1 # -*- coding: utf-8 -*-
 2 """
 3 kNN : ??? ?? 
 4 """
 5 
 6 import numpy as np # ?????, ???? ?? 
 7 import matplotlib.pyplot as plt
 8 
 9 # 1. ??? ? ?? x,y ??? ??? 
10 plt.scatter(1.2, 1.1) # A ??
11 plt.scatter(1.0, 1.0)
12 plt.scatter(1.8, 0.8) # B ?? 
13 plt.scatter(2, 0.9)
14 
15 plt.scatter(1.6, 0.85, color=‘r‘) # ????(???? ?? ??) 
16 plt.show()
17 
18 # 2. DATA ??? ?? ?? 
19 p1 = [1.2, 1.1] # A ?? 
20 p2 = [1.0, 1.0]
21 p3 = [1.8, 0.8] # B ??
22 p4 = [2, 0.9]
23 category = [‘A‘,‘A‘,‘B‘,‘B‘] # ??? ?? ????(Y??)
24 p5 = [1.6, 0.85] # ???? 
25 
26 # data ?? ?? ??
27 def data_set():
28     # ???? ?? : numpy? ?? 
29     know_group = np.array([p1, p2, p3, p4]) # ??? ?? 
30     not_know_group = np.array(p5) # ???? ?? ??
31     class_category = np.array(category) # ??(????)
32     return know_group,not_know_group,class_category 
33 
34 know_group,not_know_group,class_category=data_set()
35 print(‘??? ??‘)
36 """
37 [[1.2 1.1]
38  [1.  1. ]
39  [1.8 0.8]
40  [2.  0.9]]
41 """
42 print(know_group)
43 print(‘???? ?? ??‘)
44 print(not_know_group) #[1.6  0.85]
45 
46 print(‘??‘)
47 print(class_category) #[‘A‘ ‘A‘ ‘B‘ ‘B‘]
48 
49 #
50 #?(-) -> ??(**) -> ?(sum) -> ???(sqrt)
51 
52 diff=know_group-not_know_group #2?? -1??
53 print(‘?=\n‘,diff)
54 """
55 ?=
56  [[-0.4   0.25]
57  [-0.6   0.15]
58  [ 0.2  -0.05]
59  [ 0.4   0.05]]
60 """
61 
62 sq_diff = diff ** 2
63 sq_sum = sq_diff.sum(axis=1) #??? ??
64 print(sq_sum) #[0.2225 0.3825 0.0425 0.1625]
65 distance=np.sqrt(sq_sum)
66 print(distance) #[0.47169906 0.61846584 0.20615528 0.40311289]
67 #[3 4 1 2]??  k=3 (B(2)>A(1))
68 print(class_category)#[‘A‘ ‘A‘ ‘B‘ ‘B‘]
69 
70 def classfy(know,not_know,cate,k):
71     #????? ?????
72     diff=know-not_know
73     sq_diff = diff ** 2
74     sq_sum = sq_diff.sum(axis=1)
75     distance=np.sqrt(sq_sum)
76     
77     #2.?? ??? ?? ???? ?? -> index
78     sortDist=distance.argsort() #sort->index
79     #print(sortDist) #[2 3 0 1]
80     
81     #3.??? ??
82     class_result={} #? set
83     for i in range(k):#0~2
84         key = cate[sortDist[i]] #i=0 -> ‘B‘
85         class_result[key]=class_result.get(key,0)+1
86     return class_result
87         
88     
89 #?? ??
90 class_result=classfy(know_group,not_know_group,class_category,3)    
91 print(class_result) #{‘B‘: 2, ‘A‘: 1}
92 
93 #vot ??
94 def class_vote(class_result):
95     return max(class_result,key=class_result.get)
96 
97 vote_result=class_vote(class_result)
98 print("????=",vote_result)#????= B

 1 # -*- coding: utf-8 -*-
 2 """
 3 class ?? 
 4 """
 5 
 6 import numpy as np
 7 from Step01_kNN import data_set
 8 
 9 
10 know_group,not_know_group,class_category=data_set()
11 
12 #class =Func1+Func2+Func3
13 class kNNclassify:   
14     
15     #1.??? ??
16     def classfy(self,know,not_know,cate,k):
17         #????? ?????
18         diff=know-not_know
19         sq_diff = diff ** 2
20         sq_sum = sq_diff.sum(axis=1)
21         distance=np.sqrt(sq_sum)
22         
23         #2.?? ??? ?? ???? ?? -> index
24         sortDist=distance.argsort() #sort->index
25         #print(sortDist) #[2 3 0 1]
26         
27         #3.??? ??(k=3)
28         self.class_result={} #? set
29         for i in range(k):#0~2
30             key = cate[sortDist[i]] #i=0 -> ‘B‘
31             self.class_result[key]=self.class_result.get(key,0)+1
32             
33     #vot ??
34     def class_vote(self):
35         return max(self.class_result,key=self.class_result.get)
36 
37 #class object ??
38 obj=kNNclassify() #???
39         
40 #objext.menber : self.class_result
41 obj.classfy(know_group,not_know_group,class_category,3)
42 
43 vote_result=obj.class_vote()
44 print(‘kNN ????=‘,vote_result)#kNN ????= B

 1 # -*- coding: utf-8 -*-
 2 """
 3 ??? ??? - NB
 4 """
 5 import pandas as pd
 6 from sklearn import model_selection#train/test
 7 from sklearn.naive_bayes import GaussianNB 
 8 
 9 iris=pd.read_csv("../data/iris.csv")
10 print(iris.head())
11 """
12    Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species
13 0           5.1          3.5           1.4          0.2  setosa
14 1           4.9          3.0           1.4          0.2  setosa
15 2           4.7          3.2           1.3          0.2  setosa
16 3           4.6          3.1           1.5          0.2  setosa
17 4           5.0          3.6           1.4          0.2  setosa
18 """
19 
20 #2. x,y ?? ??
21 cols=list(iris.columns)
22 x_cols=cols[:4] #X:1~4(???)
23 y_cols=cols[-1] #y:5(???)
24 
25 #3.train/test split
26 iris_df=iris
27 print(iris_df.shape)#(150, 5)
28 train_iris,test_iris=model_selection.train_test_split(iris_df,test_size=0.3,random_state=123)
29 print(train_iris.shape)#(105, 5)
30 print(test_iris.shape)#(45, 5)
31 
32 #4. model?? train set
33 obj=GaussianNB() #object 
34 model=obj.fit(train_iris[x_cols],train_iris[y_cols])
35 
36 #5.model ?? 
37 pred=model.predict(test_iris[x_cols]) #Y??
38 Y = test_iris[y_cols] #??
39 
40 #confusion matrix
41 matrix=pd.crosstab(pred,Y)
42 print(matrix)
43 """
44 Species     setosa  versicolor  virginica
45 row_0                                    
46 setosa          18           0          0
47 versicolor       0          10          2
48 virginica        0           0         15
49 """
50 
51 acc= (matrix.ix[0,0]+matrix.ix[1,1]+matrix.ix[2,2])/len(Y)
52 print(‘?????=‘,acc)#?????= 0.9555555555555556

 1 # -*- coding: utf-8 -*-
 2 """
 3 SVM Model
 4 """
 5 import pandas as pd
 6 from sklearn import model_selection#train/test
 7 from sklearn import svm #model
 8 
 9 iris=pd.read_csv("../data/iris.csv")
10 print(iris.head())
11 """
12    Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species
13 0           5.1          3.5           1.4          0.2  setosa
14 1           4.9          3.0           1.4          0.2  setosa
15 2           4.7          3.2           1.3          0.2  setosa
16 3           4.6          3.1           1.5          0.2  setosa
17 4           5.0          3.6           1.4          0.2  setosa
18 """
19 
20 #2. x,y ?? ??
21 cols=list(iris.columns)
22 x_cols=cols[:4] #X:1~4(???)
23 y_cols=cols[-1] #y:5(???)
24 
25 #3.train/test split
26 iris_df=iris
27 print(iris_df.shape)#(150, 5)
28 train_iris,test_iris=model_selection.train_test_split(iris_df,test_size=0.3,random_state=123)
29 print(train_iris.shape)#(105, 5)
30 print(test_iris.shape)#(45, 5)
31 
32 #4.model -SVM
33 obj=svm.SVC()
34 model=obj.fit(train_iris[x_cols],train_iris[y_cols])
35 
36 
37 #5.model ??
38 pred=model.predict(test_iris[x_cols])
39 Y=test_iris[y_cols]
40 
41 #confusion matrix
42 matrix=pd.crosstab(pred,Y)
43 print(matrix)
44 """
45 Species     setosa  versicolor  virginica
46 row_0                                    
47 setosa          18           0          0
48 versicolor       0          10          1
49 virginica        0           0         16
50 """
51 
52 acc= (matrix.ix[0,0]+matrix.ix[1,1]+matrix.ix[2,2])/len(Y)
53 print(‘?????=‘,acc)#?????= 0.9777777777777777

 1 # -*- coding: utf-8 -*-
 2 """
 3 NB vs SWM
 4 -data set :sparse matrix ??
 5 -file name:../data/spam_tran_test.npy
 6 """
 7 from sklearn.naive_bayes import GaussianNB
 8 from sklearn import svm
 9 import numpy as np
10 import pandas as pd
11 
12 #1.file Loading
13 X_train,X_test,y_train,y_test=np.load("../data/spam_tran_test.npy")
14 print(X_train.shape) #(3901, 4000)
15 print(X_test.shape) #(1673, 4000)
16 print(type(y_train))#<class ‘list‘>
17 print(len(y_train)) #3901
18 print(len(y_test)) #1673
19 
20 #list -> numpy???: ???? ?? 
21 y_train=np.array(y_train)
22 y_test=np.array(y_test)
23 print(type(y_train))#<class ‘numpy.ndarray‘> ???? ?????
24 
25 #2.NB model?? 
26 obj =GaussianNB()
27 nb_model=obj.fit(X_train,y_train)
28 
29 pred=nb_model.predict(X_test)
30 Y=y_test
31 
32 matrix=pd.crosstab(pred,Y)
33 print("nb matrix\n",matrix)
34 """
35  col_0     0(ham)    1(spam)
36 row_0           
37 0      1264   28
38 1       167  214
39 """
40 acc=(matrix.ix[0,0]+matrix.ix[1,1])/len(Y)
41 print("NB acc=",acc) #NB acc= 0.8834429169157203
42 
43 
44 #2) ???:??? yes-> ??? yes
45 precision=matrix.ix[1,1]/(matrix.ix[1,0]+matrix.ix[1,1])
46 print("???=",precision)#???= 0.5616797900262467
47 
48 #3) ???:???yes -> ??? yes
49 recall=matrix.ix[1,1]/(matrix.ix[0,1]+matrix.ix[1,1])
50 print("???=",recall)#???= 0.8842975206611571
51 
52 #4) f1 score:precision,recall
53 f1_score=2 * (precision*recall)/(precision+recall)
54 print(‘f1_score=‘,f1_score)#f1_score= 0.6869983948635634
55 
56 
57 #3.SVM model
58 svm_obj =svm.SVC(kernel=‘linear‘)#kenel ??
59 svm_model=svm_obj.fit(X_train,y_train)
60 
61 svm_pred=svm_model.predict(X_test)
62 svm_Y=y_test
63 
64 svm_matrix=pd.crosstab(svm_pred,svm_Y)
65 print("svm matrix\n",svm_matrix)
66 
67 """
68 svm matrix
69  col_0     0    1
70 row_0           
71 0      1428   36
72 1         3  206
73 """
74 
75 svm_acc=(svm_matrix.ix[0,0]+svm_matrix.ix[1,1])/len(svm_Y)
76 print("svm acc=",svm_acc) #svm acc= 0.976688583383144

 1 # -*- coding: utf-8 -*-
 2 """
 3 Created on Sat Feb 23 15:52:23 2019
 4 
 5 @author: 502-03
 6 """
 7 
 8 from sklearn.naive_bayes import GaussianNB
 9 from sklearn import svm
10 import numpy as np
11 import pandas as pd
12 
13 #1.file Loading
14 X_train,X_test,y_train,y_test=np.load("../data/sms_spam_data.npy")
15 print(X_train.shape) #(4446, 6000)
16 print(X_test.shape) #(1112, 6000)
17 print(type(y_train))#<class ‘pandas.core.series.Series‘>
18 print(len(y_train)) #4446
19 print(len(y_test)) #1112
20 
21 #NB model ??
22 obj=GaussianNB()
23 nb_model=obj.fit(X_train,y_train)
24 nb_pred=nb_model.predict(X_test)
25 nb_Y=y_test
26 
27 nb_tab=pd.crosstab(nb_pred,nb_Y)
28 print("nb_tab=\n",nb_tab)
29 """
30 nb_tab=
31  type   ham  spam
32 row_0           
33 ham    812    10
34 spam   156   134
35 """
36 nb_acc=(nb_tab.ix[0,0]+nb_tab.ix[1,1])/len(nb_Y)
37 print("nb_acc=",nb_acc) #nb_acc= 0.8507194244604317
38 
39 
40 
41 
42 #svm
43 obj=svm.SVC(kernel=‘linear‘)
44 svc_model=obj.fit(X_train,y_train)
45 svc_pred=svc_model.predict(X_test)
46 svc_Y=y_test
47 
48 svc_tab=pd.crosstab(svc_pred,svc_Y)
49 print("svc_tab=\n",svc_tab)
50 """
51 svc_tab=
52  type   ham  spam
53 row_0           
54 ham    964    20
55 spam     4   124
56 """
57 svc_acc=(svc_tab.ix[0,0]+svc_tab.ix[1,1])/len(svc_Y)
58 print("svc_acc=",svc_acc) #svc_acc= 0.9784172661870504
59 
60 precision=svc_tab.ix[1,1]/(svc_tab.ix[1,0]+svc_tab.ix[1,1])
61 print("???",precision)#??? 0.96875
62 
63 recall=svc_tab.ix[1,1]/(svc_tab.ix[0,1]+svc_tab.ix[1,1])
64 print("???",recall)#??? 0.8611111111111112
65 
66 f1_score=2* (precision * recall)/(precision + recall)
67 print("f1_score",f1_score)#f1_score 0.911764705882353