今日分享:
良、恶性肿瘤病历分类预测
一:流程
1、网上获取数据,可利用pandas读取加载在线数据
2、数据缺失值处理、标准化
3、LogisticRegression估计器流程
二:数据集介绍
数据描述
(1)699条样本,共11列数据,第一列用语检索的id,后9列分别是与肿瘤
相关的医学特征,最后一列表示肿瘤类型的数值。
(2)包含16个缺失值,用”?”标出。
(3)原始数据的下载地址:
https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data
三:代码演示
导入相关库
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression,SGDRegressor,Ridge,LogisticRegression
from sklearn.metrics import mean_squared_error, classification_report
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
import pandas as pd
def logistic():
"""
逻辑回归做二分类进行癌症预测
"""
# 构造列标签名字
column = ['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']
# 读取在线数据集,确保网络状态良好
data = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data", names=column)
# print(data)
# 对存在缺失值进行处理,替换为nan
data = data.replace(to_replace='?', value=np.nan)
data = data.dropna()
# 进行数据的分割
x_train, x_test, y_train, y_test = train_test_split(data[column[1:10]], data[column[10]], test_size=0.25)
# 进行标准化处理
std = StandardScaler()
x_train = std.fit_transform(x_train)
x_test = std.transform(x_test)
# 逻辑回归预测
lg = LogisticRegression(C=1.0)
lg.fit(x_train, y_train)
print('回归系数\n',lg.coef_)
y_predict = lg.predict(x_test)
print("准确率:", lg.score(x_test, y_test))
print("召回率:", classification_report(y_test, y_predict, labels=[2, 4], target_names=["良性", "恶性"]))
if __name__ == "__main__":
logistic()
输出结果
回归系数
[[1.32854489 0.09059231 0.6221839 0.86693906 0.42247835 1.11436054
1.61155614 0.49346007 0.87032027]]
准确率:0.9590643274853801
召回率: precision recall f1-score support
良性 0.96 0.97 0.97 113
恶性 0.95 0.93 0.94 58
avg / total 0.96 0.96 0.96 171
注:结果中正确率(precision),召回率(recall)及f1-score值的说明,通过一个例子简单了解下:
某池塘有1400条鲤鱼,300只虾,300只鳖。现在以捕鲤鱼为目的。撒一大网,逮着了700条鲤鱼,200只虾,100只鳖。那么,这些指标分别如下:
正确率 = 700 / (700 + 200 + 100) = 70%
召回率 = 700 / 1400 = 50%
f1-score值 = 70% * 50% * 2 / (70% + 50%) = 58.3%