Update app.py

app.py

@@ -1,8 +1,6 @@
 import streamlit as st
 import pandas as pd
 import numpy as np
-import matplotlib.pyplot as plt
-import joblib
 
 from sklearn.ensemble import RandomForestClassifier, VotingClassifier
 from sklearn.tree import DecisionTreeClassifier
@@ -12,12 +10,9 @@ from sklearn.svm import SVC
 from sklearn.naive_bayes import GaussianNB
 from sklearn.neural_network import MLPClassifier
 from sklearn.ensemble import GradientBoostingClassifier
-from xgboost import XGBClassifier
-from lightgbm import LGBMClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
-
-
+from sklearn.multioutput import MultiOutputClassifier
 st.title('Disease Prediction Application')
 st.write('''
          Please fill in the attributes below, then hit the Predict button
@@ -32,7 +27,6 @@ st.write(''' ''')
 bmi = st.slider('BMI', min_value=0.0, max_value=50.0, value=25.0, step=0.1)
 st.write(''' ''')
 
-
 st.header('Blood Test Information')
 bs = st.radio("Is Your Fasting Blood Sugar > 120 mg/dl?", ('Yes', 'No'))
 st.write(''' ''')
@@ -62,11 +56,14 @@ max_heart = st.slider('Maximum Heart Rate', min_value=0.0, max_value=300.0, valu
 st.write(''' ''')
 resting_bp = st.slider('Resting Blood Pressure (In mm Hg)', min_value=0.0, max_value=200.0, value=100.0, step=1.0)
 st.write(''' ''')
-re = st.radio("Resting Electrocardiogram Results", ('Normal', 'ST-T Wave Abnormality (T Wave Inversions and/or ST Elevation or Depression of > 0.05 mV)', 'Showing Probable or Definite Left Ventricular Hypertrophy by Estes Criteria'))
+re = st.radio("Resting Electrocardiogram Results", (
+'Normal', 'ST-T Wave Abnormality (T Wave Inversions and/or ST Elevation or Depression of > 0.05 mV)',
+'Showing Probable or Definite Left Ventricular Hypertrophy by Estes Criteria'))
 st.write(''' ''')
 ex = st.radio("Exercise Induced Angina", ('Yes', 'No'))
 st.write(''' ''')
-oldpeak = st.slider('ST Depression Induced by Exercise Relative to Rest', min_value=-5.0, max_value=5.0, value=0.0, step=0.01)
+oldpeak = st.slider('ST Depression Induced by Exercise Relative to Rest', min_value=-5.0, max_value=5.0, value=0.0,
+                    step=0.01)
 st.write(''' ''')
 sp = st.radio("The Slope of the Peak Exercise ST Segment", ('Upsloping', 'Flat', 'Downsloping'))
 st.write(''' ''')
@@ -121,7 +118,8 @@ user_input = np.array([age, gender, chest, blood_sugar, resting_bp, electro, max
 
 # import dataset
 def get_dataset():
-    data = pd.read_csv('Fianl Dataset.csv')
+    data = pd.read_csv('Final Dataset.csv')
+
 
     # Calculate the correlation matrix
     # corr_matrix = data.corr()
@@ -138,115 +136,83 @@ def get_dataset():
     # st.pyplot()
 
     return data
-    
+
 
 if st.button('Submit'):
     # Load your dataset for prediction
     df = get_dataset()
 
+    # Create an ensemble model with 'Random Forest', 'Naive Bayes', and 'Gradient Boosting'
+    random_forest_model = RandomForestClassifier(random_state=101)
+    naive_bayes_model = GaussianNB()
+    gradient_boosting_model = GradientBoostingClassifier(random_state=42)
+
+    # Create a voting ensemble with soft voting
+    ensemble_model = VotingClassifier(estimators=[
+        ('Random Forest', random_forest_model),
+        ('Naive Bayes', naive_bayes_model),
+        ('Gradient Boosting', gradient_boosting_model)
+    ], voting='soft')
+
     # Split the dataset into features and targets for Heart and Diabetes prediction
     X = df.drop(['Diabetes', 'Heart'], axis=1)
     y_heart = df['Heart']
     y_diabetes = df['Diabetes']
 
-    # Create an ensemble model for Heart prediction
-    random_forest_model_heart = RandomForestClassifier(random_state=42)
-    naive_bayes_model_heart = GaussianNB()
-    gradient_boosting_model_heart = GradientBoostingClassifier(random_state=42)
+    # Fit the ensemble model on the entire dataset for Heart Disease prediction
+    ensemble_model.fit(X, y_heart)
 
-    # Create a voting ensemble with soft voting for Heart prediction
-    ensemble_model_heart = VotingClassifier(estimators=[
-        ('Random Forest', random_forest_model_heart),
-        ('Naive Bayes', naive_bayes_model_heart),
-        ('Gradient Boosting', gradient_boosting_model_heart)
-    ], voting='soft')
-
-    # Create an ensemble model for Diabetes prediction
-    random_forest_model_diabetes = RandomForestClassifier(random_state=42)
-    naive_bayes_model_diabetes = GaussianNB()
-    gradient_boosting_model_diabetes = GradientBoostingClassifier(random_state=42)
-
-    # Create a voting ensemble with soft voting for Diabetes prediction
-    ensemble_model_diabetes = VotingClassifier(estimators=[
-        ('Random Forest', random_forest_model_diabetes),
-        ('Naive Bayes', naive_bayes_model_diabetes),
-        ('Gradient Boosting', gradient_boosting_model_diabetes)
-    ], voting='soft')
+    # Make predictions on user input for Heart Disease
+    prediction_heart = ensemble_model.predict(user_input)
+    prediction_proba_heart = ensemble_model.predict_proba(user_input)
 
-    # Split the data into training and testing sets for both targets
-    X_train, X_test, y_heart_train, y_heart_test, y_diabetes_train, y_diabetes_test = train_test_split(
-        X, y_heart, y_diabetes, test_size=0.2, random_state=42
-    )
-
-    # Ensure the user input has the correct number of features for Heart prediction
-    if user_input.shape[1] == X_train.shape[1]:
-        # Fit the ensemble model for Heart prediction on the training data
-        ensemble_model_heart.fit(X_train, y_heart_train)
-
-        # Make predictions on user input for Heart
-        prediction_heart = ensemble_model_heart.predict(user_input)
-        prediction_proba_heart = ensemble_model_heart.predict_proba(user_input)
-
-        # Check if the dimensions of prediction_heart match y_heart_test
-        if prediction_heart.shape[0] == y_heart_test.shape[0]:
-            # You can add a threshold and provide a prediction based on class 1 for Heart
-            threshold_heart = 0.5
-            if prediction_proba_heart[0][1] >= threshold_heart:
-                st.header("Predicted Heart Disease: You might have Heart Disease")
-                st.write("Predicted Probability of Having Heart Disease:", prediction_proba_heart[0][1] * 100)
-            else:
-                st.header("Predicted Heart Disease: You do not have Heart Disease")
-                st.write("Predicted Probability of Having Heart Disease:", prediction_proba_heart[0][1] * 100)
-
-            # Calculate and print Heart prediction metrics
-            accuracy_heart = accuracy_score(y_heart_test, prediction_heart)
-            precision_heart = precision_score(y_heart_test, prediction_heart)
-            recall_heart = recall_score(y_heart_test, prediction_heart)
-            f1_heart = f1_score(y_heart_test, prediction_heart)
-
-            st.write("Heart Prediction Metrics:")
-            st.write("Accuracy:", accuracy_heart)
-            st.write("Precision:", precision_heart)
-            st.write("Recall:", recall_heart)
-            st.write("F1-score:", f1_heart)
-            st.write("____________________________________________________________________________________________")
-        else:
-            st.write("Error: Inconsistent dimensions in Heart prediction. Please check your data.")
+    # You can add a threshold and provide a prediction based on class 1 for Heart Disease
+    threshold_heart = 0.5
+    if prediction_proba_heart[0][1] >= threshold_heart:
+        st.header("Predicted Heart Disease: You might have Heart Disease")
+        st.write("Predicted Probability of Having Heart Disease:", prediction_proba_heart[0][1] * 100)
     else:
-        st.write("Error: Input features do not match the dataset. Please provide valid input.")
-
-    # Ensure the user input has the correct number of features for Diabetes prediction
-    if user_input.shape[1] == X_train.shape[1]:
-        # Fit the ensemble model for Diabetes prediction on the training data
-        ensemble_model_diabetes.fit(X_train, y_diabetes_train)
-
-        # Make predictions on user input for Diabetes
-        pred_diabetes = ensemble_model_diabetes.predict(user_input)
-        pred_diabetes_proba = ensemble_model_diabetes.predict_proba(user_input)
-
-        # Check if the dimensions of pred_diabetes match y_diabetes_test
-        if pred_diabetes.shape[0] == y_diabetes_test.shape[0]:
-            # You can add a threshold and provide a prediction based on class 1 for Diabetes
-            threshold_diabetes = 0.5
-            if pred_diabetes_proba[0][1] >= threshold_diabetes:
-                st.header("Predicted Diabetes: You might have Diabetes")
-                st.write("Predicted Probability of Having Diabetes:", pred_diabetes_proba[0][1] * 100)
-            else:
-                st.header("Predicted Diabetes: You do not have Diabetes")
-                st.write("Predicted Probability of Having Diabetes:", pred_diabetes_proba[0][1] * 100)
-
-            # Calculate and print Diabetes prediction metrics
-            accuracy_diabetes = accuracy_score(y_diabetes_test, pred_diabetes)
-            precision_diabetes = precision_score(y_diabetes_test, pred_diabetes)
-            recall_diabetes = recall_score(y_diabetes_test, pred_diabetes)
-            f1_diabetes = f1_score(y_diabetes_test, pred_diabetes)
-
-            st.write("Diabetes Prediction Metrics:")
-            st.write("Accuracy:", accuracy_diabetes)
-            st.write("Precision:", precision_diabetes)
-            st.write("Recall:", recall_diabetes)
-            st.write("F1-score:", f1_diabetes)
-        else:
-            st.write("Error: Inconsistent dimensions in Diabetes prediction. Please check your data.")
+        st.header("Predicted Heart Disease: You do not have Heart Disease")
+        st.write("Predicted Probability of Having Heart Disease:", prediction_proba_heart[0][1] * 100)
+
+    # Calculate and display evaluation metrics for Heart Disease prediction
+    accuracy_heart = accuracy_score(y_heart, ensemble_model.predict(X))
+    precision_heart = precision_score(y_heart, ensemble_model.predict(X))
+    recall_heart = recall_score(y_heart, ensemble_model.predict(X))
+    f1_heart = f1_score(y_heart, ensemble_model.predict(X))
+
+    st.header("Heart Disease Prediction Metrics:")
+    st.write("Accuracy:", accuracy_heart)
+    st.write("Precision:", precision_heart)
+    st.write("Recall:", recall_heart)
+    st.write("F1-score:", f1_heart)
+
+    # Fit the ensemble model on the entire dataset for Diabetes prediction
+    ensemble_model.fit(X, y_diabetes)
+
+    # Make predictions on user input for Diabetes
+    pred_diabetes = ensemble_model.predict(user_input)
+    pred_diabetes_proba = ensemble_model.predict_proba(user_input)
+
+    # You can add a threshold and provide a prediction based on class 1 for Diabetes
+    threshold_diabetes = 0.5
+    if pred_diabetes_proba[0][1] >= threshold_diabetes:
+        st.header("Predicted Diabetes: You might have Diabetes")
+        st.write("Predicted Probability of Having Diabetes:", pred_diabetes_proba[0][1] * 100)
     else:
-        st.write("Error: Input features do not match the dataset. Please provide valid input.")
+        st.header("Predicted Diabetes: You do not have Diabetes")
+        st.write("Predicted Probability of Having Diabetes:", pred_diabetes_proba[0][1] * 100)
+
+# Calculate and display evaluation metrics for Diabetes prediction
+    accuracy_diabetes = accuracy_score(y_diabetes, ensemble_model.predict(X))
+    precision_diabetes = precision_score(y_diabetes, ensemble_model.predict(X))
+    recall_diabetes = recall_score(y_diabetes, ensemble_model.predict(X))
+    f1_diabetes = f1_score(y_diabetes, ensemble_model.predict(X))
+
+    st.header("Diabetes Prediction Metrics:")
+    st.write("Accuracy:", accuracy_diabetes)
+    st.write("Precision:", precision_diabetes)
+    st.write("Recall:", recall_diabetes)
+    st.write("F1-score:", f1_diabetes)
+
+