def main(): print("--------------------------------------") print("STARTTIME:", (datetime.datetime.now())) print("--------------------------------------") # getting data #locations = ctag.open_location_tags(USER_TAGS_FILE) #corpus = ctag.get_corpus([x.tags for x in locations.values()]) # getting data - way 2 locations = clocation.open_locations() users = cuser.open_users_posts_afile(USER_POSTS_FILE) print("Sampling users posts...") for key, a_user in users.items(): posts = [x for x in a_user.posts if (x.time > FILTER_TIME_S) and (x.time < FILTER_TIME_E)] users[key].posts = posts locations = clocation.fit_users_to_location(locations, users, "tags") corpus = ctag.get_location_posts_corpus(locations) vector, tag_name = clda.get_tag_vector(corpus) topic_word, doc_topic = clda.fit_lda(vector, tag_name, TOPIC_NUM) ccluster.output_topics(topic_word, doc_topic, tag_name, [x.lid for x in locations.values()], OUTPUT_TAG_TOPIC, OUTPUT_LOCATION_TOPIC) print("--------------------------------------") print("ENDTIME:", (datetime.datetime.now())) print("--------------------------------------")
def main(*argv): print("--------------------------------------") print("STARTTIME:", (datetime.datetime.now())) print("--------------------------------------") # set UNIXTIME global FILTER_TIME_S global FILTER_TIME_E if len(argv) > 0: FILTER_TIME_S = argv[0] FILTER_TIME_E = argv[1] # getting data locations = clocation.open_locations() users = cuser.open_users_posts_afile(USER_POSTS_FILE) # preporcessing. remove unqualified users removes = filter_users_timeperiod(users, FILTER_TIME_S, FILTER_TIME_E) sequences = ctrajectory.split_trajectory_byday([a_user.posts for a_user in users.values() if len(a_user.posts) != 0]) sequences = ctrajectory.remove_adjacent_location(sequences) sequences = ctrajectory.remove_short(sequences) removes = list(set(removes) | (set(users.keys()) - set([x[0].uid for x in sequences]))) for key in removes: del users[key] print(" remain users #:", len(users.keys())) locations = clocation.fit_users_to_location(locations, users, "uid") set_location_user_count(locations) coordinate = numpy.array([(float(x.lat), float(x.lng)) for x in locations.values()]) location_frequency = numpy.array([x.usercount for x in locations.values()]) # clustering locations cntr, u, u0, d, jm, p, fpc, membership = cfuzzy.cmeans_location(coordinate.T, CLUSTER_NUM, MAX_KTH, location_frequency, Y, e=ERROR, algorithm="kthCluster_LocationFrequency") locations = ccluster.fit_locations_membership(locations, u, locations.keys()) locations = ccluster.fit_locations_cluster(locations, membership, locations.keys()) # output result """ cpygmaps.output_clusters(\ [(float(x.lat), float(x.lng), str(x.cluster) + " >> " + x.lname + "(" + x.lid + ")>>u:" + str(u[x.cluster, i])) \ for i, x in enumerate(locations.values())], membership, CLUSTER_NUM, OUTPUT_MAP) output_representatives(coordinate, u, MAX_KTH) """ #ccluster.output_location_cluster(locations.values(), "cluster", OUTPUT_CLUSTER) print("--------------------------------------") print("ENDTIME:", (datetime.datetime.now())) print("--------------------------------------") return users, locations
def main(*argv): start_time = datetime.datetime.now() print("--------------------------------------") print("STARTTIME:", (datetime.datetime.now())) print("--------------------------------------") # set parameters global CLUSTER_NUM global MAX_KTH global GPS_WEIGHT global FILTER_TIME_S global FILTER_TIME_E global OUTPUT_MAP global OUTPUT_PATTERN if len(argv) > 0: CLUSTER_NUM = argv[0] MAX_KTH = argv[1] GPS_WEIGHT = argv[2] FILTER_TIME_S = argv[3] FILTER_TIME_E = argv[4] LOCATION_TOPIC = "./data/LocationTopic/LocationTopic_OCT_c35.txt" else: LOCATION_TOPIC = "./data/LocationTopic/LocationTopic_NOVDEC_c35.txt" OUTPUT_MAP = OUTPUT_MAP + str(CLUSTER_NUM) + "k" + str( MAX_KTH) + "w" + str(GPS_WEIGHT) OUTPUT_PATTERN = OUTPUT_PATTERN + str(CLUSTER_NUM) + "k" + str(MAX_KTH) # Getting data users, locations = locationclustering.main(FILTER_TIME_S, FILTER_TIME_E) location_id, doc_topic = ccluster.open_doc_topic(LOCATION_TOPIC) locations = ccluster.fit_locations_membership(locations, numpy.transpose(doc_topic), location_id, "semantic_mem") print(" users # :", len(users)) users = cuser.open_users_posts_afile(USER_POSTS_FILE) # Getting sequences of posts & locations #sequences = ctrajectory.split_trajectory([a_user.posts for a_user in users.values() if len(a_user.posts) != 0], SPLIT_DAY) sequences = ctrajectory.split_trajectory_byday( [a_user.posts for a_user in users.values() if len(a_user.posts) != 0]) #sequences = ctrajectory.remove_adjacent_location(sequences) #sequences = get_specific(sequences) #sequences = ctrajectory.remove_short(sequences) print(" remain users #:", len(set([x[0].uid for x in sequences]))) location_sequences, longest_len = ctrajectory.convertto_location_sequences( sequences, locations) spatial_array = ctrajectory.get_vector_array(location_sequences, longest_len) semantic_array = ctrajectory.get_vector_array(location_sequences, longest_len, "semantic_mem") u, u0, d, jm, p, fpc, center, membership = cfuzzy.sequences_clustering_i( "Location", spatial_array, CLUSTER_NUM, MAX_KTH, semantic_array, GPS_WEIGHT, e=ERROR, algorithm="2WeightedDistance") #ouput_pattern(sequences, location_sequences, u, membership) output_each_pattern(sequences, location_sequences, u, membership, 20) ctrajectory.output_clusters(sequences, membership, u, OUTPUT_PATTERN) """ll = count(sequences, location_sequences, u, membership, 39) tag = from_to(location_sequences, membership, 39, ll) tag.extend(from_to(location_sequences, membership, 39, [ll[1]] + [ll[0]])) tag.extend(from_to(location_sequences, membership, 39, [ll[0]] + [ll[0]])) tag.extend(from_to(location_sequences, membership, 39, [ll[1]] + [ll[1]])) f = open("./data/Result/Ana_39.txt", "a") f.write("\naboves:" + str(len(set(tag)))) f.close() """ print("--------------------------------------") print("ENDTIME:", (datetime.datetime.now()), ", SPEND:", datetime.datetime.now() - start_time) print("--------------------------------------") return location_sequences, spatial_array, semantic_array, u
def main(*argv): start_time = datetime.datetime.now() print("--------------------------------------") print("STARTTIME:", (datetime.datetime.now())) print("--------------------------------------") # set parameters global CLUSTER_NUM global MAX_KTH global GPS_WEIGHT global FILTER_TIME_S global FILTER_TIME_E global OUTPUT_MAP global OUTPUT_PATTERN if len(argv) > 0: CLUSTER_NUM = argv[0] MAX_KTH = argv[1] GPS_WEIGHT = argv[2] FILTER_TIME_S = argv[3] FILTER_TIME_E = argv[4] LOCATION_TOPIC = "./data/LocationTopic/LocationTopic_OCT_c35.txt" else: LOCATION_TOPIC = "./data/LocationTopic/LocationTopic_NOVDEC_c35.txt" OUTPUT_MAP = OUTPUT_MAP + str(CLUSTER_NUM) + "k" + str(MAX_KTH) + "w" + str(GPS_WEIGHT) OUTPUT_PATTERN = OUTPUT_PATTERN + str(CLUSTER_NUM) + "k" + str(MAX_KTH) # Getting data users, locations = locationclustering.main(FILTER_TIME_S, FILTER_TIME_E) location_id, doc_topic = ccluster.open_doc_topic(LOCATION_TOPIC) locations = ccluster.fit_locations_membership(locations, numpy.transpose(doc_topic), location_id, "semantic_mem") print(" users # :", len(users)) users = cuser.open_users_posts_afile(USER_POSTS_FILE) # Getting sequences of posts & locations #sequences = ctrajectory.split_trajectory([a_user.posts for a_user in users.values() if len(a_user.posts) != 0], SPLIT_DAY) sequences = ctrajectory.split_trajectory_byday([a_user.posts for a_user in users.values() if len(a_user.posts) != 0]) #sequences = ctrajectory.remove_adjacent_location(sequences) #sequences = get_specific(sequences) #sequences = ctrajectory.remove_short(sequences) print(" remain users #:", len(set([x[0].uid for x in sequences]))) location_sequences, longest_len = ctrajectory.convertto_location_sequences(sequences, locations) spatial_array = ctrajectory.get_vector_array(location_sequences, longest_len) semantic_array = ctrajectory.get_vector_array(location_sequences, longest_len, "semantic_mem") u, u0, d, jm, p, fpc, center, membership = cfuzzy.sequences_clustering_i("Location", spatial_array, CLUSTER_NUM, MAX_KTH, semantic_array, GPS_WEIGHT, e = ERROR, algorithm="2WeightedDistance") #ouput_pattern(sequences, location_sequences, u, membership) output_each_pattern(sequences, location_sequences, u, membership, 20) ctrajectory.output_clusters(sequences, membership, u, OUTPUT_PATTERN) """ll = count(sequences, location_sequences, u, membership, 39) tag = from_to(location_sequences, membership, 39, ll) tag.extend(from_to(location_sequences, membership, 39, [ll[1]] + [ll[0]])) tag.extend(from_to(location_sequences, membership, 39, [ll[0]] + [ll[0]])) tag.extend(from_to(location_sequences, membership, 39, [ll[1]] + [ll[1]])) f = open("./data/Result/Ana_39.txt", "a") f.write("\naboves:" + str(len(set(tag)))) f.close() """ print("--------------------------------------") print("ENDTIME:", (datetime.datetime.now()), ", SPEND:", datetime.datetime.now() - start_time) print("--------------------------------------") return location_sequences, spatial_array, semantic_array, u