#!/usr/bin/env python
# coding: utf-8

# # k-means

# ## 1. k-means 란?

# - 참고: http://shabal.in/visuals/kmeans/2.html

# ## 2. scikit-learn을 활용한 k-means 수행

# - iris_data 사용
# - scikit-learn의 KMeans를 활용한 iris 전체 데이터에 대한 클러스터링
# - 각 인스턴스의 특징값만으로 클러스터링을 수행하여 그 결과를 kmeans.labels\_ 에 클러스터링 인덱스를 ndarray 자료구조를 사용하여 표현함 

# In[11]:


import numpy as np
import matplotlib.pyplot as plt
import random
from sklearn.cluster import KMeans
from sklearn import datasets

iris = datasets.load_iris()
feature_names = ('sepal length', 'sepal width', 'petal length', 'petal width')
num_feature = len(feature_names)

kmeans = KMeans(n_clusters=3)
kmeans.fit(iris.data)
print kmeans.labels_
print
print iris.target


# ## 3. 정확도 (Accuracy) 분석

# - 실제 타겟 그룹 인덱스와 Kmeans에 의해 클러스터링된 그룹 인덱스에 차이가 발생하므로 두 인덱스 사이의 Match 관계를 만들어줌

# In[12]:


import math
import operator

def euclideanDistance(instance1, instance2):
    distance = 0
    for x in range(num_feature):
        distance += pow((instance1[x] - instance2[x]), 2)
    return math.sqrt(distance)

def getGroupMatch(group1, group2):
    numGroupsOfGroups1 = len(np.unique(group1))
    numGroupsOfGroups2 = len(np.unique(group2))
    group1_dict = {}
    group2_dict = {}
    for i in range(numGroupsOfGroups1):
        group1_dict[i] = []
    for i in range(numGroupsOfGroups2):
        group2_dict[i] = []    

    index = 0
    for i in group1:
        group1_dict[i].append(index)
        index += 1

    index = 0
    for i in group2:
        group2_dict[i].append(index)
        index += 1

    group_match = {} ## actual_group_index : kmeans_group_index
    for i in range(len(group1_dict)):
        distance_set = []
        for j in range(len(group2_dict)):
            distance_set.append((j, euclideanDistance(group1_dict[i], group2_dict[j])))
        distance_set.sort(key = operator.itemgetter(1))
        group_match[i] = distance_set[0][0]

    return group1_dict, group2_dict, group_match

group1_dict, group2_dict, group_match = getGroupMatch(kmeans.labels_, iris.target)
print group1_dict
print
print group2_dict
print
print group_match


# In[13]:


def getAccuracy(group1, group2, numData):
    group1_dict, group2_dict, group_match = getGroupMatch(group1, group2)
    correct = 0.0
    for i in range(len(group1_dict)):
        for index in group1_dict[i]:
            if index in group2_dict[group_match[i]]:
                correct += 1.0
    return correct / float(numData) * 100.0

accuacy = getAccuracy(kmeans.labels_, iris.target, len(iris.data))
print('Accuracy: ' + str(accuacy) + '%')


# ## 4. 훈련 데이터를 통한 학습과 테스트 데이터의 분류 검증

# - 훈련 데이터와 테스트 데이터의 분리

# In[14]:


iris = datasets.load_iris()
split = 0.66
iris_names = ('Iris-setosa', 'Iris-versicolor', 'Iris-virginica')

def splitDataset(split, training_feature_set=[], training_target_set=[], test_feature_set=[], test_target_set=[]):
    for i in range(len(iris.data)):
        if random.random() < split:
            training_feature_set.append(iris.data[i])
            training_target_set.append(iris.target[i])
        else:
            test_feature_set.append(iris.data[i])
            test_target_set.append(iris.target[i])
    return training_feature_set, training_target_set, test_feature_set, test_target_set


training_feature_set, training_target_set, test_feature_set, test_target_set = splitDataset(split)
print 'Train: ' + str(len(training_feature_set))
print 'Test: ' + str(len(test_feature_set))
print
print training_feature_set
print training_target_set
print
print test_feature_set
print test_target_set


# - 훈련 데이터만 kmeans에 넣어 분류
# - 테스트 데이터를 kmeans.predict()에 넣어 kmeans_target_set 얻음
# - kmeans_target_set과 test_target_set과의 정확도 산출

# In[19]:


from sklearn.cluster import KMeans

kmeans = KMeans(n_clusters=3)
kmeans.fit(training_feature_set)
kmeans_target_set = kmeans.predict(test_feature_set).tolist()
print kmeans_target_set
print
print test_target_set
print

accuracy = getAccuracy(kmeans_target_set, test_target_set, len(test_target_set))
print('Accuracy: ' + str(accuracy) + '%')


# - 전체 코드

# In[20]:


import numpy as np
import matplotlib.pyplot as plt
import random
from sklearn.cluster import KMeans
from sklearn import datasets

iris = datasets.load_iris()
split = 0.66
iris_names = ('Iris-setosa', 'Iris-versicolor', 'Iris-virginica')
feature_names = ('sepal length', 'sepal width', 'petal length', 'petal width')
num_feature = len(feature_names)

def splitDataset(split, training_feature_set=[], training_target_set=[], test_feature_set=[], test_target_set=[]):
    for i in range(len(iris.data)):
        if random.random() < split:
            training_feature_set.append(iris.data[i])
            training_target_set.append(iris.target[i])
        else:
            test_feature_set.append(iris.data[i])
            test_target_set.append(iris.target[i])
    return training_feature_set, training_target_set, test_feature_set, test_target_set

if __name__ == '__main__':
    num_trials = 3
    accuracy_sum = 0.0

    for i in range(num_trials):
        training_feature_set, training_target_set, test_feature_set, test_target_set = splitDataset(split)
        kmeans = KMeans(n_clusters=3)
        kmeans.fit(training_feature_set)
        kmeans_target_set = kmeans.predict(test_feature_set).tolist()

        accuracy = getAccuracy(kmeans_target_set, test_target_set, len(test_target_set))
        accuracy_sum += accuracy
        
    print('Mean Accuracy: ' + str(accuracy_sum / float(num_trials)) + '%')


# ## 5. Refererence

# - http://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html