（逻辑斯蒂回归（主要）+随机梯度）良/恶性乳腺肿瘤预测

# -*- coding: cp936 -*-
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("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",names=column_names)
data=data.replace(to_replace='?',value=np.nan)
data=data.dropna(how='any')
#data.shape

from sklearn.cross_validation import train_test_split#分割数据
X_train,X_test,y_train,y_test=train_test_split(data[column_names[1:10]],data[column_names[10]],test_size=0.5,random_state=33)

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.fit_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','Maligant'])

求解回归系数可以这样子，我们仍然以该数据为例，计算逻辑回归的回归系数

# -*- coding: cp936 -*-
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("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",names=column_names)
data=data.replace(to_replace='?',value=np.nan)
data=data.dropna(how='any')
#data.shape


from sklearn.cross_validation import train_test_split#分割数据
X_train,X_test,y_train,y_test=train_test_split(data[column_names[1:10]],data[column_names[10]],test_size=0.5,random_state=33)

import sklearn.linear_model as sk_linear
model = sk_linear.LogisticRegression(penalty="l2", dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=None, random_state=None, solver="liblinear", max_iter=100, multi_class="ovr", verbose=0, warm_start=False, n_jobs=1)
model.fit(X_train,y_train)
acc=model.score(X_test,y_test) #返回预测的确定系数R2
print '逻辑回归:'
print '截距:',model.intercept_ #输出截距
print'系数:',model.coef_ #输出系数
print'逻辑回归模型评价:',acc

输出

======================== RESTART: C:/Python27/laji.py ========================

Warning (from warnings module):
  File "C:\Python27\lib\site-packages\sklearn\cross_validation.py", line 41
    "This module will be removed in 0.20.", DeprecationWarning)
DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
逻辑回归:
截距: [-5.321301]
系数: [[ 0.23229245  0.19913981  0.24170318  0.1652501   0.03457521  0.26294431
   0.04651961  0.11158346  0.14945944]]
逻辑回归模型评价: 0.979532163743

值得一提的是，model=sklearn.linear_model.LogisticRegression(fit_intercept=True,n_jobs=1)

                        model.get_params()

这个get_params是获取各个model的参数，并不是求解回归系数，第一次搞混乱了，一定要注意！