import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize, sent_tokenize
from nltk.stem import WordNetLemmatizer
from nltk.probability import FreqDist
from nltk.collocations import BigramAssocMeasures, BigramCollocationFinder
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.decomposition import LatentDirichletAllocation
from sklearn.metrics.pairwise import cosine_similarity
from sumy.summarizers.lex_rank import LexRankSummarizer
from textblob import TextBlob
#from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM


def preprocess_text(text):
    stop_words = set(stopwords.words('english'))
    word_tokens = word_tokenize(text.lower())
    filtered_tokens = [word for word in word_tokens if word.isalnum() and word not in stop_words]
    lemmatizer = WordNetLemmatizer()
    lemmatized_tokens = [lemmatizer.lemmatize(token) for token in filtered_tokens]
    return lemmatized_tokens
def summarize_text(text):
    summarizer = LexRankSummarizer()
    summarized_sentences = summarizer(text, sentences_count=3)
    summary = ' '.join([str(sentence) for sentence in summarized_sentences])
    return summary
def analyze_sentiment(text):
    blob = TextBlob(text)
    sentiment = blob.sentiment.polarity
    return sentiment
def perform_topic_modeling(text):
    tfidf_vectorizer = TfidfVectorizer(tokenizer=preprocess_text, max_df=0.9, min_df=0.05, ngram_range=(1,2))
    tfidf_matrix = tfidf_vectorizer.fit_transform([text])
    lda_model = LatentDirichletAllocation(n_components=3, random_state=42)
    lda_model.fit(tfidf_matrix)
    feature_names = tfidf_vectorizer.get_feature_names()
    top_words_per_topic = []
    for topic_idx, topic in enumerate(lda_model.components_):
        top_words = [feature_names[i] for i in topic.argsort()[:-5 - 1:-1]]
        top_words_per_topic.append(', '.join(top_words))
    return top_words_per_topic
def process_text(text):
    summary = summarize_text(text)
    sentiment = analyze_sentiment(text)
    topics = perform_topic_modeling(text)
    return summary, sentiment, topics
text = "As a Head of Department, you have to take much more initiative to make all processes are running, maintained well and any action pending from any department be it HR /Admin /Accounts /SCM /Help Desk must be completed within time frame. BRAND TNS has lost its shine to be recovered. This is only possible by Joint Effort and Team approach. Next meeting we will have on 18th Mar. As discussed today, Work on all REDs and Try to bring All YELLOWs to GREEN. Same you need to monitor weekly/Monthly. Have intra department formal meetings on designated days. Drive the team including support system so that we could deliver best to customer with least rework."

summary, sentiment, topics = process_text(text)

print("Summary:")
print(summary)

print("\nSentiment Analysis:")
print(sentiment)

print("\nTopic Modeling:")
for i, topic in enumerate(topics):
  print(f"Topic {i+1}: {topic}")