[优达 机器学习入门]课程9：聚类

from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=2).fit(X)
kmeans.predict(X)

n_clusters : 

The number of clusters to form as well as the number of centroids to generate.#分为几类

n_init : 

Number of time the k-means algorithm will be run with different centroid seeds. The final results will be the best output of n_init consecutive runs in terms of inertia.#初始次数

max_iter :
Maximum number of iterations of the k-means algorithm for a single run.#迭代次数

##使用 3 个特征聚类

feature_1 = "salary"
feature_2 = "exercised_stock_options"
feature_3 = "total_payments"
poi  = "poi"
features_list = [poi, feature_1, feature_2, feature_3]
data = featureFormat(data_dict, features_list )
poi, finance_features = targetFeatureSplit( data )


from sklearn.cluster import KMeans
pred =[]
pred = KMeans(n_clusters=2).fit_predict(finance_features)
### in the "clustering with 3 features" part of the mini-project,
### you'll want to change this line to 
### for f1, f2, _ in finance_features:
### (as it's currently written, the line below assumes 2 features)
for f1, f2, f3 in finance_features:
    plt.scatter( f1, f2, f3 )
plt.show()

##股票期权范围

import numpy as np 
stocklist=[]
for item in data_dict:
    stock = data_dict[item]['exercised_stock_options']
    if stock != 'NaN':
        stocklist.append(stock)

stocklist = np.array(stocklist)
print "max:",np.max(stocklist)
print "min:",np.min(stocklist)

##薪酬范围

salarylist=[]
for item in data_dict:
    stock = data_dict[item]['salary']
    if stock != 'NaN':
        salarylist.append(stock)

salarylist = np.array(salarylist)
print "max:",np.max(salarylist)
print "min:",np.min(salarylist)