From ac4cac38b91706008d73be5c99831eb1a8450f15 Mon Sep 17 00:00:00 2001
From: QY-Wu <61172812+QY-Wu@users.noreply.github.com>
Date: Mon, 18 May 2020 11:28:24 +0800
Subject: [PATCH] exercise_1 WQY

you can find the exercise_1 in cancer.py
---
 cancer.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 cancer.py

diff --git a/cancer.py b/cancer.py
new file mode 100644
index 0000000..9f63069
--- /dev/null
+++ b/cancer.py
@@ -0,0 +1,30 @@
+from sklearn import datasets
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import f1_score as f1
+from sklearn.metrics import recall_score as recall
+from sklearn.metrics import confusion_matrix as cm
+
+'''导入数据'''
+X,y = datasets.load_breast_cancer(return_X_y=True)
+
+'''分割训练集与验证集'''
+X_train,X_test,y_train,y_test = train_test_split(X,y,train_size=0.7,test_size=0.3)
+
+'''初始化逻辑回归分类器，这里对类别不平衡问题做了处理'''
+cl = LogisticRegression(class_weight='balanced')
+
+'''利用训练数据进行逻辑回归分类器的训练'''
+cl = cl.fit(X_train,y_train)
+
+'''打印训练的模型在验证集上的正确率'''
+print('逻辑回归的测试准确率：'+str(cl.score(X_test,y_test))+'\n')
+
+'''打印f1得分'''
+print('F1得分：'+str(f1(y_test,cl.predict(X_test)))+'\n')
+
+'''打印召回得分'''
+print('召回得分（越接近1越好）：'+str(recall(y_test,cl.predict(X_test)))+'\n')
+
+'''打印混淆矩阵'''
+print('混淆矩阵：'+'\n'+str(cm(y_test,cl.predict(X_test)))+'\n')
\ No newline at end of file