def word_detector(blob_text):
keyword_detector = RakunDetector(hyperparameters)
keywords = keyword_detector.find_keywords(blob_text, input_type="text")
#print(type(keywords))
keyword_detector.verbose = False
words = [i for i, j in keywords]
#print("Keywords identified are: ", words)
#keyword_detector.visualize_network()
return (words)
from mrakun import RakunDetector
from nltk.stem import WordNetLemmatizer
from nltk.corpus import stopwords
hyperparameters = {"edit_distance_threshold":3,
"num_keywords" : 10,
"pair_diff_length":2,
"stopwords" : stopwords.words('english'),
"bigram_count_threshold":2,
"lemmatizer" : WordNetLemmatizer(),
"num_tokens":[1]}
keyword_detector = RakunDetector(hyperparameters)
example_data = "../datasets/wiki20/docsutf8/7183.txt"
keywords = keyword_detector.find_keywords(example_data)
print(keywords)
keyword_detector.visualize_network()
keyword_detector.verbose = False
keyword_detector.validate_on_corpus("../datasets/Schutz2008")