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/05_multi_dataset.ipynb

@@ -95,36 +95,30 @@
    "outputs": [],
    "source": [
     "from customer_retention.analysis.notebook_progress import track_and_export_previous\n",
+    "\n",
     "track_and_export_previous(\"05_multi_dataset.ipynb\")\n",
     "\n",
+    "import pandas as pd\n",
+    "import plotly.graph_objects as go\n",
+    "import yaml\n",
+    "from plotly.subplots import make_subplots\n",
+    "\n",
     "from customer_retention.analysis.auto_explorer import (\n",
     "    ExplorationManager,\n",
-    "    MultiDatasetFindings,\n",
-    "    ExplorationFindings,\n",
     "    RecommendationRegistry,\n",
     ")\n",
+    "from customer_retention.analysis.visualization import display_figure\n",
+    "from customer_retention.core.config.column_config import ColumnType, DatasetGranularity\n",
+    "from customer_retention.core.config.experiments import FINDINGS_DIR\n",
     "from customer_retention.stages.profiling import (\n",
+    "    DimensionReductionMethod,\n",
+    "    FeatureCapacityAnalyzer,\n",
+    "    FeatureGroup,\n",
+    "    ReferenceMode,\n",
     "    RelationshipDetector,\n",
-    "    TimeWindowAggregator,\n",
-    "    RelationshipType,\n",
     "    SegmentAnalyzer,\n",
-    "    SegmentationMethod,\n",
-    "    FeatureCapacityAnalyzer,\n",
-    "    TemporalFeatureEngineer,\n",
     "    TemporalAggregationConfig,\n",
-    "    ReferenceMode,\n",
-    "    FeatureGroup,\n",
-    "    DimensionReductionMethod,\n",
-    ")\n",
-    "from customer_retention.analysis.visualization import ChartBuilder, display_figure, display_table\n",
-    "from customer_retention.core.config.column_config import DatasetGranularity, ColumnType\n",
-    "from pathlib import Path\n",
-    "import yaml\n",
-    "import pandas as pd\n",
-    "import numpy as np\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"
+    ")\n"
    ]
   },
   {
@@ -211,7 +205,7 @@
     "for ds in datasets:\n",
     "    granularity_emoji = \"\\U0001f4ca\" if ds.granularity == DatasetGranularity.ENTITY_LEVEL else \"\\U0001f4c8\"\n",
     "    target_info = f\" [TARGET: {ds.target_column}]\" if ds.target_column else \"\"\n",
-    "    \n",
+    "\n",
     "    print(f\"{granularity_emoji} {ds.name}\")\n",
     "    print(f\"   Granularity: {ds.granularity.value}\")\n",
     "    print(f\"   Rows: {ds.row_count:,} | Columns: {ds.column_count}\")\n",
@@ -268,7 +262,7 @@
     "    names = [ds.name for ds in datasets]\n",
     "    rows = [ds.row_count for ds in datasets]\n",
     "    cols = [ds.column_count for ds in datasets]\n",
-    "    granularities = [\"Entity\" if ds.granularity == DatasetGranularity.ENTITY_LEVEL else \"Event\" \n",
+    "    granularities = [\"Entity\" if ds.granularity == DatasetGranularity.ENTITY_LEVEL else \"Event\"\n",
     "                     for ds in datasets]\n",
     "    colors = [\"#2ecc71\" if ds.granularity == DatasetGranularity.ENTITY_LEVEL else \"#3498db\"\n",
     "              for ds in datasets]\n",
@@ -323,7 +317,7 @@
     "        text=\"<b>Primary Entity</b>\", showarrow=False, font=dict(size=11, color=\"#666\"), xanchor=\"left\"))\n",
     "    y_pos -= 0.06\n",
     "    annotations.append(dict(x=0.01, y=y_pos, xref=\"paper\", yref=\"paper\",\n",
-    "        text=f\"<span style='color:{primary_color}'>{primary_name}</span>\", \n",
+    "        text=f\"<span style='color:{primary_color}'>{primary_name}</span>\",\n",
     "        showarrow=False, font=dict(size=12), xanchor=\"left\"))\n",
     "    y_pos -= 0.10\n",
     "\n",
@@ -331,7 +325,7 @@
     "    annotations.append(dict(x=0.01, y=y_pos, xref=\"paper\", yref=\"paper\",\n",
     "        text=\"<b>Event Datasets</b>\", showarrow=False, font=dict(size=11, color=\"#666\"), xanchor=\"left\"))\n",
     "    y_pos -= 0.06\n",
-    "    \n",
+    "\n",
     "    if multi.event_datasets:\n",
     "        # Show each event dataset on its own line (supports 20+ datasets)\n",
     "        max_display = min(len(multi.event_datasets), 8)  # Show up to 8, then summarize\n",
@@ -339,7 +333,7 @@
     "            annotations.append(dict(x=0.03, y=y_pos, xref=\"paper\", yref=\"paper\",\n",
     "                text=f\"• {event_name}\", showarrow=False, font=dict(size=10, color=\"#3498db\"), xanchor=\"left\"))\n",
     "            y_pos -= 0.045\n",
-    "        \n",
+    "\n",
     "        if len(multi.event_datasets) > max_display:\n",
     "            remaining = len(multi.event_datasets) - max_display\n",
     "            annotations.append(dict(x=0.03, y=y_pos, xref=\"paper\", yref=\"paper\",\n",
@@ -369,7 +363,7 @@
     "    # Hide axes on left panel\n",
     "    fig.update_xaxes(visible=False, row=1, col=1)\n",
     "    fig.update_yaxes(visible=False, row=1, col=1)\n",
-    "    \n",
+    "\n",
     "    # Configure horizontal bar axes\n",
     "    fig.update_yaxes(categoryorder='total ascending', row=1, col=2)\n",
     "    fig.update_yaxes(categoryorder='total ascending', row=2, col=2)\n",
@@ -502,18 +496,18 @@
     "# If we have a primary entity dataset and event datasets, try to detect relationships\n",
     "if multi.primary_entity_dataset and multi.event_datasets:\n",
     "    primary_info = multi.datasets[multi.primary_entity_dataset]\n",
-    "    \n",
+    "\n",
     "    print(f\"Primary dataset: {multi.primary_entity_dataset}\")\n",
-    "    print(f\"Checking relationships with event datasets...\\n\")\n",
-    "    \n",
+    "    print(\"Checking relationships with event datasets...\\n\")\n",
+    "\n",
     "    for event_name in multi.event_datasets:\n",
     "        event_info = multi.datasets[event_name]\n",
-    "        \n",
+    "\n",
     "        # Check if they share common column names\n",
     "        if event_info.entity_column:\n",
     "            print(f\"\\U0001f517 {multi.primary_entity_dataset} <-> {event_name}\")\n",
     "            print(f\"   Potential join column: {event_info.entity_column}\")\n",
-    "            print(f\"   Expected relationship: one_to_many\")\n",
+    "            print(\"   Expected relationship: one_to_many\")\n",
     "            print()\n",
     "else:\n",
     "    print(\"Not enough datasets to detect relationships.\")\n",
@@ -667,7 +661,7 @@
     "print(\"=\"*70 + \"\\n\")\n",
     "\n",
     "for group in FeatureGroup:\n",
-    "    enabled = \"✓\" if group in [FeatureGroup.LAGGED_WINDOWS, FeatureGroup.VELOCITY, \n",
+    "    enabled = \"✓\" if group in [FeatureGroup.LAGGED_WINDOWS, FeatureGroup.VELOCITY,\n",
     "                               FeatureGroup.RECENCY, FeatureGroup.REGULARITY] else \"○\"\n",
     "    print(f\"  {enabled} {group.value}\")"
    ]
@@ -748,14 +742,14 @@
     "for dataset_name in multi.event_datasets:\n",
     "    ds_info = multi.datasets[dataset_name]\n",
     "    findings = manager.load_findings(dataset_name)\n",
-    "    \n",
+    "\n",
     "    if findings:\n",
     "        numeric_cols = [\n",
     "            name for name, col in findings.columns.items()\n",
     "            if col.inferred_type in [ColumnType.NUMERIC_CONTINUOUS, ColumnType.NUMERIC_DISCRETE]\n",
     "            and name not in [ds_info.entity_column, ds_info.time_column] and name not in TEMPORAL_METADATA_COLS\n",
     "        ]\n",
-    "        \n",
+    "\n",
     "        if numeric_cols:\n",
     "            registry.add_silver_temporal_config(\n",
     "                source_dataset=dataset_name,\n",
@@ -830,13 +824,13 @@
     "\n",
     "for dataset_name in multi.event_datasets:\n",
     "    ds_info = multi.datasets[dataset_name]\n",
-    "    \n",
+    "\n",
     "    print(f\"\\U0001f4c8 From {dataset_name}:\")\n",
     "    print()\n",
-    "    \n",
+    "\n",
     "    # Load findings to see numeric columns\n",
     "    findings = manager.load_findings(dataset_name)\n",
-    "    \n",
+    "\n",
     "    # Find numeric columns that could be aggregated\n",
     "    numeric_cols = []\n",
     "    if findings:\n",
@@ -845,7 +839,7 @@
     "            if col.inferred_type in [ColumnType.NUMERIC_CONTINUOUS, ColumnType.NUMERIC_DISCRETE]\n",
     "            and name not in [ds_info.entity_column, ds_info.time_column] and name not in TEMPORAL_METADATA_COLS\n",
     "        ]\n",
-    "    \n",
+    "\n",
     "    # Group 1: Lagged Window Features\n",
     "    if FeatureGroup.LAGGED_WINDOWS in FEATURE_GROUPS:\n",
     "        print(\"   📊 LAGGED WINDOWS (Group 1):\")\n",
@@ -853,21 +847,21 @@
     "            features = [f\"lag{i}_{col}_{agg}\" for i in range(NUM_LAGS) for agg in LAG_AGGREGATIONS[:2]]\n",
     "            print(f\"      {col}: {features[:4]}...\")\n",
     "        print(f\"      Total: {len(numeric_cols)} cols × {NUM_LAGS} lags × {len(LAG_AGGREGATIONS)} aggs\")\n",
-    "    \n",
+    "\n",
     "    # Group 2: Velocity Features\n",
     "    if FeatureGroup.VELOCITY in FEATURE_GROUPS:\n",
     "        print(\"\\n   🚀 VELOCITY (Group 2):\")\n",
     "        for col in numeric_cols[:2]:\n",
     "            print(f\"      - {col}_velocity, {col}_velocity_pct\")\n",
     "        print(f\"      Total: {len(numeric_cols)} cols × 2 features\")\n",
-    "    \n",
+    "\n",
     "    # Group 3: Acceleration Features\n",
     "    if FeatureGroup.ACCELERATION in FEATURE_GROUPS:\n",
     "        print(\"\\n   ⚡ ACCELERATION (Group 3):\")\n",
     "        for col in numeric_cols[:2]:\n",
     "            print(f\"      - {col}_acceleration, {col}_momentum\")\n",
     "        print(f\"      Total: {len(numeric_cols)} cols × 2 features\")\n",
-    "    \n",
+    "\n",
     "    # Group 4: Lifecycle Features\n",
     "    if FeatureGroup.LIFECYCLE in FEATURE_GROUPS:\n",
     "        print(\"\\n   📈 LIFECYCLE (Group 4):\")\n",
@@ -875,7 +869,7 @@
     "            print(f\"      - {col}_beginning, {col}_middle, {col}_end, {col}_trend_ratio\")\n",
     "        print(f\"      Total: {len(numeric_cols)} cols × 4 features\")\n",
     "        print(f\"      ℹ️ Requires {MIN_HISTORY_DAYS}+ days of history (else NaN)\")\n",
-    "    \n",
+    "\n",
     "    # Group 5: Recency Features\n",
     "    if FeatureGroup.RECENCY in FEATURE_GROUPS:\n",
     "        print(\"\\n   ⏱️ RECENCY (Group 5):\")\n",
@@ -883,7 +877,7 @@
     "        print(\"      - days_since_first_event\")\n",
     "        print(\"      - active_span_days\")\n",
     "        print(\"      - recency_ratio\")\n",
-    "    \n",
+    "\n",
     "    # Group 6: Regularity Features\n",
     "    if FeatureGroup.REGULARITY in FEATURE_GROUPS:\n",
     "        print(\"\\n   🎯 REGULARITY (Group 6):\")\n",
@@ -891,14 +885,14 @@
     "        print(\"      - inter_event_gap_mean\")\n",
     "        print(\"      - inter_event_gap_std\")\n",
     "        print(\"      - regularity_score\")\n",
-    "    \n",
+    "\n",
     "    # Group 7: Cohort Comparison\n",
     "    if FeatureGroup.COHORT_COMPARISON in FEATURE_GROUPS:\n",
     "        print(\"\\n   👥 COHORT COMPARISON (Group 7):\")\n",
     "        for col in numeric_cols[:2]:\n",
     "            print(f\"      - {col}_vs_cohort_mean, {col}_vs_cohort_pct, {col}_cohort_zscore\")\n",
     "        print(f\"      Total: {len(numeric_cols)} cols × 3 features\")\n",
-    "    \n",
+    "\n",
     "    # Summary\n",
     "    total_features = 0\n",
     "    if FeatureGroup.LAGGED_WINDOWS in FEATURE_GROUPS:\n",
@@ -915,7 +909,7 @@
     "        total_features += 4\n",
     "    if FeatureGroup.COHORT_COMPARISON in FEATURE_GROUPS:\n",
     "        total_features += len(numeric_cols) * 3\n",
-    "    \n",
+    "\n",
     "    print(f\"\\n   📝 TOTAL ESTIMATED FEATURES: ~{total_features}\")\n",
     "    print()"
    ]
@@ -1000,12 +994,12 @@
     "if multi.primary_entity_dataset:\n",
     "    primary_info = multi.datasets[multi.primary_entity_dataset]\n",
     "    primary_findings = manager.load_findings(multi.primary_entity_dataset)\n",
-    "    \n",
+    "\n",
     "    if primary_findings:\n",
     "        # Load the primary dataset from snapshot (not source) to get correct column names\n",
     "        primary_df, data_source = load_data_with_snapshot_preference(primary_findings, output_dir=str(FINDINGS_DIR))\n",
     "        print(f\"   Loaded from: {data_source}\")\n",
-    "        \n",
+    "\n",
     "        # Get numeric features for clustering (exclude temporal metadata)\n",
     "        from customer_retention.stages.temporal import TEMPORAL_METADATA_COLS\n",
     "        numeric_features = [\n",
@@ -1014,12 +1008,12 @@
     "            and name != primary_info.target_column\n",
     "            and name not in TEMPORAL_METADATA_COLS\n",
     "        ]\n",
-    "        \n",
+    "\n",
     "        print(f\"\\n📊 Dataset: {multi.primary_entity_dataset}\")\n",
     "        print(f\"   Total Samples: {len(primary_df):,}\")\n",
     "        print(f\"   Numeric Features: {len(numeric_features)}\")\n",
     "        print(f\"   Target Column: {primary_info.target_column}\")\n",
-    "        \n",
+    "\n",
     "        # Run full segmentation analysis using framework\n",
     "        analysis = segment_analyzer.run_full_analysis(\n",
     "            primary_df,\n",
@@ -1029,14 +1023,14 @@
     "            dim_reduction=DimensionReductionMethod.PCA,\n",
     "        )\n",
     "        m = analysis.metrics  # Shorthand for metrics\n",
-    "        \n",
+    "\n",
     "        # ============================================================\n",
     "        # KEY DECISION METRICS\n",
     "        # ============================================================\n",
     "        print(\"\\n\" + \"=\" * 70)\n",
     "        print(\"📊 CLUSTERING DECISION METRICS\")\n",
     "        print(\"=\" * 70)\n",
-    "        \n",
+    "\n",
     "        print(f\"\"\"\n",
     "┌─────────────────────────────────────────────────────────────────────┐\n",
     "│  METRIC                          │  VALUE      │  INTERPRETATION    │\n",
@@ -1046,19 +1040,19 @@
     "│  Optimal Segments Found          │  {m.n_segments}           │  {m.segments_interpretation:<18} │\n",
     "│  Overall Confidence              │  {m.confidence:.0%}         │  {m.confidence_interpretation:<18} │\n",
     "└──────────────────────────────────┴─────────────┴────────────────────┘\"\"\")\n",
-    "        \n",
+    "\n",
     "        print(f\"\\n🎯 RECOMMENDATION: {m.recommendation.upper().replace('_', ' ')}\")\n",
-    "        print(f\"\\n📋 Supporting Evidence:\")\n",
+    "        print(\"\\n📋 Supporting Evidence:\")\n",
     "        for r in m.rationale:\n",
     "            print(f\"   • {r}\")\n",
-    "        \n",
+    "\n",
     "        # ============================================================\n",
     "        # SEGMENT PROFILES\n",
     "        # ============================================================\n",
     "        print(\"\\n\" + \"=\" * 70)\n",
     "        print(\"📊 SEGMENT PROFILES\")\n",
     "        print(\"=\" * 70 + \"\\n\")\n",
-    "        \n",
+    "\n",
     "        segment_data = [{\n",
     "            \"Segment\": f\"Segment {p.segment_id}\",\n",
     "            \"N (count)\": f\"{p.size:,}\",\n",
@@ -1067,34 +1061,34 @@
     "            \"Viable for ML\": \"✓\" if p.size >= 100 else \"⚠️\"\n",
     "        } for p in analysis.profiles]\n",
     "        display(pd.DataFrame(segment_data))\n",
-    "        \n",
+    "\n",
     "        sd = analysis.size_distribution\n",
-    "        print(f\"\\n📊 Size Distribution:\")\n",
+    "        print(\"\\n📊 Size Distribution:\")\n",
     "        print(f\"   Total datapoints: {sd['total']:,}\")\n",
     "        print(f\"   Smallest segment: {sd['min_size']:,} ({sd['min_pct']:.1f}%)\")\n",
     "        print(f\"   Largest segment: {sd['max_size']:,} ({sd['max_pct']:.1f}%)\")\n",
     "        print(f\"   Balance ratio: {sd['balance_ratio']:.2f} (1.0 = perfectly balanced)\")\n",
-    "        \n",
+    "\n",
     "        # ============================================================\n",
     "        # CLUSTER VISUALIZATION\n",
     "        # ============================================================\n",
     "        if analysis.has_visualization:\n",
     "            viz = analysis.visualization\n",
     "            seg_result = analysis.segmentation_result\n",
-    "            \n",
+    "\n",
     "            fig = make_subplots(\n",
     "                rows=1, cols=3,\n",
     "                subplot_titles=(\n",
-    "                    f\"Cluster Visualization (PCA, {viz.explained_variance_ratio:.0%} var)\" \n",
+    "                    f\"Cluster Visualization (PCA, {viz.explained_variance_ratio:.0%} var)\"\n",
     "                    if viz.explained_variance_ratio else \"Cluster Visualization (PCA)\",\n",
     "                    \"Segment Sizes\", \"Target Rate\"\n",
     "                ),\n",
     "                horizontal_spacing=0.12,\n",
     "                column_widths=[0.4, 0.3, 0.3]\n",
     "            )\n",
-    "            \n",
+    "\n",
     "            unique_labels = sorted(set(seg_result.labels[seg_result.labels >= 0]))\n",
-    "            \n",
+    "\n",
     "            # Scatter plot - consistent colors by segment ID\n",
     "            for label in unique_labels:\n",
     "                mask = seg_result.labels == label\n",
@@ -1106,12 +1100,12 @@
     "                    marker=dict(color=color, size=6, opacity=0.6),\n",
     "                    name=name, hovertemplate=f\"{name}<br>PC1: %{{x:.2f}}<br>PC2: %{{y:.2f}}<extra></extra>\"\n",
     "                ), row=1, col=1)\n",
-    "            \n",
+    "\n",
     "            # Short labels for bar charts (avoid overlap)\n",
     "            bar_labels = [f\"Seg {p.segment_id}\" for p in analysis.profiles]\n",
     "            sizes = [p.size for p in analysis.profiles]\n",
     "            bar_colors = [SEGMENT_COLORS.get(p.segment_id, '#888888') for p in analysis.profiles]\n",
-    "            \n",
+    "\n",
     "            # Size bars - numbers inside\n",
     "            fig.add_trace(go.Bar(\n",
     "                y=bar_labels, x=sizes, orientation='h',\n",
@@ -1121,7 +1115,7 @@
     "                showlegend=False,\n",
     "                hovertemplate=\"Segment %{y}<br>Count: %{x:,}<extra></extra>\"\n",
     "            ), row=1, col=2)\n",
-    "            \n",
+    "\n",
     "            # Target rates - consistent segment colors, numbers inside\n",
     "            if all(p.target_rate is not None for p in analysis.profiles):\n",
     "                rates = [p.target_rate * 100 for p in analysis.profiles]\n",
@@ -1136,16 +1130,16 @@
     "                overall = sum(p.target_rate * p.size for p in analysis.profiles) / sd['total'] * 100\n",
     "                fig.add_vline(x=overall, line_dash=\"dash\", line_color=\"#2c3e50\",\n",
     "                             annotation_text=f\"Avg: {overall:.1f}%\", annotation_position=\"top\", row=1, col=3)\n",
-    "            \n",
+    "\n",
     "            fig.update_layout(\n",
-    "                title=\"Segment Analysis Overview\", \n",
-    "                height=400, \n",
+    "                title=\"Segment Analysis Overview\",\n",
+    "                height=400,\n",
     "                template=\"plotly_white\",\n",
     "                legend=dict(\n",
-    "                    orientation=\"h\", \n",
-    "                    yanchor=\"top\", \n",
+    "                    orientation=\"h\",\n",
+    "                    yanchor=\"top\",\n",
     "                    y=-0.15,\n",
-    "                    xanchor=\"center\", \n",
+    "                    xanchor=\"center\",\n",
     "                    x=0.5\n",
     "                ),\n",
     "                margin=dict(r=20, b=80)\n",
@@ -1153,11 +1147,11 @@
     "            fig.update_xaxes(title_text=\"PC1\", row=1, col=1)\n",
     "            fig.update_yaxes(title_text=\"PC2\", row=1, col=1)\n",
     "            display_figure(fig)\n",
-    "            \n",
-    "            print(f\"\\n📈 CLUSTER VISUALIZATION:\")\n",
+    "\n",
+    "            print(\"\\n📈 CLUSTER VISUALIZATION:\")\n",
     "            print(f\"   Method: PCA | Variance Explained: {viz.explained_variance_ratio:.1%}\" if viz.explained_variance_ratio else \"   Method: PCA\")\n",
-    "            print(f\"   Colors: Seg 0=Blue, Seg 1=Red, Seg 2=Green, Seg 3=Purple\")\n",
-    "        \n",
+    "            print(\"   Colors: Seg 0=Blue, Seg 1=Red, Seg 2=Green, Seg 3=Purple\")\n",
+    "\n",
     "        # ============================================================\n",
     "        # EPV CAPACITY ANALYSIS\n",
     "        # ============================================================\n",
@@ -1165,7 +1159,7 @@
     "            print(\"\\n\" + \"=\" * 70)\n",
     "            print(\"💡 SEGMENT CAPACITY ANALYSIS (EPV Check)\")\n",
     "            print(\"=\" * 70)\n",
-    "            \n",
+    "\n",
     "            primary_df['_segment'] = analysis.segmentation_result.labels\n",
     "            capacity = capacity_analyzer.analyze_segment_capacity(\n",
     "                primary_df[primary_df['_segment'] >= 0],\n",
@@ -1174,14 +1168,14 @@
     "                segment_col='_segment'\n",
     "            )\n",
     "            primary_df.drop('_segment', axis=1, inplace=True)\n",
-    "            \n",
+    "\n",
     "            print(f\"\\n🎯 Strategy: {capacity.recommended_strategy.upper()}\")\n",
     "            print(f\"   Reason: {capacity.strategy_reason}\")\n",
     "            if capacity.viable_segments:\n",
     "                print(f\"\\n   ✅ Viable segments: {capacity.viable_segments}\")\n",
     "            if capacity.insufficient_segments:\n",
     "                print(f\"   ⚠️ Insufficient segments: {capacity.insufficient_segments}\")\n",
-    "            \n",
+    "\n",
     "            # Store in findings\n",
     "            multi.notes.update({\n",
     "                'segmentation_recommendation': m.recommendation,\n",
@@ -1191,11 +1185,11 @@
     "                'segment_strategy': capacity.recommended_strategy,\n",
     "                'segment_sizes': {f\"segment_{p.segment_id}\": p.size for p in analysis.profiles}\n",
     "            })\n",
-    "            \n",
+    "\n",
     "            # Initialize bronze layer if not already done\n",
     "            if registry.bronze is None:\n",
     "                registry.init_bronze(primary_info.source_path)\n",
-    "            \n",
+    "\n",
     "            # Persist segmentation strategy to registry\n",
     "            registry.add_bronze_segmentation_strategy(\n",
     "                strategy=m.recommendation,\n",
@@ -1206,7 +1200,7 @@
     "                source_notebook=\"05_multi_dataset\"\n",
     "            )\n",
     "            print(f\"\\n✅ Persisted segmentation strategy to registry: {m.recommendation}\")\n",
-    "        \n",
+    "\n",
     "        # ============================================================\n",
     "        # DECISION SUMMARY\n",
     "        # ============================================================\n",
@@ -1263,26 +1257,26 @@
     "    print(\"\\n\" + \"=\"*70)\n",
     "    print(\"DATASET RELATIONSHIP DIAGRAM\")\n",
     "    print(\"=\"*70 + \"\\n\")\n",
-    "    \n",
+    "\n",
     "    # ASCII diagram\n",
     "    if multi.primary_entity_dataset:\n",
     "        primary = multi.primary_entity_dataset\n",
     "        primary_info = multi.datasets[primary]\n",
-    "        \n",
+    "\n",
     "        print(f\"   +{'='*30}+\")\n",
     "        print(f\"   |  {primary:^26}  |  <- PRIMARY (has target)\")\n",
     "        print(f\"   |  {primary_info.row_count:,} rows{' '*15}  |\")\n",
     "        if primary_info.target_column:\n",
     "            print(f\"   |  Target: {primary_info.target_column:<17}  |\")\n",
     "        print(f\"   +{'='*30}+\")\n",
-    "        \n",
+    "\n",
     "        for event_name in multi.event_datasets:\n",
     "            event_info = multi.datasets[event_name]\n",
     "            join_col = event_info.entity_column or \"?\"\n",
-    "            \n",
-    "            print(f\"          |\")\n",
+    "\n",
+    "            print(\"          |\")\n",
     "            print(f\"          | {join_col}\")\n",
-    "            print(f\"          v\")\n",
+    "            print(\"          v\")\n",
     "            print(f\"   +{'-'*30}+\")\n",
     "            print(f\"   |  {event_name:^26}  |  <- EVENT LEVEL\")\n",
     "            print(f\"   |  {event_info.row_count:,} rows{' '*15}  |\")\n",
@@ -1340,7 +1334,7 @@
     "registry.save(RECOMMENDATIONS_PATH)\n",
     "\n",
     "print(f\"\\n✅ Multi-dataset findings saved to: {MULTI_FINDINGS_PATH}\")\n",
-    "print(f\"\\n   Contents:\")\n",
+    "print(\"\\n   Contents:\")\n",
     "print(f\"   - {len(multi.datasets)} datasets\")\n",
     "print(f\"   - {len(multi.relationships)} relationships\")\n",
     "print(f\"   - {len(multi.event_datasets)} event datasets to aggregate\")\n",