'''decision tree'''
from sklearn.tree import DecisionTreeClassifier as DTC
dtc = DTC(criterion = 'entropy')
dtc.fit(x,y)

'''Artificial neural network ANN'''
from keras.models import Sequential
from keras.layers.core import Dense, Activation

model = Sequential() #set up a model
model.add(Dense(2,input_dim = 10)) #output_dim is 2, input_dim is 10
model.add(Activation('relu'))

model.add(Dense(1, input_dim = 2))
model.add(Activation('sigmoid')) #for 0-1 output
model.compil(loss = , optimizer = , class_mode = )
model.fit(x, y , nb_epoch = 1000 ,)  #train 1000 times
model.predict_classes(x)

'''K-means'''
data = 1.0 * (data - data.mean())/data.std() #standardizing data
from sklearn.cluster import KMeans
model = KMeans(n_cluster = 4, n_jobs = 4, max_iter = 1000)
model.fit(data)

r1 = pd.Series(model.labels_).value_counts()
r2 = pd.DataFrame(model.cluster_centers_)
r = pd.concat([r2,r1], axis = 1) #get the result matrix

'''clustering visualization tool TSNE'''