本文是個人學習筆記，內容主要涉及LR(LogisticRegression)和SGD(SGDClassifier)對breast-cancer資料集進行線性二分類。
線性分類器：假設資料特徵與分類目標之間是線性關係的模型，通過累加計算每個維度的特徵與各自權重的乘積來幫助類別決策。

二類分類任務的評估指標：混淆矩陣

F1 measure是Precision和Recall兩個指標的調和平均數，對於Precision和Recall更加接近的模型F1 measure的得分會更高。

import numpy as np
import pandas as pd
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.to_csv(r'data.csv',index=None)

data=pd.read_csv(r'data.csv')
data

data=data.replace(to_replace='?',value=np.nan)   #將？替換為標準缺失值
data=data.dropna(how='any')   #丟棄帶有缺失值的資料樣本
data.shape
#Output:(683, 11)

from distutils.version import LooseVersion as Version  
from
 
 sklearn import __version__ as sklearn_version  
from sklearn import datasets  
if Version(sklearn_version) < '0.18':  
    from sklearn.cross_validation import train_test_split  
else:  
    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)

y_train.value_counts()
#Output:2    344
#       4    168
#       Name: Class, dtype: int64

y_test.value_counts()
#Output:2    100
#       4     71
#       Name: Class, dtype: int64

from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression,SGDClassifier
ss=StandardScaler()   #資料幅度標準化
X_train=ss.fit_transform(X_train)
X_test=ss.transform(X_test)   #注意,對測試集不需要fit,用和訓練集一樣的變換

lr=LogisticRegression()   #初始化
lr.fit(X_train,y_train)   #fit訓練模型引數
lr_y_predict=lr.predict(X_test)   #用訓練好的模型lr進行預測,結果儲存在變數lr_y_predict裡

sgdc=SGDClassifier()
sgdc.fit(X_train,y_train)
sgdc_y_predict=sgdc.predict(X_test)

from sklearn.metrics import classification_report   #Accuracy,Precision,Recall,f1-score
print('Accuracy of LR Classifier:',lr.score(X_test,y_test))
print(classification_report(y_test,lr_y_predict,target_names=['Benign','Malignant']))

print('Accuarcy of SGD Classifier:',sgdc.score(X_test,y_test))
print(classification_report(y_test,sgdc_y_predict,target_names=['Benign','Malignant']))