sklearn学习笔记，各类算法实现，原理介绍

'''
+++++++++++++++++++++++++++++++++++++
数据处理部分，缺失值处理+数据归一化/标准化，数据列id标为名称
+++++++++++++++++++++++++++++++++++++
'''
import pandas as pd
import numpy as np
column_name = ['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_name)
#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
data = data.dropna(how='any')
#划分训练集和测试集
from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test = train_test_split(data[column_name[1:10]],data[column_name[10]],test_size=0.25,random_state=33)

from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier
#标准化数据，保证每个维度的特征数据方差为1，均值为0，使得预测结果不会被某些维度过大的特征值而主导
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)

#print y_train.value_counts() # 查看分割后的数据集
#print y_test.value_counts()
'''
+++++++++++++++++++++++++++++++++++++
初始化LogisticRegression和SgdClassifier（随机梯度下降分类器）,target_names
+++++++++++++++++++++++++++++++++++++
'''

lr = LogisticRegression()
sgdc = SGDClassifier()
#调用LogisticRegression的fit函数来训练模型,并使用predict函数进行预测
lr.fit(X_train,y_train)
lr_y_predict = lr.predict(X_test)
#调用SGDClassifier中的fit函数来训练模型，并用predict函数来进行预测
sgdc.fit(X_train,y_train)
sgdc_y_predict = sgdc.predict(X_test)

from sklearn.metrics import classification_report
#利用score方法计算准确性
print('Accruacy of LR Classifier:',lr.score(X_tes