Convolutional Sentiment Classifier

In [1]:

    

import keras
from keras.datasets import imdb
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import Dense, Dropout, Embedding
from keras.layers import SpatialDropout1D, Conv1D, GlobalMaxPooling1D # new! 
from keras.callbacks import ModelCheckpoint
import os
from sklearn.metrics import roc_auc_score 
import matplotlib.pyplot as plt 
%matplotlib inline


    

    




Using TensorFlow backend.

In [2]:

    

# output directory name:
output_dir = 'model_output/conv'

# training:
epochs = 4
batch_size = 128

# vector-space embedding: 
n_dim = 64
n_unique_words = 5000 
max_review_length = 400
pad_type = trunc_type = 'pre'
drop_embed = 0.2 # new!

# convolutional layer architecture:
n_conv = 256 # filters, a.k.a. kernels
k_conv = 3 # kernel length

# dense layer architecture: 
n_dense = 256
dropout = 0.2


    

In [3]:

    

(x_train, y_train), (x_valid, y_valid) = imdb.load_data(num_words=n_unique_words) # removed n_words_to_skip


    

In [4]:

    

x_train = pad_sequences(x_train, maxlen=max_review_length, padding=pad_type, truncating=trunc_type, value=0)
x_valid = pad_sequences(x_valid, maxlen=max_review_length, padding=pad_type, truncating=trunc_type, value=0)


    

In [5]:

    

model = Sequential()
model.add(Embedding(n_unique_words, n_dim, input_length=max_review_length)) 

model.add(SpatialDropout1D(drop_embed))
model.add(Conv1D(n_conv, k_conv))
model.add(GlobalMaxPooling1D())

model.add(Dense(n_dense, activation='relu'))
model.add(Dropout(dropout))
model.add(Dense(1, activation='sigmoid'))


    

In [6]:

    

model.summary()


    

    




_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding_1 (Embedding)      (None, 400, 64)           320000    
_________________________________________________________________
spatial_dropout1d_1 (Spatial (None, 400, 64)           0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 398, 256)          49408     
_________________________________________________________________
global_max_pooling1d_1 (Glob (None, 256)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 256)               65792     
_________________________________________________________________
dropout_1 (Dropout)          (None, 256)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 257       
=================================================================
Total params: 435,457
Trainable params: 435,457
Non-trainable params: 0
_________________________________________________________________

In [7]:

    

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


    

In [8]:

    

modelcheckpoint = ModelCheckpoint(filepath=output_dir+"/weights.{epoch:02d}.hdf5")
if not os.path.exists(output_dir):
    os.makedirs(output_dir)


    

In [9]:

    

# 89.1% validation accuracy in epoch 2
# ...with second convolutional layer is essentially the same at 89.0%
model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_valid, y_valid), callbacks=[modelcheckpoint])


    

    




Train on 25000 samples, validate on 25000 samples
Epoch 1/4
 2944/25000 [==>...........................] - ETA: 144s - loss: 0.6934 - acc: 0.5034





    




---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-9-49eaa607d295> in <module>()
      1 # 89.1% validation accuracy in epoch 2
      2 # ...with second convolutional layer is essentially the same at 89.0%
----> 3 model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_valid, y_valid), callbacks=[modelcheckpoint])

/opt/conda/lib/python3.6/site-packages/keras/models.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
    865                               class_weight=class_weight,
    866                               sample_weight=sample_weight,
--> 867                               initial_epoch=initial_epoch)
    868 
    869     def evaluate(self, x, y, batch_size=32, verbose=1,

/opt/conda/lib/python3.6/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
   1596                               initial_epoch=initial_epoch,
   1597                               steps_per_epoch=steps_per_epoch,
-> 1598                               validation_steps=validation_steps)
   1599 
   1600     def evaluate(self, x, y,

/opt/conda/lib/python3.6/site-packages/keras/engine/training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
   1181                     batch_logs['size'] = len(batch_ids)
   1182                     callbacks.on_batch_begin(batch_index, batch_logs)
-> 1183                     outs = f(ins_batch)
   1184                     if not isinstance(outs, list):
   1185                         outs = [outs]

/opt/conda/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
   2271         updated = session.run(self.outputs + [self.updates_op],
   2272                               feed_dict=feed_dict,
-> 2273                               **self.session_kwargs)
   2274         return updated[:len(self.outputs)]
   2275 

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    893     try:
    894       result = self._run(None, fetches, feed_dict, options_ptr,
--> 895                          run_metadata_ptr)
    896       if run_metadata:
    897         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1122     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1123       results = self._do_run(handle, final_targets, final_fetches,
-> 1124                              feed_dict_tensor, options, run_metadata)
   1125     else:
   1126       results = []

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1319     if handle is None:
   1320       return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1321                            options, run_metadata)
   1322     else:
   1323       return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1325   def _do_call(self, fn, *args):
   1326     try:
-> 1327       return fn(*args)
   1328     except errors.OpError as e:
   1329       message = compat.as_text(e.message)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1304           return tf_session.TF_Run(session, options,
   1305                                    feed_dict, fetch_list, target_list,
-> 1306                                    status, run_metadata)
   1307 
   1308     def _prun_fn(session, handle, feed_dict, fetch_list):

KeyboardInterrupt: 

In [ ]:

    

model.load_weights(output_dir+"/weights.01.hdf5") # zero-indexed


    

In [ ]:

    

y_hat = model.predict_proba(x_valid)


    

In [ ]:

    

plt.hist(y_hat)
_ = plt.axvline(x=0.5, color='orange')


    

In [ ]:

    

"{:0.2f}".format(roc_auc_score(y_valid, y_hat)*100.0)


    

In [ ]: