import numpy as np
import pandas as pd
import tensorflow as tf

df_fake_news = pd.read_csv('./Fake.csv')
df_true_news = pd.read_csv('./True.csv')

df_fake_news['fake'] = 1
df_true_news['fake'] = 0

df_news = pd.concat([df_fake_news, df_true_news])
df_news['date'] = pd.to_datetime(df_news['date'], errors='coerce')
df_news['Year'] = df_news['date'].dt.year
df_news['Month'] = df_news['date'].dt.month
df_news['text'] = df_news['title'] + df_news['text']
df_news.drop(labels=['title','subject','date','Year','Month'], axis=1, inplace=True)

# Split the dataset into training and testing
from sklearn.model_selection import train_test_split

train_sentences, val_sentences, train_labels, val_labels=train_test_split(
    df_news['text'].to_numpy(), df_news['fake'].to_numpy(),
    test_size=0.2, random_state=42)

# Vectorization (Tokenization)
max_vocab_length = 10000
max_length = 418

from tensorflow.keras.layers.experimental.preprocessing import TextVectorization
text_vectorizer = TextVectorization(max_tokens=max_vocab_length,
                                    output_mode='int',
                                    output_sequence_length=max_length)
text_vectorizer.adapt(train_sentences)

# Creating an Embedding using an Embedding Layer
from tensorflow.keras import layers
embedding = layers.Embedding(input_dim=max_vocab_length,
                             output_dim=128,
                             embeddings_initializer='uniform',
                             input_length=max_length)

# Modelling with LSTM, and use a Dense layer as the output
from tensorflow.keras import layers
inputs = layers.Input(shape=(1,), dtype='string')
x = text_vectorizer(inputs)
x = embedding(x)
x = layers.LSTM(64)(x)
outputs = layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(inputs, outputs, name='model_LSTM')

model.compile(loss='binary_crossentropy',
              optimizer=tf.keras.optimizers.Adam(),
              metrics=['accuracy'])

model_history = model.fit(train_sentences,
                          train_labels,
                          epochs=5,
                          validation_data=(val_sentences, val_labels))

# save our model to disk
model.save('./model')