#CS84: word2vec project


from __future__ import print_function
import os
import numpy as np
np.random.seed(1337) #re-seed generator

from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.utils.np_utils import to_categorical
from keras.layers import Dense, Input, Flatten, Dropout
from keras.layers import Conv1D, MaxPooling1D, Embedding
from keras.models import Model
import collections, numpy, sys, re

def loadGloveEmbeddings():
    #Load Glove, a model of words to numbers
    # Stores a dictionary of words, with numbers corresponding
    print('Indexing word vectors.')
    BASE_DIR = '/home/student/newsgroup' #where glove file is
    GLOVE_DIR = BASE_DIR + '/'
    GLOVE_DIR = BASE_DIR + '/glove.6B/'#accesses glove file
    embeddings_index = {} #opens Glove
    f = open(os.path.join(GLOVE_DIR, 'glove.6B.100d.txt'))
    for line in f:
        values = line.split()
        word = values[0]#sets the word to 0th value in array
        coefs = np.asarray(values[1:], dtype='float32')
        embeddings_index[word] = coefs
    #index mapping words in the embeddings set
    #to their embedding vector
    f.close()
    return embeddings_index


embeddings_index = loadGloveEmbeddings() #opens Glove

print('Found %s word vectors.' % len(embeddings_index))
# Loaded Glove.
#embeddings_index is a map. ex: 'cat' => array(100)

def loadbooks():
    filename= "bothcanonfanon.txt"
    books = []
    with open(filename) as f:
        for line in f: #splits each line at pipe
            books.append([n for n in line.strip().split('|')])
    booktexts = []     #string text
    bookisfanon = []
    for book in books:
        canonfanon,ident,text = book[0],book[1],book[2]
        #canonfanon = 0th book
        #identification = 1th book
        #text = 2th book
        text = re.sub(r'[^a-zA-Z ]+','', text)
        text = text.lower()
        #makes all lower and cleans up by taking out
        booktexts.append(text)
        bookisfanon.append(1 if canonfanon=='fanon' else 0)
    # Converts to One-Hot encoding
    y_isfanon = to_categorical(bookisfanon)
    return (booktexts,y_isfanon) #bookisfanon)

(booktexts,y_isfanon) = loadbooks()


test_text = raw_input("Input test text: ")
test_text = [test_text]

corpi = [booktexts, test_text]

def create_embedding_matrix(EMBEDDING_DIM, MAX_NB_WORDS, word_index):
    print('Preparing embedding matrix.')
    # prepare embedding matrix
    nb_words = min(MAX_NB_WORDS, len(word_index))
    embedding_matrix = np.zeros((nb_words + 1, EMBEDDING_DIM))
    for word, i in word_index.items():
        if i > MAX_NB_WORDS:
            continue
        embedding_vector = embeddings_index.get(word)
        if embedding_vector is not None: # words not found in embedding index will be all-zeros.
            embedding_matrix[i] = embedding_vector
    return (nb_words, embedding_matrix)

MAX_SEQUENCE_LENGTH = 1000

def create_tokenizer_and_embedding(MAX_SEQUENCE_LENGTH, train):
    MAX_NB_WORDS = 5000 #sets up for padding
    EMBEDDING_DIM = 100
    tokenizer = Tokenizer(nb_words=MAX_NB_WORDS)
    tokenizer.fit_on_texts(train)
    (nb_words, embedding_matrix) = create_embedding_matrix(EMBEDDING_DIM, MAX_NB_WORDS, tokenizer.word_index)
    # load pre-trained word embeddings into an Embedding layer
    # set trainable = False so as to keep the embeddings fixed
    embedding_layer = Embedding(nb_words + 1, EMBEDDING_DIM, weights=[embedding_matrix], input_length=MAX_SEQUENCE_LENGTH, trainable=False)
    return (tokenizer, embedding_layer)

(tokenizer, embedding_layer) = create_tokenizer_and_embedding(MAX_SEQUENCE_LENGTH, corpi[0])



def create_sequences(MAX_SEQUENCE_LENGTH, tokenizer, corpi):
    MAX_NB_WORDS = 5000 #sets up for padding
    EMBEDDING_DIM = 100
    padded_sequences = []
    for corpus in corpi:
        corpi_sequence = tokenizer.texts_to_sequences(corpus)
        padded_sequences.append(pad_sequences(corpi_sequence, maxlen=MAX_SEQUENCE_LENGTH))
    return padded_sequences

padded_sequences = create_sequences(MAX_SEQUENCE_LENGTH, tokenizer, corpi)

#Sequences has the index of each word
#instead of the string of each word
#length is still the same

#tokenizes to get rid of repeats
#word_index = tokenizer.word_index
# print('Found %s unique tokens.' % len(word_index))

data = padded_sequences[0] #the books, not the user input


VALIDATION_SPLIT = 0.3 #splits in train and test
# train is 70%, test 30%
indices = np.arange(data.shape[0])
np.random.shuffle(indices)
data = data[indices]
labels = y_isfanon[indices]
nb_validation_samples = int(VALIDATION_SPLIT * data.shape[0])

#sets train and test(data and labels)
x_train = data[:-nb_validation_samples]
y_train = labels[:-nb_validation_samples]
x_val = data[-nb_validation_samples:]
y_val = labels[-nb_validation_samples:]

x_test = padded_sequences[1]

print('Training model.')

# train a 1D convnet with global maxpooling
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32')

embedded_sequences = embedding_layer(sequence_input)

x = Conv1D(32, 5, activation='relu')(embedded_sequences)
x = MaxPooling1D(3)(x)
x = Dropout(0.2)(x)

x = Conv1D(32, 5, activation='tanh')(x)
x = MaxPooling1D(3)(x)
x = Dropout(0.2)(x)

x = Conv1D(32, 5, activation='tanh')(x)
x = Dropout(0.2)(x)

x = Conv1D(32, 5, activation='tanh')(x)
x = MaxPooling1D(3)(x)
x = Dropout(0.2)(x)

x = Conv1D(32, 5, activation='tanh')(x)
x = Dropout(0.2)(x)

x = Conv1D(32, 5, activation='tanh')(x)
x = MaxPooling1D(3)(x)
x = Flatten()(x)
x = Dropout(0.2)(x)
x = Dense(32, activation='softmax')(x)
preds = Dense(len(labels[0]), activation='softmax')(x)

model = Model(sequence_input, preds)
model.compile(loss='mean_squared_error',
              optimizer='adamax',
#optimizes net and minimizes losses
              metrics=['acc'])


#learning, running model
model.fit(x_train, y_train, validation_data=(x_val, y_val), nb_epoch=300, batch_size=256)


def predictText(textstr):
    textstr = re.sub(r'[^a-zA-Z ]', '', textstr)
    testcorpus = [[textstr]]
    test_sequences = create_sequences(MAX_SEQUENCE_LENGTH, tokenizer, testcorpus)
    return model.predict(test_sequences, batch_size= 256, verbose=0)