【交叉验证】k折交叉验证_从文件中划分

LansinBlog

已于 2024-07-11 22:46:46 修改

阅读量117

点赞数 2

分类专栏：实验设置文章标签： python 人工智能机器学习

于 2024-03-22 08:47:51 首次发布

本文链接：https://blog.csdn.net/weixin_45674669/article/details/136928011

版权

实验设置专栏收录该内容

4 篇文章 0 订阅

订阅专栏

from sklearn.model_selection import KFold
import pandas as pd

data = pd.read_csv("F:\\PaperCode\\Mypaper_python_code\\data\\dataset_split\\data_trainANDval.tsv", sep = "\t")

X = data.iloc[:, 0]
y = data.iloc[:, 1]

# print(X)
# print(type(X))


kf = KFold(n_splits=5, shuffle=False)  # 初始化KFold

# 存放5折的训练集划分
X_train_files = []
y_train_files = []
X_test_files = []
y_test_files = []

p = 0
for train_index , test_index in kf.split(X):  # 调用split方法切分数据
#     # print('train_index:%s , test_index: %s ' %(train_index,test_index))
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]

    # 保存方式：
    # 1.保存到列表
    X_train_files.append(X_train)
    y_train_files.append(y_train)
    X_test_files.append(X_test)
    y_test_files.append(y_test)

    # 2.存入tsv文件中
    X_train.to_csv("F:\\PaperCode\\Mypaper_python_code\\data\\dataset_split\\" + str(p) + "\\X_train.tsv", index=False)
    y_train.to_csv("F:\\PaperCode\\Mypaper_python_code\\data\\dataset_split\\" + str(p) + "\\y_train.tsv", index=False)
    X_test.to_csv("F:\\PaperCode\\Mypaper_python_code\\data\\dataset_split\\" + str(p) + "\\X_test.tsv", index=False)
    y_test.to_csv("F:\\PaperCode\\Mypaper_python_code\\data\\dataset_split\\" + str(p) + "\\y_test.tsv", index=False)

    p += 1


# print(y_test_files)