gistfile1.txt

1) Create Word Embedding using Glove 
model_glove = word2vec.Word2Vec(word2vec_sentences, size=200, window=10, sg=1, hs=0, min_count=1, negative=10, workers=-1, iter=5)

2)from sklearn.cluster import AgglomerativeClustering 

----------------to form cluster use this ------------------
In [37]:
wv_clusters = AgglomerativeClustering(n_clusters=50, affinity="cosine", linkage="average")
In [38]:
wv_clusters.fit(model_label_specific.syn0norm)
Out[38]:
AgglomerativeClustering(affinity='cosine', compute_full_tree='auto',
            connectivity=None, linkage='average',
            memory=Memory(cachedir=None), n_clusters=50, n_components=None,
            pooling_func=<function mean at 0x7f8f3c207cf8>)
In [39]:
wv_cluster_ids = wv_clusters.fit_predict(model_label_specific.syn0norm)
In [40]:
wv_cluster_mappings = {k: wv_cluster_ids[v.index] for k,v in model_label_specific.vocab.iteritems()}
In [41]:
filter(lambda x: x[1] == 4, wv_cluster_mappings.iteritems())[:10]