print

README.md

@@ -4,7 +4,9 @@ This is a neural take on LDA-style topic modeling, i.e., based on a set of docum
 
 The implementation is based on a lightweight neural architecture and aims to be a scalable alternative to LDA. It readily makes use of GPU computation and has been tested successfully on 1M documents with 200 topics (on a Titan Xp card with 12GB of memory).
 
-Getting started: `python -m tests.basic.py data/my_docs.txt`
+`export PYTHONPATH="${PYTHONPATH}:{path/to/dir}/Topic_Modeling/doc2topic"`
+
+Getting started: `python -m tests/basic.py data/my_docs.txt 3 (# of topics)`
 
 ## Method
 

doc2topic/models.py

@@ -65,9 +65,8 @@ def __init__(self, corpus, n_topics=20, batch_size=1024*6, n_epochs=5, lr=0.015,
 		#sim = dot([embD, embW], 0, normalize=True)
 		dot_prod = dot([embD, embW], 1, normalize=False)
 		dot_prod = Reshape((1,))(dot_prod)
-
+		print(embD, embW)
 		output = Activation('sigmoid')(dot_prod)
-
 		opt = Adam(lr=lr, amsgrad=True)
 
 		self.model = Model(inputs=[inlayerD,inlayerW], outputs=[output])

tests/basic.py

@@ -2,6 +2,6 @@
 import sys
 
 data = corpora.DocData(sys.argv[1])
-model = models.Doc2Topic(data, n_topics=30)
+model = models.Doc2Topic(data, n_topics=int(sys.argv[2]))
 
 model.print_topic_words()