Update app.py

app.py

@@ -5,6 +5,8 @@ from sklearn.preprocessing import StandardScaler
 import scipy
 from scipy import signal
 import pickle
+from sklearn.svm import SVC
+from sklearn.model_selection import train_test_split, GridSearchCV
 
 # Global variable to store the uploaded data
 global_data = None
@@ -14,7 +16,6 @@ def get_data_preview(file):
     global_data = pd.read_csv(file.name)
     global_data['label'] = np.nan  # Initialize a label column
     global_data['label'] = global_data['label'].astype(object)  # Ensure the label column can hold different types
-    print("Data preview:\n", global_data.head())
     return global_data.head()
 
 def label_data(ranges):
@@ -23,15 +24,11 @@ def label_data(ranges):
     for i, (start, end, label) in enumerate(ranges.values):
         start = int(start)
         end = int(end)
-        print(f"Processing range {i}: start={start}, end={end}, label={label}")
         if start < 0 or start >= len(global_data):
-            print(f"Invalid range: start={start}, end={end}, label={label}")
             continue
         if end >= len(global_data):
-            print(f"End index {end} exceeds data length {len(global_data)}. Adjusting to {len(global_data) - 1}.")
             end = len(global_data) - 1
         global_data.loc[start:end, 'label'] = label
-    print("Data after labeling:\n", global_data.tail())
     return global_data.tail()
 
 def preprocess_data():
@@ -120,34 +117,37 @@ def preprocess_data():
         return "Data preprocessing complete! Download the processed data and scaler below.", processed_data_filename, scaler_filename
     
     except Exception as e:
-        print(f"An error occurred during preprocessing: {e}")
         return f"An error occurred during preprocessing: {e}", None, None
-        
+
 def train_model():
     global global_data
-    data = preprocess_data(global_data)
-    scaler = StandardScaler()
-    X = data.drop('label', axis=1)
-    y = data['label']
-    X_scaled = scaler.fit_transform(X)
-    X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
-
-    param_grid = {'C': [0.1, 1, 10, 100], 'gamma': ['scale', 'auto', 0.1, 0.01, 0.001, 0.0001], 'kernel': ['rbf']}
-    svc = SVC(probability=True)
-    grid_search = GridSearchCV(estimator=svc, param_grid=param_grid, cv=5, verbose=2, n_jobs=-1)
-    grid_search.fit(X_train, y_train)
-
-    model = grid_search.best_estimator_
-    model_filename = 'model.pkl'
-    scaler_filename = 'scaler.pkl'
-
-    with open(model_filename, 'wb') as file:
-        pickle.dump(model, file)
+    try:
+        preprocess_status, processed_data_filename, scaler_filename = preprocess_data()
+        if processed_data_filename is None:
+            return preprocess_status, None, None
+        
+        df_scaled = pd.read_csv(processed_data_filename)
+        X = df_scaled.drop('label', axis=1)
+        y = df_scaled['label']
+        
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+        
+        param_grid = {'C': [0.1, 1, 10, 100], 'gamma': ['scale', 'auto', 0.1, 0.01, 0.001, 0.0001], 'kernel': ['rbf']}
+        svc = SVC(probability=True)
+        grid_search = GridSearchCV(estimator=svc, param_grid=param_grid, cv=5, verbose=2, n_jobs=-1)
+        grid_search.fit(X_train, y_train)
+        
+        model = grid_search.best_estimator_
+        model_filename = 'model.pkl'
 
-    with open(scaler_filename, 'wb') as file:
-        pickle.dump(scaler, file)
+        with open(model_filename, 'wb') as file:
+            pickle.dump(model, file)
 
-    return "Training complete! Model and scaler saved.", model_filename, scaler_filename
+        return "Training complete! Download the model and scaler below.", model_filename, scaler_filename
+    
+    except Exception as e:
+        print(f"An error occurred during training: {e}")
+        return f"An error occurred during training: {e}", None, None
 
 with gr.Blocks() as demo:
     file_input = gr.File(label="Upload CSV File")
@@ -155,14 +155,14 @@ with gr.Blocks() as demo:
     ranges_input = gr.Dataframe(headers=["Start Index", "End Index", "Label"], label="Ranges for Labeling")
     labeled_data_preview = gr.Dataframe(label="Labeled Data Preview", interactive=False)
 
-    preprocessing_status = gr.Textbox(label="Preprocessing Status")
-    processed_data_file = gr.File(label="Download Processed Data")
+    training_status = gr.Textbox(label="Training Status")
+    model_file = gr.File(label="Download Trained Model")
     scaler_file = gr.File(label="Download Scaler")
 
     file_input.upload(get_data_preview, inputs=file_input, outputs=data_preview)
     label_button = gr.Button("Label Data")
-    label_button.click(label_data, inputs=[ranges_input], outputs=labeled_data_preview)
-    preprocess_button = gr.Button("Preprocess Data")
-    preprocess_button.click(preprocess_data, outputs=[preprocessing_status, processed_data_file, scaler_file])
+    label_button.click(label_data, inputs=[ranges_input], outputs=labeled_data_preview, queue=True)
+    train_button = gr.Button("Train Model")
+    train_button.click(train_model, outputs=[training_status, model_file, scaler_file])
 
 demo.launch()