Delete src/streamlit_app.py

src/streamlit_app.py

@@ -1,127 +0,0 @@
-import streamlit as st
-import pandas as pd
-import os
-import matplotlib.pyplot as plt
-import seaborn as sns
-from sklearn.model_selection import train_test_split
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.preprocessing import StandardScaler
-from sklearn.metrics import accuracy_score
-
-# Title
-st.set_page_config(page_title="Diabetes Prediction", page_icon="🩺", layout="wide") 
-st.title("Diabetes Prediction System")
-st.write("A Machine Learning model trained on the PIMA Indians Diabetes Dataset (KNN Algorithm).")
-
-# Load Data
-data_file = "diabetes.csv"
-if not os.path.exists(data_file):
-    data_file = "src/diabetes.csv"
-
-if not os.path.exists(data_file):
-    st.error("Error: 'diabetes.csv' not found. Please upload the file.")
-    st.stop()
-
-# Train Model
-@st.cache_resource
-def build_model(path):
-    df = pd.read_csv(path)
-    
-    # Split features and target
-    X = df.drop('Outcome', axis=1)
-    y = df['Outcome']
-    
-    # Scale the data 
-    scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
-    
-    X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
-
-    # KNN Classifier
-    knn = KNeighborsClassifier(n_neighbors=9)
-    knn.fit(X_train, y_train)
-    
-    # Check accuracy
-    acc = accuracy_score(y_test, knn.predict(X_test))
-    
-    return knn, acc, df, scaler
-
-# Get model, data, and the scaler
-model, accuracy, df, scaler = build_model(data_file)
-
-# Display basic stats
-st.write(f"**Model Accuracy (KNN):** {accuracy * 100:.2f}%")
-st.markdown("---")
-
-# UI - User Inputs
-st.sidebar.header("Patient Data")
-
-def user_input_features():
-    pregnancies = st.sidebar.slider('Pregnancies', 0, 17, 3)
-    glucose = st.sidebar.slider('Glucose', 0, 199, 117)
-    bp = st.sidebar.slider('Blood Pressure', 0, 122, 72)
-    skin = st.sidebar.slider('Skin Thickness', 0, 99, 23)
-    insulin = st.sidebar.slider('Insulin', 0, 846, 30)
-    bmi = st.sidebar.slider('BMI', 0.0, 67.1, 32.0)
-    dpf = st.sidebar.slider('Diabetes Pedigree Function', 0.078, 2.42, 0.3725)
-    age = st.sidebar.slider('Age', 21, 81, 29)
-    
-    user_data = {
-        'Pregnancies': pregnancies,
-        'Glucose': glucose,
-        'BloodPressure': bp,
-        'SkinThickness': skin,
-        'Insulin': insulin,
-        'BMI': bmi,
-        'DiabetesPedigreeFunction': dpf,
-        'Age': age
-    }
-    return pd.DataFrame(user_data, index=[0])
-
-input_df = user_input_features()
-
-st.subheader('User Input Parameters')
-st.write(input_df)
-
-# Prediction
-if st.button('Predict Diabetes Risk'):
-    input_scaled = scaler.transform(input_df)
-    
-    prediction = model.predict(input_scaled)
-    probs = model.predict_proba(input_scaled)
-
-    st.subheader('Prediction Result')
-    if prediction[0] == 1:
-        st.error(f'High Risk of Diabetes (Confidence: {probs[0][1]*100:.2f}%)')
-    else:
-        st.success(f'Low Risk of Diabetes (Confidence: {probs[0][0]*100:.2f}%)')
-
-st.markdown("---")
-
-# Graphs
-if st.checkbox("Show Data Analysis Graphs"):
-    
-    col1, col2 = st.columns(2)
-    
-    with col1:
-        st.subheader("Outcome Distribution")
-        fig1, ax1 = plt.subplots(figsize=(6, 4))
-        df['Outcome'].value_counts().plot.pie(autopct='%1.1f%%', ax=ax1, labels=['Healthy', 'Diabetic'], colors=['#66b3ff', '#ff9999'])
-        ax1.set_ylabel('')
-        st.pyplot(fig1, use_container_width=True)
-
-    with col2:
-        st.subheader("Correlation Heatmap")
-        fig2, ax2 = plt.subplots(figsize=(6, 4))
-        sns.heatmap(df.corr(), annot=False, cmap='coolwarm', ax=ax2)
-        st.pyplot(fig2, use_container_width=True)
-    
-    st.markdown("---")
-    
-    st.subheader("Feature Comparison (Box Plot)")
-    feature_to_plot = st.selectbox("Select Feature to Compare:", df.drop('Outcome', axis=1).columns)
-    
-    fig4, ax4 = plt.subplots(figsize=(10, 4))
-    sns.boxplot(x='Outcome', y=feature_to_plot, data=df, palette=['#66b3ff', '#ff9999'], ax=ax4)
-    ax4.set_xticklabels(['Healthy', 'Diabetic'])
-    st.pyplot(fig4, use_container_width=True)