app.py

# streamlit_app.py

import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import VotingClassifier, StackingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, confusion_matrix, roc_curve, auc, classification_report

# Title and description
st.title("Classification Model Comparison: Stacking and Voting Classifiers")
st.write("""
### Predict target goals using different ensemble techniques
This application compares the performance of Stacking and Voting classifiers on the provided dataset.
""")

# File upload
uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])

if uploaded_file is not None:
    df = pd.read_csv(uploaded_file)

    st.write("### Raw Data")
    st.write(df)

    # Correlation Matrix
    corrMatrix = df.corr()

    # Plot heatmap
    st.write("### Correlation Heatmap")
    plt.figure(figsize=(25, 10))
    color_palette = sns.color_palette("viridis", as_cmap=True)
    ax = sns.heatmap(corrMatrix, vmin=-1, vmax=1, center=0, cmap=color_palette, annot=True, fmt=".2f", linewidths=0.5, square=True, cbar_kws={"shrink": 0.75})
    plt.title('Correlation Heatmap', fontsize=20, pad=20)
    plt.xticks(rotation=45, ha='right')
    plt.yticks(rotation=0)
    st.pyplot(plt)

    # Replace target variable
    df['Target_goal'] = df['Target_goal'].replace({1: 0, 2: 1})

    # Define features and target variable
    X = df.drop(columns=['Target_goal'])
    y = df['Target_goal']

    # Split the data
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Standardize the data
    scaler = StandardScaler()
    X_train = scaler.fit_transform(X_train)
    X_test = scaler.transform(X_test)

    # Define base models for stacking and voting
    estimators = [
        ('lr', LogisticRegression()),
        ('dt', DecisionTreeClassifier()),
        ('rf', RandomForestClassifier()),
        ('gb', GradientBoostingClassifier()),
        ('svc', SVC(probability=True))
    ]

    # Stacking Classifier
    stacking_clf = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())
    stacking_clf.fit(X_train, y_train)
    y_pred_stack = stacking_clf.predict(X_test)
    y_pred_stack_proba = stacking_clf.predict_proba(X_test)[:, 1]

    # Voting Classifier
    voting_clf = VotingClassifier(estimators=estimators, voting='soft')
    voting_clf.fit(X_train, y_train)
    y_pred_vote = voting_clf.predict(X_test)
    y_pred_vote_proba = voting_clf.predict_proba(X_test)[:, 1]

    # Evaluation
    st.write("### Accuracy Scores")
    accuracy_stack = accuracy_score(y_test, y_pred_stack)
    accuracy_vote = accuracy_score(y_test, y_pred_vote)
    st.write(f'Stacking Classifier Accuracy: {accuracy_stack:.2f}')
    st.write(f'Voting Classifier Accuracy: {accuracy_vote:.2f}')

    # Classification Reports
    st.write("### Classification Reports")
    st.write("#### Stacking Classifier")
    st.text(classification_report(y_test, y_pred_stack))

    st.write("#### Voting Classifier")
    st.text(classification_report(y_test, y_pred_vote))

    # Confusion Matrix
    st.write("### Confusion Matrix for Stacking Classifier")
    conf_matrix_stack = confusion_matrix(y_test, y_pred_stack)
    plt.figure(figsize=(6, 5))
    sns.heatmap(conf_matrix_stack, annot=True, fmt='d', cmap='Blues')
    plt.title('Stacking Classifier Confusion Matrix')
    plt.xlabel('Predicted')
    plt.ylabel('Actual')
    st.pyplot(plt)

    st.write("### Confusion Matrix for Voting Classifier")
    conf_matrix_vote = confusion_matrix(y_test, y_pred_vote)
    plt.figure(figsize=(6, 5))
    sns.heatmap(conf_matrix_vote, annot=True, fmt='d', cmap='Blues')
    plt.title('Voting Classifier Confusion Matrix')
    plt.xlabel('Predicted')
    plt.ylabel('Actual')
    st.pyplot(plt)

    # ROC Curve and AUC
    fpr_stack, tpr_stack, _ = roc_curve(y_test, y_pred_stack_proba)
    roc_auc_stack = auc(fpr_stack, tpr_stack)

    fpr_vote, tpr_vote, _ = roc_curve(y_test, y_pred_vote_proba)
    roc_auc_vote = auc(fpr_vote, tpr_vote)

    plt.figure(figsize=(10, 6))
    plt.plot(fpr_stack, tpr_stack, color='blue', lw=2, label='Stacking Classifier (AUC = %0.2f)' % roc_auc_stack)
    plt.plot(fpr_vote, tpr_vote, color='red', lw=2, label='Voting Classifier (AUC = %0.2f)' % roc_auc_vote)
    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)