Upload prediction_analyzer.py

prediction_analyzer.py

@@ -0,0 +1,33 @@
+import torch
+import numpy as np
+import pandas as pd
+
+class PredictionAnalyzer:
+    def __init__(self, model, df_ready):
+        self.model = model
+        self.df_ready = df_ready
+
+    def predictions_loop(self):
+        pred_total = []
+        for filter_cat in list(self.df_ready.columns):
+            df_sample = self.df_ready[self.df_ready[filter_cat]==1]
+            lb_sample = len(df_sample)/len(self.df_ready)
+            X = df_sample.values
+            X_test_tensor = torch.tensor(X, dtype=torch.float32)
+            inputs = X_test_tensor
+            outputs = self.model(inputs)
+            outputs_show = outputs.detach().numpy().flatten()
+            outputs_show[outputs_show > 0.55] = 1.0
+            outputs_show[outputs_show < 0.45] = 0.0
+            filtered_arr = outputs_show[(outputs_show == 0.0) | (outputs_show == 1.0)]
+            unique, counts = np.unique(filtered_arr, return_counts=True)
+            if len(counts) > 1:
+                sum_cat = counts[0]+counts[1]
+                pred_total.append([filter_cat, round(counts[0]/sum_cat*100, 2), round(counts[1]/sum_cat*100, 2), round(lb_sample*100, 2)])
+            else:
+                pred_total.append([filter_cat, 0, 0, round(lb_sample*100, 2)])
+        
+        pred_df_tot = pd.DataFrame(pred_total, columns=['Categoria', 'Pred==0', 'Pred==1', 'linea_base'])
+        pred_df_tot_sort = pred_df_tot.sort_values(by='Pred==1', ascending=False, ignore_index=True)
+        
+        return pred_df_tot_sort