Python分割训练集和测试集的方法示例

import pandas as pd
import numpy as np

df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data', header=None)
df_wine.columns = ['Class label', 'Alcohol',
              'Malic acid', 'Ash',
              'Alcalinity of ash', 'Magnesium',
              'Total phenols', 'Flavanoids',
              'Nonflavanoid phenols',
              'Proanthocyanins',
              'Color intensity', 'Hue',
              'OD280/OD315 of diluted wines',
              'Proline']

from sklearn.model_selection import train_test_split

X, y = df_wine.ix[:, 1:].values, df_wine.ix[:, 0].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)#随机选择25%作为测试集，剩余作为训练集