import gradio as gr
import tensorflow as tf
from keras_preprocessing.text import tokenizer_from_json
import numpy as np
import nltk
nltk.download('stopwords')
nltk.download('wordnet')
from nltk.corpus import stopwords
import re
from nltk.stem import WordNetLemmatizer
stemmer = WordNetLemmatizer()
from keras.preprocessing.text import Tokenizer
from keras import backend as K

#defining some variables and test parametrics

def recall(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
    recall = true_positives / (possible_positives + K.epsilon())
    return recall

def precision(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())
    return precision

def f1(y_true, y_pred):
    p = precision(y_true, y_pred)
    r = recall(y_true, y_pred)
    return 2 * ((p * r) / (p + r))

def accuracy(y_true, y_pred):
    return K.mean(K.equal(y_true, K.round(y_pred)), axis=1)

with open('tokenizer.json', 'r', encoding='utf-8') as f:
    tokenizer_config = f.read()

tokenizer = tokenizer_from_json(tokenizer_config)

model = tf.keras.models.load_model("sentimentality.h5", custom_objects={'f1':f1, 'recall': recall, 'precision': precision, 'accuracy':accuracy})

def get_sentiment(text):
    global model
    text = re.sub(r"@\S+|https?:\S+|http?:\S|[^A-Za-z0-9]+", ' ', str(text))
    text = re.sub(r'\s+[a-zA-Z]\s+', ' ', text)
    text = re.sub(r'\s+', ' ', text, flags=re.I)
    text = text.lower()
    text = text.split()
    text = [stemmer.lemmatize(word) for word in text]
    text = ' '.join(text)
    text = tokenizer.texts_to_sequences([text])[0]
    text += [0] * (30 - len(text))
    text = np.array(text).reshape(-1, 30)
    x = model.predict(text).tolist()[0][0]
    return x 

interface = gr.Interface(fn = get_sentiment, inputs = 'text', outputs = 'text', title = 'Sentiment Analysis', description = 'uses a custom designed model for sentiment analysis.')

interface.launch(share=False)