tgs part 2

model_day.py

@@ -119,9 +119,30 @@ def walk_forward_validation_seq(df, target_column_clf, target_column_regr, num_t
         overall_results.append(result_df)
 
     df_results = pd.concat(overall_results)
-    # model1.save_model('model_ensemble.bin')
-    # joblib.dump(model2, 'model2.bin')
-    # Return the true and predicted values, and fitted model
+
+    # Calibrate Probabilities
+    def get_quantiles(df, col_name, q):
+        return df.groupby(pd.cut(df[col_name], q))['True'].mean()
+
+    greenprobas = []
+    meanprobas = []
+    for i, pct in enumerate(df_results['Predicted']):
+        try:
+            df_q = get_quantiles(df_results.iloc[:i], 'Predicted', 7)
+            for q in df_q.index:
+                if q.left <= pct <= q.right:
+                    p = df_q[q]
+                    c = (q.left + q.right) / 2
+        except:
+            p = None
+            c = None
+
+        greenprobas.append(p)
+        meanprobas.append(c)
+
+    df_results['CalibPredicted'] = meanprobas
+    df_results['CalibGreenProba'] = greenprobas
+    
     return df_results, model1, model2
 
 def seq_predict_proba(df, trained_reg_model, trained_clf_model):