app.py

import streamlit as st
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.ensemble import StackingClassifier, VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# 定義每個分類方法的模型
def get_classifier(classifier_name):
    if classifier_name == 'SVM':
        clf = SVC(kernel='linear', probability=True)
    elif classifier_name == '堆疊法':
        estimators = [
            ('lr', LogisticRegression()),
            ('rf', RandomForestClassifier()),
            ('dt', DecisionTreeClassifier())
        ]
        clf = StackingClassifier(estimators=estimators, final_estimator=SVC())
    elif classifier_name == '軟投票':
        clf1 = LogisticRegression()
        clf2 = RandomForestClassifier()
        clf3 = SVC(probability=True)
        clf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2), ('svc', clf3)], voting='soft')
    else:  # 硬投票
        clf1 = LogisticRegression()
        clf2 = RandomForestClassifier()
        clf3 = SVC()
        clf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2), ('svc', clf3)], voting='hard')
    return clf

# 加載數據集
def load_data(file):
    data = pd.read_csv(file)
    X = data.iloc[:, :-1].values  # 特徵變量
    y = data.iloc[:, -1].values   # 目標變量
    return X, y

# 設定 Streamlit 標題
st.title("分類模型選擇器")

# 上傳 CSV 文件
uploaded_file = st.file_uploader("上傳 CSV 文件作為數據集", type="csv")

if uploaded_file is not None:
    # 加載數據集
    X, y = load_data(uploaded_file)
    
    # 分割數據集
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

    # 選擇分類器
    classifier_name = st.selectbox(
        '選擇分類器',
        ('SVM', '堆疊法', '軟投票', '硬投票')
    )

    # 獲取並訓練模型
    clf = get_classifier(classifier_name)
    clf.fit(X_train, y_train)

    # 預測結果
    y_pred = clf.predict(X_test)

    # 計算準確率
    acc = accuracy_score(y_test, y_pred)

    # 顯示結果
    st.write(f'分類器 = {classifier_name}')
    st.write(f'準確率 = {acc:.2f}')