from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.pipeline import Pipeline
import joblib

import re
import string
import nltk
nltk.download('stopwords')
nltk.download('punkt')

import streamlit as st 

import functions

torch.manual_seed(1)

# Preprocess function
import re
from contractions import contractions_dict
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize

def preprocess_text(text):
    # Remove URLs
    url_pattern = re.compile(r'https?://\S+')
    text = url_pattern.sub(' ', text)

    # Remove HTML Tags
    html_pattern = re.compile(r'<[^<>]+>')
    text = html_pattern.sub(' ', text)

    # Expand contractions
    text = ' '.join([contractions_dict.get(word, word) for word in text.split()])

    # Remove punctuation and digits
    text = re.sub(r'[^\w\s]', ' ', text)

    # Remove emojis
    emoji_pattern = re.compile("["
        u"\U0001F600-\U0001F64F"
        u"\U0001F300-\U0001F5FF"
        u"\U0001F680-\U0001F6FF"
        u"\U0001F1E0-\U0001F1FF"
        u"\U0001F1F2-\U0001F1F4"
        u"\U0001F1E6-\U0001F1FF"
        u"\U0001F600-\U0001F64F"
        u"\U00002702-\U000027B0"
        u"\U000024C2-\U0001F251"
        u"\U0001f926-\U0001f937"
        u"\U0001F1F2"
        u"\U0001F1F4"
        u"\U0001F620"
        u"\u200d"
        u"\u2640-\u2642"
        "]+", flags=re.UNICODE)
    text = emoji_pattern.sub(' ', text)

    # Convert to lowercase
    text = text.lower()

    # Tokenize and remove stopwords
    stop_words = set(stopwords.words('english'))
    tokens = word_tokenize(text)
    tokens = [token for token in tokens if token not in stop_words]

    # Join tokens back into text
    text = ' '.join(tokens)

    return text

# Main function
model_NB_path = './model_NB.sav'
model_NB = joblib.load(model_NB_path)

model_LR_path = './model_LR.sav'
model_LR = joblib.load(model_LR_path)


text = st.text_area('Enter some text !!! (English text : D )')
if text:
    out = functions.sentiment_analysis_LR(text)
    if out == 0:
        out = 'negative'
        st.json(out)
    else:
        out = 'positive'
        st.json(out)