# -*- coding: utf-8 -*-
"""
Created on Sun Jan  8 17:22:19 2023

@author: gostl
"""

import numpy as np
import pandas as pd

from keras.models import Sequential
from keras.layers import Dense, LSTM, Embedding, Bidirectional, GlobalAveragePooling1D, Dropout
from keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import tensorflow as tf
import keras.utils as ku

data=pd.read_csv(r"C:\Users\gostl\OneDrive\Desktop\data\movie_reviews.csv")[:10000]

y=data["sentiment"]
y = np.array(list(map(lambda x: 1 if x=="positive" else 0, y))).astype("float32")
x_train,x_test,y_train,y_test=train_test_split(data["review"],y,test_size=0.3)

t=Tokenizer()
t.fit_on_texts(x_train)
x_train=t.texts_to_sequences(x_train)
x_test=t.texts_to_sequences(x_test)
voc_size=len(t.word_index)

max_words=300
x_train=pad_sequences(x_train, maxlen=max_words)
x_test=pad_sequences(x_test, maxlen=max_words)

batch_size=30
x_train2,y_train2=x_train[batch_size:],y_train[batch_size:]
x_val,y_val=x_train[:batch_size],y_train[:batch_size]

model=Sequential()
model.add(Embedding(voc_size+1, 512, input_length=max_words))
model.add(LSTM(100))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss="binary_crossentropy", metrics="accuracy")
model.fit(x_train2,y_train2, validation_data=(x_val,y_val),batch_size=batch_size, epochs=5)
y_pred=model.predict(x_test)
y_score=[1 if i>0.5 else 0 for i in y_pred]
score=model.evaluate(x_test,y_test)
print(score)