app_utils.py

import streamlit as st
import pandas as pd
import streamlit.components.v1 as stc
import nltk

# NLP Package-used for text analysis
import nltk
nltk.download('all')
from sumy.parsers.plaintext import PlaintextParser
from nltk.tokenize import word_tokenize
from nltk.tag import pos_tag
from nltk.stem import WordNetLemmatizer
from sumy.summarizers.lex_rank import LexRankSummarizer
from sumy.summarizers.text_rank import TextRankSummarizer
from nltk.corpus import stopwords
from nltk.tokenize import sent_tokenize
from sumy.nlp.tokenizers import Tokenizer
from rouge import Rouge
from transformers import BartForConditionalGeneration, BartTokenizer
from transformers import T5ForConditionalGeneration, T5Tokenizer

# from nltk import ne_chunk
from nltk.tag import StanfordNERTagger

from collections import Counter

from textblob import TextBlob
import seaborn as sns
import matplotlib.pyplot as plt

from wordcloud import WordCloud

import base64
import time

stanford_ner_jar = 'https://github.com/UjjwalBansal19/stanford_model/raw/main/stanford-ner.jar'
# Path to the pre-trained NER model file
stanford_ner_model ='https://huggingface.co/spaces/UjjwalVIT/Text_analysis_and_metadata_app/raw/main/english.all.3class.distsim.crf.ser.gz'

timestr = time.strftime("%Y%m%d-%H%M%S")


# from spacy import displacy


#Text cleaning packages 
# removing stopwords, removing special characters, removing URLs, normalizing text, removing HTML tags, correcting common spelling mistakes,
import neattext as nt
import neattext.functions as nfx


HTML_WRAPPER = """<div style="overflow-x: auto; border: 1px solid red; border-radius: 0.25rem; padding: 1rem";>{}
</div> 
"""

def evaluate_summary(summary,reference):
    r=Rouge()
    eval_score=r.get_scores(summary,reference)
    eval_score_df=pd.DataFrame(eval_score[0])
    return eval_score_df


def bart_summary(docx):
    model=BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
    tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
    inputs = tokenizer.batch_encode_plus([docx], truncation=True, padding='longest', max_length=1024, return_tensors='pt')
    summary_ids = model.generate(inputs['input_ids'], num_beams=6, max_length=100, early_stopping=True)
    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
    return  summary

def T5_summary(docx):
    model = T5ForConditionalGeneration.from_pretrained('t5-base')
    tokenizer = T5Tokenizer.from_pretrained('t5-base')
    input_text = "summarize: " + docx
    input_ids = tokenizer.encode(input_text, return_tensors='pt')
    summary_ids = model.generate(input_ids, max_length=100, num_beams=4, early_stopping=True)
    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
    return summary
    
def sumy_summarizer(docx,num=5):
    parser=PlaintextParser.from_string(docx,Tokenizer("english"))
    lex_summ=LexRankSummarizer()
    summary=lex_summ(parser.document,sentences_count= num)
    summary_list=[str(sentence) for sentence in summary]
    result=' '.join(summary_list)
    return result

def sumy_text_summarizer(docx, num=5):
    parser = PlaintextParser.from_string(docx, Tokenizer("english"))
    text_rank_summarizer = TextRankSummarizer()
    summary = text_rank_summarizer(parser.document, sentences_count=num)
    summary_list = [str(sentence) for sentence in summary]
    result = ' '.join(summary_list)
    return result


def nlp_analysis(text):
    token_data = []
    tokens=word_tokenize(text)
    tagged_tokens = pos_tag(tokens) #categorize into nouns, verbs, adjectives, adverbs, pronouns etc
    stop_words = set(stopwords.words('english')) #check for words like a", "an", "the", "is", "in"
    lemmatizer = WordNetLemmatizer() #preprocessing
    for token in tagged_tokens:
        token_text=token[0]
        token_shape = None
        token_pos = token[1] # "," - Comma CC - Coordinating conjunction DT - Determiner NN - Noun VBD - Past tense verb PRP - Personal pronoun VBD - Past tense verb
        token_lemma = lemmatizer.lemmatize(token_text)
        token_is_alpha = token_text.isalpha()
        token_is_stop = token_text.lower() in stop_words
        token_data.append([token_text,token_shape,token_pos,token_lemma,token_is_alpha,token_is_stop])
    df=pd.DataFrame(token_data,columns=['Token','Shape','Position','lemma','Contains_Alphabets','Contains_Stop_words'])
    return df


def find_entities(text):
    stan = StanfordNERTagger(stanford_ner_model, stanford_ner_jar)
    text=text.replace("\n\n","\n")
    tokens = nltk.word_tokenize(text)
    tagged_tokens = stan.tag(tokens)
    entities = [(token, tag) for token, tag in tagged_tokens if tag != 'O']
    entities=HTML_WRAPPER.format(entities)
    return entities


def file_download(data):
    csv_file= data.to_csv()
    b64=base64.b64encode(csv_file.encode()).decode()
    new_filename="result_{}.csv".format(timestr)
    st.markdown('### 🗃️ Download csv file ')
    href=f'<a href="data:file/csv;base64,{b64}" download="{new_filename}"> Click Here! </a>'
    st.markdown(href, unsafe_allow_html=True)

def get_most_common_tokens(text):
    word_tokens=Counter(text.split())
    most_common=dict(word_tokens.most_common(len(text)))
    return most_common


def get_semantics(text):
    blob=TextBlob(text)
    sentiment=blob.sentiment
    return sentiment

def plot_wordcloud(text):
    text_workcloud= WordCloud().generate(text) #size indicates its frequency
    fig=plt.figure()
    plt.imshow(text_workcloud,interpolation='bilinear')
    plt.axis('off')
    st.pyplot(fig)

def pos_tags(text):
    blob=TextBlob(text)
    tagged_text=blob.tags
    tagged_df=pd.DataFrame(tagged_text,columns=['tokens','tags'])
    return tagged_df

TAGS = {
            'NN'   : 'green',
            'NNS'  : 'green',
            'NNP'  : 'green',
            'NNPS' : 'green',
            'VB'   : 'blue',
            'VBD'  : 'blue',
            'VBG'  : 'blue',
            'VBN'  : 'blue',
            'VBP'  : 'blue',
            'VBZ'  : 'blue',
            'JJ'   : 'red',
            'JJR'  : 'red',
            'JJS'  : 'red',
            'RB'   : 'cyan',
            'RBR'  : 'cyan',
            'RBS'  : 'cyan',
            'IN'   : 'darkwhite',
            'POS'  : 'darkyellow',
            'PRP$' : 'magenta',
            'PRP$' : 'magenta',
            'DET'   : 'black',
            'CC'   : 'black',
            'CD'   : 'black',
            'WDT'  : 'black',
            'WP'   : 'black',
            'WP$'  : 'black',
            'WRB'  : 'black',
            'EX'   : 'yellow',
            'FW'   : 'yellow',
            'LS'   : 'yellow',
            'MD'   : 'yellow',
            'PDT'  : 'yellow',
            'RP'   : 'yellow',
            'SYM'  : 'yellow',
            'TO'   : 'yellow',
            'None' : 'off'
        }

def tag_visualize(tagged_df):
    colored_text=[]
    for i in tagged_df:
        if i[1] in TAGS.keys():
            token=i[0]
            color_of_text=TAGS.get(i[1])
            changed_text='<span style=color:{}>{}</span>'.format(color_of_text,token)
            colored_text.append(changed_text)
    result=''.join(colored_text)
    return result