算法预测实例——癌细胞[正则化(x-min)/(max-min)]

导包

import pandas as pd
from pandas import Series,DataFrame

import numpy as np

from sklearn.neighbors import KNeighborsClassifier

数据集加载

# 将数据加载进来
cancer = pd.read_csv('../data/cancer.csv',sep ='\t')
# 细胞中微观的特征
cancer

确定特征数据和结果数据

data = cancer.iloc[:,2:]
target = cancer['Diagnosis']

划分训练数据和测试数据

from sklearn.model_selection import train_test_split

type(data)
Out：
pandas.core.frame.DataFrame

type(target)
Out：
pandas.core.series.Series

X_train,X_test,y_train,y_test = train_test_split(data,target,test_size = 69)

使用KNN算法

knn = KNeighborsClassifier(n_neighbors=5)

knn.fit(X_train,y_train)

knn.score(X_test,y_test)
Out：
0.9710144927536232

knn = KNeighborsClassifier(n_neighbors=3)

knn.fit(X_train,y_train)

knn.score(X_test,y_test)
Out：
0.9565217391304348

预测

y_ = knn.predict(X_test)
y_
Out： 
array(['M', 'B', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'M', 'B', 'B',
       'B', 'B', 'M', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'M', 'M',
       'M', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'B', 'B', 'M',
       'B', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'M',
       'M', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B',
       'B', 'B', 'B', 'B'], dtype=object)

y_test.values
Out：
array(['M', 'B', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'B', 'M', 'B', 'B',
       'B', 'B', 'M', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'M', 'M', 'M',
       'M', 'M', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'B', 'B', 'M',
       'B', 'B', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'B', 'M',
       'M', 'B', 'M', 'B', 'B', 'B', 'M', 'B', 'B', 'B', 'B', 'B', 'B',
       'B', 'B', 'B', 'B'], dtype=object)

pd.crosstab(y_,y_test,rownames=['预测'],colnames=['确诊'],margins=True)

 

正则化

# 将算法准确率提高
# 换一个算法
# 医院提供更多的样本
# 处理当前数据

 

# X_train,X_test
# 正则化---->归一化 0 ~ 1
cols = X_train.columns

for col in cols:
    v_min = X_train[col].min( )
    v_max = X_train[col].max()
    
    X_train[col] = (X_train[col] - v_min)/(v_max - v_min)

for col in cols:
    v_min = X_test[col].min( )
    v_max = X_test[col].max()
    
    X_test[col] = (X_test[col] - v_min)/(v_max - v_min)

使用KNN算法

knn = KNeighborsClassifier(n_neighbors=5)

knn.fit(X_train,y_train)

knn.score(X_test,y_test)
Out：
0.9565217391304348

# 70%时间花在了处理数据
# 30个特征，对于结果，不一样
knn = KNeighborsClassifier(n_neighbors=5)

knn.fit(X_train.iloc[:,10:],y_train)

knn.score(X_test.iloc[:,10:],y_test)
Out： 0.9710144927536232