app update

app.py

@@ -2,17 +2,16 @@ import gradio as gr
 import pandas as pd
 import json
 from sklearn.compose import ColumnTransformer
-from sklearn.preprocessing import OneHotEncoder, StandardScaler
-from io import StringIO
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
 
 # Load selected features from JSON file
 with open("selected_features.json", "r") as file:
     selected_features = json.load(file)
 
-def preprocess_data(dataframe):
+def preprocess_data(data):
     # 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]
+    numerical_cols = [col for col in data.columns if data[col].dtype in ['int64', 'float64']]
+    categorical_cols = [col for col in data.columns if col not in numerical_cols]
     
     # Preprocessing pipeline
     preprocessor = ColumnTransformer(
@@ -23,31 +22,40 @@ def preprocess_data(dataframe):
     )
     
     # Apply preprocessing
-    processed_data = preprocessor.fit_transform(dataframe)
-    feature_names = numerical_cols.tolist() + list(preprocessor.named_transformers_['cat'].get_feature_names_out(categorical_cols))
+    processed_data = preprocessor.fit_transform(data)
+    feature_names = numerical_cols + 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
+def process_manual_input(**inputs):
+    # Create a DataFrame for a single patient from inputs
     input_data = pd.DataFrame([inputs])
     
-    # Preprocess data
+    # Preprocess the data
     processed_data = preprocess_data(input_data)
-    return processed_data.head(10).to_csv(index=False)
+    return processed_data.to_csv(index=False)
+
+# GUI inputs for each feature
+gui_inputs = []
+for feature in selected_features:
+    if feature.startswith("Had"):  # Binary categorical features
+        gui_inputs.append(gr.Radio(label=feature, choices=["Yes", "No"], value="No"))
+    elif feature in ["BMI", "WeightInKilograms", "HeightInMeters"]:  # Numerical features
+        gui_inputs.append(gr.Slider(label=feature, minimum=0, maximum=300, step=0.1, value=25))
+    elif feature == "PhysicalHealthDays":  # Numerical feature with a smaller range
+        gui_inputs.append(gr.Slider(label=feature, minimum=0, maximum=30, step=1, value=5))
+    elif feature == "SleepHours":  # Hours of sleep
+        gui_inputs.append(gr.Slider(label=feature, minimum=0, maximum=24, step=0.5, value=8))
+    else:  # Default for any remaining numerical features
+        gui_inputs.append(gr.Slider(label=feature, minimum=0, maximum=100, step=1, value=50))
+
+# Create the Gradio app interface
+interface = gr.Interface(
+    fn=process_manual_input,
+    inputs=gui_inputs,
+    outputs=gr.Textbox(label="Processed Data (CSV Format)"),
+    title="Single Patient Data Preprocessor",
+    description="Input data for a single patient using sliders and radio buttons. The data will be preprocessed and displayed as CSV."
+)
 
-# GUI for manual input
-manual
+# Launch the app
+interface.launch()