# import necessary libraries
import joblib
import numpy as np
from flask import Flask, render_template, request, jsonify
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from pre_processing import preprocess_text

app = Flask(__name__)

# specify path for model and vectorizer
model_path = "log_model_final.pkl"
vectorizer_path = "vectorizer.pkl"

# Load the pre-trained model
model = joblib.load(model_path)
vectorizer = joblib.load(vectorizer_path)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/predict', methods=['POST'])
def predict():
    # predict
    try:
        # Get input text from the form
        input_text = request.get_json(force=True)['input']
        print(input_text)
        test_data =  vectorizer.transform([input_text])
        y_pred = model.predict(test_data)
        print(y_pred)
                # Return the prediction as JSON
        return jsonify({'prediction': y_pred[0]})
    
    except Exception as e:
        return jsonify({'error': str(e)})
    
    
if __name__ == '__main__':
    app.run(host="0.0.0.0",port=5000)