add conv sentiment classifier

%% Cell type:markdown id: tags:

# Convolutional Sentiment Classifier

%% Cell type:markdown id: tags:

In this notebook, we build a *convolutional* neural net to classify IMDB movie reviews by their sentiment.

%% Cell type:markdown id: tags:

#### Load dependencies

%% Cell type:code id: tags:

``` python

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

```

%% Cell type:markdown id: tags:

#### Set hyperparameters

%% Cell type:code id: tags:

``` python

# 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

```

%% Cell type:markdown id: tags:

#### Load data

%% Cell type:code id: tags:

``` python

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

```

%% Cell type:markdown id: tags:

#### Preprocess data

%% Cell type:code id: tags:

``` python

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)

```

%% Cell type:markdown id: tags:

#### Design neural network architecture

%% Cell type:code id: tags:

``` python

model = Sequential()

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

# CODE HERE

model.add(Dense(n_dense, activation='relu'))

model.add(Dropout(dropout))

model.add(Dense(1, activation='sigmoid'))

```

%% Cell type:code id: tags:

``` python

model.summary()

```

%% Cell type:markdown id: tags:

#### Configure model

%% Cell type:code id: tags:

``` python

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

```

%% Cell type:code id: tags:

``` python

modelcheckpoint = ModelCheckpoint(filepath=output_dir+"/weights.{epoch:02d}.hdf5")

if not os.path.exists(output_dir):

    os.makedirs(output_dir)

```

%% Cell type:markdown id: tags:

#### Train!

%% Cell type:code id: tags:

``` python

# 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])

```

%% Cell type:markdown id: tags:

#### Evaluate

%% Cell type:code id: tags:

``` python

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

```

%% Cell type:code id: tags:

``` python

y_hat = model.predict_proba(x_valid)

```

%% Cell type:code id: tags:

``` python

plt.hist(y_hat)

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

```

%% Cell type:code id: tags:

``` python

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

```

%% Cell type:code id: tags:

``` python

```