initial pre commit

Author: SamoraHunter

.aiexclude

@@ -15,4 +15,4 @@ __pycache__/
 *.csv
 *.json
 *.tsv
-*.log
+*.log

.githooks/pre-push

@@ -24,4 +24,4 @@ if [ $? -ne 0 ]; then
 fi
 
 echo "All checks passed. Proceeding with push."
-exit 0
+exit 0

.githooks/pre-push.sh

@@ -40,4 +40,4 @@ if [ $? -ne 0 ]; then
 fi
 
 echo "All checks passed. Proceeding with push."
-exit 0
+exit 0

assets/data_feature_importance_methods.mmd

@@ -1,41 +1,41 @@
 flowchart TD
     A[ml_grid_object] --> B[feature_importance_methods]
-    
+
     B --> C{Check feature_selection_method}
-    
+
     C -->|"anova or None"| D[ANOVA Method]
     C -->|"markov_blanket"| E[Markov Blanket Method]
-    
+
     D --> F[feature_methods.getNfeaturesANOVAF]
     E --> G[feature_methods.getNFeaturesMarkovBlanket]
-    
+
     F --> H[Calculate F-values using f_classif]
     F --> I[Sort features by F-value]
     F --> J[Return top n feature names]
-    
+
     G --> K[Initialize PPIMBC with SVC]
     G --> L[Fit and transform training data]
     G --> M[Extract top n features from MB]
-    
+
     J --> N[Apply feature selection]
     M --> N
-    
+
     N --> O[Filter X_train with selected features]
     N --> P[Filter X_test with selected features]
     N --> Q[Filter X_test_orig with selected features]
-    
+
     O --> R[Return filtered datasets]
     P --> R
     Q --> R
-    
+
     subgraph "Input Data"
         S[target_n_features]
         T[X_train]
         U[X_test]
         V[y_train]
         W[X_test_orig]
     end
-    
+
     subgraph "Feature Methods Class"
         F
         G
@@ -46,25 +46,25 @@ flowchart TD
         L
         M
     end
-    
+
     subgraph "Output"
         X[Filtered X_train]
         Y[Filtered X_test]
         Z[Filtered X_test_orig]
     end
-    
+
     S --> B
     T --> B
     U --> B
     V --> B
     W --> B
-    
+
     R --> X
     R --> Y
     R --> Z
-    
+
     style B fill:#e1f5fe
     style C fill:#fff3e0
     style D fill:#f3e5f5
     style E fill:#e8f5e8
-    style N fill:#fff8e1
+    style N fill:#fff8e1

assets/data_feature_importance_methods.svg

@@ -3,68 +3,68 @@ flowchart TD
     B --> C{Read Data}
     C -->|Sample Mode| D[Read Sample Data]
     C -->|Full Mode| E[Read Full Data]
-    
+
     D --> F[Apply Test/Column Sampling]
     E --> F
-    
+
     F --> G[Get Perturbation Columns]
     G --> H[Set Outcome Variable]
     H --> I[Handle Correlation Matrix]
-    
+
     I --> J[Handle Percent Missing]
     J --> K[Handle Outcome List]
     K --> L[Remove Constant Columns]
-    
+
     L --> M{Final Column List Empty?}
     M -->|Yes| N[Safety Retention Mechanism]
     M -->|No| O[Proceed with Final Columns]
-    
+
     N --> P[Retain Protected Columns]
     P --> Q{Still Empty?}
     Q -->|Yes| R[Select Random Features]
     Q -->|No| O
     R --> O
-    
+
     O --> S[Clean Up Data]
     S --> T[Screen Non-Float Types]
     T --> U[Handle Column Names]
-    
+
     U --> V{Scale Data?}
     V -->|Yes| W[Apply Standard Scaling]
     V -->|No| X[Skip Scaling]
     W --> X
-    
+
     X --> Y{Time Series Mode?}
     Y -->|Yes| Z[Convert to Time Series]
     Y -->|No| AA[Regular Processing]
-    
+
     Z --> BB[Get Max Sequence Length]
     BB --> CC[Convert X,y to Time Series]
     CC --> DD[Train/Test Split]
-    
+
     AA --> DD
     DD --> EE[Remove Constant Columns After Split]
-    
+
     EE --> FF{Feature Reduction Needed?}
     FF -->|Yes| GG[Apply Feature Importance Methods]
     FF -->|No| HH[Skip Feature Reduction]
-    
+
     GG --> II{Features Remain?}
     II -->|No| JJ[Error: All Features Removed]
     II -->|Yes| HH
-    
+
     HH --> KK{Time Series Mode?}
     KK -->|Yes| LL[Get Time Series Model List]
     KK -->|No| MM[Get Regular Model List]
-    
+
     LL --> NN[Pipeline Complete]
     MM --> NN
-    
+
     JJ --> OO[Pipeline Failed]
-    
+
     style A fill:#e1f5fe
     style NN fill:#c8e6c9
     style OO fill:#ffcdd2
     style N fill:#fff3e0
     style P fill:#fff3e0
-    style R fill:#fff3e0
+    style R fill:#fff3e0

assets/data_pipeline.mmd

@@ -2,7 +2,7 @@ graph TD
     A[Grid Class Initialization] --> B[Set Global Parameters]
     B --> C[Set sample_n default=1000]
     C --> D[Initialize Grid Dictionary]
-    
+
     D --> E[Grid Parameters]
     E --> E1[resample: undersample/oversample/None]
     E --> E2[scale: True/False]
@@ -14,7 +14,7 @@ graph TD
     E --> E8[corr: 0.98,0.85,0.5,0.25]
     E --> E9[feature_selection_method: anova/markov_blanket]
     E --> E10[data: nested dictionary]
-    
+
     E10 --> F[Data Features]
     F --> F1[age: True/False]
     F --> F2[sex: True/False]
@@ -30,29 +30,29 @@ graph TD
     F --> F12[vte_status: True]
     F --> F13[hosp_site: True]
     F --> F14[Other features: False]
-    
+
     D --> G[c_prod Function Definition]
     G --> H[Generate Cartesian Product]
     H --> I[Create settings_list]
     I --> J[Print Full Size]
     J --> K[Shuffle List]
     K --> L[Sample n Items]
     L --> M[Create Iterator]
-    
+
     subgraph "c_prod Function Logic"
         N[Input: Dictionary or List]
         N --> O{Is List?}
         O -->|Yes| P[Yield Items Recursively]
         O -->|No| Q[Generate Product of Values]
         Q --> R[Yield Dictionary with Keys]
     end
-    
+
     subgraph "Key Dependencies"
         S[itertools as it]
         T[random]
         U[ml_grid.util.global_params]
     end
-    
+
     subgraph "Class Attributes"
         V[self.global_params]
         W[self.verbose]
@@ -61,8 +61,8 @@ graph TD
         Z[self.settings_list]
         AA[self.settings_list_iterator]
     end
-    
+
     style A fill:#e1f5fe
     style D fill:#f3e5f5
     style G fill:#fff3e0
-    style M fill:#e8f5e8
+    style M fill:#e8f5e8