# Imports
import gradio as gr
from sklearn.linear_model import LogisticRegression
import pickle5 as pickle
import re
import string
import nltk
from nltk.corpus import stopwords
nltk.download('stopwords')
from sklearn.feature_extraction.text import CountVectorizer

# file name
lr_filename = 'logistic_regression.pkl'

# Process input text, including removing stopwords, converting to lowercase, and removing punctuation
def process_text(text):
    text = stopwords.words('english')
    text = str(text).lower()
    text = re.sub(
        f"[{re.escape(string.punctuation)}]", " ", text
    )
    text = " ".join(text.split())
    return text

# Vectorize input text
vectorizer = CountVectorizer()
def vectorize_text(text):
    text = process_text(text)
    return vectorizer.transform(text)

# Load model from pickle file
model = pickle.load(open(lr_filename, 'rb'))

def predict(text):
    text = vectorize_text(text)
    prediction = model.predict(text)
    return prediction


# Define interface
demo = gr.Interface(fn=predict,
                        title="Text Classification Demo",
                        description="This is a demo of a text classification model using Logistic Regression.",
                        inputs=gr.Textbox(lines=10, placeholder='Input text here...', label="Input Text"),
                        outputs=gr.Textbox(label="Predicted Label: Other: 1, Healthcare: 2, Technology: 3", lines=2, placeholder='Predicted label will appear here...'),
                        allow_flagging='never'
)

demo.launch()