Update app.py

app.py

@@ -75,10 +75,6 @@ X_train, X_val, y_train, y_val = train_test_split(X, y, train_size=0.8, random_s
 # Random Forest model
 random_forest_model = RandomForestClassifier(n_estimators=100, max_depth=16, min_samples_split=10, random_state=RANDOM_STATE).fit(X_train, y_train)
 
-# Model performance
-print(f"Metrics train:\n\tAccuracy score: {accuracy_score(random_forest_model.predict(X_train), y_train):.4f}")
-print(f"Metrics test:\n\tAccuracy score: {accuracy_score(random_forest_model.predict(X_val), y_val):.4f}")
-
 # Make predictions on validation data
 predictions_random_forest = random_forest_model.predict(X_val)
 
@@ -96,10 +92,10 @@ from sklearn.ensemble import RandomForestClassifier
 import seaborn as sns
 
 # Load the data and model
-x_train = pd.read_csv("x_train.csv")
-x_val = pd.read_csv("x_val.csv")
-y_train = pd.read_csv("y_train_refined.csv")
-y_val = pd.read_csv("y_val_refined.csv")
+x_train = pd.read_csv("X_train.csv")
+x_val = pd.read_csv("X_val.csv")
+y_train = pd.read_csv("y_train.csv")
+y_val = pd.read_csv("y_val.csv")
 
 RANDOM_STATE = 55
 random_forest_model = RandomForestClassifier(
@@ -110,7 +106,12 @@ random_forest_model = RandomForestClassifier(
 ).fit(x_train, y_train)
 
 # Make predictions
-y_pred = random_forest_model.predict(x_val)
+y_pred = random_forest_model.predict(x_val.drop(columns=['ID']))
+
+# Calculate metrics
+precision = precision_score(y_val, y_pred, average='weighted')
+recall = recall_score(y_val, y_pred, average='weighted')
+accuracy = accuracy_score(y_val, y_pred)
 
 # Calculate metrics
 precision = precision_score(y_val, y_pred, average='weighted')
@@ -298,3 +299,4 @@ iface = gr.Interface(
 
 iface.launch()
 'gradio deploy'
+