1_肿瘤

column_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 = column_names )

# 将?替换为标准缺失值表示。
data = data.replace(to_replace=‘?‘, value=np.nan)
# 丢弃带有缺失值的数据（只要有一个维度有缺失）。
data = data.dropna(how=‘any‘)
　print(data.shape) 
# (683,11) 筛选后还有683条数据，维度是11

# 分割模块 一个训练一个测试
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

X_train, X_test, y_train, y_test = train_test_split(data[column_names[1:10]], data[column_names[10]], test_size=0.25, random_state=33)

from sklearn.preprocessing import StandardScaler
# 从sklearn.linear_model里导入LogisticRegression与SGDClassifier。
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier

ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)
#  把data变成正态分布，减小方差

lr = LogisticRegression()
# 调用LogisticRegression中的fit函数/模块用来训练模型参数。
lr.fit(X_train, y_train)
# 使用训练好的模型lr对X_test进行预测，结果储存在变量lr_y_predict中。
lr_y_predict = lr.predict(X_test)

print(lr_y_predict)

# 从sklearn.metrics里导入classification_report模块。 对预测结果进行评分
from sklearn.metrics import classification_report

print(lr.score(X_test, y_test))
print(classification_report(y_test, lr_y_predict, target_names=[‘Benign‘, ‘Malignant‘]))

sgdc = SGDClassifier()
# 调用SGDClassifier中的fit函数/模块用来训练模型参数。
sgdc.fit(X_train, y_train)
# 使用训练好的模型sgdc对X_test进行预测，结果储存在变量sgdc_y_predict中。
sgdc_y_predict = sgdc.predict(X_test)
print(sgdc_y_predict)

print(sgdc.score(X_test, y_test))
print(classification_report(y_test, sgdc_y_predict, target_names=[‘Benign‘, ‘Malignant‘]))