churnkit 0.76.0a3__py3-none-any.whl → 0.76.1a2__py3-none-any.whl

{churnkit-0.76.0a3.data → churnkit-0.76.1a2.data}/data/share/churnkit/exploration_notebooks/02a_text_columns_deep_dive.ipynb

@@ -112,22 +112,27 @@
    "outputs": [],
    "source": [
     "from customer_retention.analysis.notebook_progress import track_and_export_previous\n",
+    "\n",
     "track_and_export_previous(\"02a_text_columns_deep_dive.ipynb\")\n",
     "\n",
-    "from customer_retention.analysis.auto_explorer import ExplorationFindings, TextProcessingMetadata\n",
-    "from customer_retention.analysis.visualization import ChartBuilder, display_figure, display_table, console\n",
-    "from customer_retention.core.config.column_config import ColumnType\n",
-    "from customer_retention.stages.profiling import (\n",
-    "    TextColumnProcessor, TextProcessingConfig, TextColumnResult,\n",
-    "    TextEmbedder, TextDimensionalityReducer,\n",
-    "    EMBEDDING_MODELS, get_model_info, list_available_models\n",
-    ")\n",
-    "import pandas as pd\n",
     "import numpy as np\n",
-    "import plotly.graph_objects as go\n",
     "import plotly.express as px\n",
+    "import plotly.graph_objects as go\n",
     "from plotly.subplots import make_subplots\n",
-    "from customer_retention.core.config.experiments import FINDINGS_DIR, EXPERIMENTS_DIR, OUTPUT_DIR, setup_experiments_structure"
+    "\n",
+    "from customer_retention.analysis.auto_explorer import ExplorationFindings, TextProcessingMetadata\n",
+    "from customer_retention.analysis.visualization import ChartBuilder, display_figure\n",
+    "from customer_retention.core.config.column_config import ColumnType\n",
+    "from customer_retention.core.config.experiments import (\n",
+    "    EXPERIMENTS_DIR,\n",
+    "    FINDINGS_DIR,\n",
+    ")\n",
+    "from customer_retention.stages.profiling import (\n",
+    "    TextColumnProcessor,\n",
+    "    TextProcessingConfig,\n",
+    "    get_model_info,\n",
+    "    list_available_models,\n",
+    ")"
    ]
   },
   {
@@ -249,7 +254,7 @@
    },
    "outputs": [],
    "source": [
-    "from customer_retention.stages.temporal import load_data_with_snapshot_preference, TEMPORAL_METADATA_COLS\n",
+    "from customer_retention.stages.temporal import load_data_with_snapshot_preference\n",
     "\n",
     "df, data_source = load_data_with_snapshot_preference(findings, output_dir=str(FINDINGS_DIR))\n",
     "charts = ChartBuilder()\n",
@@ -427,27 +432,27 @@
     "        print(f\"\\n{'='*70}\")\n",
     "        print(f\"Column: {col_name}\")\n",
     "        print(f\"{'='*70}\")\n",
-    "        \n",
+    "\n",
     "        text_series = df[col_name].fillna(\"\")\n",
-    "        \n",
+    "\n",
     "        # Basic statistics\n",
     "        non_empty = (text_series.str.len() > 0).sum()\n",
     "        avg_length = text_series.str.len().mean()\n",
     "        max_length = text_series.str.len().max()\n",
-    "        \n",
-    "        print(f\"\\n\\U0001f4ca Statistics:\")\n",
+    "\n",
+    "        print(\"\\n\\U0001f4ca Statistics:\")\n",
     "        print(f\"   Total rows: {len(text_series):,}\")\n",
     "        print(f\"   Non-empty: {non_empty:,} ({non_empty/len(text_series)*100:.1f}%)\")\n",
     "        print(f\"   Avg length: {avg_length:.0f} characters\")\n",
     "        print(f\"   Max length: {max_length:,} characters\")\n",
-    "        \n",
+    "\n",
     "        # Sample texts\n",
-    "        print(f\"\\n\\U0001f4dd Sample texts:\")\n",
+    "        print(\"\\n\\U0001f4dd Sample texts:\")\n",
     "        samples = text_series[text_series.str.len() > 10].head(3)\n",
     "        for i, sample in enumerate(samples, 1):\n",
     "            truncated = sample[:100] + \"...\" if len(sample) > 100 else sample\n",
     "            print(f\"   {i}. {truncated}\")\n",
-    "        \n",
+    "\n",
     "        # Text length distribution\n",
     "        lengths = text_series.str.len()\n",
     "        fig = go.Figure()\n",
@@ -511,27 +516,27 @@
    "source": [
     "if text_columns:\n",
     "    processor = TextColumnProcessor(config)\n",
-    "    \n",
+    "\n",
     "    print(\"Processing TEXT columns...\")\n",
     "    print(\"(This may take a moment for large datasets)\\n\")\n",
-    "    \n",
+    "\n",
     "    results = []\n",
     "    df_processed = df.copy()\n",
-    "    \n",
+    "\n",
     "    for col_name in text_columns:\n",
     "        print(f\"\\n{'='*70}\")\n",
     "        print(f\"Processing: {col_name}\")\n",
     "        print(f\"{'='*70}\")\n",
-    "        \n",
+    "\n",
     "        df_processed, result = processor.process_column(df_processed, col_name)\n",
     "        results.append(result)\n",
-    "        \n",
-    "        print(f\"\\n\\u2705 Processing complete:\")\n",
+    "\n",
+    "        print(\"\\n\\u2705 Processing complete:\")\n",
     "        print(f\"   Embedding shape: {result.embeddings_shape}\")\n",
     "        print(f\"   Components kept: {result.n_components}\")\n",
     "        print(f\"   Explained variance: {result.explained_variance:.1%}\")\n",
     "        print(f\"   Features created: {', '.join(result.component_columns)}\")\n",
-    "    \n",
+    "\n",
     "    print(f\"\\n\\n{'='*70}\")\n",
     "    print(\"PROCESSING SUMMARY\")\n",
     "    print(f\"{'='*70}\")\n",
@@ -586,32 +591,32 @@
     "        print(f\"\\n{'='*70}\")\n",
     "        print(f\"Results: {result.column_name}\")\n",
     "        print(f\"{'='*70}\")\n",
-    "        \n",
+    "\n",
     "        # Explained variance per component\n",
     "        reducer = processor._reducers[result.column_name]\n",
     "        var_ratios = reducer._pca.explained_variance_ratio_\n",
     "        cumulative = np.cumsum(var_ratios)\n",
-    "        \n",
+    "\n",
     "        fig = make_subplots(rows=1, cols=2,\n",
     "                            subplot_titles=(\"Variance per Component\", \"Cumulative Variance\"))\n",
-    "        \n",
+    "\n",
     "        fig.add_trace(go.Bar(\n",
     "            x=[f\"PC{i+1}\" for i in range(len(var_ratios))],\n",
     "            y=var_ratios,\n",
     "            marker_color='steelblue'\n",
     "        ), row=1, col=1)\n",
-    "        \n",
+    "\n",
     "        fig.add_trace(go.Scatter(\n",
     "            x=[f\"PC{i+1}\" for i in range(len(cumulative))],\n",
     "            y=cumulative,\n",
     "            mode='lines+markers',\n",
     "            line_color='green'\n",
     "        ), row=1, col=2)\n",
-    "        \n",
+    "\n",
     "        fig.add_hline(y=config.variance_threshold, line_dash=\"dash\", line_color=\"red\",\n",
     "                      annotation_text=f\"Target: {config.variance_threshold:.0%}\",\n",
     "                      row=1, col=2)\n",
-    "        \n",
+    "\n",
     "        fig.update_layout(\n",
     "            title=f\"PCA Results: {result.column_name}\",\n",
     "            height=400,\n",
@@ -621,7 +626,7 @@
     "        fig.update_yaxes(title_text=\"Variance Ratio\", row=1, col=1)\n",
     "        fig.update_yaxes(title_text=\"Cumulative Variance\", row=1, col=2)\n",
     "        display_figure(fig)\n",
-    "        \n",
+    "\n",
     "        # PC feature distributions\n",
     "        if len(result.component_columns) >= 2:\n",
     "            fig = px.scatter(\n",
@@ -687,16 +692,17 @@
     "            processing_approach=\"pca\"\n",
     "        )\n",
     "        findings.text_processing[result.column_name] = metadata\n",
-    "        \n",
+    "\n",
     "        print(f\"\\u2705 Added metadata for {result.column_name}:\")\n",
     "        print(f\"   Model: {metadata.embedding_model}\")\n",
     "        print(f\"   Components: {metadata.n_components}\")\n",
     "        print(f\"   Explained variance: {metadata.explained_variance:.1%}\")\n",
-    "    \n",
+    "\n",
     "    findings.save(FINDINGS_PATH)\n",
     "    print(f\"\\nFindings saved to: {FINDINGS_PATH}\")\n",
     "\n",
     "from customer_retention.analysis.notebook_html_exporter import export_notebook_html\n",
+    "\n",
     "export_notebook_html(Path(\"02a_text_columns_deep_dive.ipynb\"), EXPERIMENTS_DIR / \"docs\")\n"
    ]
   },
@@ -743,15 +749,15 @@
     "    print(\"\\n\" + \"=\"*70)\n",
     "    print(\"PRODUCTION RECOMMENDATIONS\")\n",
     "    print(\"=\"*70)\n",
-    "    \n",
+    "\n",
     "    for result in results:\n",
     "        print(f\"\\n\\U0001f527 {result.column_name}:\")\n",
-    "        print(f\"   Action: embed_reduce (embeddings + PCA)\")\n",
+    "        print(\"   Action: embed_reduce (embeddings + PCA)\")\n",
     "        print(f\"   Model: {config.embedding_model}\")\n",
     "        print(f\"   Variance threshold: {config.variance_threshold:.0%}\")\n",
     "        print(f\"   Expected features: {result.n_components}\")\n",
     "        print(f\"   Feature names: {', '.join(result.component_columns[:3])}...\")\n",
-    "    \n",
+    "\n",
     "    print(\"\\n\\U0001f4a1 These recommendations will be used by the pipeline generator.\")\n",
     "    print(\"   The same processing will be applied in production.\")"
    ]