This is source code for Text Classification for Different Datasets CNN based on the code from
Text Classification, Part I – Convolutional Networks
# -*- coding: utf-8 -*-
import os
from bs4 import BeautifulSoup
def clean_str(string):
return string.strip().lower()
def get_only_text_from_html_doc(page):
"""
return the title and the text of the article
"""
soup = BeautifulSoup(page, "lxml")
text = ' '.join(map(lambda p: p.text, soup.find_all('p')))
return soup.title.text + " " + text
texts=[]
labels=[]
i=0
topdir="C:\\Users\\files_for_classification"
for dirpath, dirnames, files in os.walk(topdir):
for name in files:
print (name)
print (dirpath)
print (dirnames)
with open(dirpath + "\\" + name, "r", encoding="utf8" ) as f:
page = f.read()
txt=get_only_text_from_html_doc(page)
texts.append(clean_str(txt))
if "text_mining" in dirpath :
labels.append (0)
else :
labels.append (1)
i=i+1
print (labels)
import numpy as np
import os
os.environ['KERAS_BACKEND']='tensorflow'
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
from keras.layers import Conv1D, MaxPooling1D, Embedding, Merge, Dropout
from keras.models import Model
MAX_SEQUENCE_LENGTH = 1000
MAX_NB_WORDS = 20000
EMBEDDING_DIM = 100
VALIDATION_SPLIT = 0.2
print ("START")
tokenizer = Tokenizer(nb_words=MAX_NB_WORDS)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
word_index = tokenizer.word_index
print('Found %s unique tokens.' % len(word_index))
data = pad_sequences(sequences, maxlen=MAX_SEQUENCE_LENGTH)
labels = to_categorical(np.asarray(labels))
print('Shape of data tensor:', data.shape)
print('Shape of label tensor:', labels.shape)
indices = np.arange(data.shape[0])
np.random.shuffle(indices)
data = data[indices]
labels = labels[indices]
nb_validation_samples = int(VALIDATION_SPLIT * data.shape[0])
x_train = data[:-nb_validation_samples]
y_train = labels[:-nb_validation_samples]
x_val = data[-nb_validation_samples:]
y_val = labels[-nb_validation_samples:]
print('Number of positive and negative reviews in traing and validation set ')
print (y_train.sum(axis=0))
print (y_val.sum(axis=0))
GLOVE_DIR = "C:\\Users\\pythonrunfiles"
embeddings_index = {}
f = open(os.path.join(GLOVE_DIR, 'glove.6B.100d.txt'), encoding="utf-8")
for line in f:
values = line.split()
word = values[0]
coefs = np.asarray(values[1:], dtype='float32')
embeddings_index[word] = coefs
f.close()
print('Total %s word vectors in Glove 6B 100d.' % len(embeddings_index))
embedding_matrix = np.random.random((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items():
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
embedding_layer = Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True)
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
l_cov1= Conv1D(128, 5, activation='relu')(embedded_sequences)
l_pool1 = MaxPooling1D(5)(l_cov1)
l_cov2 = Conv1D(128, 5, activation='relu')(l_pool1)
l_pool2 = MaxPooling1D(5)(l_cov2)
l_cov3 = Conv1D(128, 5, activation='relu')(l_pool2)
l_pool3 = MaxPooling1D(35)(l_cov3) # global max pooling
l_flat = Flatten()(l_pool3)
l_dense = Dense(128, activation='relu')(l_flat)
preds = Dense(2, activation='softmax')(l_dense) # was 2 instead 11
model = Model(sequence_input, preds)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['acc'])
print("model fitting - simplified convolutional neural network")
model.summary()
print (x_train)
print (y_train)
model.fit(x_train, y_train, validation_data=(x_val, y_val),
nb_epoch=1, batch_size=128) #epoch was 10
embedding_matrix = np.random.random((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items():
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
embedding_layer = Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True)
# applying a more complex convolutional approach
convs = []
filter_sizes = [3,4,5]
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
for fsz in filter_sizes:
l_conv = Conv1D(nb_filter=128,filter_length=fsz,activation='relu')(embedded_sequences)
l_pool = MaxPooling1D(5)(l_conv)
convs.append(l_pool)
l_merge = Merge(mode='concat', concat_axis=1)(convs)
l_cov1= Conv1D(128, 5, activation='relu')(l_merge)
l_pool1 = MaxPooling1D(5)(l_cov1)
l_cov2 = Conv1D(128, 5, activation='relu')(l_pool1)
l_pool2 = MaxPooling1D(30)(l_cov2)
l_flat = Flatten()(l_pool2)
l_dense = Dense(128, activation='relu')(l_flat)
preds = Dense(2, activation='softmax')(l_dense)
model = Model(sequence_input, preds)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['acc'])
print("model fitting - more complex convolutional neural network")
model.summary()
model.fit(x_train, y_train, validation_data=(x_val, y_val),
nb_epoch=30, batch_size=50)