def main():
text_file = "Chapter01/sherlock_holmes.txt"
text = read_text_file(text_file)
#sherlock_data = Image.open("Chapter08/sherlock.png")
#sherlock_mask = np.array(sherlock_data)
create_wordcloud(text, compile_stopwords_list_frequency(text),
"Chapter08/sherlock_wc.png")
def main():
text = read_text_file("Chapter01/sherlock_holmes.txt")
sentences = divide_into_sentences_nltk(text)
model = SentenceTransformer('bert-base-nli-mean-tokens')
sentence_embeddings = model.encode(["the beautiful lake"])
print("Sentence embeddings:")
print(sentence_embeddings)
def visualize_verbs(text_file):
text = read_text_file(text_file)
doc = nlp(text)
verb_dict = {"Inf": 0, "Past": 0, "Present": 0}
for token in doc:
if (token.tag_ == "VB"):
verb_dict["Inf"] = verb_dict["Inf"] + 1
if (token.tag_ in past_tags):
verb_dict["Past"] = verb_dict["Past"] + 1
if (token.tag_ in present_tags):
verb_dict["Present"] = verb_dict["Present"] + 1
plt.bar(range(len(verb_dict)),
list(verb_dict.values()),
align='center',
color=["red", "green", "blue"])
plt.xticks(range(len(verb_dict)), list(verb_dict.keys()))
plt.show()
def get_sherlock_holmes_noun_chunks():
text = read_text_file("Chapter01/sherlock_holmes_1.txt")
text = preprocess_text(text)
doc = nlp(text)
for noun_chunk in doc.noun_chunks:
print(noun_chunk.text)
def get_sentences(filename):
sherlock_holmes_text = read_text_file(filename)
sherlock_holmes_text = preprocess_text(sherlock_holmes_text)
sentences = divide_into_sentences_nltk(sherlock_holmes_text)
return sentences