导入包

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report,roc_auc_score

读取数据集

# 特征名称
feature_names = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
                 'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin',
                 'Normal Nucleoli', 'Mitoses', 'Class']

data = pd.read_csv(
    "https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",
    names=feature_names)
data.head()

	Sample code number	Clump Thickness	Uniformity of Cell Size	Uniformity of Cell Shape	Marginal Adhesion	Single Epithelial Cell Size	Bare Nuclei	Bland Chromatin	Normal Nucleoli	Mitoses	Class
0	1000025	5	1	1	1	2	1	3	1	1	2
1	1002945	5	4	4	5	7	10	3	2	1	2
2	1015425	3	1	1	1	2	2	3	1	1	2
3	1016277	6	8	8	1	3	4	3	7	1	2
4	1017023	4	1	1	3	2	1	3	1	1	2

列名解释

在实际工作中，要弄清楚每一个肿瘤特征代表什么含义，这样才能做好异常值缺失值的处理

• Sample code number 样本编号 用不到
• Clump Thickness 肿瘤特征1
• Uniformity of Cell Size 肿瘤特征2
• Uniformity of Cell Shape 肿瘤特征3
• Marginal Adhesion 肿瘤特征4
• Single Epithelial Cell Size 肿瘤特征5
• Bare Nuclei 肿瘤特征6
• Bland Chromatin 肿瘤特征7
• Normal Nucleoli 肿瘤特征8
• Mitoses 肿瘤特征9
• Class 肿瘤的种类

查看目标值

• 2表示良性，444条数据
• 4表示恶性，239条数据

data.Class.value_counts()

2    458
4    241
Name: Class, dtype: int64

数据基本处理 缺失值处理

# 替换缺失值
data = data.replace(to_replace='?', value=np.nan)
# 删除缺失值的样本
data = data.dropna()

划分数据集

X = data[feature_names[0:-1]]  # ==> X = data.iloc[:, 0:-1]
y = data["Class"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

特征工程 标准化

transform = StandardScaler()
X_train = transform.fit_transform(X_train)
X_test = transform.fit_transform(X_test)

模型训练

lr_model = LogisticRegression()
lr_model.fit(X_train, y_train)

LogisticRegression()

模型评估（准确率、精确率、召回率）

模型在训练集上的准确率

lr_model.score(X_train, y_train)

0.9688644688644689

模型在测试集上的准确率

lr_model.score(X_test, y_test)

0.9781021897810219

预测精确率、召回率

y_pred = lr_model.predict(X_test)
report = classification_report(y_test, y_pred, labels=(2, 4), target_names=("良性", "恶性"))
print(report)

              precision    recall  f1-score   support

          良性       0.99      0.98      0.98        96
          恶性       0.95      0.98      0.96        41

    accuracy                           0.98       137
   macro avg       0.97      0.98      0.97       137
weighted avg       0.98      0.98      0.98       137