生成分类数据集（make_classification）

from sklearn.datasets import make_classification
X, y = make_classification(n_samples=10000, # 样本个数
n_features=25, # 特征个数
n_informative=3, # 有效特征个数
n_redundant=2, # 冗余特征个数（有效特征的随机组合）
n_repeated=0, # 重复特征个数（有效特征和冗余特征的随机组合）
n_classes=3, # 样本类别
n_clusters_per_class=1, # 簇的个数
random_state=0)

print("原始特征维度", X.shape)

# 读取数据
print("读取数据")
# import pandas as pd
# data = pd.read_csv(datapath)

# 数据划分
print("数据划分")
from sklearn.model_selection import train_test_split
global x_train, x_valid, x_test, y_train, y_valid, y_test
x_train, x_test, y_train, y_test = train_test_split(X, y, random_state=33, test_size=0.25)
x_train, x_valid, y_train, y_valid = train_test_split(x_train, y_train, random_state=33, test_size=0.25)