# Required Libraries #Base and Cleaning import json import requests import pandas as pd import numpy as np import emoji import regex import re import string from collections import Counter import tqdm from operator import itemgetter #Visualizations import plotly.express as px import seaborn as sns import matplotlib.pyplot as plt import pyLDAvis.gensim import chart_studio import chart_studio.plotly as py import chart_studio.tools as tls #Natural Language Processing (NLP) import spacy import gensim import json from spacy.tokenizer import Tokenizer from gensim.corpora import Dictionary from gensim.models.ldamulticore import LdaMulticore from gensim.models.coherencemodel import CoherenceModel from gensim.parsing.preprocessing import STOPWORDS as SW from sklearn.decomposition import LatentDirichletAllocation, TruncatedSVD from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer from sklearn.model_selection import GridSearchCV from pprint import pprint from wordcloud import STOPWORDS from gensim.parsing.preprocessing import preprocess_string, strip_punctuation, strip_numeric import gradio as gr def give_emoji_free_text(text): """ Removes emoji's from tweets Accepts: Text (tweets) Returns: Text (emoji free tweets) """ emoji_list = [c for c in text if c in emoji.EMOJI_DATA] clean_text = ' '.join([str for str in text.split() if not any(i in str for i in emoji_list)]) return clean_text def url_free_text(text): ''' Cleans text from urls ''' text = re.sub(r'http\S+', '', text) return text # Tokenizer function def tokenize(text): """ Parses a string into a list of semantic units (words) Args: text (str): The string that the function will tokenize. Returns: list: tokens parsed out """ # Removing url's pattern = r"http\S+" tokens = re.sub(pattern, "", text) # https://www.youtube.com/watch?v=O2onA4r5UaY tokens = re.sub('[^a-zA-Z 0-9]', '', text) tokens = re.sub('[%s]' % re.escape(string.punctuation), '', text) # Remove punctuation tokens = re.sub('\w*\d\w*', '', text) # Remove words containing numbers # tokens = re.sub('@*!*$*', '', text) # Remove @ ! $ tokens = tokens.strip(',') # TESTING THIS LINE tokens = tokens.strip('?') # TESTING THIS LINE tokens = tokens.strip('!') # TESTING THIS LINE tokens = tokens.strip("'") # TESTING THIS LINE tokens = tokens.strip(".") # TESTING THIS LINE tokens = tokens.lower().split() # Make text lowercase and split it return tokens def compute_coherence_values(dictionary, corpus, texts, limit, start=2, step=1): coherence_values = [] model_list = [] for num_topics in range(start, limit, step): model = gensim.models.ldamodel.LdaModel(corpus=corpus, num_topics=num_topics, random_state=100, chunksize=200, passes=10, per_word_topics=True, id2word=id2word) model_list.append(model) coherencemodel = CoherenceModel(model=model, texts=texts, dictionary=dictionary, coherence='c_v') coherence_values.append(coherencemodel.get_coherence()) return model_list, coherence_values def compute_coherence_values2(corpus, dictionary, k, a, b): lda_model = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=id2word, num_topics=num_topics, random_state=100, chunksize=200, passes=10, alpha=a, eta=b, per_word_topics=True) coherence_model_lda = CoherenceModel(model=lda_model, texts=df['lemma_tokens'], dictionary=id2word, coherence='c_v') return coherence_model_lda.get_coherence() def assignTopic(l): maxTopic = max(l,key=itemgetter(1))[0] return maxTopic def get_topic_value(row, i): if len(row) == 1: return row[0][1] else: return row[i][1] def dataframeProcessing(dataset): # Opening JSON file f = open('stopwords-tl.json') tlStopwords = json.loads(f.read()) stopwords = set(STOPWORDS) stopwords.update(tlStopwords) stopwords.update(['na', 'sa', 'ko', 'ako', 'ng', 'mga', 'ba', 'ka', 'yung', 'lang', 'di', 'mo', 'kasi']) global df df = pd.read_csv(dataset + '.csv') df.rename(columns = {'tweet':'original_tweets'}, inplace = True) df = df.apply(lambda row: row[df['language'].isin(['en'])]) df.reset_index(inplace=True) # Apply the function above and get tweets free of emoji's call_emoji_free = lambda x: give_emoji_free_text(x) # Apply `call_emoji_free` which calls the function to remove all emoji's df['emoji_free_tweets'] = df['original_tweets'].apply(call_emoji_free) #Create a new column with url free tweets df['url_free_tweets'] = df['emoji_free_tweets'].apply(url_free_text) # Load spacy # Make sure to restart the runtime after running installations and libraries tab nlp = spacy.load('en_core_web_lg') # Tokenizer tokenizer = Tokenizer(nlp.vocab) # Custom stopwords custom_stopwords = ['hi','\n','\n\n', '&', ' ', '.', '-', 'got', "it's", 'it’s', "i'm", 'i’m', 'im', 'want', 'like', '$', '@'] # Customize stop words by adding to the default list STOP_WORDS = nlp.Defaults.stop_words.union(custom_stopwords) # ALL_STOP_WORDS = spacy + gensim + wordcloud ALL_STOP_WORDS = STOP_WORDS.union(SW).union(stopwords) tokens = [] STOP_WORDS.update(stopwords) for doc in tokenizer.pipe(df['url_free_tweets'], batch_size=500): doc_tokens = [] for token in doc: if token.text.lower() not in STOP_WORDS: doc_tokens.append(token.text.lower()) tokens.append(doc_tokens) # Makes tokens column df['tokens'] = tokens # Make tokens a string again df['tokens_back_to_text'] = [' '.join(map(str, l)) for l in df['tokens']] def get_lemmas(text): '''Used to lemmatize the processed tweets''' lemmas = [] doc = nlp(text) # Something goes here :P for token in doc: if ((token.is_stop == False) and (token.is_punct == False)) and (token.pos_ != 'PRON'): lemmas.append(token.lemma_) return lemmas df['lemmas'] = df['tokens_back_to_text'].apply(get_lemmas) # Make lemmas a string again df['lemmas_back_to_text'] = [' '.join(map(str, l)) for l in df['lemmas']] # Apply tokenizer df['lemma_tokens'] = df['lemmas_back_to_text'].apply(tokenize) # Create a id2word dictionary global id2word id2word = Dictionary(df['lemma_tokens']) # Filtering Extremes id2word.filter_extremes(no_below=2, no_above=.99) print(len(id2word)) # Creating a corpus object corpus = [id2word.doc2bow(d) for d in df['lemma_tokens']] lda_model = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=id2word, num_topics=5, random_state=100, chunksize=200, passes=10, per_word_topics=True) pprint(lda_model.print_topics()) doc_lda = lda_model[corpus] coherence_model_lda = CoherenceModel(model=lda_model, texts=df['lemma_tokens'], dictionary=id2word, coherence='c_v') coherence_lda = coherence_model_lda.get_coherence() model_list, coherence_values = compute_coherence_values(dictionary=id2word, corpus=corpus, texts=df['lemma_tokens'], start=2, limit=10, step=1) k_max = max(coherence_values) global num_topics num_topics = coherence_values.index(k_max) + 2 lda_model = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=id2word, num_topics=num_topics, random_state=100, chunksize=200, passes=10, per_word_topics=True) grid = {} grid['Validation_Set'] = {} alpha = [0.05, 0.1, 0.5, 1, 5, 10] beta = [0.05, 0.1, 0.5, 1, 5, 10] num_of_docs = len(corpus) corpus_sets = [gensim.utils.ClippedCorpus(corpus, int(num_of_docs*0.75)), corpus] corpus_title = ['75% Corpus', '100% Corpus'] model_results = {'Validation_Set': [], 'Alpha': [], 'Beta': [], 'Coherence': [] } if 1 == 1: pbar = tqdm.tqdm(total=540) for i in range(len(corpus_sets)): for a in alpha: for b in beta: cv = compute_coherence_values2(corpus=corpus_sets[i], dictionary=id2word, k=num_topics, a=a, b=b) model_results['Validation_Set'].append(corpus_title[i]) model_results['Alpha'].append(a) model_results['Beta'].append(b) model_results['Coherence'].append(cv) pbar.update(1) pd.DataFrame(model_results).to_csv('lda_tuning_results_new.csv', index=False) pbar.close() params_df = pd.read_csv('lda_tuning_results_new.csv') params_df = params_df[params_df.Validation_Set == '100% Corpus'] params_df.reset_index(inplace=True) max_params = params_df.loc[params_df['Coherence'].idxmax()] max_coherence = max_params['Coherence'] max_alpha = max_params['Alpha'] max_beta = max_params['Beta'] lda_model_final = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=id2word, num_topics=7, random_state=100, chunksize=200, passes=10, alpha=max_alpha, eta=max_beta, per_word_topics=True) coherence_model_lda = CoherenceModel(model=lda_model_final, texts=df['lemma_tokens'], dictionary=id2word, coherence='c_v') coherence_lda = coherence_model_lda.get_coherence() lda_topics = lda_model_final.show_topics(num_words=10) topics = [] filters = [lambda x: x.lower(), strip_punctuation, strip_numeric] for topic in lda_topics: print(topic) topics.append(preprocess_string(topic[1], filters)) df['topic'] = [sorted(lda_model_final[corpus][text][0]) for text in range(len(df['original_tweets']))] df = df[df['topic'].map(lambda d: len(d)) > 0] df['topic'][0] df['max_topic'] = df['topic'].map(lambda row: assignTopic(row)) topic_clusters = [] for i in range(num_topics): topic_clusters.append(df[df['max_topic'].isin(([i]))]) topic_clusters[i] = topic_clusters[i]['original_tweets'].tolist() for i in range(len(topic_clusters)): tweets = df.loc[df['max_topic'] == i] tweets['topic'] = tweets['topic'].apply(lambda x: get_topic_value(x, i)) # tweets['topic'] = [row[i][1] for row in tweets['topic']] tweets_sorted = tweets.sort_values('topic', ascending=False) tweets_sorted.drop_duplicates(subset=['original_tweets']) rep_tweets = tweets_sorted['original_tweets'] rep_tweets = [*set(rep_tweets)] print('Topic ', i) print(rep_tweets[:5]) output_df = df[['original_tweets', 'max_topic']].copy() return output_df def greet(name): return "Hello " + name + "!!" iface = gr.Interface(fn=dataframeProcessing, inputs=gr.Dropdown(["katip-december", "katipunan-december", "bgc-december", "bonifacio global city-december"], label="Dataset"), outputs=gr.Dataframe(headers=['original_tweets', 'max_topic'])) iface.launch()