Spaces:
Sleeping
Sleeping
Commit
Β·
389e084
1
Parent(s):
2fafc02
Improved UI
Browse files- app.py +29 -23
- bot-detection-model.ipynb +825 -79
app.py
CHANGED
|
@@ -199,9 +199,8 @@ def main():
|
|
| 199 |
st.title("π€ Twitter Bot Detection System")
|
| 200 |
st.markdown("""
|
| 201 |
<div style='background-color: #262730; color: white; padding: 1rem; border-radius: 0.5rem; margin-bottom: 1rem;'>
|
| 202 |
-
<h4>Welcome to the
|
| 203 |
-
<p>This
|
| 204 |
-
Our system uses multiple features and sophisticated algorithms to provide accurate detection results.</p>
|
| 205 |
</div>
|
| 206 |
""", unsafe_allow_html=True)
|
| 207 |
|
|
@@ -250,7 +249,13 @@ def main():
|
|
| 250 |
st.markdown("### Tweet Content")
|
| 251 |
tweet_content = st.text_area("Sample Tweet", height=100) # UI stays, ignored in logic
|
| 252 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 253 |
if st.button("π Analyze Account"):
|
|
|
|
| 254 |
with st.spinner('Analyzing account characteristics...'):
|
| 255 |
# β
Build ONLY the exact 11 features your RF expects
|
| 256 |
features = build_model_features_from_ui(
|
|
@@ -279,12 +284,11 @@ def main():
|
|
| 279 |
else:
|
| 280 |
st.success("π€ Human Account Detected!")
|
| 281 |
|
| 282 |
-
|
| 283 |
-
|
| 284 |
-
|
| 285 |
-
|
| 286 |
-
|
| 287 |
-
st.plotly_chart(create_probability_chart(probs), use_container_width=True)
|
| 288 |
|
| 289 |
st.markdown("### Feature Analysis")
|
| 290 |
|
|
@@ -320,10 +324,13 @@ def main():
|
|
| 320 |
color_continuous_scale='Viridis'
|
| 321 |
)
|
| 322 |
st.plotly_chart(fig, use_container_width=True)
|
|
|
|
|
|
|
|
|
|
| 323 |
|
| 324 |
elif page == "CSV Analysis":
|
| 325 |
st.title("CSV Batch Analysis")
|
| 326 |
-
st.markdown("Upload a CSV file with account data to run batch predictions. You can use
|
| 327 |
uploaded_file = st.file_uploader("Upload CSV", type=["csv"])
|
| 328 |
|
| 329 |
if uploaded_file is not None:
|
|
@@ -416,9 +423,7 @@ def main():
|
|
| 416 |
st.markdown("""
|
| 417 |
<div class='info-box'>
|
| 418 |
<h3>π― System Overview</h3>
|
| 419 |
-
<p>Our Twitter Bot Detection System
|
| 420 |
-
and determine whether they are automated bots or genuine human users. The system achieves this through multi-faceted
|
| 421 |
-
analysis of various account characteristics and behaviors.</p>
|
| 422 |
</div>
|
| 423 |
""", unsafe_allow_html=True)
|
| 424 |
st.markdown("### π Key Features Analyzed")
|
|
@@ -445,25 +450,21 @@ def main():
|
|
| 445 |
- Friend acquisition rate
|
| 446 |
- Network growth patterns
|
| 447 |
|
| 448 |
-
#### Content Analysis
|
| 449 |
-
- Tweet sentiment
|
| 450 |
-
- Language patterns
|
| 451 |
-
- URL sharing frequency
|
| 452 |
-
- Hashtag usage
|
| 453 |
""")
|
| 454 |
|
| 455 |
st.markdown("""
|
| 456 |
<div class='info-box'>
|
| 457 |
<h3>β Technical Implementation</h3>
|
| 458 |
-
<p>The system employs a hierarchical classification approach:</p>
|
| 459 |
<ul>
|
| 460 |
-
<li><strong>
|
| 461 |
-
<li><strong>
|
| 462 |
-
<li><strong>
|
|
|
|
| 463 |
</ul>
|
| 464 |
</div>
|
| 465 |
""", unsafe_allow_html=True)
|
| 466 |
|
|
|
|
| 467 |
st.markdown("### π System Performance")
|
| 468 |
metrics_col1, metrics_col2, metrics_col3, metrics_col4 = st.columns(4)
|
| 469 |
|
|
@@ -486,6 +487,10 @@ def main():
|
|
| 486 |
|
| 487 |
else: # Statistics page
|
| 488 |
st.title("System Statistics")
|
|
|
|
|
|
|
|
|
|
|
|
|
| 489 |
col1, col2 = st.columns(2)
|
| 490 |
|
| 491 |
with col1:
|
|
@@ -526,7 +531,7 @@ def main():
|
|
| 526 |
fig = px.line(
|
| 527 |
monthly_data,
|
| 528 |
x='Month',
|
| 529 |
-
y=['Bots Detected'
|
| 530 |
title='Monthly Performance Metrics',
|
| 531 |
markers=True
|
| 532 |
)
|
|
@@ -544,6 +549,7 @@ def main():
|
|
| 544 |
with metric_col4:
|
| 545 |
st.metric("Processing Time", "1.2s", "-0.3s")
|
| 546 |
|
|
|
|
| 547 |
|
| 548 |
if __name__ == "__main__":
|
| 549 |
main()
|
|
|
|
| 199 |
st.title("π€ Twitter Bot Detection System")
|
| 200 |
st.markdown("""
|
| 201 |
<div style='background-color: #262730; color: white; padding: 1rem; border-radius: 0.5rem; margin-bottom: 1rem;'>
|
| 202 |
+
<h4>Welcome to the Social Media Bot Detection System</h4>
|
| 203 |
+
<p>This application demonstrates a metadata-based machine learning approach for detecting automated social media accounts.</p>
|
|
|
|
| 204 |
</div>
|
| 205 |
""", unsafe_allow_html=True)
|
| 206 |
|
|
|
|
| 249 |
st.markdown("### Tweet Content")
|
| 250 |
tweet_content = st.text_area("Sample Tweet", height=100) # UI stays, ignored in logic
|
| 251 |
|
| 252 |
+
st.caption(
|
| 253 |
+
"Note: The prediction model uses only profile and activity metadata. "
|
| 254 |
+
"Text fields are shown for completeness and are not used in model inference."
|
| 255 |
+
)
|
| 256 |
+
|
| 257 |
if st.button("π Analyze Account"):
|
| 258 |
+
|
| 259 |
with st.spinner('Analyzing account characteristics...'):
|
| 260 |
# β
Build ONLY the exact 11 features your RF expects
|
| 261 |
features = build_model_features_from_ui(
|
|
|
|
| 284 |
else:
|
| 285 |
st.success("π€ Human Account Detected!")
|
| 286 |
|
| 287 |
+
# Confidence gauge directly below the result
|
| 288 |
+
st.plotly_chart(
|
| 289 |
+
create_gauge_chart(confidence, prediction_is_bot),
|
| 290 |
+
use_container_width=True
|
| 291 |
+
)
|
|
|
|
| 292 |
|
| 293 |
st.markdown("### Feature Analysis")
|
| 294 |
|
|
|
|
| 324 |
color_continuous_scale='Viridis'
|
| 325 |
)
|
| 326 |
st.plotly_chart(fig, use_container_width=True)
|
| 327 |
+
|
| 328 |
+
|
| 329 |
+
|
| 330 |
|
| 331 |
elif page == "CSV Analysis":
|
| 332 |
st.title("CSV Batch Analysis")
|
| 333 |
+
st.markdown("Upload a CSV file with account data to run batch predictions. You can use \"testClick.csv\" from Dataset folder of this repository.")
|
| 334 |
uploaded_file = st.file_uploader("Upload CSV", type=["csv"])
|
| 335 |
|
| 336 |
if uploaded_file is not None:
|
|
|
|
| 423 |
st.markdown("""
|
| 424 |
<div class='info-box'>
|
| 425 |
<h3>π― System Overview</h3>
|
| 426 |
+
<p>Our Twitter Bot Detection System demonstrates a supervised machine learning approach for detecting automated social media accounts using structured profile and activity metadata. The goal of the system is to understand how different behavioral and account-level attributes contribute to identifying bot-like patterns, rather than relying on text or content-based signals.</p>
|
|
|
|
|
|
|
| 427 |
</div>
|
| 428 |
""", unsafe_allow_html=True)
|
| 429 |
st.markdown("### π Key Features Analyzed")
|
|
|
|
| 450 |
- Friend acquisition rate
|
| 451 |
- Network growth patterns
|
| 452 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 453 |
""")
|
| 454 |
|
| 455 |
st.markdown("""
|
| 456 |
<div class='info-box'>
|
| 457 |
<h3>β Technical Implementation</h3>
|
|
|
|
| 458 |
<ul>
|
| 459 |
+
<li><strong>Data Processing:</strong> Cleaned and structured profile and activity metadata.</li>
|
| 460 |
+
<li><strong>Feature Engineering:</strong> Derived behavioral features such as followerβfollowing ratio, posting activity, and account age.</li>
|
| 461 |
+
<li><strong>Modeling:</strong> Trained a Random Forest classifier on the engineered features.</li>
|
| 462 |
+
<li><strong>Explainability:</strong> Used feature importance to interpret model predictions.</li>
|
| 463 |
</ul>
|
| 464 |
</div>
|
| 465 |
""", unsafe_allow_html=True)
|
| 466 |
|
| 467 |
+
|
| 468 |
st.markdown("### π System Performance")
|
| 469 |
metrics_col1, metrics_col2, metrics_col3, metrics_col4 = st.columns(4)
|
| 470 |
|
|
|
|
| 487 |
|
| 488 |
else: # Statistics page
|
| 489 |
st.title("System Statistics")
|
| 490 |
+
st.info(
|
| 491 |
+
"This dashboard is a demo visualization intended to illustrate how system-level statistics and trends could be presented. The data shown here is illustrative and not generated from live usage or production logs."
|
| 492 |
+
)
|
| 493 |
+
|
| 494 |
col1, col2 = st.columns(2)
|
| 495 |
|
| 496 |
with col1:
|
|
|
|
| 531 |
fig = px.line(
|
| 532 |
monthly_data,
|
| 533 |
x='Month',
|
| 534 |
+
y=['Accuracy','Bots Detected' ],
|
| 535 |
title='Monthly Performance Metrics',
|
| 536 |
markers=True
|
| 537 |
)
|
|
|
|
| 549 |
with metric_col4:
|
| 550 |
st.metric("Processing Time", "1.2s", "-0.3s")
|
| 551 |
|
| 552 |
+
st.caption("*Demo Dashboard (Concept Visualization)*")
|
| 553 |
|
| 554 |
if __name__ == "__main__":
|
| 555 |
main()
|
bot-detection-model.ipynb
CHANGED
|
@@ -2,14 +2,14 @@
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
-
"execution_count":
|
| 6 |
"metadata": {
|
| 7 |
"execution": {
|
| 8 |
-
"iopub.execute_input": "2026-01-
|
| 9 |
-
"iopub.status.busy": "2026-01-
|
| 10 |
-
"iopub.status.idle": "2026-01-
|
| 11 |
-
"shell.execute_reply": "2026-01-
|
| 12 |
-
"shell.execute_reply.started": "2026-01-
|
| 13 |
},
|
| 14 |
"trusted": true
|
| 15 |
},
|
|
@@ -25,18 +25,26 @@
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"cell_type": "code",
|
| 28 |
-
"execution_count":
|
| 29 |
"metadata": {
|
| 30 |
"execution": {
|
| 31 |
-
"iopub.execute_input": "2026-01-
|
| 32 |
-
"iopub.status.busy": "2026-01-
|
| 33 |
-
"iopub.status.idle": "2026-01-
|
| 34 |
-
"shell.execute_reply": "2026-01-
|
| 35 |
-
"shell.execute_reply.started": "2026-01-
|
| 36 |
},
|
| 37 |
"trusted": true
|
| 38 |
},
|
| 39 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
"source": [
|
| 41 |
"# DATA_PATH = \"/kaggle/input/bot-detection-data/bot_detection_data.csv\"\n",
|
| 42 |
"DATA_PATH = \"/kaggle/input/bot-detection-data/training_data.csv\"\n",
|
|
@@ -47,39 +55,244 @@
|
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"cell_type": "code",
|
| 50 |
-
"execution_count":
|
| 51 |
-
"metadata": {},
|
| 52 |
-
"outputs": [],
|
| 53 |
-
"source": []
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"cell_type": "code",
|
| 57 |
-
"execution_count": null,
|
| 58 |
"metadata": {
|
| 59 |
"execution": {
|
| 60 |
-
"iopub.execute_input": "2026-01-
|
| 61 |
-
"iopub.status.busy": "2026-01-
|
| 62 |
-
"iopub.status.idle": "2026-01-
|
| 63 |
-
"shell.execute_reply": "2026-01-
|
| 64 |
-
"shell.execute_reply.started": "2026-01-
|
| 65 |
},
|
| 66 |
"trusted": true
|
| 67 |
},
|
| 68 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
"source": [
|
| 70 |
"df.head()"
|
| 71 |
]
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"cell_type": "code",
|
| 75 |
-
"execution_count":
|
| 76 |
"metadata": {
|
| 77 |
"execution": {
|
| 78 |
-
"iopub.execute_input": "2026-01-
|
| 79 |
-
"iopub.status.busy": "2026-01-
|
| 80 |
-
"iopub.status.idle": "2026-01-
|
| 81 |
-
"shell.execute_reply": "2026-01-
|
| 82 |
-
"shell.execute_reply.started": "2026-01-
|
| 83 |
},
|
| 84 |
"trusted": true
|
| 85 |
},
|
|
@@ -103,14 +316,14 @@
|
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"cell_type": "code",
|
| 106 |
-
"execution_count":
|
| 107 |
"metadata": {
|
| 108 |
"execution": {
|
| 109 |
-
"iopub.execute_input": "2026-01-
|
| 110 |
-
"iopub.status.busy": "2026-01-
|
| 111 |
-
"iopub.status.idle": "2026-01-
|
| 112 |
-
"shell.execute_reply": "2026-01-
|
| 113 |
-
"shell.execute_reply.started": "2026-01-
|
| 114 |
},
|
| 115 |
"trusted": true
|
| 116 |
},
|
|
@@ -129,14 +342,14 @@
|
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"cell_type": "code",
|
| 132 |
-
"execution_count":
|
| 133 |
"metadata": {
|
| 134 |
"execution": {
|
| 135 |
-
"iopub.execute_input": "2026-01-
|
| 136 |
-
"iopub.status.busy": "2026-01-
|
| 137 |
-
"iopub.status.idle": "2026-01-
|
| 138 |
-
"shell.execute_reply": "2026-01-
|
| 139 |
-
"shell.execute_reply.started": "2026-01-
|
| 140 |
},
|
| 141 |
"trusted": true
|
| 142 |
},
|
|
@@ -147,14 +360,14 @@
|
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"cell_type": "code",
|
| 150 |
-
"execution_count":
|
| 151 |
"metadata": {
|
| 152 |
"execution": {
|
| 153 |
-
"iopub.execute_input": "2026-01-
|
| 154 |
-
"iopub.status.busy": "2026-01-
|
| 155 |
-
"iopub.status.idle": "2026-01-
|
| 156 |
-
"shell.execute_reply": "2026-01-
|
| 157 |
-
"shell.execute_reply.started": "2026-01-
|
| 158 |
},
|
| 159 |
"trusted": true
|
| 160 |
},
|
|
@@ -169,14 +382,14 @@
|
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"cell_type": "code",
|
| 172 |
-
"execution_count":
|
| 173 |
"metadata": {
|
| 174 |
"execution": {
|
| 175 |
-
"iopub.execute_input": "2026-01-
|
| 176 |
-
"iopub.status.busy": "2026-01-
|
| 177 |
-
"iopub.status.idle": "2026-01-
|
| 178 |
-
"shell.execute_reply": "2026-01-
|
| 179 |
-
"shell.execute_reply.started": "2026-01-
|
| 180 |
},
|
| 181 |
"trusted": true
|
| 182 |
},
|
|
@@ -194,18 +407,453 @@
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"cell_type": "code",
|
| 197 |
-
"execution_count":
|
| 198 |
"metadata": {
|
| 199 |
"execution": {
|
| 200 |
-
"iopub.execute_input": "2026-01-
|
| 201 |
-
"iopub.status.busy": "2026-01-
|
| 202 |
-
"iopub.status.idle": "2026-01-
|
| 203 |
-
"shell.execute_reply": "2026-01-
|
| 204 |
-
"shell.execute_reply.started": "2026-01-
|
| 205 |
},
|
| 206 |
"trusted": true
|
| 207 |
},
|
| 208 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
"source": [
|
| 210 |
"from sklearn.ensemble import RandomForestClassifier\n",
|
| 211 |
"\n",
|
|
@@ -223,18 +871,35 @@
|
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"cell_type": "code",
|
| 226 |
-
"execution_count":
|
| 227 |
"metadata": {
|
| 228 |
"execution": {
|
| 229 |
-
"iopub.execute_input": "2026-01-
|
| 230 |
-
"iopub.status.busy": "2026-01-
|
| 231 |
-
"iopub.status.idle": "2026-01-
|
| 232 |
-
"shell.execute_reply": "2026-01-
|
| 233 |
-
"shell.execute_reply.started": "2026-01-
|
| 234 |
},
|
| 235 |
"trusted": true
|
| 236 |
},
|
| 237 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 238 |
"source": [
|
| 239 |
"preds = rf.predict(X_test)\n",
|
| 240 |
"\n",
|
|
@@ -244,18 +909,37 @@
|
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"cell_type": "code",
|
| 247 |
-
"execution_count":
|
| 248 |
"metadata": {
|
| 249 |
"execution": {
|
| 250 |
-
"iopub.execute_input": "2026-01-
|
| 251 |
-
"iopub.status.busy": "2026-01-
|
| 252 |
-
"iopub.status.idle": "2026-01-
|
| 253 |
-
"shell.execute_reply": "2026-01-
|
| 254 |
-
"shell.execute_reply.started": "2026-01-
|
| 255 |
},
|
| 256 |
"trusted": true
|
| 257 |
},
|
| 258 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 259 |
"source": [
|
| 260 |
"imp = pd.DataFrame({\n",
|
| 261 |
" \"feature\": X.columns,\n",
|
|
@@ -265,6 +949,68 @@
|
|
| 265 |
"print(imp)"
|
| 266 |
]
|
| 267 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 268 |
{
|
| 269 |
"cell_type": "code",
|
| 270 |
"execution_count": null,
|
|
@@ -306,7 +1052,7 @@
|
|
| 306 |
"name": "python",
|
| 307 |
"nbconvert_exporter": "python",
|
| 308 |
"pygments_lexer": "ipython3",
|
| 309 |
-
"version": "3.
|
| 310 |
}
|
| 311 |
},
|
| 312 |
"nbformat": 4,
|
|
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
+
"execution_count": 15,
|
| 6 |
"metadata": {
|
| 7 |
"execution": {
|
| 8 |
+
"iopub.execute_input": "2026-01-20T09:42:14.745657Z",
|
| 9 |
+
"iopub.status.busy": "2026-01-20T09:42:14.744873Z",
|
| 10 |
+
"iopub.status.idle": "2026-01-20T09:42:14.750198Z",
|
| 11 |
+
"shell.execute_reply": "2026-01-20T09:42:14.749406Z",
|
| 12 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.745620Z"
|
| 13 |
},
|
| 14 |
"trusted": true
|
| 15 |
},
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"cell_type": "code",
|
| 28 |
+
"execution_count": 16,
|
| 29 |
"metadata": {
|
| 30 |
"execution": {
|
| 31 |
+
"iopub.execute_input": "2026-01-20T09:42:14.752013Z",
|
| 32 |
+
"iopub.status.busy": "2026-01-20T09:42:14.751712Z",
|
| 33 |
+
"iopub.status.idle": "2026-01-20T09:42:14.831116Z",
|
| 34 |
+
"shell.execute_reply": "2026-01-20T09:42:14.830201Z",
|
| 35 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.751978Z"
|
| 36 |
},
|
| 37 |
"trusted": true
|
| 38 |
},
|
| 39 |
+
"outputs": [
|
| 40 |
+
{
|
| 41 |
+
"name": "stdout",
|
| 42 |
+
"output_type": "stream",
|
| 43 |
+
"text": [
|
| 44 |
+
"(1562, 20)\n"
|
| 45 |
+
]
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
"source": [
|
| 49 |
"# DATA_PATH = \"/kaggle/input/bot-detection-data/bot_detection_data.csv\"\n",
|
| 50 |
"DATA_PATH = \"/kaggle/input/bot-detection-data/training_data.csv\"\n",
|
|
|
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"cell_type": "code",
|
| 58 |
+
"execution_count": 17,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
"metadata": {
|
| 60 |
"execution": {
|
| 61 |
+
"iopub.execute_input": "2026-01-20T09:42:14.833146Z",
|
| 62 |
+
"iopub.status.busy": "2026-01-20T09:42:14.832832Z",
|
| 63 |
+
"iopub.status.idle": "2026-01-20T09:42:14.849605Z",
|
| 64 |
+
"shell.execute_reply": "2026-01-20T09:42:14.848831Z",
|
| 65 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.833119Z"
|
| 66 |
},
|
| 67 |
"trusted": true
|
| 68 |
},
|
| 69 |
+
"outputs": [
|
| 70 |
+
{
|
| 71 |
+
"data": {
|
| 72 |
+
"text/html": [
|
| 73 |
+
"<div>\n",
|
| 74 |
+
"<style scoped>\n",
|
| 75 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
| 76 |
+
" vertical-align: middle;\n",
|
| 77 |
+
" }\n",
|
| 78 |
+
"\n",
|
| 79 |
+
" .dataframe tbody tr th {\n",
|
| 80 |
+
" vertical-align: top;\n",
|
| 81 |
+
" }\n",
|
| 82 |
+
"\n",
|
| 83 |
+
" .dataframe thead th {\n",
|
| 84 |
+
" text-align: right;\n",
|
| 85 |
+
" }\n",
|
| 86 |
+
"</style>\n",
|
| 87 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
| 88 |
+
" <thead>\n",
|
| 89 |
+
" <tr style=\"text-align: right;\">\n",
|
| 90 |
+
" <th></th>\n",
|
| 91 |
+
" <th>id</th>\n",
|
| 92 |
+
" <th>id_str</th>\n",
|
| 93 |
+
" <th>screen_name</th>\n",
|
| 94 |
+
" <th>location</th>\n",
|
| 95 |
+
" <th>description</th>\n",
|
| 96 |
+
" <th>url</th>\n",
|
| 97 |
+
" <th>followers_count</th>\n",
|
| 98 |
+
" <th>friends_count</th>\n",
|
| 99 |
+
" <th>listedcount</th>\n",
|
| 100 |
+
" <th>created_at</th>\n",
|
| 101 |
+
" <th>favourites_count</th>\n",
|
| 102 |
+
" <th>verified</th>\n",
|
| 103 |
+
" <th>statuses_count</th>\n",
|
| 104 |
+
" <th>lang</th>\n",
|
| 105 |
+
" <th>status</th>\n",
|
| 106 |
+
" <th>default_profile</th>\n",
|
| 107 |
+
" <th>default_profile_image</th>\n",
|
| 108 |
+
" <th>has_extended_profile</th>\n",
|
| 109 |
+
" <th>name</th>\n",
|
| 110 |
+
" <th>bot</th>\n",
|
| 111 |
+
" </tr>\n",
|
| 112 |
+
" </thead>\n",
|
| 113 |
+
" <tbody>\n",
|
| 114 |
+
" <tr>\n",
|
| 115 |
+
" <th>0</th>\n",
|
| 116 |
+
" <td>1.953701e+08</td>\n",
|
| 117 |
+
" <td>195370058</td>\n",
|
| 118 |
+
" <td>kanyejordan</td>\n",
|
| 119 |
+
" <td>NaN</td>\n",
|
| 120 |
+
" <td>This is what I do. I drop truth bombs.</td>\n",
|
| 121 |
+
" <td>NaN</td>\n",
|
| 122 |
+
" <td>2925</td>\n",
|
| 123 |
+
" <td>3</td>\n",
|
| 124 |
+
" <td>139</td>\n",
|
| 125 |
+
" <td>9/26/2010 14:45</td>\n",
|
| 126 |
+
" <td>0</td>\n",
|
| 127 |
+
" <td>False</td>\n",
|
| 128 |
+
" <td>708</td>\n",
|
| 129 |
+
" <td>en</td>\n",
|
| 130 |
+
" <td>Status(in_reply_to_status_id=None, favorited=F...</td>\n",
|
| 131 |
+
" <td>True</td>\n",
|
| 132 |
+
" <td>False</td>\n",
|
| 133 |
+
" <td>False</td>\n",
|
| 134 |
+
" <td>Kanye Jordan</td>\n",
|
| 135 |
+
" <td>1</td>\n",
|
| 136 |
+
" </tr>\n",
|
| 137 |
+
" <tr>\n",
|
| 138 |
+
" <th>1</th>\n",
|
| 139 |
+
" <td>7.950000e+17</td>\n",
|
| 140 |
+
" <td>7.95E+17</td>\n",
|
| 141 |
+
" <td>astronaut_bot</td>\n",
|
| 142 |
+
" <td>NaN</td>\n",
|
| 143 |
+
" <td>Keeping an eye on astronauts coming and going....</td>\n",
|
| 144 |
+
" <td>NaN</td>\n",
|
| 145 |
+
" <td>9</td>\n",
|
| 146 |
+
" <td>0</td>\n",
|
| 147 |
+
" <td>5</td>\n",
|
| 148 |
+
" <td>Fri Nov 04 12:11:27 +0000 2016</td>\n",
|
| 149 |
+
" <td>0</td>\n",
|
| 150 |
+
" <td>False</td>\n",
|
| 151 |
+
" <td>6</td>\n",
|
| 152 |
+
" <td>en</td>\n",
|
| 153 |
+
" <td>{'created_at': 'Tue Nov 22 16:52:31 +0000 2016...</td>\n",
|
| 154 |
+
" <td>True</td>\n",
|
| 155 |
+
" <td>False</td>\n",
|
| 156 |
+
" <td>False</td>\n",
|
| 157 |
+
" <td>Astronaut Notifier</td>\n",
|
| 158 |
+
" <td>1</td>\n",
|
| 159 |
+
" </tr>\n",
|
| 160 |
+
" <tr>\n",
|
| 161 |
+
" <th>2</th>\n",
|
| 162 |
+
" <td>2.976541e+09</td>\n",
|
| 163 |
+
" <td>2976541239</td>\n",
|
| 164 |
+
" <td>TheRiddlerBot</td>\n",
|
| 165 |
+
" <td>Coimbra, Portugal</td>\n",
|
| 166 |
+
" <td>Solve the riddle by replying only the name of ...</td>\n",
|
| 167 |
+
" <td>https://t.co/1v8BON9QpT</td>\n",
|
| 168 |
+
" <td>132</td>\n",
|
| 169 |
+
" <td>46</td>\n",
|
| 170 |
+
" <td>24</td>\n",
|
| 171 |
+
" <td>1/13/2015 15:10</td>\n",
|
| 172 |
+
" <td>740</td>\n",
|
| 173 |
+
" <td>False</td>\n",
|
| 174 |
+
" <td>7346</td>\n",
|
| 175 |
+
" <td>en</td>\n",
|
| 176 |
+
" <td>Status(contributors=None, truncated=False, tex...</td>\n",
|
| 177 |
+
" <td>True</td>\n",
|
| 178 |
+
" <td>False</td>\n",
|
| 179 |
+
" <td>False</td>\n",
|
| 180 |
+
" <td>TheRiddlerBot</td>\n",
|
| 181 |
+
" <td>1</td>\n",
|
| 182 |
+
" </tr>\n",
|
| 183 |
+
" <tr>\n",
|
| 184 |
+
" <th>3</th>\n",
|
| 185 |
+
" <td>2.243832e+08</td>\n",
|
| 186 |
+
" <td>224383150</td>\n",
|
| 187 |
+
" <td>mlegoudes262</td>\n",
|
| 188 |
+
" <td>NaN</td>\n",
|
| 189 |
+
" <td>NaN</td>\n",
|
| 190 |
+
" <td>NaN</td>\n",
|
| 191 |
+
" <td>54</td>\n",
|
| 192 |
+
" <td>1351</td>\n",
|
| 193 |
+
" <td>0</td>\n",
|
| 194 |
+
" <td>Wed Dec 08 21:29:31 +0000 2010</td>\n",
|
| 195 |
+
" <td>2</td>\n",
|
| 196 |
+
" <td>False</td>\n",
|
| 197 |
+
" <td>6</td>\n",
|
| 198 |
+
" <td>en</td>\n",
|
| 199 |
+
" <td>{'truncated': False, 'entities': {'user_mentio...</td>\n",
|
| 200 |
+
" <td>True</td>\n",
|
| 201 |
+
" <td>False</td>\n",
|
| 202 |
+
" <td>False</td>\n",
|
| 203 |
+
" <td>Laurie Poulsen</td>\n",
|
| 204 |
+
" <td>1</td>\n",
|
| 205 |
+
" </tr>\n",
|
| 206 |
+
" <tr>\n",
|
| 207 |
+
" <th>4</th>\n",
|
| 208 |
+
" <td>1.134712e+07</td>\n",
|
| 209 |
+
" <td>11347122</td>\n",
|
| 210 |
+
" <td>GavinNewsom</td>\n",
|
| 211 |
+
" <td>California</td>\n",
|
| 212 |
+
" <td>Husband & father. 49th Lt. Gov. of California ...</td>\n",
|
| 213 |
+
" <td>https://t.co/XrGnfzTDJD</td>\n",
|
| 214 |
+
" <td>1300380</td>\n",
|
| 215 |
+
" <td>24248</td>\n",
|
| 216 |
+
" <td>7089</td>\n",
|
| 217 |
+
" <td>Wed Dec 19 19:53:42 +0000 2007</td>\n",
|
| 218 |
+
" <td>4184</td>\n",
|
| 219 |
+
" <td>True</td>\n",
|
| 220 |
+
" <td>8536</td>\n",
|
| 221 |
+
" <td>en</td>\n",
|
| 222 |
+
" <td>{u'contributors': None, u'truncated': True, u'...</td>\n",
|
| 223 |
+
" <td>False</td>\n",
|
| 224 |
+
" <td>False</td>\n",
|
| 225 |
+
" <td>False</td>\n",
|
| 226 |
+
" <td>Gavin Newsom</td>\n",
|
| 227 |
+
" <td>0</td>\n",
|
| 228 |
+
" </tr>\n",
|
| 229 |
+
" </tbody>\n",
|
| 230 |
+
"</table>\n",
|
| 231 |
+
"</div>"
|
| 232 |
+
],
|
| 233 |
+
"text/plain": [
|
| 234 |
+
" id id_str screen_name location \\\n",
|
| 235 |
+
"0 1.953701e+08 195370058 kanyejordan NaN \n",
|
| 236 |
+
"1 7.950000e+17 7.95E+17 astronaut_bot NaN \n",
|
| 237 |
+
"2 2.976541e+09 2976541239 TheRiddlerBot Coimbra, Portugal \n",
|
| 238 |
+
"3 2.243832e+08 224383150 mlegoudes262 NaN \n",
|
| 239 |
+
"4 1.134712e+07 11347122 GavinNewsom California \n",
|
| 240 |
+
"\n",
|
| 241 |
+
" description url \\\n",
|
| 242 |
+
"0 This is what I do. I drop truth bombs. NaN \n",
|
| 243 |
+
"1 Keeping an eye on astronauts coming and going.... NaN \n",
|
| 244 |
+
"2 Solve the riddle by replying only the name of ... https://t.co/1v8BON9QpT \n",
|
| 245 |
+
"3 NaN NaN \n",
|
| 246 |
+
"4 Husband & father. 49th Lt. Gov. of California ... https://t.co/XrGnfzTDJD \n",
|
| 247 |
+
"\n",
|
| 248 |
+
" followers_count friends_count listedcount \\\n",
|
| 249 |
+
"0 2925 3 139 \n",
|
| 250 |
+
"1 9 0 5 \n",
|
| 251 |
+
"2 132 46 24 \n",
|
| 252 |
+
"3 54 1351 0 \n",
|
| 253 |
+
"4 1300380 24248 7089 \n",
|
| 254 |
+
"\n",
|
| 255 |
+
" created_at favourites_count verified statuses_count \\\n",
|
| 256 |
+
"0 9/26/2010 14:45 0 False 708 \n",
|
| 257 |
+
"1 Fri Nov 04 12:11:27 +0000 2016 0 False 6 \n",
|
| 258 |
+
"2 1/13/2015 15:10 740 False 7346 \n",
|
| 259 |
+
"3 Wed Dec 08 21:29:31 +0000 2010 2 False 6 \n",
|
| 260 |
+
"4 Wed Dec 19 19:53:42 +0000 2007 4184 True 8536 \n",
|
| 261 |
+
"\n",
|
| 262 |
+
" lang status default_profile \\\n",
|
| 263 |
+
"0 en Status(in_reply_to_status_id=None, favorited=F... True \n",
|
| 264 |
+
"1 en {'created_at': 'Tue Nov 22 16:52:31 +0000 2016... True \n",
|
| 265 |
+
"2 en Status(contributors=None, truncated=False, tex... True \n",
|
| 266 |
+
"3 en {'truncated': False, 'entities': {'user_mentio... True \n",
|
| 267 |
+
"4 en {u'contributors': None, u'truncated': True, u'... False \n",
|
| 268 |
+
"\n",
|
| 269 |
+
" default_profile_image has_extended_profile name bot \n",
|
| 270 |
+
"0 False False Kanye Jordan 1 \n",
|
| 271 |
+
"1 False False Astronaut Notifier 1 \n",
|
| 272 |
+
"2 False False TheRiddlerBot 1 \n",
|
| 273 |
+
"3 False False Laurie Poulsen 1 \n",
|
| 274 |
+
"4 False False Gavin Newsom 0 "
|
| 275 |
+
]
|
| 276 |
+
},
|
| 277 |
+
"execution_count": 17,
|
| 278 |
+
"metadata": {},
|
| 279 |
+
"output_type": "execute_result"
|
| 280 |
+
}
|
| 281 |
+
],
|
| 282 |
"source": [
|
| 283 |
"df.head()"
|
| 284 |
]
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"cell_type": "code",
|
| 288 |
+
"execution_count": 18,
|
| 289 |
"metadata": {
|
| 290 |
"execution": {
|
| 291 |
+
"iopub.execute_input": "2026-01-20T09:42:14.851012Z",
|
| 292 |
+
"iopub.status.busy": "2026-01-20T09:42:14.850700Z",
|
| 293 |
+
"iopub.status.idle": "2026-01-20T09:42:14.867213Z",
|
| 294 |
+
"shell.execute_reply": "2026-01-20T09:42:14.866311Z",
|
| 295 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.850985Z"
|
| 296 |
},
|
| 297 |
"trusted": true
|
| 298 |
},
|
|
|
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"cell_type": "code",
|
| 319 |
+
"execution_count": 19,
|
| 320 |
"metadata": {
|
| 321 |
"execution": {
|
| 322 |
+
"iopub.execute_input": "2026-01-20T09:42:14.869442Z",
|
| 323 |
+
"iopub.status.busy": "2026-01-20T09:42:14.869099Z",
|
| 324 |
+
"iopub.status.idle": "2026-01-20T09:42:14.884158Z",
|
| 325 |
+
"shell.execute_reply": "2026-01-20T09:42:14.883300Z",
|
| 326 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.869405Z"
|
| 327 |
},
|
| 328 |
"trusted": true
|
| 329 |
},
|
|
|
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"cell_type": "code",
|
| 345 |
+
"execution_count": 20,
|
| 346 |
"metadata": {
|
| 347 |
"execution": {
|
| 348 |
+
"iopub.execute_input": "2026-01-20T09:42:14.885944Z",
|
| 349 |
+
"iopub.status.busy": "2026-01-20T09:42:14.885337Z",
|
| 350 |
+
"iopub.status.idle": "2026-01-20T09:42:14.899788Z",
|
| 351 |
+
"shell.execute_reply": "2026-01-20T09:42:14.898857Z",
|
| 352 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.885913Z"
|
| 353 |
},
|
| 354 |
"trusted": true
|
| 355 |
},
|
|
|
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"cell_type": "code",
|
| 363 |
+
"execution_count": 21,
|
| 364 |
"metadata": {
|
| 365 |
"execution": {
|
| 366 |
+
"iopub.execute_input": "2026-01-20T09:42:14.901446Z",
|
| 367 |
+
"iopub.status.busy": "2026-01-20T09:42:14.901029Z",
|
| 368 |
+
"iopub.status.idle": "2026-01-20T09:42:14.920930Z",
|
| 369 |
+
"shell.execute_reply": "2026-01-20T09:42:14.920119Z",
|
| 370 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.901408Z"
|
| 371 |
},
|
| 372 |
"trusted": true
|
| 373 |
},
|
|
|
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"cell_type": "code",
|
| 385 |
+
"execution_count": 22,
|
| 386 |
"metadata": {
|
| 387 |
"execution": {
|
| 388 |
+
"iopub.execute_input": "2026-01-20T09:42:14.922400Z",
|
| 389 |
+
"iopub.status.busy": "2026-01-20T09:42:14.922068Z",
|
| 390 |
+
"iopub.status.idle": "2026-01-20T09:42:14.940152Z",
|
| 391 |
+
"shell.execute_reply": "2026-01-20T09:42:14.939293Z",
|
| 392 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.922365Z"
|
| 393 |
},
|
| 394 |
"trusted": true
|
| 395 |
},
|
|
|
|
| 407 |
},
|
| 408 |
{
|
| 409 |
"cell_type": "code",
|
| 410 |
+
"execution_count": 23,
|
| 411 |
"metadata": {
|
| 412 |
"execution": {
|
| 413 |
+
"iopub.execute_input": "2026-01-20T09:42:14.941565Z",
|
| 414 |
+
"iopub.status.busy": "2026-01-20T09:42:14.941261Z",
|
| 415 |
+
"iopub.status.idle": "2026-01-20T09:42:15.734600Z",
|
| 416 |
+
"shell.execute_reply": "2026-01-20T09:42:15.733765Z",
|
| 417 |
+
"shell.execute_reply.started": "2026-01-20T09:42:14.941540Z"
|
| 418 |
},
|
| 419 |
"trusted": true
|
| 420 |
},
|
| 421 |
+
"outputs": [
|
| 422 |
+
{
|
| 423 |
+
"data": {
|
| 424 |
+
"text/html": [
|
| 425 |
+
"<style>#sk-container-id-2 {\n",
|
| 426 |
+
" /* Definition of color scheme common for light and dark mode */\n",
|
| 427 |
+
" --sklearn-color-text: #000;\n",
|
| 428 |
+
" --sklearn-color-text-muted: #666;\n",
|
| 429 |
+
" --sklearn-color-line: gray;\n",
|
| 430 |
+
" /* Definition of color scheme for unfitted estimators */\n",
|
| 431 |
+
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
|
| 432 |
+
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
|
| 433 |
+
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
|
| 434 |
+
" --sklearn-color-unfitted-level-3: chocolate;\n",
|
| 435 |
+
" /* Definition of color scheme for fitted estimators */\n",
|
| 436 |
+
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
|
| 437 |
+
" --sklearn-color-fitted-level-1: #d4ebff;\n",
|
| 438 |
+
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
|
| 439 |
+
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
|
| 440 |
+
"\n",
|
| 441 |
+
" /* Specific color for light theme */\n",
|
| 442 |
+
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
| 443 |
+
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
|
| 444 |
+
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
| 445 |
+
" --sklearn-color-icon: #696969;\n",
|
| 446 |
+
"\n",
|
| 447 |
+
" @media (prefers-color-scheme: dark) {\n",
|
| 448 |
+
" /* Redefinition of color scheme for dark theme */\n",
|
| 449 |
+
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
| 450 |
+
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
|
| 451 |
+
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
| 452 |
+
" --sklearn-color-icon: #878787;\n",
|
| 453 |
+
" }\n",
|
| 454 |
+
"}\n",
|
| 455 |
+
"\n",
|
| 456 |
+
"#sk-container-id-2 {\n",
|
| 457 |
+
" color: var(--sklearn-color-text);\n",
|
| 458 |
+
"}\n",
|
| 459 |
+
"\n",
|
| 460 |
+
"#sk-container-id-2 pre {\n",
|
| 461 |
+
" padding: 0;\n",
|
| 462 |
+
"}\n",
|
| 463 |
+
"\n",
|
| 464 |
+
"#sk-container-id-2 input.sk-hidden--visually {\n",
|
| 465 |
+
" border: 0;\n",
|
| 466 |
+
" clip: rect(1px 1px 1px 1px);\n",
|
| 467 |
+
" clip: rect(1px, 1px, 1px, 1px);\n",
|
| 468 |
+
" height: 1px;\n",
|
| 469 |
+
" margin: -1px;\n",
|
| 470 |
+
" overflow: hidden;\n",
|
| 471 |
+
" padding: 0;\n",
|
| 472 |
+
" position: absolute;\n",
|
| 473 |
+
" width: 1px;\n",
|
| 474 |
+
"}\n",
|
| 475 |
+
"\n",
|
| 476 |
+
"#sk-container-id-2 div.sk-dashed-wrapped {\n",
|
| 477 |
+
" border: 1px dashed var(--sklearn-color-line);\n",
|
| 478 |
+
" margin: 0 0.4em 0.5em 0.4em;\n",
|
| 479 |
+
" box-sizing: border-box;\n",
|
| 480 |
+
" padding-bottom: 0.4em;\n",
|
| 481 |
+
" background-color: var(--sklearn-color-background);\n",
|
| 482 |
+
"}\n",
|
| 483 |
+
"\n",
|
| 484 |
+
"#sk-container-id-2 div.sk-container {\n",
|
| 485 |
+
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
|
| 486 |
+
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
|
| 487 |
+
" so we also need the `!important` here to be able to override the\n",
|
| 488 |
+
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
|
| 489 |
+
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
|
| 490 |
+
" display: inline-block !important;\n",
|
| 491 |
+
" position: relative;\n",
|
| 492 |
+
"}\n",
|
| 493 |
+
"\n",
|
| 494 |
+
"#sk-container-id-2 div.sk-text-repr-fallback {\n",
|
| 495 |
+
" display: none;\n",
|
| 496 |
+
"}\n",
|
| 497 |
+
"\n",
|
| 498 |
+
"div.sk-parallel-item,\n",
|
| 499 |
+
"div.sk-serial,\n",
|
| 500 |
+
"div.sk-item {\n",
|
| 501 |
+
" /* draw centered vertical line to link estimators */\n",
|
| 502 |
+
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
|
| 503 |
+
" background-size: 2px 100%;\n",
|
| 504 |
+
" background-repeat: no-repeat;\n",
|
| 505 |
+
" background-position: center center;\n",
|
| 506 |
+
"}\n",
|
| 507 |
+
"\n",
|
| 508 |
+
"/* Parallel-specific style estimator block */\n",
|
| 509 |
+
"\n",
|
| 510 |
+
"#sk-container-id-2 div.sk-parallel-item::after {\n",
|
| 511 |
+
" content: \"\";\n",
|
| 512 |
+
" width: 100%;\n",
|
| 513 |
+
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
|
| 514 |
+
" flex-grow: 1;\n",
|
| 515 |
+
"}\n",
|
| 516 |
+
"\n",
|
| 517 |
+
"#sk-container-id-2 div.sk-parallel {\n",
|
| 518 |
+
" display: flex;\n",
|
| 519 |
+
" align-items: stretch;\n",
|
| 520 |
+
" justify-content: center;\n",
|
| 521 |
+
" background-color: var(--sklearn-color-background);\n",
|
| 522 |
+
" position: relative;\n",
|
| 523 |
+
"}\n",
|
| 524 |
+
"\n",
|
| 525 |
+
"#sk-container-id-2 div.sk-parallel-item {\n",
|
| 526 |
+
" display: flex;\n",
|
| 527 |
+
" flex-direction: column;\n",
|
| 528 |
+
"}\n",
|
| 529 |
+
"\n",
|
| 530 |
+
"#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
|
| 531 |
+
" align-self: flex-end;\n",
|
| 532 |
+
" width: 50%;\n",
|
| 533 |
+
"}\n",
|
| 534 |
+
"\n",
|
| 535 |
+
"#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
|
| 536 |
+
" align-self: flex-start;\n",
|
| 537 |
+
" width: 50%;\n",
|
| 538 |
+
"}\n",
|
| 539 |
+
"\n",
|
| 540 |
+
"#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
|
| 541 |
+
" width: 0;\n",
|
| 542 |
+
"}\n",
|
| 543 |
+
"\n",
|
| 544 |
+
"/* Serial-specific style estimator block */\n",
|
| 545 |
+
"\n",
|
| 546 |
+
"#sk-container-id-2 div.sk-serial {\n",
|
| 547 |
+
" display: flex;\n",
|
| 548 |
+
" flex-direction: column;\n",
|
| 549 |
+
" align-items: center;\n",
|
| 550 |
+
" background-color: var(--sklearn-color-background);\n",
|
| 551 |
+
" padding-right: 1em;\n",
|
| 552 |
+
" padding-left: 1em;\n",
|
| 553 |
+
"}\n",
|
| 554 |
+
"\n",
|
| 555 |
+
"\n",
|
| 556 |
+
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
|
| 557 |
+
"clickable and can be expanded/collapsed.\n",
|
| 558 |
+
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
|
| 559 |
+
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
|
| 560 |
+
"*/\n",
|
| 561 |
+
"\n",
|
| 562 |
+
"/* Pipeline and ColumnTransformer style (default) */\n",
|
| 563 |
+
"\n",
|
| 564 |
+
"#sk-container-id-2 div.sk-toggleable {\n",
|
| 565 |
+
" /* Default theme specific background. It is overwritten whether we have a\n",
|
| 566 |
+
" specific estimator or a Pipeline/ColumnTransformer */\n",
|
| 567 |
+
" background-color: var(--sklearn-color-background);\n",
|
| 568 |
+
"}\n",
|
| 569 |
+
"\n",
|
| 570 |
+
"/* Toggleable label */\n",
|
| 571 |
+
"#sk-container-id-2 label.sk-toggleable__label {\n",
|
| 572 |
+
" cursor: pointer;\n",
|
| 573 |
+
" display: flex;\n",
|
| 574 |
+
" width: 100%;\n",
|
| 575 |
+
" margin-bottom: 0;\n",
|
| 576 |
+
" padding: 0.5em;\n",
|
| 577 |
+
" box-sizing: border-box;\n",
|
| 578 |
+
" text-align: center;\n",
|
| 579 |
+
" align-items: start;\n",
|
| 580 |
+
" justify-content: space-between;\n",
|
| 581 |
+
" gap: 0.5em;\n",
|
| 582 |
+
"}\n",
|
| 583 |
+
"\n",
|
| 584 |
+
"#sk-container-id-2 label.sk-toggleable__label .caption {\n",
|
| 585 |
+
" font-size: 0.6rem;\n",
|
| 586 |
+
" font-weight: lighter;\n",
|
| 587 |
+
" color: var(--sklearn-color-text-muted);\n",
|
| 588 |
+
"}\n",
|
| 589 |
+
"\n",
|
| 590 |
+
"#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
|
| 591 |
+
" /* Arrow on the left of the label */\n",
|
| 592 |
+
" content: \"βΈ\";\n",
|
| 593 |
+
" float: left;\n",
|
| 594 |
+
" margin-right: 0.25em;\n",
|
| 595 |
+
" color: var(--sklearn-color-icon);\n",
|
| 596 |
+
"}\n",
|
| 597 |
+
"\n",
|
| 598 |
+
"#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
|
| 599 |
+
" color: var(--sklearn-color-text);\n",
|
| 600 |
+
"}\n",
|
| 601 |
+
"\n",
|
| 602 |
+
"/* Toggleable content - dropdown */\n",
|
| 603 |
+
"\n",
|
| 604 |
+
"#sk-container-id-2 div.sk-toggleable__content {\n",
|
| 605 |
+
" max-height: 0;\n",
|
| 606 |
+
" max-width: 0;\n",
|
| 607 |
+
" overflow: hidden;\n",
|
| 608 |
+
" text-align: left;\n",
|
| 609 |
+
" /* unfitted */\n",
|
| 610 |
+
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
| 611 |
+
"}\n",
|
| 612 |
+
"\n",
|
| 613 |
+
"#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
|
| 614 |
+
" /* fitted */\n",
|
| 615 |
+
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
| 616 |
+
"}\n",
|
| 617 |
+
"\n",
|
| 618 |
+
"#sk-container-id-2 div.sk-toggleable__content pre {\n",
|
| 619 |
+
" margin: 0.2em;\n",
|
| 620 |
+
" border-radius: 0.25em;\n",
|
| 621 |
+
" color: var(--sklearn-color-text);\n",
|
| 622 |
+
" /* unfitted */\n",
|
| 623 |
+
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
| 624 |
+
"}\n",
|
| 625 |
+
"\n",
|
| 626 |
+
"#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
|
| 627 |
+
" /* unfitted */\n",
|
| 628 |
+
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
| 629 |
+
"}\n",
|
| 630 |
+
"\n",
|
| 631 |
+
"#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
| 632 |
+
" /* Expand drop-down */\n",
|
| 633 |
+
" max-height: 200px;\n",
|
| 634 |
+
" max-width: 100%;\n",
|
| 635 |
+
" overflow: auto;\n",
|
| 636 |
+
"}\n",
|
| 637 |
+
"\n",
|
| 638 |
+
"#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
|
| 639 |
+
" content: \"βΎ\";\n",
|
| 640 |
+
"}\n",
|
| 641 |
+
"\n",
|
| 642 |
+
"/* Pipeline/ColumnTransformer-specific style */\n",
|
| 643 |
+
"\n",
|
| 644 |
+
"#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 645 |
+
" color: var(--sklearn-color-text);\n",
|
| 646 |
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 647 |
+
"}\n",
|
| 648 |
+
"\n",
|
| 649 |
+
"#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 650 |
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 651 |
+
"}\n",
|
| 652 |
+
"\n",
|
| 653 |
+
"/* Estimator-specific style */\n",
|
| 654 |
+
"\n",
|
| 655 |
+
"/* Colorize estimator box */\n",
|
| 656 |
+
"#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 657 |
+
" /* unfitted */\n",
|
| 658 |
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 659 |
+
"}\n",
|
| 660 |
+
"\n",
|
| 661 |
+
"#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 662 |
+
" /* fitted */\n",
|
| 663 |
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 664 |
+
"}\n",
|
| 665 |
+
"\n",
|
| 666 |
+
"#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
|
| 667 |
+
"#sk-container-id-2 div.sk-label label {\n",
|
| 668 |
+
" /* The background is the default theme color */\n",
|
| 669 |
+
" color: var(--sklearn-color-text-on-default-background);\n",
|
| 670 |
+
"}\n",
|
| 671 |
+
"\n",
|
| 672 |
+
"/* On hover, darken the color of the background */\n",
|
| 673 |
+
"#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
|
| 674 |
+
" color: var(--sklearn-color-text);\n",
|
| 675 |
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 676 |
+
"}\n",
|
| 677 |
+
"\n",
|
| 678 |
+
"/* Label box, darken color on hover, fitted */\n",
|
| 679 |
+
"#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
|
| 680 |
+
" color: var(--sklearn-color-text);\n",
|
| 681 |
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 682 |
+
"}\n",
|
| 683 |
+
"\n",
|
| 684 |
+
"/* Estimator label */\n",
|
| 685 |
+
"\n",
|
| 686 |
+
"#sk-container-id-2 div.sk-label label {\n",
|
| 687 |
+
" font-family: monospace;\n",
|
| 688 |
+
" font-weight: bold;\n",
|
| 689 |
+
" display: inline-block;\n",
|
| 690 |
+
" line-height: 1.2em;\n",
|
| 691 |
+
"}\n",
|
| 692 |
+
"\n",
|
| 693 |
+
"#sk-container-id-2 div.sk-label-container {\n",
|
| 694 |
+
" text-align: center;\n",
|
| 695 |
+
"}\n",
|
| 696 |
+
"\n",
|
| 697 |
+
"/* Estimator-specific */\n",
|
| 698 |
+
"#sk-container-id-2 div.sk-estimator {\n",
|
| 699 |
+
" font-family: monospace;\n",
|
| 700 |
+
" border: 1px dotted var(--sklearn-color-border-box);\n",
|
| 701 |
+
" border-radius: 0.25em;\n",
|
| 702 |
+
" box-sizing: border-box;\n",
|
| 703 |
+
" margin-bottom: 0.5em;\n",
|
| 704 |
+
" /* unfitted */\n",
|
| 705 |
+
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
| 706 |
+
"}\n",
|
| 707 |
+
"\n",
|
| 708 |
+
"#sk-container-id-2 div.sk-estimator.fitted {\n",
|
| 709 |
+
" /* fitted */\n",
|
| 710 |
+
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
| 711 |
+
"}\n",
|
| 712 |
+
"\n",
|
| 713 |
+
"/* on hover */\n",
|
| 714 |
+
"#sk-container-id-2 div.sk-estimator:hover {\n",
|
| 715 |
+
" /* unfitted */\n",
|
| 716 |
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 717 |
+
"}\n",
|
| 718 |
+
"\n",
|
| 719 |
+
"#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
|
| 720 |
+
" /* fitted */\n",
|
| 721 |
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 722 |
+
"}\n",
|
| 723 |
+
"\n",
|
| 724 |
+
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
|
| 725 |
+
"\n",
|
| 726 |
+
"/* Common style for \"i\" and \"?\" */\n",
|
| 727 |
+
"\n",
|
| 728 |
+
".sk-estimator-doc-link,\n",
|
| 729 |
+
"a:link.sk-estimator-doc-link,\n",
|
| 730 |
+
"a:visited.sk-estimator-doc-link {\n",
|
| 731 |
+
" float: right;\n",
|
| 732 |
+
" font-size: smaller;\n",
|
| 733 |
+
" line-height: 1em;\n",
|
| 734 |
+
" font-family: monospace;\n",
|
| 735 |
+
" background-color: var(--sklearn-color-background);\n",
|
| 736 |
+
" border-radius: 1em;\n",
|
| 737 |
+
" height: 1em;\n",
|
| 738 |
+
" width: 1em;\n",
|
| 739 |
+
" text-decoration: none !important;\n",
|
| 740 |
+
" margin-left: 0.5em;\n",
|
| 741 |
+
" text-align: center;\n",
|
| 742 |
+
" /* unfitted */\n",
|
| 743 |
+
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
| 744 |
+
" color: var(--sklearn-color-unfitted-level-1);\n",
|
| 745 |
+
"}\n",
|
| 746 |
+
"\n",
|
| 747 |
+
".sk-estimator-doc-link.fitted,\n",
|
| 748 |
+
"a:link.sk-estimator-doc-link.fitted,\n",
|
| 749 |
+
"a:visited.sk-estimator-doc-link.fitted {\n",
|
| 750 |
+
" /* fitted */\n",
|
| 751 |
+
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
| 752 |
+
" color: var(--sklearn-color-fitted-level-1);\n",
|
| 753 |
+
"}\n",
|
| 754 |
+
"\n",
|
| 755 |
+
"/* On hover */\n",
|
| 756 |
+
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
|
| 757 |
+
".sk-estimator-doc-link:hover,\n",
|
| 758 |
+
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
|
| 759 |
+
".sk-estimator-doc-link:hover {\n",
|
| 760 |
+
" /* unfitted */\n",
|
| 761 |
+
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
| 762 |
+
" color: var(--sklearn-color-background);\n",
|
| 763 |
+
" text-decoration: none;\n",
|
| 764 |
+
"}\n",
|
| 765 |
+
"\n",
|
| 766 |
+
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
|
| 767 |
+
".sk-estimator-doc-link.fitted:hover,\n",
|
| 768 |
+
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
|
| 769 |
+
".sk-estimator-doc-link.fitted:hover {\n",
|
| 770 |
+
" /* fitted */\n",
|
| 771 |
+
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
| 772 |
+
" color: var(--sklearn-color-background);\n",
|
| 773 |
+
" text-decoration: none;\n",
|
| 774 |
+
"}\n",
|
| 775 |
+
"\n",
|
| 776 |
+
"/* Span, style for the box shown on hovering the info icon */\n",
|
| 777 |
+
".sk-estimator-doc-link span {\n",
|
| 778 |
+
" display: none;\n",
|
| 779 |
+
" z-index: 9999;\n",
|
| 780 |
+
" position: relative;\n",
|
| 781 |
+
" font-weight: normal;\n",
|
| 782 |
+
" right: .2ex;\n",
|
| 783 |
+
" padding: .5ex;\n",
|
| 784 |
+
" margin: .5ex;\n",
|
| 785 |
+
" width: min-content;\n",
|
| 786 |
+
" min-width: 20ex;\n",
|
| 787 |
+
" max-width: 50ex;\n",
|
| 788 |
+
" color: var(--sklearn-color-text);\n",
|
| 789 |
+
" box-shadow: 2pt 2pt 4pt #999;\n",
|
| 790 |
+
" /* unfitted */\n",
|
| 791 |
+
" background: var(--sklearn-color-unfitted-level-0);\n",
|
| 792 |
+
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
|
| 793 |
+
"}\n",
|
| 794 |
+
"\n",
|
| 795 |
+
".sk-estimator-doc-link.fitted span {\n",
|
| 796 |
+
" /* fitted */\n",
|
| 797 |
+
" background: var(--sklearn-color-fitted-level-0);\n",
|
| 798 |
+
" border: var(--sklearn-color-fitted-level-3);\n",
|
| 799 |
+
"}\n",
|
| 800 |
+
"\n",
|
| 801 |
+
".sk-estimator-doc-link:hover span {\n",
|
| 802 |
+
" display: block;\n",
|
| 803 |
+
"}\n",
|
| 804 |
+
"\n",
|
| 805 |
+
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
|
| 806 |
+
"\n",
|
| 807 |
+
"#sk-container-id-2 a.estimator_doc_link {\n",
|
| 808 |
+
" float: right;\n",
|
| 809 |
+
" font-size: 1rem;\n",
|
| 810 |
+
" line-height: 1em;\n",
|
| 811 |
+
" font-family: monospace;\n",
|
| 812 |
+
" background-color: var(--sklearn-color-background);\n",
|
| 813 |
+
" border-radius: 1rem;\n",
|
| 814 |
+
" height: 1rem;\n",
|
| 815 |
+
" width: 1rem;\n",
|
| 816 |
+
" text-decoration: none;\n",
|
| 817 |
+
" /* unfitted */\n",
|
| 818 |
+
" color: var(--sklearn-color-unfitted-level-1);\n",
|
| 819 |
+
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
| 820 |
+
"}\n",
|
| 821 |
+
"\n",
|
| 822 |
+
"#sk-container-id-2 a.estimator_doc_link.fitted {\n",
|
| 823 |
+
" /* fitted */\n",
|
| 824 |
+
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
| 825 |
+
" color: var(--sklearn-color-fitted-level-1);\n",
|
| 826 |
+
"}\n",
|
| 827 |
+
"\n",
|
| 828 |
+
"/* On hover */\n",
|
| 829 |
+
"#sk-container-id-2 a.estimator_doc_link:hover {\n",
|
| 830 |
+
" /* unfitted */\n",
|
| 831 |
+
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
| 832 |
+
" color: var(--sklearn-color-background);\n",
|
| 833 |
+
" text-decoration: none;\n",
|
| 834 |
+
"}\n",
|
| 835 |
+
"\n",
|
| 836 |
+
"#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
|
| 837 |
+
" /* fitted */\n",
|
| 838 |
+
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
| 839 |
+
"}\n",
|
| 840 |
+
"</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(class_weight='balanced', max_depth=20,\n",
|
| 841 |
+
" min_samples_leaf=2, n_estimators=300, n_jobs=-1,\n",
|
| 842 |
+
" random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(class_weight='balanced', max_depth=20,\n",
|
| 843 |
+
" min_samples_leaf=2, n_estimators=300, n_jobs=-1,\n",
|
| 844 |
+
" random_state=42)</pre></div> </div></div></div></div>"
|
| 845 |
+
],
|
| 846 |
+
"text/plain": [
|
| 847 |
+
"RandomForestClassifier(class_weight='balanced', max_depth=20,\n",
|
| 848 |
+
" min_samples_leaf=2, n_estimators=300, n_jobs=-1,\n",
|
| 849 |
+
" random_state=42)"
|
| 850 |
+
]
|
| 851 |
+
},
|
| 852 |
+
"execution_count": 23,
|
| 853 |
+
"metadata": {},
|
| 854 |
+
"output_type": "execute_result"
|
| 855 |
+
}
|
| 856 |
+
],
|
| 857 |
"source": [
|
| 858 |
"from sklearn.ensemble import RandomForestClassifier\n",
|
| 859 |
"\n",
|
|
|
|
| 871 |
},
|
| 872 |
{
|
| 873 |
"cell_type": "code",
|
| 874 |
+
"execution_count": 24,
|
| 875 |
"metadata": {
|
| 876 |
"execution": {
|
| 877 |
+
"iopub.execute_input": "2026-01-20T09:42:15.736130Z",
|
| 878 |
+
"iopub.status.busy": "2026-01-20T09:42:15.735775Z",
|
| 879 |
+
"iopub.status.idle": "2026-01-20T09:42:15.851114Z",
|
| 880 |
+
"shell.execute_reply": "2026-01-20T09:42:15.850291Z",
|
| 881 |
+
"shell.execute_reply.started": "2026-01-20T09:42:15.736093Z"
|
| 882 |
},
|
| 883 |
"trusted": true
|
| 884 |
},
|
| 885 |
+
"outputs": [
|
| 886 |
+
{
|
| 887 |
+
"name": "stdout",
|
| 888 |
+
"output_type": "stream",
|
| 889 |
+
"text": [
|
| 890 |
+
"Accuracy: 0.8785942492012779\n",
|
| 891 |
+
" precision recall f1-score support\n",
|
| 892 |
+
"\n",
|
| 893 |
+
" 0 0.90 0.87 0.89 169\n",
|
| 894 |
+
" 1 0.85 0.89 0.87 144\n",
|
| 895 |
+
"\n",
|
| 896 |
+
" accuracy 0.88 313\n",
|
| 897 |
+
" macro avg 0.88 0.88 0.88 313\n",
|
| 898 |
+
"weighted avg 0.88 0.88 0.88 313\n",
|
| 899 |
+
"\n"
|
| 900 |
+
]
|
| 901 |
+
}
|
| 902 |
+
],
|
| 903 |
"source": [
|
| 904 |
"preds = rf.predict(X_test)\n",
|
| 905 |
"\n",
|
|
|
|
| 909 |
},
|
| 910 |
{
|
| 911 |
"cell_type": "code",
|
| 912 |
+
"execution_count": 25,
|
| 913 |
"metadata": {
|
| 914 |
"execution": {
|
| 915 |
+
"iopub.execute_input": "2026-01-20T09:42:15.853420Z",
|
| 916 |
+
"iopub.status.busy": "2026-01-20T09:42:15.853099Z",
|
| 917 |
+
"iopub.status.idle": "2026-01-20T09:42:15.919231Z",
|
| 918 |
+
"shell.execute_reply": "2026-01-20T09:42:15.918360Z",
|
| 919 |
+
"shell.execute_reply.started": "2026-01-20T09:42:15.853391Z"
|
| 920 |
},
|
| 921 |
"trusted": true
|
| 922 |
},
|
| 923 |
+
"outputs": [
|
| 924 |
+
{
|
| 925 |
+
"name": "stdout",
|
| 926 |
+
"output_type": "stream",
|
| 927 |
+
"text": [
|
| 928 |
+
" feature importance\n",
|
| 929 |
+
"1 friends_count 0.204309\n",
|
| 930 |
+
"9 follow_ratio 0.144836\n",
|
| 931 |
+
"3 favourites_count 0.135528\n",
|
| 932 |
+
"0 followers_count 0.109556\n",
|
| 933 |
+
"5 verified 0.099516\n",
|
| 934 |
+
"10 account_age_days 0.090862\n",
|
| 935 |
+
"2 listedcount 0.088300\n",
|
| 936 |
+
"4 statuses_count 0.076216\n",
|
| 937 |
+
"6 default_profile 0.039780\n",
|
| 938 |
+
"8 has_extended_profile 0.008163\n",
|
| 939 |
+
"7 default_profile_image 0.002935\n"
|
| 940 |
+
]
|
| 941 |
+
}
|
| 942 |
+
],
|
| 943 |
"source": [
|
| 944 |
"imp = pd.DataFrame({\n",
|
| 945 |
" \"feature\": X.columns,\n",
|
|
|
|
| 949 |
"print(imp)"
|
| 950 |
]
|
| 951 |
},
|
| 952 |
+
{
|
| 953 |
+
"cell_type": "code",
|
| 954 |
+
"execution_count": 26,
|
| 955 |
+
"metadata": {
|
| 956 |
+
"execution": {
|
| 957 |
+
"iopub.execute_input": "2026-01-20T09:42:15.920668Z",
|
| 958 |
+
"iopub.status.busy": "2026-01-20T09:42:15.920341Z",
|
| 959 |
+
"iopub.status.idle": "2026-01-20T09:42:16.022530Z",
|
| 960 |
+
"shell.execute_reply": "2026-01-20T09:42:16.021678Z",
|
| 961 |
+
"shell.execute_reply.started": "2026-01-20T09:42:15.920632Z"
|
| 962 |
+
},
|
| 963 |
+
"trusted": true
|
| 964 |
+
},
|
| 965 |
+
"outputs": [
|
| 966 |
+
{
|
| 967 |
+
"data": {
|
| 968 |
+
"text/plain": [
|
| 969 |
+
"['bot_model.joblib']"
|
| 970 |
+
]
|
| 971 |
+
},
|
| 972 |
+
"execution_count": 26,
|
| 973 |
+
"metadata": {},
|
| 974 |
+
"output_type": "execute_result"
|
| 975 |
+
}
|
| 976 |
+
],
|
| 977 |
+
"source": [
|
| 978 |
+
"import joblib\n",
|
| 979 |
+
"\n",
|
| 980 |
+
"joblib.dump(rf, \"bot_model.joblib\")"
|
| 981 |
+
]
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"cell_type": "code",
|
| 985 |
+
"execution_count": 27,
|
| 986 |
+
"metadata": {
|
| 987 |
+
"execution": {
|
| 988 |
+
"iopub.execute_input": "2026-01-20T09:42:16.024523Z",
|
| 989 |
+
"iopub.status.busy": "2026-01-20T09:42:16.023646Z",
|
| 990 |
+
"iopub.status.idle": "2026-01-20T09:42:16.029010Z",
|
| 991 |
+
"shell.execute_reply": "2026-01-20T09:42:16.028344Z",
|
| 992 |
+
"shell.execute_reply.started": "2026-01-20T09:42:16.024490Z"
|
| 993 |
+
},
|
| 994 |
+
"trusted": true
|
| 995 |
+
},
|
| 996 |
+
"outputs": [
|
| 997 |
+
{
|
| 998 |
+
"name": "stdout",
|
| 999 |
+
"output_type": "stream",
|
| 1000 |
+
"text": [
|
| 1001 |
+
"RF trained feature count: 11\n",
|
| 1002 |
+
"RF trained feature names:\n",
|
| 1003 |
+
"['followers_count', 'friends_count', 'listedcount', 'favourites_count', 'statuses_count', 'verified', 'default_profile', 'default_profile_image', 'has_extended_profile', 'follow_ratio', 'account_age_days']\n"
|
| 1004 |
+
]
|
| 1005 |
+
}
|
| 1006 |
+
],
|
| 1007 |
+
"source": [
|
| 1008 |
+
"# β
After training RF\n",
|
| 1009 |
+
"print(\"RF trained feature count:\", len(rf.feature_names_in_))\n",
|
| 1010 |
+
"print(\"RF trained feature names:\")\n",
|
| 1011 |
+
"print(list(rf.feature_names_in_))\n"
|
| 1012 |
+
]
|
| 1013 |
+
},
|
| 1014 |
{
|
| 1015 |
"cell_type": "code",
|
| 1016 |
"execution_count": null,
|
|
|
|
| 1052 |
"name": "python",
|
| 1053 |
"nbconvert_exporter": "python",
|
| 1054 |
"pygments_lexer": "ipython3",
|
| 1055 |
+
"version": "3.10.11"
|
| 1056 |
}
|
| 1057 |
},
|
| 1058 |
"nbformat": 4,
|