hanneshapke

sequence_input = Input(shape=(maxlen_text,))

x = Embedding(name='embedding_layer', 
              input_dim=max_words_to_keep, 
              output_dim=token_vec_size, 
              input_length=maxlen_text)(sequence_input)
x = Dropout(.20)(x)

x = Conv1D(64, 5, activation='relu', name='1-conv1d', padding='same')(x)
x = MaxPooling1D(pool_size=4)(x)

hanneshapke

hanneshapke

def get_conv_layer(model, layer_name):
    conv_layer = model.get_layer(layer_name)
    output_dim = conv_layer.output_shape[1]
    return conv_layer, output_dim

hanneshapke

def get_heatmap(model, layer_name, matrix, y_labels):

    # obtain probability of the label with the highest certainty
    network_output = model.get_output_at(0)[:, np.argmax(y_labels)]
    # obtain the output vector and its dimension of the convolutional layer we want to visualize
    conv_layer, layer_output_dim = get_conv_layer(model, layer_name)
    
    # Setting up the calculation of the gradients between the output and the conv layer. Will be executed in the iteration step
    grads = K.gradients(network_output, conv_layer.output)[0]
    # average the gradients across our samples (one sample) and all filters

hanneshapke

def norm_heatmap(heatmap): 
    # element-wise maximum calculation, basically setting all negative values to zero
    heatmap = np.maximum(heatmap, 0)
    # normalizing the heatmap to values between 0 and 1
    norm_heatmap = heatmap / np.max(heatmap)
    return norm_heatmap

hanneshapke

def plot_heatmap(heatmap, height_ratio=0.05):
        # calculating how often the vector should be repeated to display a height relative to the vector length
        repeat_vector_n_times = int(heatmap.shape[0] * height_ratio)
        plt.matshow([heatmap] * repeat_vector_n_times)

hanneshapke

def cstr(s, color='black'):
    return "<text style=\"color:{}\">{}</text>".format(color, s)

hanneshapke

def color(hvalue, threshold, max=1, cdefault='black', colors=['red', 'yellow', 'green', 'cyan', 'blue']):
    num_colors = len(colors)
    if hvalue < threshold:
        return cdefault
    for i, color in enumerate(colors):
        if hvalue > (max - (max - threshold) / num_colors * (i + 1)):
            return color

hanneshapke

def get_token_indices(model, layer_name, threshold, matrix, y_labels):
    heatmap = get_heatmap(model=model, layer_name=layer_name, matrix=matrix, y_labels=y_labels)
    _, output_dim = get_conv_layer(model, layer_name)

    # depending on the ration between the input and layer output shape, we need to calculate 
    # how many original tokens have contributed to the layer output
    dim_ratio = matrix.shape[1] / output_dim
    if dim_ratio < 1.5:
        window_size = 1
    else:

hanneshapke

def get_highlighted_tokens(tokens, matrix, model, layer_name, threshold, y_labels):
    indices = get_token_indices(model, layer_name, threshold, matrix, y_labels)
    
    ctokens = []
    for i, t in enumerate(tokens):
        if i in indices.keys():
            _color = color(indices[i], threshold=threshold)
            ctokens.append(cstr(t, color=_color))
        else:
            ctokens.append(t)