STRLCPY/Maryam

To answer Mr. Saeed's comments = - imports are heavy and decrease the speed of the framework. So, try to import them in the class. - also, add them all to the requirements file.
Hatma Suryotrisongko committed 2 years ago

7e0c987b

1 parent 2f4539d5

Revision indexing in progress... (symbol navigation in revisions will be accurate after indexed)

■ ■ ■ ■ ■ ■

maryam/core/util/iris/topic.py

		skipped 2 lines
3	3
4	4		import pandas as pd
5	5		import numpy as np
6		-	import json
7		-	import csv
8		-	from dask import dataframe as dd
9		-
10		-	from sklearn.cluster import KMeans
11		-	import scipy
12	6		import matplotlib.pyplot as plt
13		-	import umap
14		-
15		-	from bertopic import BERTopic
16	7		from sentence_transformers import SentenceTransformer
17		-
18		-	from gensim.parsing.preprocessing import remove_stopwords, STOPWORDS
19		-
20		-	from top2vec import Top2Vec
21	8
22	9		class main:
23	10
24	11		def __init__(self, inputfile, filetype, keyword, showcharts, verbose):
25	12
	13	+	from dask import dataframe as dd
	14	+	import json
	15	+	from gensim.parsing.preprocessing import remove_stopwords
	16	+
26	17		if verbose == True:
27	18		print("\n\n DATASET = reading file : " + inputfile)
28	19		print("\n\n Search keyword = " + keyword)
		skipped 42 lines
71	62
72	63		def run_sklearn_cluster_kmeans(self, selected_pretrained_model, showcharts, verbose):
73	64
	65	+	from sklearn.cluster import KMeans
	66	+	import scipy
	67	+	import umap
	68	+
74	69		pretrained_model = selected_pretrained_model
75	70		if verbose == True:
76	71		print("\n\n Model selection")
		skipped 54 lines
131	126
132	127		def run_topic_modeling_bertopic(self, selected_pretrained_model, verbose):
133	128
	129	+	from bertopic import BERTopic
	130	+
134	131		pretrained_model = selected_pretrained_model
135	132		if verbose == True:
136	133		print("\n\n Model selection")
		skipped 41 lines
178	175
179	176
180	177		def run_search_topics_top2vec(self, keyword, showcharts, verbose):
	178	+
	179	+	from top2vec import Top2Vec
181	180
182	181		print("\n\n Search Topics Using Top2Vec (caution: might not work well for a small dataset)")
183	182		print("\n the Search Keyword = " + keyword)
		skipped 43 lines

■ ■ ■ ■ ■ ■

setup.py

		skipped 43 lines
44	44		'nltk',
45	45		'matplotlib',
46	46		'pandas',
47		-	'wordcloud'
	47	+	'wordcloud',
	48	+	'numpy',
	49	+	'dask',
	50	+	'scikit-learn',
	51	+	'scipy',
	52	+	'umap',
	53	+	'bertopic',
	54	+	'sentence_transformers',
	55	+	'gensim',
	56	+	'top2vec'
48	57		],
49	58		classifiers=[
50	59		'Programming Language :: Python :: 3.10',
		skipped 8 lines

To answer Mr. Saeed's comments = - imports are heavy and decrease the speed of the framework. So, try to import them in the class. - also, add them all to the requirements file.