Update app.py

app.py

@@ -7,19 +7,32 @@ from catboost import CatBoostRegressor
 
 def predict(team, inning, venue, hits, errors, lob, runs, opp_team, opp_runs, opp_hits):
     data = [team, opp_team, inning, venue, hits, opp_hits, errors, runs, opp_runs, lob]
+
+    df_main = pd.read_csv("Score_prediction_dataset_11th_July.csv")
+    df_main = df_main.drop(columns=['Final_Score', 'Opp_LOB'])
+    df_main = pd.get_dummies(df_main, columns=['Team_Name', 'Opposition_Team'])
+
     df = pd.DataFrame([data], columns=["Team_Name", "Opposition_Team", "Inning", "Home/Away", "Hits", "Opp_Hits", "Errors", "Runs", "Opp_Runs", "LOB"])
+    df = pd.get_dummies(df, columns=['Team_Name', 'Opposition_Team'])
 
+    df = df.reindex(columns=df_main.columns, fill_value=0)
+
+    # print(df.columns)
+    # print(len(df.columns))
     xgb_model = xgb.XGBRegressor()
-    xgb_model.load_model('alpha1_xgbr1.json')
+    xgb_model.load_model('xgbr1_exp3_model.json')
     
-    with open('label_encoder_teams_alpha1_xgbr1.pkl', 'rb') as f:
-        label_encoder = pickle.load(f)
-
-    df['Team_Name'] = label_encoder.transform(df['Team_Name'])
-    df['Opposition_Team'] = label_encoder.transform(df['Opposition_Team'])
+    with open('pca_model1.pkl', 'rb') as f:
+        pca = pickle.load(f)
 
+    # with open('label_encoder_teams_xgbr1_exp3.pkl', 'rb') as f:
+    #     label_encoder = pickle.load(f)
+    
     home_away_status = {'Home': 0, 'Away': 1}
     df['Home/Away'] = df['Home/Away'].map(home_away_status)
+
+    df = pca.transform(df)
+
     score = xgb_model.predict(df)
     if score[0] < 0:
         score = np.clip(score[0], a_min=0, a_max=None)
@@ -28,19 +41,33 @@ def predict(team, inning, venue, hits, errors, lob, runs, opp_team, opp_runs, op
 
 def predict_2(team, inning, venue, hits, errors, lob, runs, opp_team, opp_runs, opp_hits):
     data = [team, opp_team, inning, venue, hits, opp_hits, errors, runs, opp_runs, lob]
+
+    df_main = pd.read_csv("Score_prediction_dataset_11th_July.csv")
+    df_main = df_main.drop(columns=['Final_Score', 'Opp_LOB'])
+    df_main = pd.get_dummies(df_main, columns=['Team_Name', 'Opposition_Team'])
+
     df = pd.DataFrame([data], columns=["Team_Name", "Opposition_Team", "Inning", "Home/Away", "Hits", "Opp_Hits", "Errors", "Runs", "Opp_Runs", "LOB"])
+    df = pd.get_dummies(df, columns=['Team_Name', 'Opposition_Team'])
+
+    df = df.reindex(columns=df_main.columns, fill_value=0)
 
     cat_model = CatBoostRegressor()
-    cat_model.load_model('CATBR1_model1_exp1.json')
+    cat_model.load_model('catbr1_exp4_model.json')
     
-    with open('label_encoder_teams_catbr1_exp1.pkl', 'rb') as f:
-        label_encoder = pickle.load(f)
+    # with open('label_encoder_teams_catbr1_exp1.pkl', 'rb') as f:
+    #     label_encoder = pickle.load(f)
 
-    df['Team_Name'] = label_encoder.transform(df['Team_Name'])
-    df['Opposition_Team'] = label_encoder.transform(df['Opposition_Team'])
+    # df['Team_Name'] = label_encoder.transform(df['Team_Name'])
+    # df['Opposition_Team'] = label_encoder.transform(df['Opposition_Team'])
 
     home_away_status = {'Home': 0, 'Away': 1}
     df['Home/Away'] = df['Home/Away'].map(home_away_status)
+
+    with open('pca_model1.pkl', 'rb') as f:
+        pca = pickle.load(f)    
+
+    df = pca.transform(df)
+    
     score = cat_model.predict(df)
     if score[0] < 0:
         score = np.clip(score[0], a_min=0, a_max=None)