changes

app.py

@@ -0,0 +1,137 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, confusion_matrix, roc_curve, auc
+
+st.title("🩺 Diabetes Prediction App")
+
+# Load dataset
+@st.cache_data
+def load_data():
+    file_path = "diabetes_prediction_dataset.csv"
+    df = pd.read_csv(file_path)
+    return df
+
+df = load_data()
+
+# Encode categorical features
+label_encoders = {}
+for col in ["gender", "smoking_history"]:
+    le = LabelEncoder()
+    df[col] = le.fit_transform(df[col])
+    label_encoders[col] = le
+
+# Convert binary features (0,1) to "Yes" and "No" for display
+binary_columns = ["hypertension", "heart_disease", "diabetes"]
+df_display = df.copy()  # Keep a copy for display
+for col in binary_columns:
+    df_display[col] = df_display[col].map({0: "No", 1: "Yes"})
+
+# Splitting dataset
+X = df.drop(columns=["diabetes"])
+y = df["diabetes"]  # Keep original 0/1 format
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Standardizing data
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+# Train Random Forest model
+rf = RandomForestClassifier(n_estimators=100, random_state=42)
+rf.fit(X_train_scaled, y_train)
+
+# Tabs
+tab1, tab2, tab3 = st.tabs(["📄 Dataset Preview", "📈 Model Performance", "🩺 Prediction"])
+
+# 1️⃣ **Tab 1: Dataset Preview**
+with tab1:
+    st.subheader("📄 Complete Dataset Preview")
+    st.write(df_display)  # Show dataset with Yes/No for better readability
+
+    st.subheader("📊 Correlation Heatmap")
+    plt.figure(figsize=(10,6))
+    sns.heatmap(df.corr(), annot=True, cmap="coolwarm", fmt=".2f")
+    st.pyplot(plt)
+
+# 2️⃣ **Tab 2: Model Performance**
+with tab2:
+    st.subheader("📈 Model Performance")
+    
+    # Evaluate model
+    y_pred = rf.predict(X_test_scaled)
+    accuracy = accuracy_score(y_test, y_pred)
+    st.write(f"### ⚡ Random Forest Accuracy: **{accuracy:.2f}**")
+
+    # Confusion Matrix
+    st.write("### 📊 Confusion Matrix")
+    cm = confusion_matrix(y_test, y_pred)
+    plt.figure(figsize=(5,4))
+    sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", xticklabels=["No Diabetes", "Diabetes"], yticklabels=["No Diabetes", "Diabetes"])
+    plt.xlabel("Predicted")
+    plt.ylabel("Actual")
+    st.pyplot(plt)
+
+    # ROC Curve
+    st.write("### 📉 ROC Curve")
+    fpr, tpr, _ = roc_curve(y_test, rf.predict_proba(X_test_scaled)[:,1])
+    roc_auc = auc(fpr, tpr)
+    plt.figure(figsize=(6,4))
+    plt.plot(fpr, tpr, color='darkorange', lw=2, label='ROC curve (area = {:.2f})'.format(roc_auc))
+    plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
+    plt.xlabel("False Positive Rate")
+    plt.ylabel("True Positive Rate")
+    plt.title("Receiver Operating Characteristic (ROC) Curve")
+    plt.legend(loc="lower right")
+    st.pyplot(plt)
+
+# 3️⃣ **Tab 3: Prediction**
+with tab3:
+    st.subheader("🩺 Make a Prediction")
+
+    # User inputs
+    user_name = st.text_input("Patient Name", value="John Doe")
+    user_gender = st.selectbox("Gender", label_encoders["gender"].classes_, key="gender_input")
+    user_smoking = st.selectbox("Smoking History", label_encoders["smoking_history"].classes_, key="smoking_input")
+
+    # Convert categorical inputs using label encoders
+    user_gender_encoded = label_encoders["gender"].transform([user_gender])[0]
+    user_smoking_encoded = label_encoders["smoking_history"].transform([user_smoking])[0]
+
+    # User inputs numerical features
+    user_data = [user_gender_encoded, user_smoking_encoded]
+    for col in ["age", "bmi", "HbA1c_level", "blood_glucose_level"]:
+        user_data.append(st.number_input(f"Enter {col}", float(df[col].min()), float(df[col].max()), float(df[col].mean())))
+
+    # User inputs binary features
+    user_binary_data = {}
+    for col in ["hypertension", "heart_disease"]:
+        user_binary_data[col] = st.radio(f"{col.replace('_', ' ').title()} (Yes/No)", ["No", "Yes"])
+
+    # Convert "Yes"/"No" to numerical (0 or 1) before prediction
+    for col in ["hypertension", "heart_disease"]:
+        user_data.append(1 if user_binary_data[col] == "Yes" else 0)
+
+    # Convert input into array
+    user_data = np.array([user_data]).reshape(1, -1)
+
+    # Predict button
+    if st.button("🔮 Predict"):
+        user_data_scaled = scaler.transform(user_data)
+        
+        # Prediction
+        prediction = rf.predict(user_data_scaled)
+        probability = rf.predict_proba(user_data_scaled)[:, 1][0]
+        
+        # Display result with patient name
+        st.subheader(f"🤖 Prediction for {user_name}")
+        if prediction[0] == 1:
+            st.error(f"🚨 **{user_name} is likely to have diabetes.** (Probability: {probability:.2f})")
+        else:
+            st.success(f"✅ **{user_name} is not likely to have diabetes.** (Probability: {probability:.2f})")

requirements.txt

@@ -0,0 +1,6 @@
+streamlit 
+pandas
+numpy
+matplotlib
+seaborn
+scikit-learn