corrected app.py

app.py

@@ -1,49 +1,53 @@
-
 import gradio as gr
-import joblib
+import pandas as pd
 import json
-import numpy as np
-
-# Load the trained model
-model = joblib.load('trained_model.pkl')
-
-# Load feature names
-with open('selected_features.json', 'r') as f:
-    feature_names = json.load(f)
-
-# Define prediction function
-def predict_heart_failure(*args):
-    """
-    Predict heart failure likelihood based on input features.
-
-    Args:
-        *args: Input values for each feature.
-
-    Returns:
-        str: Prediction result.
-        str: Prediction probability as a percentage.
-    """
-    input_data = np.array(args).reshape(1, -1)
-    prediction = model.predict(input_data)
-    probability = model.predict_proba(input_data)
-    result = "Likely" if prediction[0] == 1 else "Unlikely"
-    return result, f"{probability[0][1] * 100:.2f}%"
-
-# Create Gradio interface
-inputs = [gr.inputs.Number(label=feature) for feature in feature_names]
-outputs = [
-    gr.outputs.Textbox(label="Prediction"),
-    gr.outputs.Textbox(label="Probability (%)")
-]
-
-app = gr.Interface(
-    fn=predict_heart_failure,
-    inputs=inputs,
-    outputs=outputs,
-    title="Heart Failure Prediction",
-    description="Enter the values for the features to predict the likelihood of heart failure."
-)
-
-# Launch the app
-if __name__ == "__main__":
-    app.launch()
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
+from io import StringIO
+
+# Load selected features from JSON file
+with open("selected_features.json", "r") as file:
+    selected_features = json.load(file)
+
+def preprocess_data(dataframe):
+    # Identify numerical and categorical columns
+    numerical_cols = dataframe.select_dtypes(include=["number"]).columns
+    categorical_cols = [col for col in dataframe.columns if col not in numerical_cols]
+    
+    # Preprocessing pipeline
+    preprocessor = ColumnTransformer(
+        transformers=[
+            ('num', StandardScaler(), numerical_cols),
+            ('cat', OneHotEncoder(sparse_output=False, drop='first'), categorical_cols)
+        ]
+    )
+    
+    # Apply preprocessing
+    processed_data = preprocessor.fit_transform(dataframe)
+    feature_names = numerical_cols.tolist() + list(preprocessor.named_transformers_['cat'].get_feature_names_out(categorical_cols))
+    return pd.DataFrame(processed_data, columns=feature_names)
+
+def process_uploaded_data(file):
+    # Load dataset from uploaded file
+    data = pd.read_csv(file.name)
+    
+    # Check for missing selected features
+    missing_features = [feature for feature in selected_features if feature not in data.columns]
+    if missing_features:
+        return f"Missing features: {', '.join(missing_features)}. Please upload a valid dataset."
+    
+    # Preprocess data
+    data = data[selected_features]
+    processed_data = preprocess_data(data)
+    return processed_data.head(10).to_csv(index=False)
+
+def process_manual_data(**inputs):
+    # Construct dataframe from manual inputs
+    input_data = pd.DataFrame([inputs])
+    
+    # Preprocess data
+    processed_data = preprocess_data(input_data)
+    return processed_data.head(10).to_csv(index=False)
+
+# GUI for manual input
+manual