def get_tf_idf_scores(accu_path, input_data=None, vis=False):
try:
(code_book, graphlets, data) = input_data
except:
code_book, graphlets, data = utils.load_all_learning_files(accu_path)
"""BINARY COUNTING OF FEATURES:"""
feature_freq = (data != 0).sum(axis=0) # TF: document_frequencies
(N, f) = data.shape # Number of documents, and number of features
print "number of documents = %s, number of features = %s " % (N, f)
"""
## Inverse document frequency scores
## LONG HAND
# idf_scores=[]
# for i in feature_freq:
# try:
# idf_scores.append(math.log((N /float(i))))
# except:
# idf_scores.append(0)
"""
idf_scores = [(math.log((N / float(i)))) if i > 0 else 0 for i in feature_freq]
tf_idf_scores = np.array([[]])
for histogram in data:
#freq = 1+math.log(freq) if freq>0 else 0 #log normalisation of Term Frequency
foo = [idf_scores[cnt]*(math.log(1+freq)) for cnt, freq in enumerate(histogram)]
try:
tf_idf_scores = np.append(tf_idf_scores, np.array([foo]), axis=0)
except ValueError:
tf_idf_scores = np.array([foo])
print "tf-idf shape:", tf_idf_scores.shape
return tf_idf_scores
def run_topic_model(accu_path, n_iters, n_topics, create_images, dirichlet_params, class_thresh=0):
code_book, graphlets, data = utils.load_all_learning_files(accu_path)
dictionary_codebook = {}
try:
import pyLDAvis
dictionary_codebook = get_dic_codebook(code_book, graphlets, create_images)
except ImportError:
print "No module pyLDAvis. Cannot visualise topic model"
print "sum of all data:", data.shape, data.sum()
vocab = [ "{:20.0f}".format(hash).lstrip() for hash in list(code_book) ]
# print "vocab:", len(vocab)
doc_topic, topic_word = learn_topic_model(data, vocab, n_topics, n_iters, dictionary_codebook, dirichlet_params, class_thresh)
print " per document topic proportions: ", doc_topic.shape
print " per topic word distributions: ", topic_word.shape
return doc_topic, topic_word
