def initialize_models(src_corpus, trg_corpus):
transition_model = TransitionModel(src_corpus, trg_corpus)
translation_model = TranslationModel(src_corpus, trg_corpus)
return transition_model, translation_model
def initialize_models(src_corpus, trg_corpus):
prior_model = PriorModel(src_corpus, trg_corpus)
translation_model = TranslationModel(src_corpus, trg_corpus)
return prior_model, translation_model
])
len(word_count_de)
word_count_de.most_common()[:100]
word_count_de['<u>']
model_de.predict_next_word('<\s>')
max_de = 0
max_en = 0
for text_de, text_en in zip(texts_de[:n_text], texts_en[:n_text]):
max_de = max(max_de, len(split(text_de)))
max_en = max(max_en, len(split(text_en)))
print(max_de)
print(max_en)
de_en = TranslationModel(model_de, model_en, 11)
de_en.train(texts_de[:n_text], texts_en[:n_text], epochs=epochs_translation)
pd.DataFrame({'loss': de_en.history.history['loss']}).plot()
plt.yscale('log')
plt.grid()
plt.show(block=False)
i = 4000
target_text = texts_de[i]
target_text = 'ich aß einen apfel.'
target_text = 'du aßest einen apfel.'
target_text
texts_en[i]
de_en.predict_word_count(texts_en[i], length=20, ref=texts_de[i])