请参考《数据准备和特征工程》中的相关章节，调试如下代码。
import pandas as pd
df_wine = pd.read_csv("/home/aistudio/data/data20527/wine_data.csv")
df_wine.head()
| 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1 | 14.23 | 1.71 | 2.43 | 15.6 | 127 | 2.80 | 3.06 | 0.28 | 2.29 | 5.64 | 1.04 | 3.92 | 1065 |
| 1 | 1 | 13.20 | 1.78 | 2.14 | 11.2 | 100 | 2.65 | 2.76 | 0.26 | 1.28 | 4.38 | 1.05 | 3.40 | 1050 |
| 2 | 1 | 13.16 | 2.36 | 2.67 | 18.6 | 101 | 2.80 | 3.24 | 0.30 | 2.81 | 5.68 | 1.03 | 3.17 | 1185 |
| 3 | 1 | 14.37 | 1.95 | 2.50 | 16.8 | 113 | 3.85 | 3.49 | 0.24 | 2.18 | 7.80 | 0.86 | 3.45 | 1480 |
| 4 | 1 | 13.24 | 2.59 | 2.87 | 21.0 | 118 | 2.80 | 2.69 | 0.39 | 1.82 | 4.32 | 1.04 | 2.93 | 735 |
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
# X为数据集中特征的集合，y为数据集中标签的集合
# test_size=0.3: 测试数据集所占比例为0.3
# random_state=0: 随机数种子
# stratify=y 训练和测试集都按照y中的比例分配
X, y = df_wine.iloc[:, 1:], 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, stratify=y)
# 对测试集和训练集分别实现特征标准化。
std = StandardScaler()
X_train_std = std.fit_transform(X_train)
X_test_std = std.fit_transform(X_test)
from sklearn.linear_model import LogisticRegression
# LogisticRegression()：建立对数概率回归模型，并添加惩罚项，防止模型出现过拟合
lr = LogisticRegression(C = 1.0, penalty = 'l1',solver='liblinear')
lr.fit(X_train_std, y_train)
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=100,
multi_class='auto', n_jobs=None, penalty='l1',
random_state=None, solver='liblinear', tol=0.0001, verbose=0,
warm_start=False)
# 输出13个特征的系数(权重)。特征系数为0的,说明此类特征与预测结果无关。
lr.coef_
array([[ 1.24625685, 0.18107053, 0.74257832, -1.16001118, 0. ,
0. , 1.17611757, 0. , 0. , 0. ,
0. , 0.54232728, 2.51117025],
[-1.53720803, -0.387145 , -0.99522705, 0.36479669, -0.05946812,
0. , 0.66779999, 0. , 0. , -1.93405254,
1.23412954, 0. , -2.2316079 ],
[ 0.1355303 , 0.1687654 , 0.3572857 , 0. , 0. ,
0. , -2.43734423, 0. , 0. , 1.5634205 ,
-0.81896512, -0.49331848, 0. ]])
# 截距，由于Class_label有3个可选值0，1，2；故存在3条截距
lr.intercept_
array([-1.26341218, -1.21591946, -2.37057917])