分类学习-线性分类器

良/恶性乳腺癌肿瘤数据预处理

import pandas as pd
import numpy as np

#创建特征列表
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']

#从互联网读取指定数据
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)   #将?替换为标准缺失值表示
data = data.dropna(how = 'any')                         #丢弃带有缺失值的数据
print(data.shape)                                        #输出数据的数据量

out:
(683, 11)








准备良/恶性乳腺癌肿瘤训练、测试数据

#准备训练测试数据
from sklearn.cross_validation 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())
使用线性分类器进行分类

#使用线性分类模型从事良/恶性肿瘤预测任务
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier
#数据处理，归一化
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)
#训练
lr = LogisticRegression()
sgdc = SGDClassifier()
lr.fit(X_train, y_train)
sgdc.fit(X_train, y_train)
print(lr.predict(X_test))
print(sgdc.predict(X_test))
使用线性分类器进行性能分析

from sklearn.metrics import classification_report
print('Accuracy of LR Classifier:', lr.score(X_test, y_test))
print(classification_report(y_test, lr_predict, target_names=['Benign','Malignant']))
print('Accuracy of SGD Classifier:', sgdc.score(X_test, y_test))
print(classification_report(y_test, sgdc_predict, target_names=['Benign','Malignant']))




输出结果可知，逻辑回归比梯度下降法在测试集上表现有更高的准确性。衡量分类性能的参数通常有精确度（precision）、召回率(recall)、F1指标（f1-score）、