技術標籤：機器學習

import numpy as np
import pandas as pd
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split



breast_cancer=datasets.load_breast_cancer()
x=breast_cancer.data
y=
 
breast_cancer['target']

print (type(x))
print (type(y))
print (y)
print (y.shape)
X_train,X_test,y_train,y_test=train_test_split(x,y,random_state=42)

print (len(X_train))
print (len(X_test))
print (type(X_train))
print (type(y_train))
print (X_train.shape)
print (y_train.shape)

log_reg=LogisticRegression(
 
max_iter=10000)

log_reg.fit(X_train,y_train)
y_predict=log_reg.predict(X_test)
print(confusion_matrix(y_test, y_predict))

[[51  3]
 [ 2 87]]

• 由於這個例子中的y是0或者1
• 我計算了一下sum(y_test)是89
• 由於1表示良性，所以這個混淆矩陣實際是表示這樣的

• 其中正樣本是得病的！
• 負樣本是沒有得病的！