Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/SoulDGXu/NLPVisualizationSystem
/ functions
Functions
252 in github.com/SoulDGXu/NLPVisualizationSystem
⨍
Functions
252
◇
Types & classes
21
↳
Endpoints
62
↓ 11 callers
Function
read_file
Read the local file and transform to text. Parameters ---------- filepath : TYPE-str DESCRIPTION: the text file path.
src/exe/exe_03.py:61
↓ 10 callers
Function
read_file
Read the local file and transform to text. Parameters ---------- filepath : TYPE-str DESCRIPTION:
src/exe/exe_02.py:66
↓ 9 callers
Function
save_to_file
(filepath, content)
app.py:184
↓ 8 callers
Method
pos_tag
(self)
src/exe/review_sentiment/sentence.py:21
↓ 8 callers
Method
word_tokenize
(self)
src/exe/review_sentiment/sentence.py:17
↓ 6 callers
Method
parse
(self, document_text, debug=False)
src/exe/worddiscovery/entropy_based.py:50
↓ 4 callers
Method
find
Args: text: string Returns: count: int, frequent of text
src/exe/worddiscovery/trie.py:33
↓ 4 callers
Method
insert
(self, text)
src/exe/worddiscovery/trie.py:20
↓ 4 callers
Function
itemcount
此函数用于计算字典重复的key个数 。 Parameters ---------- dictionary : TYPE-dict Returns ------- count : TYPE-dict
src/exe/exe_01.py:24
↓ 4 callers
Function
save_to_file
Write the text to the local file. Parameters ---------- filepath : TYPE-str DESCRIPTION: the file save path. Re
src/exe/exe_03.py:41
↓ 3 callers
Method
_cal_word_aggregation
(self, word, word_count)
src/exe/worddiscovery/entropy_based.py:143
↓ 3 callers
Function
extract_words
Statistical word frequency. Parameters ---------- content : TYPE-str DESCRIPTION: text. Returns -------
src/exe/exe_02.py:40
↓ 3 callers
Function
generate_random_filename
According to the specified prefix name and suffix name, this function is used to generate a random file name. Parameters: pr
src/exe/exe_02.py:263
↓ 3 callers
Method
getEmbedding
(self, sentence, type, isUseAveragePooling, isUseStopwords)
src/exe/sentiment_analysis/embedding_manager_cyd.py:14
↓ 3 callers
Function
get_abstract
Use Textrank algorithm to extract text summaries/abstract. Parameters ---------- text : TYPE-str DESCRIPTION: the
src/exe/exe_03.py:104
↓ 3 callers
Function
get_keywords
Use Textrank algorithm to extract text keywords. Parameters ---------- text : TYPE-str DESCRIPTION: the text conte
src/exe/exe_03.py:126
↓ 3 callers
Function
get_num_by_prob
(num_list, prob_list)
src/utils/data_prepare.py:47
↓ 3 callers
Function
get_sorted_dict
Sort the dictionary by value and take the top n with the largest value. Parameters: dic: TYPE-dictionary DESCRI
src/exe/exe_02.py:87
↓ 3 callers
Function
review_summary
According to the input product ID number, summarize the user's evaluation of the product. parameters: product_id: type-int,
src/exe/sentiment_analysis/review_sentiment_analysis.py:485
↓ 3 callers
Function
save_to_file
(filepath, content)
src/exe/exe_02.py:35
↓ 3 callers
Method
show_main
(self, content, picturefile, words_num, save_name)
src/exe/key_info_extraction/create_wordcloud.py:158
↓ 2 callers
Method
_cal_word_neighbor_char_entropy
(self, trie_tree, word)
src/exe/worddiscovery/entropy_based.py:156
↓ 2 callers
Method
addEdge
(self, start, end, weight)
src/exe/key_info_extraction/textrank.py:19
↓ 2 callers
Function
check_url
Check if the URL can be accessed normally. Open a simulated browser and visit. If the access is normal, the output is normal,
app.py:189
↓ 2 callers
Function
data_process
Process the multiple document input: remove non-text characters, remove stop words, word segmentation, etc., to generate dictionary and cor
src/exe/key_info_extraction/topic_cluster_lda.py:23
↓ 2 callers
Method
get_all_words
(self)
src/exe/worddiscovery/trie.py:61
↓ 2 callers
Method
get_new_words
(self, top=20)
src/exe/worddiscovery/entropy_based.py:58
↓ 2 callers
Function
get_train_test
(features,tags,test_size=0.3)
src/exe/review_sentiment/model_training.py:80
↓ 2 callers
Function
get_train_test
(features,tags,test_size=0.3)
src/exe/sentiment_analysis/review_sentiment_analysis.py:417
↓ 2 callers
Method
get_wordvector
(self, word)
src/exe/key_info_extraction/sentence_similarity.py:24
↓ 2 callers
Function
handle_text
(text, isUseStopWords)
src/exe/sentiment_analysis/utils.py:7
↓ 2 callers
Function
hist_user_company_size_base
It is used to respond to requests for chart parameters. Returns ------- c : TYPE-echarts parameters return echarts par
src/exe/exe_06.py:176
↓ 2 callers
Function
hist_user_industry_base
It is used to respond to requests for chart parameters. Returns ------- c : TYPE-echarts parameters return echarts par
src/exe/exe_06.py:147
↓ 2 callers
Function
hist_user_product_use_time_base
It is used to respond to requests for chart parameters. Returns ------- c : TYPE-echarts parameters return echarts par
src/exe/exe_06.py:204
↓ 2 callers
Method
predict_prob
(self, review_segment)
src/exe/sentiment_analysis/sentiment_model.py:16
↓ 2 callers
Function
preplexity
Calculate the preplexity of a lda-model. Parameters: ldamodel: a LDA Model testset: corpus data dictionary: voca
src/exe/key_info_extraction/topic_cluster_lda.py:63
↓ 2 callers
Function
product_edc_feature_query
此函数用于获取EDC产品功能的分组统计数据。 Returns ------- dataX : TYPE-list EDC feature names. dataY : TYPE-list EDC featur
src/exe/exe_01.py:76
↓ 2 callers
Method
rank
(self)
src/exe/key_info_extraction/textrank.py:24
↓ 2 callers
Method
show_cloud
(self, word_dict, max_words, picturefile, save_name)
src/exe/key_info_extraction/create_wordcloud.py:93
↓ 2 callers
Function
user_job_wordcloud_freq_query
It is used to count the frequency of words for user job title. Returns ------- data_pair : TYPE-list(tuple) DESCRIPTIO
src/exe/exe_06.py:119
↓ 2 callers
Function
wordcloud_user_job_base
It is used to respond to requests for chart parameters. Returns ------- c : TYPE-echarts parameters return echarts par
src/exe/exe_06.py:231
↓ 1 callers
Method
_build_trie
(self, sentences)
src/exe/worddiscovery/entropy_based.py:115
↓ 1 callers
Method
_generate_word_fragment
(self, word)
src/exe/worddiscovery/entropy_based.py:152
↓ 1 callers
Method
_preprocess
(self, document_text)
src/exe/worddiscovery/entropy_based.py:129
↓ 1 callers
Method
aspect_based_summary
返回一个business的summary. 针对于每一个aspect计算出它的正面负面情感以及TOP reviews. 具体细节请看给定的文档。
src/exe/review_sentiment/business.py:76
↓ 1 callers
Method
aspect_based_summary
返回一个business的summary. 针对于每一个aspect计算出它的正面负面情感以及TOP reviews. 具体细节请看给定的文档。
src/exe/sentiment_analysis/review_sentiment_analysis.py:85
↓ 1 callers
Method
build_wordsdict
(self, text)
src/exe/key_info_extraction/compute_keywords_tfidf.py:58
↓ 1 callers
Method
cal_aggregation
(self, debug)
src/exe/worddiscovery/entropy_based.py:66
↓ 1 callers
Method
cal_neighbor_char_entropy
(self, debug)
src/exe/worddiscovery/entropy_based.py:80
↓ 1 callers
Method
cal_score
(self, debug)
src/exe/worddiscovery/entropy_based.py:107
↓ 1 callers
Function
classification_logistic
(features, tags)
src/exe/sentiment_analysis/review_sentiment_analysis.py:427
↓ 1 callers
Function
classification_svm
(features, tags)
src/exe/review_sentiment/model_training.py:124
↓ 1 callers
Function
classification_svm
(features, tags)
src/exe/sentiment_analysis/review_sentiment_analysis.py:456
↓ 1 callers
Method
clear
(self)
src/exe/worddiscovery/entropy_based.py:40
↓ 1 callers
Method
extract_abstract
(self, text, num_sentences)
src/exe/key_info_extraction/abstract_textrank.py:28
↓ 1 callers
Method
extract_aspects
从一个business的review中抽取aspects
src/exe/review_sentiment/business.py:256
↓ 1 callers
Method
extract_aspects
从一个business的review中抽取aspects
src/exe/sentiment_analysis/review_sentiment_analysis.py:281
↓ 1 callers
Method
extract_keywords
(self, text, num_keywords)
src/exe/key_info_extraction/keywords_textrank.py:17
↓ 1 callers
Method
extract_keywords
(self, content, words_num=20)
src/exe/key_info_extraction/create_wordcloud.py:83
↓ 1 callers
Method
extract_words
(self, content)
src/exe/key_info_extraction/create_wordcloud.py:72
↓ 1 callers
Function
fill_missing_data
It is used to generate random number or string based on your given distribution. Here specifically refers to the frequency distribution,li
src/utils/data_prepare.py:68
↓ 1 callers
Method
getSenetnceEmbedding
(self, sentence, isUseAveragePooling, isUseStopwords)
src/exe/sentiment_analysis/bert_embedding_extend.py:14
↓ 1 callers
Method
getSentenceVectorCommon
(self, sentence, isUseAveragePooling, isUseStopwords)
src/exe/sentiment_analysis/glove_embedding.py:42
↓ 1 callers
Function
get_best_num_topics
This is the optimal number of topics obtained through perplexity assessment. Parameters: data: type: array or dataframe or m
src/exe/key_info_extraction/topic_cluster_lda.py:114
↓ 1 callers
Method
get_children_char_count
function for entropy based word discovery
src/exe/worddiscovery/trie.py:65
↓ 1 callers
Method
get_cur_aspect_adj
(self, text)
src/exe/review_sentiment/business.py:229
↓ 1 callers
Method
get_cur_aspect_adj
(self, text)
src/exe/sentiment_analysis/review_sentiment_analysis.py:254
↓ 1 callers
Function
get_review_data
It is used to read data and build a specific data frame, includes review data items and product data items. Return -------
src/utils/data_prepare.py:176
↓ 1 callers
Function
get_review_summary_for_business
(biz_id)
src/exe/review_sentiment/main.py:22
↓ 1 callers
Method
get_segment
(self, review_text, aspect, aspects_dic)
src/exe/review_sentiment/business.py:171
↓ 1 callers
Method
get_segment
(self, review_text, aspect, aspects_dic)
src/exe/sentiment_analysis/review_sentiment_analysis.py:196
↓ 1 callers
Function
get_uniform_random_num
(low, high)
src/utils/data_prepare.py:64
↓ 1 callers
Function
get_webcontent
Online mode: According to the URL, grab the text content of the news. Parameters ---------- url : TYPE-str
src/exe/exe_02.py:123
↓ 1 callers
Function
get_webcontent
Online mode: According to the URL, grab the text content of the news. Parameters ---------- url : TYPE-str
src/exe/exe_03.py:82
↓ 1 callers
Method
get_webcontent
(self, url)
src/exe/key_info_extraction/create_wordcloud.py:132
↓ 1 callers
Function
hist_product_deployment_base
此函数用于获取产品安装的柱状图的参数。 Returns ------- c : TYPE-echarts parameters return echarts parameters.
src/exe/exe_01.py:355
↓ 1 callers
Function
hist_product_edc_feature_base
此函数用于获取产品EDC功能柱状图的参数。 Returns ------- c : TYPE-echarts parameters return echarts parameters.
src/exe/exe_01.py:327
↓ 1 callers
Function
hist_product_feature_base
此函数用于获取产品功能柱状图的参数。 Returns ------- c : TYPE-echarts parameters return echarts parameters.
src/exe/exe_01.py:298
↓ 1 callers
Function
hist_product_support_base
此函数用于获取产品售后支持的柱状图的参数。 Returns ------- c : TYPE-echarts parameters return echarts parameters.
src/exe/exe_01.py:430
↓ 1 callers
Function
hist_product_train_base
此函数用于获取产品培训的柱状图的参数。 Returns ------- c : TYPE-echarts parameters return echarts parameters.
src/exe/exe_01.py:383
↓ 1 callers
Method
init_data
初始化数据 :return:
src/exe/sentiment_analysis/glove_embedding.py:16
↓ 1 callers
Method
is_review_only_one_aspect
判断评论里面是否只包含一个方面 :param review: :return:
src/exe/review_sentiment/business.py:237
↓ 1 callers
Method
is_review_only_one_aspect
判断评论里面是否只包含一个方面 :param review: :return:
src/exe/sentiment_analysis/review_sentiment_analysis.py:262
↓ 1 callers
Function
keyinfo_by_import_file_query
According to the local file imported by the user, an abstract and keywords are automatically generated. Returns -------
src/exe/exe_03.py:198
↓ 1 callers
Function
keyinfo_by_input_text_query
According to the text input by the user, an abstract and keywords are automatically generated. Returns ------- abstra
src/exe/exe_03.py:175
↓ 1 callers
Function
keyinfo_by_url_query
According to the user's input to specify the URL, the text of the URL is collected, and an abstract and keywords are automatically generat
src/exe/exe_03.py:151
↓ 1 callers
Function
lda_model
(data, file_path)
src/exe/key_info_extraction/topic_cluster_lda.py:153
↓ 1 callers
Function
lda_topics_query
It is used to get the optimal number of topics and save the topic keywords and topic distribution of documents to a file based on the fi
src/exe/exe_03.py:285
↓ 1 callers
Method
load_idf
(self)
src/exe/key_info_extraction/compute_keywords_tfidf.py:45
↓ 1 callers
Function
main
()
src/exe/review_sentiment/model_training.py:23
↓ 1 callers
Function
main
()
src/exe/review_sentiment/main.py:26
↓ 1 callers
Function
new_word_discovery_query
It is used to get the user input: source text, maximum number of new words and maximum of new word length. Returns -------
src/exe/exe_03.py:331
↓ 1 callers
Function
product_deployment_query
此函数用于获取EDC产品安装的分组统计数据。 Returns ------- dataX : TYPE-list EDC deployment method names. dataY : TYPE-list
src/exe/exe_01.py:115
↓ 1 callers
Function
product_feature_query
此函数用于返回产品功能的分组统计数据。 Returns ------- dataX: TYPE-list all product feature names. dataY: TYPE-list Product feature percentag
src/exe/exe_01.py:53
↓ 1 callers
Function
product_price_query
此函数用于获取EDC产品价格的分组统计数据。 Returns ------- dataX : TYPE-list EDC product pricing. dataY : TYPE-list EDC prod
src/exe/exe_01.py:191
↓ 1 callers
Function
product_rating_query
It is used to get the average score of each product rating. Returns ------- dataX : TYPE-list rating index: i.e. 'rati
src/exe/exe_01.py:216
↓ 1 callers
Function
product_support_query
此函数用于获取EDC产品售后支持的分组统计数据。 Returns ------- dataX : TYPE-list EDC support method names. dataY : TYPE-list e
src/exe/exe_01.py:164
↓ 1 callers
Function
product_train_query
此函数用于获取EDC产品培训的分组统计数据。 Returns ------- dataX : TYPE-list EDC training method names. dataY : TYPE-list ea
src/exe/exe_01.py:139
↓ 1 callers
Function
radar_product_rating_base
此函数用于获取产品多维评价的雷达图的参数。 Returns ------- tl : TYPE-echarts parameters return echarts parameters.
src/exe/exe_01.py:459
↓ 1 callers
Method
read_data
(self)
src/exe/review_sentiment/business.py:48
next →
1–100 of 252, ranked by callers