Quora Insincere Questions Classification

def F1(y_true, y_pred):
    def recall(y_true, y_pred):
        """Recall metric.

        Only computes a batch-wise average of recall.

        Computes the recall, a metric for multi-label classification of
        how many relevant items are selected.
        """
        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
        recall = true_positives / (possible_positives + K.epsilon())
        return recall

    def precision(y_true, y_pred):
        """Precision metric.

        Only computes a batch-wise average of precision.

        Computes the precision, a metric for multi-label classification of
        how many selected items are relevant.
        """
        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
        precision = true_positives / (predicted_positives + K.epsilon())
        return precision
    precision = precision(y_true, y_pred)
    recall = recall(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall+K.epsilon()))

model.compile(
        loss='binary_crossentropy',
        optimizer=adam,metrics=[F1])
    print(model.summary())

class Attention(Layer):
    def __init__(self, step_dim,
                 W_regularizer=None, b_regularizer=None,
                 W_constraint=None, b_constraint=None,
                 bias=True, **kwargs):
        self.supports_masking = True
        # self.init = initializations.get('glorot_uniform')
        self.init = initializers.get('glorot_uniform')

        self.W_regularizer = regularizers.get(W_regularizer)
        self.b_regularizer = regularizers.get(b_regularizer)

        self.W_constraint = constraints.get(W_constraint)
        self.b_constraint = constraints.get(b_constraint)

        self.bias = bias
        self.step_dim = step_dim
        self.features_dim = 0
        super(Attention, self).__init__(**kwargs)

    def build(self, input_shape):
        assert len(input_shape) == 3

        self.W = self.add_weight((input_shape[-1],),
                                 initializer=self.init,
                                 name='{}_W'.format(self.name),
                                 regularizer=self.W_regularizer,
                                 constraint=self.W_constraint)
        self.features_dim = input_shape[-1]

        if self.bias:
            self.b = self.add_weight((input_shape[1],),
                                     initializer='zero',
                                     name='{}_b'.format(self.name),
                                     regularizer=self.b_regularizer,
                                     constraint=self.b_constraint)
        else:
            self.b = None

        self.built = True

    def compute_mask(self, input, input_mask=None):
        # do not pass the mask to the next layers
        return None

    def call(self, x, mask=None):
        input_shape = K.int_shape(x)

        features_dim = self.features_dim
        # step_dim = self.step_dim
        step_dim = input_shape[1]

        eij = K.reshape(K.dot(K.reshape(x, (-1, features_dim)), K.reshape(self.W, (features_dim, 1))), (-1, step_dim))

        if self.bias:
            eij += self.b[:input_shape[1]]

        eij = K.tanh(eij)

        a = K.exp(eij)

        # apply mask after the exp. will be re-normalized next
        if mask is not None:
            # Cast the mask to floatX to avoid float64 upcasting in theano
            a *= K.cast(mask, K.floatx())

        # in some cases especially in the early stages of training the sum may be almost zero
        # and this results in NaN's. A workaround is to add a very small positive number ε to the sum.
        a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())

        a = K.expand_dims(a)
        weighted_input = x * a
    	# print weigthted_input.shape
        return K.sum(weighted_input, axis=1)

    def compute_output_shape(self, input_shape):
        # return input_shape[0], input_shape[-1]
    	return input_shape[0], self.features_dim
# end Attention

def load_imdb_sentiment_analysis_dataset(data_path, seed=123):
    """Loads the IMDb movie reviews sentiment analysis dataset.

    # Arguments
        data_path: string, path to the data directory.
        seed: int, seed for randomizer.

    # Returns
        A tuple of training and validation data.
        Number of training samples: 25000
        Number of test samples: 25000
        Number of categories: 2 (0 - negative, 1 - positive)

    # References
        Mass et al., http://www.aclweb.org/anthology/P11-1015

        Download and uncompress archive from:
        http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz
    """
    imdb_data_path = os.path.join(data_path, 'aclImdb')

    # Load the training data
    train_texts = []
    train_labels = []
    for category in ['pos', 'neg']:
        train_path = os.path.join(imdb_data_path, 'train', category)
        for fname in sorted(os.listdir(train_path)):
            if fname.endswith('.txt'):
                with open(os.path.join(train_path, fname)) as f:
                    train_texts.append(f.read())
                train_labels.append(0 if category == 'neg' else 1)

    # Load the validation data.
    test_texts = []
    test_labels = []
    for category in ['pos', 'neg']:
        test_path = os.path.join(imdb_data_path, 'test', category)
        for fname in sorted(os.listdir(test_path)):
            if fname.endswith('.txt'):
                with open(os.path.join(test_path, fname)) as f:
                    test_texts.append(f.read())
                test_labels.append(0 if category == 'neg' else 1)

    # Shuffle the training data and labels.
    random.seed(seed)
    random.shuffle(train_texts)
    random.seed(seed)
    random.shuffle(train_labels)

    return ((train_texts, np.array(train_labels)),
            (test_texts, np.array(test_labels)))

from keras.callbacks import EarlyStopping
early_stopping = EarlyStopping(monitor='val_loss', patience=3)

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=train_epochs,
          validation_data=(x_val, y_val),verbose = 2,
          callbacks=[early_stopping])

keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-8, kappa=1-1e-8)