#!/usr/bin/env python
# coding: utf-8

# Credits: Forked from [deep-learning-keras-tensorflow](https://github.com/leriomaggio/deep-learning-keras-tensorflow) by Valerio Maggio

# Recurrent Neural networks
# =====

# ### RNN  

# <img src ="imgs/rnn.png" width="20%">

# A recurrent neural network (RNN) is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior.

# In[ ]:


keras.layers.recurrent.SimpleRNN(output_dim, 
                                 init='glorot_uniform', inner_init='orthogonal', activation='tanh', 
                                 W_regularizer=None, U_regularizer=None, b_regularizer=None, 
                                 dropout_W=0.0, dropout_U=0.0)


# #### Backprop Through time  

# Contrary to feed-forward neural networks, the RNN is characterized by the ability of encoding longer past information, thus very suitable for sequential models. The BPTT extends the ordinary BP algorithm to suit the recurrent neural
# architecture.

# <img src ="imgs/rnn2.png" width="45%">

# In[3]:


get_ipython().run_line_magic('matplotlib', 'inline')


# In[1]:


import numpy as np
import pandas as pd
import theano
import theano.tensor as T
import keras 
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.preprocessing import image
from __future__ import print_function
import numpy as np
import matplotlib.pyplot as plt

from keras.datasets import imdb
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras.preprocessing import sequence
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM, GRU, SimpleRNN
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.cross_validation import train_test_split
from keras.layers.core import Activation, TimeDistributedDense, RepeatVector
from keras.callbacks import EarlyStopping, ModelCheckpoint


# #### IMDB sentiment classification task

# This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. 
# 
# IMDB provided a set of 25,000 highly polar movie reviews for training, and 25,000 for testing. 
# 
# There is additional unlabeled data for use as well. Raw text and already processed bag of words formats are provided. 
# 
# http://ai.stanford.edu/~amaas/data/sentiment/

# #### Data Preparation - IMDB

# In[4]:


max_features = 20000
maxlen = 100  # cut texts after this number of words (among top max_features most common words)
batch_size = 32

print("Loading data...")
(X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features, test_split=0.2)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')

print('Example:')
print(X_train[:1])

print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)


# #### Model building 

# In[7]:


print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
model.add(SimpleRNN(128))  
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy', optimizer='adam', class_mode="binary")

print("Train...")
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=1, validation_data=(X_test, y_test), show_accuracy=True)


# ### LSTM  

# A LSTM network is an artificial neural network that contains LSTM blocks instead of, or in addition to, regular network units. A LSTM block may be described as a "smart" network unit that can remember a value for an arbitrary length of time. 
# 
# Unlike traditional RNNs, an Long short-term memory network is well-suited to learn from experience to classify, process and predict time series when there are very long time lags of unknown size between important events.

# <img src ="imgs/gru.png" width="60%">

# In[ ]:


keras.layers.recurrent.LSTM(output_dim, init='glorot_uniform', inner_init='orthogonal', 
                            forget_bias_init='one', activation='tanh', 
                            inner_activation='hard_sigmoid', 
                            W_regularizer=None, U_regularizer=None, b_regularizer=None, 
                            dropout_W=0.0, dropout_U=0.0)


# ### GRU  

# Gated recurrent units are a gating mechanism in recurrent neural networks. 
# 
# Much similar to the LSTMs, they have fewer parameters than LSTM, as they lack an output gate.

# In[ ]:


keras.layers.recurrent.GRU(output_dim, init='glorot_uniform', inner_init='orthogonal', 
                           activation='tanh', inner_activation='hard_sigmoid', 
                           W_regularizer=None, U_regularizer=None, b_regularizer=None, 
                           dropout_W=0.0, dropout_U=0.0)


# ### Your Turn! - Hands on Rnn

# In[ ]:


print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))

# Play with those! try and get better results!
#model.add(SimpleRNN(128))  
#model.add(GRU(128))  
#model.add(LSTM(128))  

model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy', optimizer='adam', class_mode="binary")

print("Train...")
model.fit(X_train, y_train, batch_size=batch_size, 
          nb_epoch=4, validation_data=(X_test, y_test), show_accuracy=True)
score, acc = model.evaluate(X_test, y_test, batch_size=batch_size, show_accuracy=True)
print('Test score:', score)
print('Test accuracy:', acc)


# # Sentence Generation using RNN(LSTM)

# In[ ]:


from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy as np
import random
import sys

path = get_file('nietzsche.txt', origin="https://s3.amazonaws.com/text-datasets/nietzsche.txt")
text = open(path).read().lower()
print('corpus length:', len(text))

chars = sorted(list(set(text)))
print('total chars:', len(chars))
char_indices = dict((c, i) for i, c in enumerate(chars))
indices_char = dict((i, c) for i, c in enumerate(chars))

# cut the text in semi-redundant sequences of maxlen characters
maxlen = 40
step = 3
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
    sentences.append(text[i: i + maxlen])
    next_chars.append(text[i + maxlen])
print('nb sequences:', len(sentences))

print('Vectorization...')
X = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):
    for t, char in enumerate(sentence):
        X[i, t, char_indices[char]] = 1
    y[i, char_indices[next_chars[i]]] = 1


# build the model: a single LSTM
print('Build model...')
model = Sequential()
model.add(LSTM(128, input_shape=(maxlen, len(chars))))
model.add(Dense(len(chars)))
model.add(Activation('softmax'))

optimizer = RMSprop(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)


def sample(preds, temperature=1.0):
    # helper function to sample an index from a probability array
    preds = np.asarray(preds).astype('float64')
    preds = np.log(preds) / temperature
    exp_preds = np.exp(preds)
    preds = exp_preds / np.sum(exp_preds)
    probas = np.random.multinomial(1, preds, 1)
    return np.argmax(probas)

# train the model, output generated text after each iteration
for iteration in range(1, 60):
    print()
    print('-' * 50)
    print('Iteration', iteration)
    model.fit(X, y, batch_size=128, nb_epoch=1)

    start_index = random.randint(0, len(text) - maxlen - 1)

    for diversity in [0.2, 0.5, 1.0, 1.2]:
        print()
        print('----- diversity:', diversity)

        generated = ''
        sentence = text[start_index: start_index + maxlen]
        generated += sentence
        print('----- Generating with seed: "' + sentence + '"')
        sys.stdout.write(generated)

        for i in range(400):
            x = np.zeros((1, maxlen, len(chars)))
            for t, char in enumerate(sentence):
                x[0, t, char_indices[char]] = 1.

            preds = model.predict(x, verbose=0)[0]
            next_index = sample(preds, diversity)
            next_char = indices_char[next_index]

            generated += next_char
            sentence = sentence[1:] + next_char

            sys.stdout.write(next_char)
            sys.stdout.flush()
        print()