def summarize(self,input_path):
dataset_preprocessor = Preprocessor()
dataset_FeatureReducer = FeatureReducer()
dataset_WeightsHandler = WeightsHandler()
files = [f for f in os.listdir(input_path) if os.path.isfile(input_path + f)]
preprocessed_list = dataset_preprocessor.preprocess(files, input_path)
sentencelist = dataset_preprocessor.extract_sentences(files, input_path)
dataset_WeightsHandler.set_preprocessed_list(preprocessed_list)
dataset_WeightsHandler.set_sentence_list(sentencelist)
dataset_WeightsHandler.update_totfreq_dict()
dataset_WeightsHandler.replace_totfreq_dict(dataset_FeatureReducer.reduceFeatures(dataset_WeightsHandler.tot_freq_dict()))
dataset_WeightsHandler.generate_inv_doc_freq_dict(preprocessed_list)
dataset_WeightsHandler.generate_tot_weight_dict()
dataset_WeightsHandler.generate_STM()
vector_dict = dataset_WeightsHandler.sentence_weight_dict() #vector_dict[sentence]=vector
dataset_FeatureReducer.remove_features_with_zero_weight(vector_dict)
sentencelist_without_stopwords = dataset_preprocessor.remove_stop_words_from_sentencelist(sentencelist)
VectorSineRelationExtractor = SineRelationExtractor()
sine_matrix = VectorSineRelationExtractor.extract_sine_similarity(vector_dict)
synonym_assigner = SynonymAssigner()
synonym_dict = synonym_assigner.assign_synonyms(sentencelist_without_stopwords)
SentenceDissimilarityScorer = DissimilarityScorer()
dissimilarity_matrix = SentenceDissimilarityScorer.assign_dissimilarity_score(synonym_dict, sentencelist_without_stopwords)
final_score_matrix = SentenceDissimilarityScorer.multiply_sine(dissimilarity_matrix, sine_matrix)
SentenceRanker = NodeRanker()
scorelist_of_sentences= SentenceRanker.calculate_score_of_each_sentence(final_score_matrix)
ranked_indices = SentenceRanker.rank_nodes(scorelist_of_sentences)
for each_index in ranked_indices:
print sentencelist[each_index]
from utils.preprocessor import Preprocessor
import os
from sets.size import Size
from sets.intersections import Intersections
from sets.scorer import Scorer
from graphs.node_ranker import NodeRanker
from sets.distributed_ranks import RankDistributor
input_path = '/home/animesh/T-Sum/Data sets/Inception/'
files = [f for f in os.listdir(input_path) if os.path.isfile(input_path + f)]
prep = Preprocessor()
sentence_list = prep.extract_sentences(files, input_path)
preprocessed_words_in_each_sentence = []
for s in sentence_list:
preprocessed_words_in_each_sentence.append(prep.preprocess_sentence(s))
size = Size()
intersections = Intersections()
scorer = Scorer()
ranker = NodeRanker()
rank_counter_in_0_to_1 = RankDistributor()
size_of_sets = size.calculate_size_of_set(preprocessed_words_in_each_sentence)
number_of_intersections_of_each_sentence = intersections.count_itersections_of_each_set(preprocessed_words_in_each_sentence)
scores = scorer.score_sentences(number_of_intersections_of_each_sentence, size_of_sets)
normalised_scores = scorer.normalise_score(scores)
distributed_ranks = rank_counter_in_0_to_1.distribute_ranks(normalised_scores)