Classification

kNN1

 # -*- coding: utf-8 -*-
 """
 kNN : 최근접 이웃
 """

 import numpy as np # 다차원배열, 선형대수 연산
 import matplotlib.pyplot as plt

 # 1. 알려진 두 집단 x,y 산점도 시각화
 plt.scatter(1.2, 1.1) # A 집단
 plt.scatter(1.0, 1.0)
 plt.scatter(1.8, 0.8) # B 집단
 plt.scatter(2, 0.9)

 plt.scatter(1.6, 0.85, color='r') # 분류대상(알려지지 않은 집단)
 plt.show()

 # 2. DATA 생성과 함수 정의
 p1 = [1.2, 1.1] # A 집단
 p2 = [1.0, 1.0]
 p3 = [1.8, 0.8] # B 집단
 p4 = [2, 0.9]
 category = ['A','A','B','B'] # 알려진 집단 분류범주(Y변수)
 p5 = [1.6, 0.85] # 분류대상 

 # data 생성 함수 정의
 def data_set():
     # 선형대수 연산 : numpy형 변환
     know_group = np.array([p1, p2, p3, p4]) # 알려진 집단
     not_know_group = np.array(p5) # 알려지지 않은 집단
     class_category = np.array(category) # 정답(분류범주)
     return know_group,not_know_group,class_category 

 know_group,not_know_group,class_category=data_set()
 print('알려진 집단')
 """
 [[1.2 1.1]
  [1.  1. ]
  [1.8 0.8]
  [2.  0.9]]
 """
 print(know_group)
 print('알려지지 않은 집단')
 print(not_know_group) #[1.6  0.85]

 print('정답')
 print(class_category) #['A' 'A' 'B' 'B']

 #
 #차(-) -> 자곱(**) -> 합(sum) -> 제곱근(sqrt)

 diff=know_group-not_know_group #2차원 -1차원
 print('차=\n',diff)
 """
 차=
  [[-0.4   0.25]
  [-0.6   0.15]
  [ 0.2  -0.05]
  [ 0.4   0.05]]
 """

 sq_diff = diff ** 2
 sq_sum = sq_diff.sum(axis=1) #행단위 합계
 print(sq_sum) #[0.2225 0.3825 0.0425 0.1625]
 distance=np.sqrt(sq_sum)
 print(distance) #[0.47169906 0.61846584 0.20615528 0.40311289]
 #[3 4 1 2]거리  k=3 (B(2)>A(1))
 print(class_category)#['A' 'A' 'B' 'B']

 def classfy(know,not_know,cate,k):
     #유클리드인 거리계산식
     diff=know-not_know
     sq_diff = diff ** 2
     sq_sum = sq_diff.sum(axis=1)
     distance=np.sqrt(sq_sum)

     #2.가장 가까운 거리 오름차순 정렬 -> index
     sortDist=distance.argsort() #sort->index
     #print(sortDist) #[2 3 0 1]

     #3.최근접 이윳
     class_result={} #빈 set
     for i in range(k):#0~2
         key = cate[sortDist[i]] #i=0 -> 'B'
         class_result[key]=class_result.get(key,0)+1
     return class_result

 #함수 호출
 class_result=classfy(know_group,not_know_group,class_category,3)
 print(class_result) #{'B': 2, 'A': 1}

 #vot 함수
 def class_vote(class_result):
     return max(class_result,key=class_result.get)

 vote_result=class_vote(class_result)
 print("분류결과=",vote_result)#분류결과= B

kNN Class

 # -*- coding: utf-8 -*-
 """
 class 구현
 """

 import numpy as np
 from Step01_kNN import data_set

 know_group,not_know_group,class_category=data_set()

 #class =Func1+Func2+Func3
 class kNNclassify:   

     #1.최근접 이웃
     def classfy(self,know,not_know,cate,k):
         #유클리드인 거리계산식
         diff=know-not_know
         sq_diff = diff ** 2
         sq_sum = sq_diff.sum(axis=1)
         distance=np.sqrt(sq_sum)

         #2.가장 가까운 거리 오름차순 정렬 -> index
         sortDist=distance.argsort() #sort->index
         #print(sortDist) #[2 3 0 1]

         #3.최근접 이윳(k=3)
         self.class_result={} #빈 set
         for i in range(k):#0~2
             key = cate[sortDist[i]] #i=0 -> 'B'
             self.class_result[key]=self.class_result.get(key,0)+1

     #vot 함수
     def class_vote(self):
         return max(self.class_result,key=self.class_result.get)

 #class object 생성
 obj=kNNclassify() #생성자

 #objext.menber : self.class_result
 obj.classfy(know_group,not_know_group,class_category,3)

 vote_result=obj.class_vote()
 print('kNN 분류결과=',vote_result)#kNN 분류결과= B

NB

 # -*- coding: utf-8 -*-
 """
 통계적 분류기 - NB
 """
 import pandas as pd
 from sklearn import model_selection#train/test
 from sklearn.naive_bayes import GaussianNB 

 iris=pd.read_csv("../data/iris.csv")
 print(iris.head())
 """
    Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species
 0           5.1          3.5           1.4          0.2  setosa
 1           4.9          3.0           1.4          0.2  setosa
 2           4.7          3.2           1.3          0.2  setosa
 3           4.6          3.1           1.5          0.2  setosa
 4           5.0          3.6           1.4          0.2  setosa
 """

 #2. x,y 변수 선정
 cols=list(iris.columns)
 x_cols=cols[:4] #X:1~4(연속형)
 y_cols=cols[-1] #y:5(범주형)

 #3.train/test split
 iris_df=iris
 print(iris_df.shape)#(150, 5)
 train_iris,test_iris=model_selection.train_test_split(iris_df,test_size=0.3,random_state=123)
 print(train_iris.shape)#(105, 5)
 print(test_iris.shape)#(45, 5)

 #4. model생성 train set
 obj=GaussianNB() #object
 model=obj.fit(train_iris[x_cols],train_iris[y_cols])

 #5.model 평가
 pred=model.predict(test_iris[x_cols]) #Y예측
 Y = test_iris[y_cols] #정답

 #confusion matrix
 matrix=pd.crosstab(pred,Y)
 print(matrix)
 """
 Species     setosa  versicolor  virginica
 row_0
 setosa          18           0          0
 versicolor       0          10          2
 virginica        0           0         15
 """

 acc= (matrix.ix[0,0]+matrix.ix[1,1]+matrix.ix[2,2])/len(Y)
 print('분류정확도=',acc)#분류정확도= 0.9555555555555556

SVM

 # -*- coding: utf-8 -*-
 """
 SVM Model
 """
 import pandas as pd
 from sklearn import model_selection#train/test
 from sklearn import svm #model

 iris=pd.read_csv("../data/iris.csv")
 print(iris.head())
 """
    Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species
 0           5.1          3.5           1.4          0.2  setosa
 1           4.9          3.0           1.4          0.2  setosa
 2           4.7          3.2           1.3          0.2  setosa
 3           4.6          3.1           1.5          0.2  setosa
 4           5.0          3.6           1.4          0.2  setosa
 """

 #2. x,y 변수 선정
 cols=list(iris.columns)
 x_cols=cols[:4] #X:1~4(연속형)
 y_cols=cols[-1] #y:5(범주형)

 #3.train/test split
 iris_df=iris
 print(iris_df.shape)#(150, 5)
 train_iris,test_iris=model_selection.train_test_split(iris_df,test_size=0.3,random_state=123)
 print(train_iris.shape)#(105, 5)
 print(test_iris.shape)#(45, 5)

 #4.model -SVM
 obj=svm.SVC()
 model=obj.fit(train_iris[x_cols],train_iris[y_cols])

 #5.model 평가
 pred=model.predict(test_iris[x_cols])
 Y=test_iris[y_cols]

 #confusion matrix
 matrix=pd.crosstab(pred,Y)
 print(matrix)
 """
 Species     setosa  versicolor  virginica
 row_0
 setosa          18           0          0
 versicolor       0          10          1
 virginica        0           0         16
 """

 acc= (matrix.ix[0,0]+matrix.ix[1,1]+matrix.ix[2,2])/len(Y)
 print('분류정확도=',acc)#분류정확도= 0.9777777777777777

spam_train_test

 # -*- coding: utf-8 -*-
 """
 NB vs SWM
 -data set :sparse matrix 이용
 -file name:../data/spam_tran_test.npy
 """
 from sklearn.naive_bayes import GaussianNB
 from sklearn import svm
 import numpy as np
 import pandas as pd

 #1.file Loading
 X_train,X_test,y_train,y_test=np.load("../data/spam_tran_test.npy")
 print(X_train.shape) #(3901, 4000)
 print(X_test.shape) #(1673, 4000)
 print(type(y_train))#<class 'list'>

 #list -> numpy형변환: 선형대수 연산
 y_train=np.array(y_train)
 y_test=np.array(y_test)
 print(type(y_train))#<class 'numpy.ndarray'> 선형대수 하기위해서

 #2.NB model생성
 obj =GaussianNB()
 nb_model=obj.fit(X_train,y_train)

 pred=nb_model.predict(X_test)
 Y=y_test

 matrix=pd.crosstab(pred,Y)
 print("nb matrix\n",matrix)
 """
  col_0     0(ham)    1(spam)
 row_0
 0      1264   28
 1       167  214
 """
 acc=(matrix.ix[0,0]+matrix.ix[1,1])/len(Y)
 print("NB acc=",acc) #NB acc= 0.8834429169157203

 #2) 정확률:예측치 yes-> 실제값 yes
 precision=matrix.ix[1,1]/(matrix.ix[1,0]+matrix.ix[1,1])
 print("정확률=",precision)#정확률= 0.5616797900262467

 #3) 재현률:실제값yes -> 예측치 yes
 recall=matrix.ix[1,1]/(matrix.ix[0,1]+matrix.ix[1,1])
 print("재현률=",recall)#재현률= 0.8842975206611571

 #4) f1 score:precision,recall
 f1_score=2 * (precision*recall)/(precision+recall)
 print('f1_score=',f1_score)#f1_score= 0.6869983948635634

 #3.SVM model
 svm_obj =svm.SVC(kernel='linear')#kenel 함수
 svm_model=svm_obj.fit(X_train,y_train)

 svm_pred=svm_model.predict(X_test)
 svm_Y=y_test

 svm_matrix=pd.crosstab(svm_pred,svm_Y)
 print("svm matrix\n",svm_matrix)

 """
 svm matrix
  col_0     0    1
 row_0
 0      1428   36
 1         3  206
 """

 svm_acc=(svm_matrix.ix[0,0]+svm_matrix.ix[1,1])/len(svm_Y)
 print("svm acc=",svm_acc) #svm acc= 0.976688583383144

sms_spam_data

 # -*- coding: utf-8 -*-
 """
 Created on Sat Feb 23 15:52:23 2019

 @author: 502-03
 """

 from sklearn.naive_bayes import GaussianNB
 from sklearn import svm
 import numpy as np
 import pandas as pd

 #1.file Loading
 X_train,X_test,y_train,y_test=np.load("../data/sms_spam_data.npy")
 print(X_train.shape) #(4446, 6000)
 print(X_test.shape) #(1112, 6000)
 print(type(y_train))#<class 'pandas.core.series.Series'>

 #NB model 생성
 obj=GaussianNB()
 nb_model=obj.fit(X_train,y_train)
 nb_pred=nb_model.predict(X_test)
 nb_Y=y_test

 nb_tab=pd.crosstab(nb_pred,nb_Y)
 print("nb_tab=\n",nb_tab)
 """
 nb_tab=
  type   ham  spam
 row_0
 ham    812    10
 spam   156   134
 """
 nb_acc=(nb_tab.ix[0,0]+nb_tab.ix[1,1])/len(nb_Y)
 print("nb_acc=",nb_acc) #nb_acc= 0.8507194244604317

 #svm
 obj=svm.SVC(kernel='linear')
 svc_model=obj.fit(X_train,y_train)
 svc_pred=svc_model.predict(X_test)
 svc_Y=y_test

 svc_tab=pd.crosstab(svc_pred,svc_Y)
 print("svc_tab=\n",svc_tab)
 """
 svc_tab=
  type   ham  spam
 row_0
 ham    964    20
 spam     4   124
 """
 svc_acc=(svc_tab.ix[0,0]+svc_tab.ix[1,1])/len(svc_Y)
 print("svc_acc=",svc_acc) #svc_acc= 0.9784172661870504

 precision=svc_tab.ix[1,1]/(svc_tab.ix[1,0]+svc_tab.ix[1,1])
 print("정확률",precision)#정확률 0.96875

 recall=svc_tab.ix[1,1]/(svc_tab.ix[0,1]+svc_tab.ix[1,1])
 print("재현률",recall)#재현률 0.8611111111111112

 f1_score=2* (precision * recall)/(precision + recall)
 print("f1_score",f1_score)#f1_score 0.911764705882353