Update app.py

app.py

@@ -1,99 +1,167 @@
 import streamlit as st
+import pandas as pd
 import joblib
 import numpy as np
 
-def calculate_failed_rates(number_of_previous, number_of_failed):
-    """
-    Calculate failure rates for Bup or Meth episodes.
-    Handles cases where 'number_of_previous' is zero to avoid division errors.
-    """
-    return number_of_failed / number_of_previous if number_of_previous > 0 else 0.0
-
-
 # Load the trained model
 model = joblib.load("stacked_model.pkl")
 
-# Feature list (15 features including dynamically calculated ones)
-feature_names = [
-    "MOUDType_Meth", "prior_BUP_days_supply", "RxLocation_O", "Previous_Meth_Episodes",
-    "TimeSinceLastEpisode", "prior_Meth_days_supply", "YearOfInitiation", "MOUDType_Nalt",
-    "RPL_THEME3", "NumberofMHVisits", "CtRxsEpisode", "RPL_THEME2", 
-    "CtDaysCoveredAntidepEpisode", "Failed_Bup_Rate", "Failed_Meth_Rate"
-]
-
-# Page title and description
+# Set page configuration
 st.set_page_config(page_title="Retention Prediction App", layout="centered")
 st.title("📈 Retention Prediction App")
-st.markdown("Predict the probability of **retention** and the corresponding class using a trained StackingClassifier model.")
-
-# Sidebar description
-st.sidebar.header("📝 Input Patient Data")
-st.sidebar.markdown("Enter the required patient data below. Fields marked with * are dynamically calculated.")
-
-# Create a form for inputs
-with st.form("patient_form"):
-    st.subheader("Patient Information")
-
-    # Collect inputs
-    col1, col2 = st.columns(2)  # Two-column layout for better organization
-    with col1:
-        moudtype_meth = st.selectbox("MOUDType_Meth (1=Yes, 0=No)", [0, 1], help="Whether the patient is on Meth MOUD")
-        prior_bup_days_supply = st.number_input("Prior BUP Days Supply (days)", min_value=0, value=30, step=1)
-        rxlocation_o = st.selectbox("RxLocation_O (1=Yes, 0=No)", [0, 1], help="Whether RxLocation is O")
-        previous_meth_episodes = st.number_input("Previous Meth Episodes", min_value=0, value=0)
-        timesince_last_episode = st.number_input("Time Since Last Episode (days)", min_value=0, value=0)
-        ctrxs_episode = st.number_input("CtRxsEpisode", min_value=0, value=0)
-        rpl_theme2 = st.number_input("RPL_THEME2", min_value=0.0, value=0.5, step=0.001)
-
-    with col2:
-        prior_meth_days_supply = st.number_input("Prior Meth Days Supply (days)", min_value=0, value=0, step=1)
-        year_of_initiation = st.number_input("Year of Initiation", min_value=2005, value=2022, step=1)
-        moudtype_nalt = st.selectbox("MOUDType_Nalt (1=Yes, 0=No)", [0, 1], help="Whether the patient is on Nalt MOUD")
-        rpl_theme3 = st.number_input("RPL_THEME3", min_value=0.0, value=0.5, step=0.001)
-        numberof_mhvisits = st.number_input("Number of MH Visits", min_value=0, value=0)
-        ct_days_covered_antidep_episode = st.number_input("CtDaysCoveredAntidepEpisode", min_value=0, value=0)
-
-    st.subheader("Calculated Features *")
-    col3, col4 = st.columns(2)
-    with col3:
-        number_of_previous_bup_episodes = st.number_input("Number of Previous BUP Episodes", min_value=0, value=0)
-        number_of_failed_bup_episodes = st.number_input("Number of Failed BUP Episodes", min_value=0, value=0)
-    with col4:
-        number_of_previous_meth_episodes = st.number_input("Number of Previous Meth Episodes", min_value=0, value=0)
-        number_of_failed_meth_episodes = st.number_input("Number of Failed Meth Episodes", min_value=0, value=0)
-
-    # Dynamic calculations
-    failed_bup_rate = calculate_failed_rates(number_of_previous_bup_episodes, number_of_failed_bup_episodes)
-    failed_meth_rate = calculate_failed_rates(number_of_previous_meth_episodes, number_of_failed_meth_episodes)
-
-    # Submit button
-    submitted = st.form_submit_button("Predict Retention")
-
-if submitted:
-    # Create input feature array
-    input_features = np.array([
-        moudtype_meth, prior_bup_days_supply, rxlocation_o, previous_meth_episodes,
-        timesince_last_episode, prior_meth_days_supply, year_of_initiation, moudtype_nalt,
-        rpl_theme3, numberof_mhvisits, ctrxs_episode, rpl_theme2,
-        ct_days_covered_antidep_episode, failed_bup_rate, failed_meth_rate
-    ]).reshape(1, -1)
-
-    # Check if the input matches the model's expected feature count
-    expected_feature_count = 15
-    if input_features.shape[1] != expected_feature_count:
-        st.error(f"Feature mismatch! Expected {expected_feature_count} features, but got {input_features.shape[1]}.")
+st.markdown("Upload an Excel file containing **20% unseen data** to predict retention probabilities and classes.")
+
+# Upload Excel file
+uploaded_file = st.file_uploader("Upload your Excel file (with all required columns):", type=["xlsx"])
+
+if uploaded_file is not None:
+    # Read the uploaded Excel file
+    data = pd.read_excel(uploaded_file)
+
+    st.subheader("Preview of Uploaded Data:")
+    st.write(data.head())
+
+    # Check if the required columns are in the uploaded file
+    required_columns = [
+        "MOUDType_Meth", "prior_BUP_days_supply", "RxLocation_O", "Previous_Meth_Episodes",
+        "Failed_Bup_Rate", "TimeSinceLastEpisode", "prior_Meth_days_supply", "YearOfInitiation",
+        "MOUDType_Nalt", "RPL_THEME3", "NumberofMHVisits", "CtRxsEpisode",
+        "RPL_THEME2", "CtDaysCoveredAntidepEpisode", "Failed_Meth_Rate"
+    ]
+
+    if all(col in data.columns for col in required_columns):
+        st.success("All required columns are present!")
+        
+        # Extract features for prediction
+        X = data[required_columns]
+
+        # Predict probabilities and classes
+        predicted_probabilities = model.predict_proba(X)[:, 1]
+        predicted_classes = model.predict(X)
+
+        # Add predictions to the original data
+        data["Predicted_Probability"] = predicted_probabilities
+        data["Predicted_Retention"] = predicted_classes
+
+        st.subheader("Predictions:")
+        st.write(data.head())
+
+        # Downloadable Excel file with predictions
+        output_file = "predicted_retention.xlsx"
+        data.to_excel(output_file, index=False)
+
+        # Create a download link
+        st.download_button(
+            label="Download Predictions as Excel",
+            data=data.to_excel(index=False, engine="openpyxl"),
+            file_name="predicted_retention.xlsx",
+            mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+        )
     else:
-        # Predict retention probability and class
-        predicted_probability = model.predict_proba(input_features)[:, 1][0]  # Probability of positive class
-        predicted_class = model.predict(input_features)[0]  # Predicted class (0 or 1)
-
-        # Display the results
-        st.success("Prediction Results:")
-        st.write(f"**Predicted Class:** {'Retention (1)' if predicted_class == 1 else 'No Retention (0)'}")
-        st.write(f"**Predicted Probability of Retention:** {predicted_probability:.2%}")
-
-        # Highlight results
-        st.markdown("""
-            - **Predicted Class:** Based on the highest probability.
-            - **Probability:** Shows the likelihood of retention.
-        """)
+        missing_cols = [col for col in required_columns if col not in data.columns]
+        st.error(f"The following required columns are missing: {missing_cols}")
+
+
+
+
+
+
+# import streamlit as st
+# import joblib
+# import numpy as np
+
+# def calculate_failed_rates(number_of_previous, number_of_failed):
+#     """
+#     Calculate failure rates for Bup or Meth episodes.
+#     Handles cases where 'number_of_previous' is zero to avoid division errors.
+#     """
+#     return number_of_failed / number_of_previous if number_of_previous > 0 else 0.0
+
+
+# # Load the trained model
+# model = joblib.load("stacked_model.pkl")
+
+# # Feature list (15 features including dynamically calculated ones)
+# feature_names = [
+#     "MOUDType_Meth", "prior_BUP_days_supply", "RxLocation_O", "Previous_Meth_Episodes",
+#     "TimeSinceLastEpisode", "prior_Meth_days_supply", "YearOfInitiation", "MOUDType_Nalt",
+#     "RPL_THEME3", "NumberofMHVisits", "CtRxsEpisode", "RPL_THEME2", 
+#     "CtDaysCoveredAntidepEpisode", "Failed_Bup_Rate", "Failed_Meth_Rate"
+# ]
+
+# # Page title and description
+# st.set_page_config(page_title="Retention Prediction App", layout="centered")
+# st.title("📈 Retention Prediction App")
+# st.markdown("Predict the probability of **retention** and the corresponding class using a trained StackingClassifier model.")
+
+# # Sidebar description
+# st.sidebar.header("📝 Input Patient Data")
+# st.sidebar.markdown("Enter the required patient data below. Fields marked with * are dynamically calculated.")
+
+# # Create a form for inputs
+# with st.form("patient_form"):
+#     st.subheader("Patient Information")
+
+#     # Collect inputs
+#     col1, col2 = st.columns(2)  # Two-column layout for better organization
+#     with col1:
+#         moudtype_meth = st.selectbox("MOUDType_Meth (1=Yes, 0=No)", [0, 1], help="Whether the patient is on Meth MOUD")
+#         prior_bup_days_supply = st.number_input("Prior BUP Days Supply (days)", min_value=0, value=30, step=1)
+#         rxlocation_o = st.selectbox("RxLocation_O (1=Yes, 0=No)", [0, 1], help="Whether RxLocation is O")
+#         previous_meth_episodes = st.number_input("Previous Meth Episodes", min_value=0, value=0)
+#         timesince_last_episode = st.number_input("Time Since Last Episode (days)", min_value=0, value=0)
+#         ctrxs_episode = st.number_input("CtRxsEpisode", min_value=0, value=0)
+#         rpl_theme2 = st.number_input("RPL_THEME2", min_value=0.0, value=0.5, step=0.001)
+
+#     with col2:
+#         prior_meth_days_supply = st.number_input("Prior Meth Days Supply (days)", min_value=0, value=0, step=1)
+#         year_of_initiation = st.number_input("Year of Initiation", min_value=2005, value=2022, step=1)
+#         moudtype_nalt = st.selectbox("MOUDType_Nalt (1=Yes, 0=No)", [0, 1], help="Whether the patient is on Nalt MOUD")
+#         rpl_theme3 = st.number_input("RPL_THEME3", min_value=0.0, value=0.5, step=0.001)
+#         numberof_mhvisits = st.number_input("Number of MH Visits", min_value=0, value=0)
+#         ct_days_covered_antidep_episode = st.number_input("CtDaysCoveredAntidepEpisode", min_value=0, value=0)
+
+#     st.subheader("Calculated Features *")
+#     col3, col4 = st.columns(2)
+#     with col3:
+#         number_of_previous_bup_episodes = st.number_input("Number of Previous BUP Episodes", min_value=0, value=0)
+#         number_of_failed_bup_episodes = st.number_input("Number of Failed BUP Episodes", min_value=0, value=0)
+#     with col4:
+#         number_of_previous_meth_episodes = st.number_input("Number of Previous Meth Episodes", min_value=0, value=0)
+#         number_of_failed_meth_episodes = st.number_input("Number of Failed Meth Episodes", min_value=0, value=0)
+
+#     # Dynamic calculations
+#     failed_bup_rate = calculate_failed_rates(number_of_previous_bup_episodes, number_of_failed_bup_episodes)
+#     failed_meth_rate = calculate_failed_rates(number_of_previous_meth_episodes, number_of_failed_meth_episodes)
+
+#     # Submit button
+#     submitted = st.form_submit_button("Predict Retention")
+
+# if submitted:
+#     # Create input feature array
+#     input_features = np.array([
+#         moudtype_meth, prior_bup_days_supply, rxlocation_o, previous_meth_episodes,
+#         timesince_last_episode, prior_meth_days_supply, year_of_initiation, moudtype_nalt,
+#         rpl_theme3, numberof_mhvisits, ctrxs_episode, rpl_theme2,
+#         ct_days_covered_antidep_episode, failed_bup_rate, failed_meth_rate
+#     ]).reshape(1, -1)
+
+#     # Check if the input matches the model's expected feature count
+#     expected_feature_count = 15
+#     if input_features.shape[1] != expected_feature_count:
+#         st.error(f"Feature mismatch! Expected {expected_feature_count} features, but got {input_features.shape[1]}.")
+#     else:
+#         # Predict retention probability and class
+#         predicted_probability = model.predict_proba(input_features)[:, 1][0]  # Probability of positive class
+#         predicted_class = model.predict(input_features)[0]  # Predicted class (0 or 1)
+
+#         # Display the results
+#         st.success("Prediction Results:")
+#         st.write(f"**Predicted Class:** {'Retention (1)' if predicted_class == 1 else 'No Retention (0)'}")
+#         st.write(f"**Predicted Probability of Retention:** {predicted_probability:.2%}")
+
+#         # Highlight results
+#         st.markdown("""
+#             - **Predicted Class:** Based on the highest probability.
+#             - **Probability:** Shows the likelihood of retention.
+#         """)