使用Python處理KNN分類算法的實現代碼

1.5 40 thin
1.5 50 fat
1.5 60 fat
1.6 40 thin
1.6 50 thin
1.6 60 fat
1.6 70 fat
1.7 50 thin
1.7 60 thin
1.7 70 fat
1.7 80 fat
1.8 60 thin
1.8 70 thin
1.8 80 fat
1.8 90 fat
1.9 80 thin
1.9 90 fat

import numpy as np
from sklearn import neighbors
from sklearn.metrics import precision_recall_curve
from sklearn.metrics import classification_report
from sklearn.cross_validation import train_test_split
import matplotlib.pyplot as plt
 
''' 數據讀入 '''
data = []
labels = []
with open("data\\1.txt") as ifile:
 for line in ifile:
  tokens = line.strip().split(' ')
  data.append([float(tk) for tk in tokens[:-1]])
  labels.append(tokens[-1])
x = np.array(data)
labels = np.array(labels)
y = np.zeros(labels.shape)
 
''' 標簽轉換為0/1 '''
y[labels=='fat']=1
 
''' 拆分訓練數據與測試數據 '''
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2)
 
''' 創建網格以方便繪制 '''
h = .01
x_min, x_max = x[:, 0].min() - 0.1, x[:, 0].max() + 0.1
y_min, y_max = x[:, 1].min() - 1, x[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
   np.arange(y_min, y_max, h))
 
''' 訓練KNN分類器 '''
clf = neighbors.KNeighborsClassifier(algorithm='kd_tree')
clf.fit(x_train, y_train)
 
'''測試結果的打印'''
answer = clf.predict(x)
print(x)
print(answer)
print(y)
print(np.mean( answer == y))
 
'''準確率與召回率'''
precision, recall, thresholds = precision_recall_curve(y_train, clf.predict(x_train))
answer = clf.predict_proba(x)[:,1]
print(classification_report(y, answer, target_names = ['thin', 'fat']))
 
''' 將整個測試空間的分類結果用不同顏色區分開'''
answer = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:,1]
z = answer.reshape(xx.shape)
plt.contourf(xx, yy, z, cmap=plt.cm.Paired, alpha=0.8)
 
''' 繪制訓練樣本 '''
plt.scatter(x_train[:, 0], x_train[:, 1], c=y_train, cmap=plt.cm.Paired)
plt.xlabel(u'身高')
plt.ylabel(u'體重')
plt.show()