def train_lda():
"""
Train the LDA model.
generate_dictionary() must be called before this method.
"""
print("------------------")
print("Training LDA model")
print("------------------")
# load dictionary, as generated by generate_dictionary()
print("Loading dictionary...")
dictionary = gensim.corpora.dictionary.Dictionary.load(cfg.LDA_DICTIONARY_FILEPATH)
# generate a mapping from word id to word
print("Generating id2word...")
id2word = {}
for word in dictionary.token2id:
id2word[dictionary.token2id[word]] = word
# initialize LDA
print("Initializing LDA...")
lda_model = LdaMulticore(corpus=None, num_topics=cfg.LDA_COUNT_TOPICS, id2word=id2word,
workers=LDA_COUNT_WORKERS, chunksize=LDA_CHUNK_SIZE)
# Train the LDA model
print("Training...")
examples = []
update_every_n_windows = 25000
windows = load_windows(load_articles(cfg.ARTICLES_FILEPATH), cfg.LDA_WINDOW_SIZE,
only_labeled_windows=True)
for i, window in enumerate(windows):
tokens_str = [token.word.lower() for token in window.tokens]
bow = dictionary.doc2bow(tokens_str) # each window as bag of words
examples.append(bow)
if len(examples) >= update_every_n_windows:
print("Updating (at window %d of max %d)..." % (i, COUNT_EXAMPLES_FOR_LDA))
# this is where the LDA model is trained
lda_model.update(examples)
examples = []
if i >= COUNT_EXAMPLES_FOR_LDA:
print("Reached max of %d windows." % (COUNT_EXAMPLES_FOR_LDA,))
break
# i don't update here with the remainder of windows, because im not sure if each update step's
# results are heavily influenced/skewed by the the number of examples
#if len(examples) > 0:
# print("Updating with remaining windows...")
# lda_model.update(examples)
# save trained model to HDD
print("Saving...")
lda_model.save(cfg.LDA_MODEL_FILEPATH)
class Lda(BaseEstimator, TransformerMixin):
def __init__(self, id2word=None, num_topics=25, passes=1):
self.lda = None
self.id2word = id2word
self.num_topics = num_topics
self.passes = passes
def fit(self, X, y=None):
"""
Parameter
---------
X : [sp.csr_matrix]
Returns
-------
self
"""
if self.lda is None:
self.lda = LdaMulticore(id2word=self.id2word,
num_topics=self.num_topics,
passes=self.passes)
X_flat = sp.vstack(X)
self.lda.update(Sparse2Corpus(X_flat, documents_columns=False))
return self
def fit_transform(self, X, y=None):
self.fit(X)
return self.transform(X)
def transform(self, X):
"""
Parameter
---------
X : [sp.csr_matrix]
Returns
-------
topic_vectors : [np.ndarray]
each matrix is of shape (sent_count, topic_count)
"""
topic_vectors = []
for doc in X:
sents_bow = Sparse2Corpus(doc, documents_columns=False)
gamma, _ = self.lda.inference(sents_bow)
# divide row by row sum
topic_dist = (gamma.T / np.sum(gamma, axis=1)).T
topic_vectors.append(topic_dist)
return topic_vectors
class Lda(BaseEstimator, TransformerMixin):
def __init__(self, id2word=None, num_topics=25, passes=1):
self.lda = None
self.id2word = id2word
self.num_topics = num_topics
self.passes = passes
def fit(self, X, y=None):
"""
Parameter
---------
X : [sp.csr_matrix]
Returns
-------
self
"""
if self.lda is None:
self.lda = LdaMulticore(
id2word=self.id2word, num_topics=self.num_topics, passes=self.passes)
X_flat = sp.vstack(X)
self.lda.update(Sparse2Corpus(X_flat, documents_columns=False))
return self
def fit_transform(self, X, y=None):
self.fit(X)
return self.transform(X)
def transform(self, X):
"""
Parameter
---------
X : [sp.csr_matrix]
Returns
-------
topic_vectors : [np.ndarray]
each matrix is of shape (sent_count, topic_count)
"""
topic_vectors = []
for doc in X:
sents_bow = Sparse2Corpus(doc, documents_columns=False)
gamma, _ = self.lda.inference(sents_bow)
# divide row by row sum
topic_dist = (gamma.T / np.sum(gamma, axis=1)).T
topic_vectors.append(topic_dist)
return topic_vectors
