mlp_full = SentimentNetwork(reviews[:-1000],labels[:-1000],min_count=0,polarity_cutoff=0,learning_rate=0.01)
mlp_full.train(reviews[:-1000],labels[:-1000])
def get_most_similar_words(focus = "horrible"):
    most_similar = Counter()

    for word in mlp_full.word2index.keys():
        most_similar[word] = np.dot(mlp_full.weights_0_1[mlp_full.word2index[word]],mlp_full.weights_0_1[mlp_full.word2index[focus]])

    return most_similar.most_common()

get_most_similar_words("excellent")
get_most_similar_words("terrible")

import matplotlib.colors as colors

words_to_visualize = list()
for word, ratio in pos_neg_ratios.most_common(500):
    if(word in mlp_full.word2index.keys()):
        words_to_visualize.append(word)

for word, ratio in list(reversed(pos_neg_ratios.most_common()))[0:500]:
    if(word in mlp_full.word2index.keys()):
        words_to_visualize.append(word)

pos = 0
neg = 0

colors_list = list()
vectors_list = list()
for word in words_to_visualize:
    if word in pos_neg_ratios.keys():
        vectors_list.append(mlp_full.weights_0_1[mlp_full.word2index[word]])
        if(pos_neg_ratios[word] > 0):
            pos+=1
            colors_list.append("#00ff00")
        else:
            neg+=1
            colors_list.append("#000000")

from sklearn.manifold import TSNE
tsne = TSNE(n_components=2, random_state=0)
words_top_ted_tsne = tsne.fit_transform(vectors_list)

p = figure(tools="pan,wheel_zoom,reset,save",
           toolbar_location="above",
           title="vector T-SNE for most polarized words")

source = ColumnDataSource(data=dict(x1=words_top_ted_tsne[:,0],
                                    x2=words_top_ted_tsne[:,1],
                                    names=words_to_visualize,
                                    color=colors_list))

p.scatter(x="x1", y="x2", size=8, source=source, fill_color="color")

word_labels = LabelSet(x="x1", y="x2", text="names", y_offset=6,
                  text_font_size="8pt", text_color="#555555",
                  source=source, text_align='center')
p.add_layout(word_labels)

show(p)

# green indicates positive words, black indicates negative words