import os
import pandas as pd
import numpy as np
from sklearn.model_selection import KFold, cross_val_score
from sklearn.svm import SVC
from sklearn.ensemble import AdaBoostClassifier
from sklearn.neural_network import MLPClassifier
import xgboost as xgb
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.pipeline import Pipeline
from concurrent.futures import ThreadPoolExecutor

# 1. 讀取文件夾中的所有.xlsx文件
data_folder = "./分類數據集"  
file_list = [f for f in os.listdir(data_folder) if f.endswith('.xlsx')]
result_folder = "./results"

# 定義分類器
classifiers = {
    "XGBoost": xgb.XGBClassifier(),
    "AdaBoost": AdaBoostClassifier(n_estimators=50), #https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.AdaBoostClassifier.html
    "SVM_rbf": SVC(C=1.0, kernel="rbf", gamma='scale'),  #gamma默認為1 / (n_features * X.var())，
                                                           #可以根據數據集進行調整
    "Neural_Network": MLPClassifier(hidden_layer_sizes=(100), max_iter=1000)
}

# # 對每一個文件進行分類實驗
# def process_file(file):

# 對每一個文件進行分類實驗
for file in file_list:    
    df = pd.read_excel(os.path.join(data_folder, file))
    X = df.iloc[:, :-1].values
    y = df.iloc[:, -1].values
    
    # 類別映射
    le = LabelEncoder()
    y = le.fit_transform(y)

    results = {
        "Classifier": [],
        "Experiment 1": [],
        "Experiment 2": [],
        "Experiment 3": [],
        "Experiment 4": [],
        "Experiment 5": [],
        "Mean Accuracy": [],
        "Accuracy Variance": []
    }
    
    # 使用四種分類器
    for clf_name, clf in classifiers.items():
        all_accuracies = []
        
        # 使用標準化和分類器創建流水線
        pipeline = Pipeline([
            ('scaler', StandardScaler()),
            ('classifier', clf)
        ])

        # 重復5次實驗
        for exp_num in range(1, 6):
            print(clf_name, exp_num)
            kf = KFold(n_splits=10, shuffle=True, random_state=None)
            accuracies = cross_val_score(pipeline, X, y, cv=kf,n_jobs=16)
            results[f"Experiment {exp_num}"].append(np.mean(accuracies))
            all_accuracies.extend(accuracies)
        
        results["Classifier"].append(clf_name)
        results["Mean Accuracy"].append(np.mean(all_accuracies))
        results["Accuracy Variance"].append(np.var(all_accuracies))
    
    # 保存到.csv文件
    result_df = pd.DataFrame(results)
    result_df.to_csv(os.path.join(result_folder, f"results_{file.replace('.xlsx', '.csv')}"), index=False)

# # 使用多線程處理文件
# with ThreadPoolExecutor() as executor:
#     executor.map(process_file, file_list)

print("Experiments completed!")