Create app.py

app.py

@@ -0,0 +1,89 @@
+# Import necessary libraries for streamlit and model loading
+import streamlit as st
+import pandas as pd
+import joblib
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import roc_curve, auc, confusion_matrix, classification_report, accuracy_score
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Load the saved model from Hugging Face Space
+@st.cache(allow_output_mutation=True)
+def load_model():
+    model_path = 'best_stacking_model.pkl'  # Assuming you uploaded the model to the space root directory
+    model = joblib.load(model_path)
+    return model
+
+# Function to process uploaded CSV
+def process_csv(uploaded_file):
+    # Read the CSV file
+    df = pd.read_csv(uploaded_file)
+    return df
+
+# Streamlit app starts here
+st.title("Conjunctivitis Model Analysis App")
+
+# File uploader
+uploaded_file = st.file_uploader("Upload your CSV file", type="csv")
+
+if uploaded_file is not None:
+    # Process uploaded file
+    df = process_csv(uploaded_file)
+    st.write("Data Preview:")
+    st.write(df.head())
+    
+    # Split into features and target (assuming the file has a 'Target_goal' column)
+    if 'Target_goal' not in df.columns:
+        st.error("Error: The uploaded CSV does not contain a 'Target_goal' column.")
+    else:
+        X = df.drop(columns=['Target_goal'])
+        y = df['Target_goal']
+        
+        # Standardize the data
+        scaler = StandardScaler()
+        X_scaled = scaler.fit_transform(X)
+        
+        # Load the model
+        model = load_model()
+        
+        # Make predictions
+        y_pred = model.predict(X_scaled)
+        y_pred_proba = model.predict_proba(X_scaled)[:, 1]
+        
+        # Calculate metrics
+        acc = accuracy_score(y, y_pred)
+        fpr, tpr, _ = roc_curve(y, y_pred_proba)
+        roc_auc = auc(fpr, tpr)
+        
+        st.write(f"Accuracy: {acc:.2f}")
+        st.write(f"AUC: {roc_auc:.2f}")
+        
+        # Classification report
+        st.write("Classification Report:")
+        report = classification_report(y, y_pred, output_dict=True)
+        st.write(pd.DataFrame(report).transpose())
+        
+        # Confusion Matrix
+        st.write("Confusion Matrix:")
+        conf_matrix = confusion_matrix(y, y_pred)
+        sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues')
+        plt.title('Confusion Matrix')
+        plt.xlabel('Predicted')
+        plt.ylabel('Actual')
+        st.pyplot(plt.gcf())
+        
+        # ROC Curve
+        st.write("ROC Curve:")
+        plt.figure(figsize=(10, 6))
+        plt.plot(fpr, tpr, color='blue', lw=2, label='ROC Curve (AUC = %0.2f)' % roc_auc)
+        plt.plot([0, 1], [0, 1], color='gray', lw=1, linestyle='--')
+        plt.xlim([0.0, 1.0])
+        plt.ylim([0.0, 1.05])
+        plt.xlabel('False Positive Rate')
+        plt.ylabel('True Positive Rate')
+        plt.title('ROC Curve')
+        plt.legend(loc="lower right")
+        st.pyplot(plt.gcf())
+
+# Option to download the saved model
+st.write("[Download best model](best_stacking_model.pkl)")