本文整理汇总了Python中sklearn.decomposition.NMF.fit_predict方法的典型用法代码示例。如果您正苦于以下问题：Python NMF.fit_predict方法的具体用法？Python NMF.fit_predict怎么用？Python NMF.fit_predict使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.decomposition.NMF的用法示例。
在下文中一共展示了NMF.fit_predict方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: Topicmodel
# 需要导入模块: from sklearn.decomposition import NMF [as 别名]
# 或者: from sklearn.decomposition.NMF import fit_predict [as 别名]
class Topicmodel():
'''
Wrapper class for different topic models
'''
def __init__(self,folder='model',modeltype='kmeans',topics=100,topwords=10):
# the classifier, which also contains the trained BoW transformer
self.bow = cPickle.load(open(folder+'/BoW_transformer.pickle'))
self.folder = folder
self.modeltype = modeltype
self.topics = topics
self.topwords = topwords
if self.modeltype is 'kmeans':
from sklearn.cluster import KMeans
self.model = KMeans(n_clusters=topics,n_init=50)
if self.modeltype is 'kpcakmeans':
from sklearn.cluster import KMeans
from sklearn.decomposition import KernelPCA
self.model = {'kpca':KernelPCA(kernel='rbf',gamma=.1),\
'kmeans':KMeans(n_clusters=topics,n_init=50)}
if self.modeltype is 'nmf':
from sklearn.decomposition import NMF
self.model = NMF(n_components=topics)
def fit(self,X):
'''
fits a topic model
INPUT
X list of strings
'''
# transform list of strings into sparse BoW matrix
X = self.bow['tfidf_transformer'].fit_transform(\
self.bow['count_vectorizer'].fit_transform(X))
# transform word to BoW index into reverse lookup table
words = self.bow['count_vectorizer'].vocabulary_.values()
wordidx = self.bow['count_vectorizer'].vocabulary_.keys()
self.idx2word = dict(zip(words,wordidx))
# depending on the model, train
if self.modeltype is 'kmeans':
Xc = self.model.fit_predict(X)
if self.modeltype is 'kpcakmeans':
Xc = self.model['kpca'].fit_transform(X)
Xc = self.model['kmeans'].fit_predict(Xc)
if self.modeltype is 'nmf':
Xc = self.model.fit_transform(X).argmax(axis=0)
# for each cluster/topic compute covariance of word with cluster label
# this measure is indicative of the importance of the word for the topic
ass = zeros(self.topics)
self.topicstats = []
for cluster in range(self.topics):
# this is a binary vector, true if a data point was in this cluster
y = double(Xc==cluster)
# this is the covariance of the data with the cluster label
Xcov = X.T.dot(y)
# find the most strongly covarying (with the cluster label) words
wordidx = reversed(Xcov.argsort()[-self.topwords:])
topicwords = dict([(self.idx2word[idx],Xcov[idx]) for idx in wordidx])
self.topicstats.append({'assignments':y.sum(),'clusterid':cluster,\
'words': topicwords})
print 'Topic %d: %3d Assignments '%(cluster,y.sum())\
+ 'Topwords: ' + ' '.join(topicwords.keys()[:10])
datestr = datetime.datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
fn = self.folder+'/topicmodel-%s-'%self.modeltype +datestr+'.json'
print "Saving model stats to "+fn
open(fn,'wb').write(json.dumps(self.topicstats))
def predict(self,X):
'''
predicts cluster assignment from list of strings
INPUT
X list of strings
'''
if X is not list: X = [X]
X = self.bow['tfidf_transformer'].transform(\
self.bow['count_vectorizer'].transform(X))
if self.modeltype is 'kmeans':
return self.model.predict(X)
if self.modeltype is 'kpcakmeans':
return self.model['kmeans'].predict(self.model['kpca'].transform(X))
if self.modeltype is 'nmf':
return self.model.transform(X).argmax(axis=0)