: you should always think about what to do\n",
|
||
"Action: the action to take, should be one of [Delegate work to coworker, Ask question to coworker]\n",
|
||
"Action Input: the input to the action, dictionary enclosed in curly braces\n",
|
||
"Observation: the result of the action\n",
|
||
"```\n",
|
||
"This Thought/Action/Action Input/Result can repeat N times. Once I know the final answer, I must return the following format:\n",
|
||
"\n",
|
||
"```\n",
|
||
"Thought: I now can give a great answer\n",
|
||
"Final Answer: Your final answer must be the great and the most complete as possible, it must be outcome described\n",
|
||
"\n",
|
||
"```\u001b[00m\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m\u001b[95m# Agent:\u001b[00m \u001b[1m\u001b[92mPredictive Modeling Advisor\u001b[00m\n",
|
||
"\u001b[95m## Final Answer:\u001b[00m \u001b[92m\n",
|
||
"['Survived', 'Pclass', 'Sex', 'Age', 'Fare', 'Embarked', 'FamilySize', 'Title']\u001b[00m\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;33m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[2;33mExecuting Task...\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">Executing Task...</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[1;36m🚀 Crew: \u001b[0m\u001b[1;36mcrew\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mData Quality Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"├── \u001b[1;32m📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32\u001b[0m\n",
|
||
"│ \u001b[37m Assigned to: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"│ └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mStatistical Analyst\u001b[0m\n",
|
||
"│ \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
"└── \u001b[1;32m📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m\n",
|
||
" \u001b[37m Assigned to: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n",
|
||
" ├── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" │ \u001b[37m Status: \u001b[0m\u001b[1;32mIn Progress\u001b[0m\n",
|
||
" └── \u001b[1;32m🤖 Agent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m\n",
|
||
" \u001b[37m Status: \u001b[0m\u001b[1;32m✅ Completed\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">🚀 Crew: crew</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 27b3e8e5-4f73-4516-8113-ca44b6419eb4</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Data Quality Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 133ee44e-4b91-4802-8f23-e5d38d410e32</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"│ └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Statistical Analyst</span>\n",
|
||
"│ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"└── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">📋 Task: 173c49d4-6975-4241-8596-c7daf5293e5e</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Assigned to: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
" ├── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" │ <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">In Progress</span>\n",
|
||
" └── <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">🤖 Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span>\n",
|
||
" <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\"> Status: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">✅ Completed</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[32m╭─\u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m Task Completion \u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m─╮\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[1;32mTask Completed\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[32m173c49d4-6975-4241-8596-c7daf5293e5e\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mAgent: \u001b[0m\u001b[32mPredictive Modeling Advisor\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000\">╭──────────────────────────────────────────────── Task Completion ────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">Task Completed</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #008000; text-decoration-color: #008000\">173c49d4-6975-4241-8596-c7daf5293e5e</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Agent: </span><span style=\"color: #008000; text-decoration-color: #008000\">Predictive Modeling Advisor</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\u001b[32m╭─\u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m Crew Completion \u001b[0m\u001b[32m───────────────────────────────────────────────\u001b[0m\u001b[32m─╮\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[1;32mCrew Execution Completed\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mName: \u001b[0m\u001b[32mcrew\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[37mID: \u001b[0m\u001b[32m29f787f1-e6ba-4749-8b57-97e51a2c4aa5\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m│\u001b[0m \u001b[32m│\u001b[0m\n",
|
||
"\u001b[32m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000\">╭──────────────────────────────────────────────── Crew Completion ────────────────────────────────────────────────╮</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">Crew Execution Completed</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">Name: </span><span style=\"color: #008000; text-decoration-color: #008000\">crew</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0\">ID: </span><span style=\"color: #008000; text-decoration-color: #008000\">29f787f1-e6ba-4749-8b57-97e51a2c4aa5</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n",
|
||
"<span style=\"color: #008000; text-decoration-color: #008000\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"text/plain": [
|
||
"\n"
|
||
],
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
|
||
"</pre>\n"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\n",
|
||
"Crew Output:\n",
|
||
"['Survived', 'Pclass', 'Sex', 'Age', 'Fare', 'Embarked', 'FamilySize', 'Title']\n"
|
||
]
|
||
}
|
||
]
|
||
}
|
||
]
|
||
} |