import keras
import numpy as np
from keras.datasets import imdb
from matplotlib import pyplot as plt
from keras.models import Model
from keras.layers import Flatten,Dense,Input,Conv1D,MaxPooling1D,Dropout,GlobalAveragePooling1D
from keras.models import Model
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence

top_words = 5000

(x_train,y_train),(x_test,y_test) = imdb.load_data(num_words=top_words)


def data_analysis():
    print("Training data shape:")
    print(f"X_train:{x_train.shape}")
    print(f"Y_train:{y_train.shape}")

    print("Average length review:")
    lengths = [len(x) for x in x_train]
    print(f"Mean:{np.mean(lengths)} std:{np.std(lengths)}")
    plt.boxplot(lengths)
    plt.title(f"Mean:{np.mean(lengths)} std:{np.std(lengths)}")
    plt.show()


#data_analysis()

max_words = 500
x_train = sequence.pad_sequences(x_train,maxlen=max_words)
x_test = sequence.pad_sequences(x_test,maxlen=max_words)

def test_dense():
    inputs = Input((max_words,))
    h = Embedding(top_words,128,input_length=max_words)(inputs)
    h = Flatten()(h)
    h = Dense(256,activation='relu')(h)
    outputs = Dense(1,activation='sigmoid')(h)
    model = Model(inputs=inputs,outputs=outputs)
    model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
    model.summary()
    history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=20, batch_size=128, verbose=2)
    scores = model.evaluate(x_test, y_test, verbose=0)
    print("Accuracy: %.2f%%" % (scores[1]*100))
    # Plot training & validation accuracy values
    plt.plot(history.history['acc'])
    plt.plot(history.history['val_acc'])
    plt.title('Model accuracy')
    plt.ylabel('Accuracy')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Test'], loc='upper left')
    plt.show()

    # Plot training & validation loss values
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('Model loss')
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Test'], loc='upper left')
    plt.show()


def test_cnn():
    inputs = Input((max_words,))
    h = Embedding(top_words,128,input_length=max_words)(inputs)
    h = Conv1D(filters=8,kernel_size=3,padding='same',activation='relu')(h)
    h = MaxPooling1D(pool_size=2)(h)
    h = Conv1D(filters=16,kernel_size=3,padding='same',activation='relu')(h)
    h = GlobalAveragePooling1D()(h)
    h = Dropout(0.5)(h)
    outputs = Dense(1,activation='sigmoid')(h)

    model = Model(inputs=inputs,outputs=outputs)
    model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
    model.summary()
    history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=20, batch_size=128)
    scores = model.evaluate(x_test, y_test, verbose=0)
    print("Accuracy: %.2f%%" % (scores[1]*100))
    # Plot training & validation accuracy values
    plt.plot(history.history['acc'])
    plt.plot(history.history['val_acc'])
    plt.title('Model accuracy')
    plt.ylabel('Accuracy')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Test'], loc='upper left')
    plt.show()

    # Plot training & validation loss values
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('Model loss')
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Test'], loc='upper left')
    plt.show()


#test_dense()
test_cnn()