Keras.py

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Fri Dec  8 11:43:58 2017

@author: rhubner
"""
from sklearn.datasets import load_files
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.linear_model import SGDClassifier
import numpy as np
import random
import sys
import keras
from keras.datasets import reuters
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.preprocessing.text import Tokenizer

from keras.models import Sequential
from keras.layers import Dense

max_words = 10000
batch_size = 32
epochs = 5

print('Loading data...')
language_data = load_files(container_path='./HACKATHON_TEXT-FILES', 
                          load_content=True,
                          encoding='UTF-8',
                          shuffle=True)

x_train, x_test, y_train, y_test = train_test_split(language_data.data, language_data.target, 
                                                    test_size=0.33, random_state=random.randint(1,4294967295))



print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
print(" ")

num_classes = np.max(y_train) + 1
print(num_classes, 'classes')

print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

print('Convert class vector to binary class matrix '
      '(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)

print('Building model...')
model = Sequential()
model.add(Dense(512, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_split=0.1)
score = model.evaluate(x_test, y_test,
                       batch_size=batch_size, verbose=1)
print('Test score:', score[0])
print('Test accuracy:', score[1])