import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
plt.rcParams['font.sans-serif']=['SimHei'] #用來(lái)正常顯示中文標(biāo)簽
#準(zhǔn)備數(shù)據(jù)集
iris=datasets.load_iris()
X=iris.data
print('X:\n',X)
Y=iris.target
print('Y:\n',Y)
 
#處理二分類(lèi)問(wèn)題，所以只針對(duì)Y=0,1的行，然后從這些行中取X的前兩列
x=X[Y<2,:2]
print(x.shape)
print('x:\n',x)
y=Y[Y<2]
print('y:\n',y)
#target=0的點(diǎn)標(biāo)紅，target=1的點(diǎn)標(biāo)藍(lán),點(diǎn)的橫坐標(biāo)為data的第一列，點(diǎn)的縱坐標(biāo)為data的第二列
plt.scatter(x[y==0,0],x[y==0,1],color='red')
plt.scatter(x[y==1,0],x[y==1,1],color='green')
plt.scatter(5.6,3.2,color='blue')
x_1=np.array([5.6,3.2])
plt.title('紅色點(diǎn)標(biāo)簽為0,綠色點(diǎn)標(biāo)簽為1，待預(yù)測(cè)的點(diǎn)為藍(lán)色')

#采用歐式距離計(jì)算
distances=[np.sqrt(np.sum((x_t-x_1)**2)) for x_t in x]
#對(duì)數(shù)組進(jìn)行排序，返回的是排序后的索引
d=np.sort(distances)
nearest=np.argsort(distances)
k=6
topk_y=[y[i] for i in nearest[:k]]
from collections import Counter
#對(duì)topk_y進(jìn)行統(tǒng)計(jì)返回字典
votes=Counter(topk_y)
#返回票數(shù)最多的1類(lèi)元素
print(votes)
predict_y=votes.most_common(1)[0][0]
print(predict_y)
plt.show()

Counter({1: 4, 0: 2})
1

import numpy as np
from collections import Counter
from metrics import accuracy_score
class KNNClassifier:
 def __init__(self,k):
 assert k>=1,'k must be valid'
 self.k=k
 self._x_train=None
 self._y_train=None
 
 def fit(self,x_train,y_train):
 self._x_train=x_train
 self._y_train=y_train
 return self
 
 def _predict(self,x):
 d=[np.sqrt(np.sum((x_i-x)**2)) for x_i in self._x_train]
 nearest=np.argsort(d)
 top_k=[self._y_train[i] for i in nearest[:self.k]]
 votes=Counter(top_k)
 return votes.most_common(1)[0][0]
 
 def predict(self,X_predict):
 y_predict=[self._predict(x1) for x1 in X_predict]
 return np.array(y_predict)
 
 def __repr__(self):
 return 'knn(k=%d):'%self.k
 
 def score(self,x_test,y_test):
 y_predict=self.predict(x_test)
 return sum(y_predict==y_test)/len(x_test)

import numpy as np
def train_test_split(x,y,test_ratio=0.2,seed=None):
 if seed:
 np.random.seed(seed)
 #生成樣本隨機(jī)的序號(hào)
 shuffed_indexes=np.random.permutation(len(x))
 print(shuffed_indexes)
 #測(cè)試集占樣本總數(shù)的20%
 test_size=int(test_ratio*len(x))
 test_indexes=shuffed_indexes[:test_size]
 train_indexes=shuffed_indexes[test_size:]
 x_test=x[test_indexes]
 y_test=y[test_indexes]
 x_train=x[train_indexes]
 y_train=y[train_indexes]
 return x_train,x_test,y_train,y_test
 
'''
sklearn中的train_test_split
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=tran_test_split(x,y,test_size=0.2,random_state=666)
'''

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
iris=datasets.load_iris()
x=iris.data
y=iris.target
 
#sklearn自帶的train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y)
knn_classifier=KNeighborsClassifier(6)
knn_classifier.fit(x_train,y_train)
y_predict=knn_classifier.predict(x_test)
scores=knn_classifier.score(x_test,y_test)
print('acc:{}'.format(sum(y_predict==y_test)/len(x_test)),scores)
 
 
#采用我們自己寫(xiě)的
from model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(x,y)
from KNN import KNNClassifier
from metrics import accuracy_score
my_knn=KNNClassifier(k=6)
my_knn.fit(X_train,y_train)
y_predict=my_knn.predict(X_test)
print(accuracy_score(y_test,y_predict))
score=my_knn.score(X_test,y_test)
print(score)

def main():
 from sklearn import datasets
 digits=datasets.load_digits()
 x=digits.data
 y=digits.target
 from sklearn.model_selection import train_test_split
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
 from sklearn.neighbors import KNeighborsClassifier
 # 尋找最好的k
 best_k=-1
 best_score=0
 for i in range(1,11):
 knn_clf=KNeighborsClassifier(n_neighbors=i)
 knn_clf.fit(x_train,y_train)
 scores=knn_clf.score(x_test,y_test)
 if scores>best_score:
  best_score=scores
  best_k=i
 print('最好的k為:%d,最好的得分為:%.4f'%(best_k,best_score))
if __name__ == '__main__':
 main()

def main():
 from sklearn import datasets
 digits=datasets.load_digits()
 x=digits.data
 y=digits.target
 from sklearn.model_selection import train_test_split
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
 from sklearn.neighbors import KNeighborsClassifier
 # 尋找最好的k,weights
 best_k=-1
 best_score=0
 best_method=''
 for method in ['uniform','distance']:
 for i in range(1,11):
  knn_clf=KNeighborsClassifier(n_neighbors=i,weights=method)
  knn_clf.fit(x_train,y_train)
  scores=knn_clf.score(x_test,y_test)
  if scores>best_score:
  best_score=scores
  best_k=i
  best_method=method
 print('最好的k為:%d,最好的得分為:%.4f,最好的方法%s'%(best_k,best_score,best_method))
if __name__ == '__main__':
 main()

def main():
 from sklearn import datasets
 digits=datasets.load_digits()
 x=digits.data
 y=digits.target
 from sklearn.model_selection import train_test_split
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
 from sklearn.neighbors import KNeighborsClassifier
 # 尋找最好的k,weights
 best_k=-1
 best_score=0
 best_p=-1
 
 for i in range(1,11):
 for p in range(1,6):
  knn_clf=KNeighborsClassifier(n_neighbors=i,weights='distance',p=p)
  knn_clf.fit(x_train,y_train)
  scores=knn_clf.score(x_test,y_test)
  if scores>best_score:
  best_score=scores
  best_k=i
  best_p=p
 print('最好的k為:%d,最好的得分為:%.4f,最好的p為%d'%(best_k,best_score,best_p))
if __name__ == '__main__':
 main()

param_grid = [
 {'C': [1, 10, 100, 1000], 'kernel': ['linear']},
 {'C': [1, 10, 100, 1000], 'gamma': [0.001, 0.0001], 'kernel': ['rbf']},
 ]

def main():
 import numpy as np
 from sklearn import datasets
 digits=datasets.load_digits()
 x=digits.data
 y=digits.target
 from sklearn.model_selection import train_test_split
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
 from sklearn.neighbors import KNeighborsClassifier
 
 #Grid Search定義要搜索的參數(shù)
 param_grid=[
 {
  'weights':['uniform'],
  'n_neighbors':[i for i in range(1,11)]
 },
 {
  'weights':['distance'],
  'n_neighbors':[i for i in range(1,11)],
  'p':[i for i in range(1,6)]
 }
 ]
 knn_clf=KNeighborsClassifier()
 from sklearn.model_selection import GridSearchCV
 #n_jobs采用幾個(gè)核來(lái)處理，-1代表計(jì)算機(jī)有幾個(gè)核就用幾個(gè)核進(jìn)行并行處理,搜索過(guò)程中verbose可以進(jìn)行信息輸出，幫助理解搜索狀態(tài)
 grid_search=GridSearchCV(knn_clf,param_grid,n_jobs=-1,verbose=1)
 grid_search.fit(x_train,y_train)
 #返回網(wǎng)格搜索最佳分類(lèi)器
 print(grid_search.best_estimator_)
 #返回網(wǎng)格搜索最佳分類(lèi)器的參數(shù)
 print(grid_search.best_params_)
 #返回網(wǎng)格搜索最佳分類(lèi)器的分?jǐn)?shù)
 print(grid_search.best_score_)
 knn_clf=grid_search.best_estimator_
 print(knn_clf.score(x_test,y_test))
if __name__ == '__main__':
 main()
Fitting 3 folds for each of 60（10+50） candidates, totalling 180 fits
[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 1.6s
[Parallel(n_jobs=-1)]: Done 180 out of 180 | elapsed: 30.6s finished
KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
  metric_params=None, n_jobs=1, n_neighbors=3, p=3,
  weights='distance')
{'n_neighbors': 3, 'weights': 'distance', 'p': 3}
0.985386221294
0.983333333333

import numpy as np
import matplotlib.pyplot as plt
#最值歸一化
x=np.random.randint(0,100,size=100)
print(x)
normal_x=(x-np.min(x))/(np.max(x)-np.min(x))
print(normal_x)
#均值方差歸一化
x2=np.random.randint(0,100,(50,2))
print(x2)
x2=np.array(x2,dtype=float)
x2[:,0]=(x2[:,0]-np.mean(x2[:,0]))/np.std(x2[:,0])
x2[:,1]=(x2[:,1]-np.mean(x2[:,1]))/np.std(x2[:,1])
plt.scatter(x2[:,0],x2[:,1])
plt.show()

x:[49 27 88 47 6 89 9 98 17 72 46 46 80 62 28 38 0 27 22 14 2 79 70 73 15
 57 85 6 11 76 59 62 23 32 82 78 0 45 8 82 13 81 99 61 43 21 45 61 93 63
 66 57 78 60 50 8 29 63 74 8 25 55 10 69 3 77 41 24 15 23 21 31 36 78 94
 52 12 1 23 99 8 12 15 37 75 75 27 14 31 75 6 56 29 96 23 0 22 98 86 10]
normal_x:[ 0.49494949 0.27272727 0.88888889 0.47474747 0.06060606 0.8989899
 0.09090909 0.98989899 0.17171717 0.72727273 0.46464646 0.46464646
 0.80808081 0.62626263 0.28282828 0.38383838 0.  0.27272727
 0.22222222 0.14141414 0.02020202 0.7979798 0.70707071 0.73737374
 0.15151515 0.57575758 0.85858586 0.06060606 0.11111111 0.76767677
 0.5959596 0.62626263 0.23232323 0.32323232 0.82828283 0.78787879
 0.  0.45454545 0.08080808 0.82828283 0.13131313 0.81818182
 1.  0.61616162 0.43434343 0.21212121 0.45454545 0.61616162
 0.93939394 0.63636364 0.66666667 0.57575758 0.78787879 0.60606061
 0.50505051 0.08080808 0.29292929 0.63636364 0.74747475 0.08080808
 0.25252525 0.55555556 0.1010101 0.6969697 0.03030303 0.77777778
 0.41414141 0.24242424 0.15151515 0.23232323 0.21212121 0.31313131
 0.36363636 0.78787879 0.94949495 0.52525253 0.12121212 0.01010101
 0.23232323 1.  0.08080808 0.12121212 0.15151515 0.37373737
 0.75757576 0.75757576 0.27272727 0.14141414 0.31313131 0.75757576
 0.06060606 0.56565657 0.29292929 0.96969697 0.23232323 0.
 0.22222222 0.98989899 0.86868687 0.1010101 ]

sklearn中的StandardScaler
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=666)
#sklearn中的StandardScaler
from sklearn.preprocessing import StandardScaler
standardscaler=StandardScaler()
standardscaler.fit(x_train)
#均值
print(standardscaler.mean_)
#方差
print(standardscaler.scale_)
x_train_standard=standardscaler.transform(x_train)
x_test_standard=standardscaler.transform(x_test)
print(x_train_standard)
from sklearn.neighbors import KNeighborsClassifier
knn_clf=KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(x_train_standard,y_train)
scores=knn_clf.score(x_test_standard,y_test)
print(scores)