churnkit 0.76.1a1__py3-none-any.whl → 0.76.1a2__py3-none-any.whl

{churnkit-0.76.1a1.data → churnkit-0.76.1a2.data}/data/share/churnkit/exploration_notebooks/02_column_deep_dive.ipynb

@@ -73,24 +73,28 @@
    "outputs": [],
    "source": [
     "from customer_retention.analysis.notebook_progress import track_and_export_previous\n",
+    "\n",
     "track_and_export_previous(\"02_column_deep_dive.ipynb\")\n",
     "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import plotly.graph_objects as go\n",
+    "from scipy import stats\n",
+    "\n",
     "from customer_retention.analysis.auto_explorer import ExplorationFindings, RecommendationRegistry\n",
-    "from customer_retention.analysis.visualization import ChartBuilder, display_figure, display_table, console\n",
+    "from customer_retention.analysis.visualization import ChartBuilder, console, display_figure, display_table\n",
     "from customer_retention.core.config.column_config import ColumnType\n",
+    "from customer_retention.core.config.experiments import (\n",
+    "    FINDINGS_DIR,\n",
+    ")\n",
     "from customer_retention.stages.profiling import (\n",
-    "    DistributionAnalyzer, TransformationType,\n",
-    "    TemporalAnalyzer, TemporalGranularity,\n",
-    "    CategoricalDistributionAnalyzer, EncodingType\n",
+    "    CategoricalDistributionAnalyzer,\n",
+    "    DistributionAnalyzer,\n",
+    "    TemporalAnalyzer,\n",
+    "    TemporalGranularity,\n",
+    "    TransformationType,\n",
     ")\n",
-    "from customer_retention.stages.validation import DataValidator, RuleGenerator\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "from scipy import stats\n",
-    "import plotly.graph_objects as go\n",
-    "import plotly.express as px\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.stages.validation import DataValidator, RuleGenerator\n"
    ]
   },
   {
@@ -121,7 +125,6 @@
     "\n",
     "# Option 2: Auto-discover findings file (prefers aggregated over event-level)\n",
     "from pathlib import Path\n",
-    "import os\n",
     "\n",
     "# FINDINGS_DIR imported from customer_retention.core.config.experiments\n",
     "\n",
@@ -157,9 +160,9 @@
     "# Warn if this is event-level data (should run 01d first)\n",
     "if findings.is_time_series and \"_aggregated\" not in FINDINGS_PATH:\n",
     "    ts_meta = findings.time_series_metadata\n",
-    "    print(f\"\\n⚠️  WARNING: This appears to be EVENT-LEVEL data\")\n",
+    "    print(\"\\n⚠️  WARNING: This appears to be EVENT-LEVEL data\")\n",
     "    print(f\"   Entity: {ts_meta.entity_column}, Time: {ts_meta.time_column}\")\n",
-    "    print(f\"   Recommendation: Run 01d_event_aggregation.ipynb first to create entity-level data\")"
+    "    print(\"   Recommendation: Run 01d_event_aggregation.ipynb first to create entity-level data\")"
    ]
   },
   {
@@ -202,7 +205,7 @@
    "outputs": [],
    "source": [
     "# Load data - handle aggregated parquet files directly\n",
-    "from customer_retention.stages.temporal import load_data_with_snapshot_preference, TEMPORAL_METADATA_COLS\n",
+    "from customer_retention.stages.temporal import TEMPORAL_METADATA_COLS, load_data_with_snapshot_preference\n",
     "\n",
     "# For aggregated data, load directly from the parquet source\n",
     "if \"_aggregated\" in FINDINGS_PATH and findings.source_path.endswith('.parquet'):\n",
@@ -301,20 +304,20 @@
     "\n",
     "if range_rules:\n",
     "    range_results = validator.validate_value_ranges(df, range_rules)\n",
-    "    \n",
+    "\n",
     "    issues_found = []\n",
     "    for r in range_results:\n",
     "        detail = f\"{r.invalid_values} invalid\" if r.invalid_values > 0 else None\n",
     "        console.check(f\"{r.column_name} ({r.rule_type})\", r.invalid_values == 0, detail)\n",
     "        if r.invalid_values > 0:\n",
     "            issues_found.append(r)\n",
-    "    \n",
+    "\n",
     "    all_invalid = sum(r.invalid_values for r in range_results)\n",
     "    if all_invalid == 0:\n",
     "        console.success(\"All value ranges valid\")\n",
     "    else:\n",
     "        console.error(f\"Found {all_invalid:,} values outside expected ranges\")\n",
-    "        \n",
+    "\n",
     "        console.info(\"Examples of invalid values:\")\n",
     "        for r in issues_found[:3]:\n",
     "            col = r.column_name\n",
@@ -333,19 +336,19 @@
     "                    condition = \"value < 0 or value > 1\"\n",
     "                else:\n",
     "                    continue\n",
-    "                \n",
+    "\n",
     "                invalid_values = df.loc[invalid_mask, col].dropna()\n",
     "                if len(invalid_values) > 0:\n",
     "                    examples = invalid_values.head(5).tolist()\n",
     "                    console.metric(f\"  {col}\", f\"{examples}\")\n",
-    "                    \n",
+    "\n",
     "                    # Add filtering recommendation\n",
     "                    registry.add_bronze_filtering(\n",
     "                        column=col, condition=condition, action=\"cap\",\n",
     "                        rationale=f\"{r.invalid_values} values violate {r.rule_type} constraint\",\n",
     "                        source_notebook=\"02_column_deep_dive\"\n",
     "                    )\n",
-    "    \n",
+    "\n",
     "    console.info(\"Rules auto-generated from detected column types\")\n",
     "else:\n",
     "    range_results = []\n",
@@ -425,32 +428,32 @@
     "\n",
     "# Analyze all numeric columns using the framework\n",
     "analyses = analyzer.analyze_dataframe(df, numeric_cols)\n",
-    "recommendations = {col: analyzer.recommend_transformation(analysis) \n",
+    "recommendations = {col: analyzer.recommend_transformation(analysis)\n",
     "                   for col, analysis in analyses.items()}\n",
     "\n",
     "for col_name in numeric_cols:\n",
     "    col_info = findings.columns[col_name]\n",
     "    analysis = analyses.get(col_name)\n",
     "    rec = recommendations.get(col_name)\n",
-    "    \n",
+    "\n",
     "    print(f\"\\n{'='*70}\")\n",
     "    print(f\"Column: {col_name}\")\n",
     "    print(f\"Type: {col_info.inferred_type.value} (Confidence: {col_info.confidence:.0%})\")\n",
-    "    print(f\"-\" * 70)\n",
-    "    \n",
+    "    print(\"-\" * 70)\n",
+    "\n",
     "    if analysis:\n",
-    "        print(f\"📊 Distribution Statistics:\")\n",
+    "        print(\"📊 Distribution Statistics:\")\n",
     "        print(f\"   Mean: {analysis.mean:.3f}  |  Median: {analysis.median:.3f}  |  Std: {analysis.std:.3f}\")\n",
     "        print(f\"   Range: [{analysis.min_value:.3f}, {analysis.max_value:.3f}]\")\n",
     "        print(f\"   Percentiles: 1%={analysis.percentiles['p1']:.3f}, 25%={analysis.q1:.3f}, 75%={analysis.q3:.3f}, 99%={analysis.percentiles['p99']:.3f}\")\n",
-    "        print(f\"\\n📈 Shape Analysis:\")\n",
+    "        print(\"\\n📈 Shape Analysis:\")\n",
     "        skew_label = '(Right-skewed)' if analysis.skewness > 0.5 else '(Left-skewed)' if analysis.skewness < -0.5 else '(Symmetric)'\n",
     "        print(f\"   Skewness: {analysis.skewness:.2f} {skew_label}\")\n",
     "        kurt_label = '(Heavy tails/outliers)' if analysis.kurtosis > 3 else '(Light tails)'\n",
     "        print(f\"   Kurtosis: {analysis.kurtosis:.2f} {kurt_label}\")\n",
     "        print(f\"   Zeros: {analysis.zero_count:,} ({analysis.zero_percentage:.1f}%)\")\n",
     "        print(f\"   Outliers (IQR): {analysis.outlier_count_iqr:,} ({analysis.outlier_percentage:.1f}%)\")\n",
-    "        \n",
+    "\n",
     "        if rec:\n",
     "            print(f\"\\n🔧 Recommended Transformation: {rec.recommended_transform.value}\")\n",
     "            print(f\"   Reason: {rec.reason}\")\n",
@@ -458,45 +461,45 @@
     "            if rec.warnings:\n",
     "                for warn in rec.warnings:\n",
     "                    print(f\"   ⚠️ {warn}\")\n",
-    "    \n",
+    "\n",
     "    # Create enhanced histogram with Plotly\n",
     "    data = df[col_name].dropna()\n",
     "    fig = go.Figure()\n",
-    "    \n",
+    "\n",
     "    fig.add_trace(go.Histogram(x=data, nbinsx=50, name='Distribution',\n",
     "                                marker_color='steelblue', opacity=0.7))\n",
-    "    \n",
+    "\n",
     "    # Calculate mean and median\n",
     "    mean_val = data.mean()\n",
     "    median_val = data.median()\n",
-    "    \n",
+    "\n",
     "    # Position labels on opposite sides (left/right) to avoid overlap\n",
     "    # The larger value gets right-justified, smaller gets left-justified\n",
     "    mean_position = \"top right\" if mean_val >= median_val else \"top left\"\n",
     "    median_position = \"top left\" if mean_val >= median_val else \"top right\"\n",
-    "    \n",
+    "\n",
     "    # Add mean line\n",
     "    fig.add_vline(\n",
-    "        x=mean_val, \n",
-    "        line_dash=\"dash\", \n",
+    "        x=mean_val,\n",
+    "        line_dash=\"dash\",\n",
     "        line_color=\"red\",\n",
     "        annotation_text=f\"Mean: {mean_val:.2f}\",\n",
     "        annotation_position=mean_position,\n",
     "        annotation_font_color=\"red\",\n",
     "        annotation_bgcolor=\"rgba(255,255,255,0.8)\"\n",
     "    )\n",
-    "    \n",
+    "\n",
     "    # Add median line\n",
     "    fig.add_vline(\n",
-    "        x=median_val, \n",
-    "        line_dash=\"solid\", \n",
+    "        x=median_val,\n",
+    "        line_dash=\"solid\",\n",
     "        line_color=\"green\",\n",
     "        annotation_text=f\"Median: {median_val:.2f}\",\n",
     "        annotation_position=median_position,\n",
     "        annotation_font_color=\"green\",\n",
     "        annotation_bgcolor=\"rgba(255,255,255,0.8)\"\n",
     "    )\n",
-    "    \n",
+    "\n",
     "    # Add 99th percentile marker if there are outliers\n",
     "    if analysis and analysis.outlier_percentage > 5:\n",
     "        fig.add_vline(x=analysis.percentiles['p99'], line_dash=\"dot\", line_color=\"orange\",\n",
@@ -504,7 +507,7 @@
     "                      annotation_position=\"top right\",\n",
     "                      annotation_font_color=\"orange\",\n",
     "                      annotation_bgcolor=\"rgba(255,255,255,0.8)\")\n",
-    "    \n",
+    "\n",
     "    transform_label = rec.recommended_transform.value if rec else \"none\"\n",
     "    fig.update_layout(\n",
     "        title=f\"Distribution: {col_name}<br><sub>Skew: {analysis.skewness:.2f} | Kurt: {analysis.kurtosis:.2f} | Strategy: {transform_label}</sub>\",\n",
@@ -559,16 +562,16 @@
     "                \"skewness\": stats.skew(series),\n",
     "                \"kurtosis\": stats.kurtosis(series)\n",
     "            })\n",
-    "    \n",
+    "\n",
     "    stats_df = pd.DataFrame(stats_data)\n",
-    "    \n",
+    "\n",
     "    # Format for display\n",
     "    display_stats = stats_df.copy()\n",
     "    for col in [\"mean\", \"std\", \"min\", \"25%\", \"50%\", \"75%\", \"95%\", \"99%\", \"max\"]:\n",
     "        display_stats[col] = display_stats[col].apply(lambda x: f\"{x:.3f}\")\n",
     "    display_stats[\"skewness\"] = display_stats[\"skewness\"].apply(lambda x: f\"{x:.3f}\")\n",
     "    display_stats[\"kurtosis\"] = display_stats[\"kurtosis\"].apply(lambda x: f\"{x:.3f}\")\n",
-    "    \n",
+    "\n",
     "    print(\"=\" * 80)\n",
     "    print(\"NUMERICAL FEATURE STATISTICS\")\n",
     "    print(\"=\" * 80)\n",
@@ -621,7 +624,7 @@
     "for col_name in numeric_cols:\n",
     "    analysis = analyses.get(col_name)\n",
     "    rec = recommendations.get(col_name)\n",
-    "    \n",
+    "\n",
     "    if analysis and rec:\n",
     "        summary_data.append({\n",
     "            \"Column\": col_name,\n",
@@ -632,7 +635,7 @@
     "            \"Transform\": rec.recommended_transform.value,\n",
     "            \"Priority\": rec.priority\n",
     "        })\n",
-    "        \n",
+    "\n",
     "        # Add Gold transformation recommendation if not \"none\"\n",
     "        if rec.recommended_transform != TransformationType.NONE and registry.gold:\n",
     "            registry.add_gold_transformation(\n",
@@ -646,7 +649,7 @@
     "if summary_data:\n",
     "    summary_df = pd.DataFrame(summary_data)\n",
     "    display_table(summary_df)\n",
-    "    \n",
+    "\n",
     "    # Show how many transformation recommendations were added\n",
     "    transform_count = sum(1 for r in recommendations.values() if r and r.recommended_transform != TransformationType.NONE)\n",
     "    if transform_count > 0 and registry.gold:\n",
@@ -728,7 +731,7 @@
     "cat_analyses = cat_analyzer.analyze_dataframe(df, categorical_cols)\n",
     "\n",
     "# Get encoding recommendations\n",
-    "cyclical_cols = [name for name, col in findings.columns.items() \n",
+    "cyclical_cols = [name for name, col in findings.columns.items()\n",
     "                 if col.inferred_type == ColumnType.CATEGORICAL_CYCLICAL]\n",
     "cat_recommendations = cat_analyzer.get_all_recommendations(df, categorical_cols, cyclical_columns=cyclical_cols)\n",
     "\n",
@@ -736,56 +739,56 @@
     "    col_info = findings.columns[col_name]\n",
     "    analysis = cat_analyses.get(col_name)\n",
     "    rec = next((r for r in cat_recommendations if r.column_name == col_name), None)\n",
-    "    \n",
+    "\n",
     "    print(f\"\\n{'='*70}\")\n",
     "    print(f\"Column: {col_name}\")\n",
     "    print(f\"Type: {col_info.inferred_type.value} (Confidence: {col_info.confidence:.0%})\")\n",
-    "    print(f\"-\" * 70)\n",
-    "    \n",
+    "    print(\"-\" * 70)\n",
+    "\n",
     "    if analysis:\n",
-    "        print(f\"\\n📊 Distribution Metrics:\")\n",
+    "        print(\"\\n📊 Distribution Metrics:\")\n",
     "        print(f\"   Categories: {analysis.category_count}\")\n",
     "        print(f\"   Imbalance Ratio: {analysis.imbalance_ratio:.1f}x (largest/smallest)\")\n",
     "        print(f\"   Entropy: {analysis.entropy:.2f} ({analysis.normalized_entropy*100:.0f}% of max)\")\n",
     "        print(f\"   Top-1 Concentration: {analysis.top1_concentration:.1f}%\")\n",
     "        print(f\"   Top-3 Concentration: {analysis.top3_concentration:.1f}%\")\n",
     "        print(f\"   Rare Categories (<1%): {analysis.rare_category_count}\")\n",
-    "        \n",
+    "\n",
     "        # Interpretation\n",
-    "        print(f\"\\n📈 Interpretation:\")\n",
+    "        print(\"\\n📈 Interpretation:\")\n",
     "        if analysis.has_low_diversity:\n",
-    "            print(f\"   ⚠️ LOW DIVERSITY: Distribution dominated by few categories\")\n",
+    "            print(\"   ⚠️ LOW DIVERSITY: Distribution dominated by few categories\")\n",
     "        elif analysis.normalized_entropy > 0.9:\n",
-    "            print(f\"   ✓ HIGH DIVERSITY: Categories are relatively balanced\")\n",
+    "            print(\"   ✓ HIGH DIVERSITY: Categories are relatively balanced\")\n",
     "        else:\n",
-    "            print(f\"   ✓ MODERATE DIVERSITY: Some category dominance but acceptable\")\n",
-    "        \n",
+    "            print(\"   ✓ MODERATE DIVERSITY: Some category dominance but acceptable\")\n",
+    "\n",
     "        if analysis.imbalance_ratio > 100:\n",
-    "            print(f\"   🔴 SEVERE IMBALANCE: Rarest category has very few samples\")\n",
+    "            print(\"   🔴 SEVERE IMBALANCE: Rarest category has very few samples\")\n",
     "        elif analysis.is_imbalanced:\n",
-    "            print(f\"   🟡 MODERATE IMBALANCE: Consider grouping rare categories\")\n",
-    "        \n",
+    "            print(\"   🟡 MODERATE IMBALANCE: Consider grouping rare categories\")\n",
+    "\n",
     "        # Recommendations\n",
     "        if rec:\n",
-    "            print(f\"\\n🔧 Recommendations:\")\n",
+    "            print(\"\\n🔧 Recommendations:\")\n",
     "            print(f\"   Encoding: {rec.encoding_type.value}\")\n",
     "            print(f\"   Reason: {rec.reason}\")\n",
     "            print(f\"   Priority: {rec.priority}\")\n",
-    "            \n",
+    "\n",
     "            if rec.preprocessing_steps:\n",
-    "                print(f\"   Preprocessing:\")\n",
+    "                print(\"   Preprocessing:\")\n",
     "                for step in rec.preprocessing_steps:\n",
     "                    print(f\"      • {step}\")\n",
-    "            \n",
+    "\n",
     "            if rec.warnings:\n",
     "                for warn in rec.warnings:\n",
     "                    print(f\"   ⚠️ {warn}\")\n",
-    "    \n",
+    "\n",
     "    # Visualization\n",
     "    value_counts = df[col_name].value_counts()\n",
     "    subtitle = f\"Entropy: {analysis.normalized_entropy*100:.0f}% | Imbalance: {analysis.imbalance_ratio:.1f}x | Rare: {analysis.rare_category_count}\" if analysis else \"\"\n",
     "    fig = charts.bar_chart(\n",
-    "        value_counts.head(10).index.tolist(), \n",
+    "        value_counts.head(10).index.tolist(),\n",
     "        value_counts.head(10).values.tolist(),\n",
     "        title=f\"Top Categories: {col_name}<br><sub>{subtitle}</sub>\"\n",
     "    )\n",
@@ -808,7 +811,7 @@
     "            \"Rare (<1%)\": analysis.rare_category_count,\n",
     "            \"Encoding\": rec.encoding_type.value if rec else \"N/A\"\n",
     "        })\n",
-    "        \n",
+    "\n",
     "        # Add encoding recommendation to Gold layer\n",
     "        if rec and registry.gold:\n",
     "            registry.add_gold_encoding(\n",
@@ -817,9 +820,9 @@
     "                rationale=rec.reason,\n",
     "                source_notebook=\"02_column_deep_dive\"\n",
     "            )\n",
-    "    \n",
+    "\n",
     "    display_table(pd.DataFrame(summary_data))\n",
-    "    \n",
+    "\n",
     "    if registry.gold:\n",
     "        print(f\"\\n✅ Added {len(cat_recommendations)} encoding recommendations to Gold layer\")"
    ]
@@ -900,76 +903,76 @@
     "    print(f\"Column: {col_name}\")\n",
     "    print(f\"Type: {col_info.inferred_type.value} (Confidence: {col_info.confidence:.0%})\")\n",
     "    print(f\"{'='*70}\")\n",
-    "    \n",
+    "\n",
     "    date_series = pd.to_datetime(df[col_name], errors='coerce', format='mixed')\n",
     "    valid_dates = date_series.dropna()\n",
-    "    \n",
+    "\n",
     "    print(f\"\\n📅 Date Range: {valid_dates.min()} to {valid_dates.max()}\")\n",
     "    print(f\"   Nulls: {date_series.isna().sum():,} ({date_series.isna().mean()*100:.1f}%)\")\n",
-    "    \n",
+    "\n",
     "    # Basic temporal analysis\n",
     "    analysis = temporal_analyzer.analyze(date_series)\n",
     "    print(f\"   Auto-detected granularity: {analysis.granularity.value}\")\n",
     "    print(f\"   Span: {analysis.span_days:,} days ({analysis.span_days/365:.1f} years)\")\n",
-    "    \n",
+    "\n",
     "    # Growth analysis\n",
     "    growth = temporal_analyzer.calculate_growth_rate(date_series)\n",
     "    if growth.get(\"has_data\"):\n",
-    "        print(f\"\\n📈 Growth Analysis:\")\n",
+    "        print(\"\\n📈 Growth Analysis:\")\n",
     "        print(f\"   Trend: {growth['trend_direction'].upper()}\")\n",
     "        print(f\"   Overall growth: {growth['overall_growth_pct']:+.1f}%\")\n",
     "        print(f\"   Avg monthly growth: {growth['avg_monthly_growth']:+.1f}%\")\n",
-    "    \n",
+    "\n",
     "    # Seasonality analysis\n",
     "    seasonality = temporal_analyzer.analyze_seasonality(date_series)\n",
     "    if seasonality.has_seasonality:\n",
-    "        print(f\"\\n🔄 Seasonality Detected:\")\n",
+    "        print(\"\\n🔄 Seasonality Detected:\")\n",
     "        print(f\"   Peak months: {', '.join(seasonality.peak_periods[:3])}\")\n",
     "        print(f\"   Trough months: {', '.join(seasonality.trough_periods[:3])}\")\n",
     "        print(f\"   Seasonal strength: {seasonality.seasonal_strength:.2f}\")\n",
-    "    \n",
+    "\n",
     "    # Get recommendations using framework\n",
     "    other_dates = [c for c in datetime_cols if c != col_name]\n",
     "    recommendations = temporal_analyzer.recommend_features(date_series, col_name, other_date_columns=other_dates)\n",
-    "    \n",
+    "\n",
     "    # Group by recommendation type\n",
     "    col_feature_recs = [r for r in recommendations if r.recommendation_type == TemporalRecommendationType.FEATURE_ENGINEERING]\n",
     "    col_modeling_recs = [r for r in recommendations if r.recommendation_type == TemporalRecommendationType.MODELING_STRATEGY]\n",
     "    col_quality_recs = [r for r in recommendations if r.recommendation_type == TemporalRecommendationType.DATA_QUALITY]\n",
-    "    \n",
+    "\n",
     "    feature_engineering_recs.extend(col_feature_recs)\n",
     "    modeling_strategy_recs.extend(col_modeling_recs)\n",
     "    data_quality_recs.extend(col_quality_recs)\n",
-    "    \n",
+    "\n",
     "    # Display recommendations grouped by type\n",
     "    if col_feature_recs:\n",
-    "        print(f\"\\n🛠️ FEATURES TO CREATE:\")\n",
+    "        print(\"\\n🛠️ FEATURES TO CREATE:\")\n",
     "        for rec in col_feature_recs:\n",
     "            priority_icon = \"🔴\" if rec.priority == \"high\" else \"🟡\" if rec.priority == \"medium\" else \"✓\"\n",
     "            print(f\"   {priority_icon} {rec.feature_name} ({rec.category})\")\n",
     "            print(f\"      Why: {rec.reason}\")\n",
     "            if rec.code_hint:\n",
     "                print(f\"      Code: {rec.code_hint}\")\n",
-    "    \n",
+    "\n",
     "    if col_modeling_recs:\n",
-    "        print(f\"\\n⚙️ MODELING CONSIDERATIONS:\")\n",
+    "        print(\"\\n⚙️ MODELING CONSIDERATIONS:\")\n",
     "        for rec in col_modeling_recs:\n",
     "            priority_icon = \"🔴\" if rec.priority == \"high\" else \"🟡\" if rec.priority == \"medium\" else \"✓\"\n",
     "            print(f\"   {priority_icon} {rec.feature_name}\")\n",
     "            print(f\"      Why: {rec.reason}\")\n",
-    "    \n",
+    "\n",
     "    if col_quality_recs:\n",
-    "        print(f\"\\n⚠️ DATA QUALITY ISSUES:\")\n",
+    "        print(\"\\n⚠️ DATA QUALITY ISSUES:\")\n",
     "        for rec in col_quality_recs:\n",
     "            priority_icon = \"🔴\" if rec.priority == \"high\" else \"🟡\" if rec.priority == \"medium\" else \"✓\"\n",
     "            print(f\"   {priority_icon} {rec.feature_name}\")\n",
     "            print(f\"      Why: {rec.reason}\")\n",
     "            if rec.code_hint:\n",
     "                print(f\"      Code: {rec.code_hint}\")\n",
-    "    \n",
+    "\n",
     "    # Standard extractions always available\n",
-    "    print(f\"\\n   Standard extractions available: year, month, day, day_of_week, quarter\")\n",
-    "    \n",
+    "    print(\"\\n   Standard extractions available: year, month, day, day_of_week, quarter\")\n",
+    "\n",
     "    # Store summary\n",
     "    datetime_summaries.append({\n",
     "        \"Column\": col_name,\n",
@@ -980,31 +983,31 @@
     "        \"Modeling Notes\": len(col_modeling_recs),\n",
     "        \"Quality Issues\": len(col_quality_recs)\n",
     "    })\n",
-    "    \n",
+    "\n",
     "    # === VISUALIZATIONS ===\n",
-    "    \n",
+    "\n",
     "    if growth.get(\"has_data\"):\n",
     "        fig = charts.growth_summary_indicators(growth, title=f\"Growth Summary: {col_name}\")\n",
     "        display_figure(fig)\n",
-    "    \n",
+    "\n",
     "    chart_type = \"line\" if analysis.granularity in [TemporalGranularity.DAY, TemporalGranularity.WEEK] else \"bar\"\n",
     "    fig = charts.temporal_distribution(analysis, title=f\"Records Over Time: {col_name}\", chart_type=chart_type)\n",
     "    display_figure(fig)\n",
-    "    \n",
+    "\n",
     "    fig = charts.temporal_trend(analysis, title=f\"Trend Analysis: {col_name}\")\n",
     "    display_figure(fig)\n",
-    "    \n",
+    "\n",
     "    yoy_data = temporal_analyzer.year_over_year_comparison(date_series)\n",
     "    if len(yoy_data) > 1:\n",
     "        fig = charts.year_over_year_lines(yoy_data, title=f\"Year-over-Year: {col_name}\")\n",
     "        display_figure(fig)\n",
     "        fig = charts.year_month_heatmap(yoy_data, title=f\"Records Heatmap: {col_name}\")\n",
     "        display_figure(fig)\n",
-    "    \n",
+    "\n",
     "    if growth.get(\"has_data\"):\n",
     "        fig = charts.cumulative_growth_chart(growth[\"cumulative\"], title=f\"Cumulative Records: {col_name}\")\n",
     "        display_figure(fig)\n",
-    "    \n",
+    "\n",
     "    fig = charts.temporal_heatmap(date_series, title=f\"Day of Week Distribution: {col_name}\")\n",
     "    display_figure(fig)\n",
     "\n",
@@ -1014,32 +1017,32 @@
     "    print(\"DATETIME COLUMNS SUMMARY\")\n",
     "    print(\"=\" * 70)\n",
     "    display_table(pd.DataFrame(datetime_summaries))\n",
-    "    \n",
+    "\n",
     "    # Summary by recommendation type\n",
     "    print(\"\\n📋 ALL RECOMMENDATIONS BY TYPE:\")\n",
-    "    \n",
+    "\n",
     "    if feature_engineering_recs:\n",
     "        print(f\"\\n🛠️ FEATURES TO CREATE ({len(feature_engineering_recs)}):\")\n",
     "        for i, rec in enumerate(feature_engineering_recs, 1):\n",
     "            priority_icon = \"🔴\" if rec.priority == \"high\" else \"🟡\" if rec.priority == \"medium\" else \"✓\"\n",
     "            print(f\"   {i}. {priority_icon} {rec.feature_name}\")\n",
-    "    \n",
+    "\n",
     "    if modeling_strategy_recs:\n",
     "        print(f\"\\n⚙️ MODELING CONSIDERATIONS ({len(modeling_strategy_recs)}):\")\n",
     "        for i, rec in enumerate(modeling_strategy_recs, 1):\n",
     "            priority_icon = \"🔴\" if rec.priority == \"high\" else \"🟡\" if rec.priority == \"medium\" else \"✓\"\n",
     "            print(f\"   {i}. {priority_icon} {rec.feature_name}: {rec.reason}\")\n",
-    "    \n",
+    "\n",
     "    if data_quality_recs:\n",
     "        print(f\"\\n⚠️ DATA QUALITY TO ADDRESS ({len(data_quality_recs)}):\")\n",
     "        for i, rec in enumerate(data_quality_recs, 1):\n",
     "            priority_icon = \"🔴\" if rec.priority == \"high\" else \"🟡\" if rec.priority == \"medium\" else \"✓\"\n",
     "            print(f\"   {i}. {priority_icon} {rec.feature_name}: {rec.reason}\")\n",
-    "    \n",
+    "\n",
     "    # Add recommendations to registry\n",
     "    added_derived = 0\n",
     "    added_modeling = 0\n",
-    "    \n",
+    "\n",
     "    # Add feature engineering recommendations to Silver layer (derived columns)\n",
     "    if registry.silver:\n",
     "        for rec in feature_engineering_recs:\n",
@@ -1051,7 +1054,7 @@
     "                source_notebook=\"02_column_deep_dive\"\n",
     "            )\n",
     "            added_derived += 1\n",
-    "    \n",
+    "\n",
     "    # Add modeling strategy recommendations to Bronze layer\n",
     "    seen_strategies = set()\n",
     "    for rec in modeling_strategy_recs:\n",
@@ -1065,7 +1068,7 @@
     "            )\n",
     "            seen_strategies.add(rec.feature_name)\n",
     "            added_modeling += 1\n",
-    "    \n",
+    "\n",
     "    print(f\"\\n✅ Added {added_derived} derived column recommendations to Silver layer\")\n",
     "    print(f\"✅ Added {added_modeling} modeling strategy recommendations to Bronze layer\")"
    ]
@@ -1217,14 +1220,14 @@
     "    max_segments=5\n",
     ")\n",
     "\n",
-    "print(f\"\\n🎯 Analysis Results:\")\n",
+    "print(\"\\n🎯 Analysis Results:\")\n",
     "print(f\"   Method: {segmentation.method.value}\")\n",
     "print(f\"   Detected Segments: {segmentation.n_segments}\")\n",
     "print(f\"   Cluster Quality Score: {segmentation.quality_score:.2f}\")\n",
     "if segmentation.target_variance_ratio is not None:\n",
     "    print(f\"   Target Variance Ratio: {segmentation.target_variance_ratio:.2f}\")\n",
     "\n",
-    "print(f\"\\n📊 Segment Profiles:\")\n",
+    "print(\"\\n📊 Segment Profiles:\")\n",
     "for profile in segmentation.profiles:\n",
     "    target_info = f\" | Target Rate: {profile.target_rate*100:.1f}%\" if profile.target_rate is not None else \"\"\n",
     "    print(f\"   Segment {profile.segment_id}: {profile.size:,} records ({profile.size_pct:.1f}%){target_info}\")\n",
@@ -1242,7 +1245,7 @@
     "    fig = charts.segment_feature_comparison(segmentation, title=\"Feature Comparison Across Segments\")\n",
     "    display_figure(fig)\n",
     "\n",
-    "print(f\"\\n📝 Rationale:\")\n",
+    "print(\"\\n📝 Rationale:\")\n",
     "for reason in segmentation.rationale:\n",
     "    print(f\"   • {reason}\")"
    ]
@@ -1297,7 +1300,7 @@
     "\n",
     "# Summary of recommendations\n",
     "all_recs = registry.all_recommendations\n",
-    "print(f\"\\n📋 Recommendations Summary:\")\n",
+    "print(\"\\n📋 Recommendations Summary:\")\n",
     "print(f\"   Bronze layer: {len(registry.get_by_layer('bronze'))} recommendations\")\n",
     "print(f\"   Silver layer: {len(registry.get_by_layer('silver'))} recommendations\")\n",
     "print(f\"   Gold layer: {len(registry.get_by_layer('gold'))} recommendations\")\n",