import pandas as pd
import numpy as np
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('http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data', names=column_names)
#print(data)
data = data.replace(to_replace='?', value=np.nan)
#print(data)
data = data.dropna(how='any')
#print(data)
data.shape
from sklearn.model_selection import train_test_split
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)
print(y_train.value_counts())
print(y_test.value_counts())
from sklearn.preprocessing import StandardScaler
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)
lr = LogisticRegression()
sgdc = SGDClassifier()
lr.fit(x_train, y_train)
lr_y_predict = lr.predict(x_test)
sgdc.fit(x_train, y_train)
sgdc_y_predict = sgdc.predict(x_test)
from sklearn.metrics import classification_report
print('Accuracy of LR Classifier:', lr.score(x_test, y_test))
print(classification_report(y_test, lr_y_predict, target_names=['Benign', 'Malignant']))
print('Accuracy of SGD Classifier:', sgdc.score(x_test, y_test))
print(classification_report(y_test, sgdc_y_predict, target_names=['Benign', 'Malignant']))
运行上面程序会出现一下警告：
Warning (from warnings module):
File "D:\Python362\lib\site-packages\sklearn\linear_model\stochastic_gradient.py", line 84
"and default tol will be 1e-3." % type(self), FutureWarning)
FutureWarning: max_iter and tol parameters have been added in <class 'sklearn.linear_model.stochastic_gradient.SGDClassifier'> in 0.19. If both are left unset, they default to max_iter=5 and tol=None. If tol is not None, max_iter defaults to max_iter=1000. From 0.21, default max_iter will be 1000, and default tol will be 1e-3.翻看了官方文档是版本升级的问题：
max_iter : int, optional
The maximum number of passes over the training data (aka epochs).
It only impacts the behavior in the ``fit`` method, and not the
`partial_fit`.
Defaults to 5. Defaults to 1000 from 0.21, or if tol is not None.
.. versionadded:: 0.19
在0.19的版本中，SDGClassifier默认的迭代次数是5，0.21版本默认的迭代次数是1000，要想不出现warnings只需手动设定SDGClassifier的迭代次数，代码如下：
sgdc = SGDClassifier(max_iter=5)运行修改后的代码最终结果如下：
Accuracy of LR Classifier: 0.988304093567
precision recall f1-score support
Benign 0.99 0.99 0.99 100
Malignant 0.99 0.99 0.99 71
avg / total 0.99 0.99 0.99 171
Accuracy of SGD Classifier: 0.982456140351
precision recall f1-score support
Benign 0.99 0.98 0.98 100
Malignant 0.97 0.99 0.98 71
avg / total 0.98 0.98 0.98 171
