Obsidian-Knowledge-Base/X-Knowledge-Base/raw/Joplin/_resources/cancer_demo.py

#!/usr/bin/env python
# coding: utf-8

# In[33]:


import pandas as pd
import numpy as np
import os
import urllib


# In[34]:


# 1、读取数据
data_url = "https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data"
if not os.path.exists("breast-cancer-wisconsin.data"):
    urllib.request.urlretrieve(data_url, "breast-cancer-wisconsin.data")
column_name = ['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("breast-cancer-wisconsin.data", names=column_name)


# In[35]:


data.head()


# In[36]:


# 2、缺失值处理
# 1）替换-》np.nan
data = data.replace(to_replace="?", value=np.nan)
# 2）删除缺失样本
data.dropna(inplace=True)


# In[37]:


data.isnull().any()  # 不存在缺失值


# In[38]:


# 3、划分数据集
from sklearn.model_selection import train_test_split


# In[39]:


data.head()


# In[40]:


# 筛选特征值和目标值
x = data.iloc[:, 1:-1]
y = data["Class"]


# In[41]:


x.head()


# In[42]:


y.head()


# In[43]:


x_train, x_test, y_train, y_test = train_test_split(x, y)


# In[44]:


x_train.head()


# In[45]:


# 4、标准化
from sklearn.preprocessing import StandardScaler


# In[46]:


transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)


# In[47]:


x_train


# In[48]:


from sklearn.linear_model import LogisticRegression


# In[49]:


# 5、预估器流程
estimator = LogisticRegression()
estimator.fit(x_train, y_train)


# In[50]:


# 逻辑回归的模型参数：回归系数和偏置
estimator.coef_


# In[51]:


estimator.intercept_


# In[52]:


# 6、模型评估
# 方法1：直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)

# 方法2：计算准确率
score = estimator.score(x_test, y_test)
print("准确率为：\n", score)


# In[53]:


# 查看精确率、召回率、F1-score
from sklearn.metrics import classification_report


# In[54]:


report = classification_report(y_test, y_predict, labels=[2, 4], target_names=["良性", "恶性"])


# In[55]:


print(report)


# In[56]:


y_test.head()


# In[57]:


# y_true：每个样本的真实类别，必须为0(反例),1(正例)标记
# 将y_test 转换成 0 1
y_true = np.where(y_test > 3, 1, 0)  # 3以上为恶性1(正例)，否则为良性0(反例)


# In[58]:


y_true


# In[59]:


from sklearn.metrics import roc_auc_score


# In[60]:


roc_auc_score(y_true, y_predict)