加载数据集
import pandas as pd
df_wine = pd.read_csv(‘https://archive.ics.uci.edu/ml/’
‘machine-learning-databases/wine/wine.data’,
header=None)
1
2
3
4
5
划分数据集
if Version(sklearn_version) < ‘0.18’:
from sklearn.cross_validation import train_test_split
else:
from sklearn.model_selection import train_test_split
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test =
train_test_split(X, y, test_size=0.3, random_state=0)
1
2
3
4
5
6
7
8
9
标准化
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.transform(X_test)