knn的练习题---小麦种类预测

读取seeds.tsv文件（文件已经上转到本博客下载中心，可免费下载），
最后一列是小麦品种，其他列是小麦特征

导包

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

数据获取

seeds = pd.read_csv('./seeds.tsv',sep='\t',header=None)

data = seeds.iloc[:,:-1]
data = np.array(data)

target = seeds.iloc[:,-1:]

训练数据

# 数据切分
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(data,target,test_size=0.1)

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
knn.fit(X_train,y_train)

预测数据，并查看得分

y_ = knn.predict(X_test)
knn.score(X_test,y_test)

画交叉表

pd.crosstab(index=y_,columns=y_test.values.reshape(1,-1)[0], rownames=['预测'], colnames=['真实'], margins=True)