def load_file_sentences(filepath, filename):
""" Loads sentences of a file into a list and converts everything to
lower case. """
# Read file as string first
f = open(filepath, 'r')
text = f.read()
f.close()
# Strip the newlines
text = filter(lambda x: x != '\n', text)
# Now use nltks method to read the sentences
sentences = sent_tokenize(text)
# convert everything to lower case
sentences = map(str.lower, sentences)
"""sentences = [(s.lower(), filename) for s in sentences]"""
# Create segments by clustering. Let's say 3 segments per text.
# Similarity metric shall be cosine.
fs = create_feature_space(sentences)
vectors = [vectorize(fs, sent) for sent in sentences]
compute_similarity_matrix(vectors, cosine_similarity, filename+".similarities")
if (len(vectors) < 2):
# There are not enough sentences to cluster, so we'll just use the same segment for all
# of them. Only happens once in the given project data anyway.
segments = [0]*len(vectors)
else:
segments = cluster_sentences(filename+".similarities", __cluto_bin, 2)
# Stitch it all together
return zip(sentences, [filename]*len(sentences), segments)
def ordering_preprocessing(collection_name):
""" Given a collection name, will create the themes for the collection and
return them, thus enabling to order the themes/sentences.
"""
print("Starting Preprocessing")
collection_path = __collection_root + collection_name
topic_file = __project_root + 'topicwords/' + collection_name + '.ts'
print("Loading and ranking sentences")
sentences = rank_by_tweight(collection_path, topic_file)
sentences = extract_dates(sentences)
# We need to vectorize all the sentences to cluster them.
print("Vectorizing Sentences")
list_of_sents = [sent for ((sent, f, d, s), w) in sentences]
fs = create_feature_space(list_of_sents)
vectors = vectorize_sentence_list(fs, list_of_sents)
# Now we can cluster into themes
print("Creating Themes")
compute_similarity_matrix(vectors, cosine_similarity, './similarity_matrix')
clusters = cluster_sentences('./similarity_matrix', __cluto_bin, 5)
themes = make_themes_from_clusters(sentences, clusters)
return themes
