import keras
from keras.datasets import imdb
import numpy as np
from keras import models
from keras import layers
from keras import optimizers
from keras import regularizers


np.random.seed(4747) # to replicate the results. 

def vectorize_sequences(sequences, dimension=10000):
    # Create an all-zero matrix of shape (len(sequences), dimension)
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1.  # set specific indices of results[i] to 1s
    return results

def main(reg_param=0.001,n0_of_epochs=5, bat_size=512, act='relu', no_of_h_nodes = 4 , validate=1):
	
	(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000,seed=100)
	# Our vectorized training data
	x_train = vectorize_sequences(train_data)
	# Our vectorized test data
	x_test = vectorize_sequences(test_data)
	# Our vectorized labels
	y_train = np.asarray(train_labels).astype('float32')
	y_test = np.asarray(test_labels).astype('float32')

	model = models.Sequential()
	
	# modify to add layers with regularizer and activation function
	model.add()

#	 modify to add optimizer, loss function and metric
	model.compile()
	#model.summary() # to see the summary of the model built

# Biuld the model
		output = model.fit()

	# Evaluate the model with test data
		accuracy = model.evaluate()
	
	print('Test accuracy')
	print(score[1])