Created
December 22, 2020 01:08
-
-
Save alex2awesome/a62b338b59477343c813a380aee1d7a5 to your computer and use it in GitHub Desktop.
Quick LDA with SKLearn Pipelining
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
from gensim.sklearn_api import LdaTransformer | |
from gensim.corpora import Dictionary | |
from sklearn.base import BaseEstimator, MetaEstimatorMixin | |
import re | |
from sklearn.pipeline import Pipeline | |
from sklearn.feature_extraction.text import CountVectorizer | |
from collections import defaultdict | |
class CV2BOW(BaseEstimator, MetaEstimatorMixin): | |
"""Transform a corpus into Bag-of-Word representation.""" | |
def fit(self, X, y=None): | |
return self | |
def transform(self, X): | |
t = X.tocoo() | |
# (token_id, token_count) | |
docs = defaultdict(list) | |
for d, r, c in list(zip(t.data, t.row, t.col)): | |
docs[r].append((c, d)) | |
docs = list(map(lambda x: docs[x], range(len(docs)))) | |
return docs | |
pipeline__lda = Pipeline([ | |
('cv', CountVectorizer(min_df=.01, max_df=0.5, stop_words='english')), | |
('doc2bow', CV2BOW()), | |
('lda', LdaTransformer(num_topics=10, iterations=50)), | |
]) | |
lda = pipeline__lda.fit_transform(docs) | |
beta_matrix = pd.DataFrame( | |
data=pipeline__lda['lda'].gensim_model.expElogbeta, | |
columns=sorted(pipeline__lda['cv'].vocabulary_) | |
).T | |
top_words = {} | |
for col in beta_matrix.columns: | |
topic = beta_matrix[col].sort_values(ascending=False) | |
topic_key = '%s, %s, %s' % (topic.index[0], topic.index[1], topic.index[2]) | |
top_words[topic_key] = list(topic.iloc[3:10].index) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment