def loadFeatures(catalog):
featuresfile = cf.data_dir + "context_content_features-small.csv"
input_file = csv.DictReader(open(featuresfile, encoding='utf-8'))
for event in input_file:
model.assignGenre(catalog, event)
model.addEvent(catalog, event)
model.updateHour_Tree(catalog, event)
def loadEvents(analyzer):
"""
Carga los datos de los archivos CSV en el modelo
"""
context = cf.data_dir + 'context_content_features-small.csv'
input_file = csv.DictReader(open(context, encoding="utf-8"),
delimiter=",")
# "artist_id","track_id","user_id","id"
for line in input_file:
filtered = {
"instrumentalness": float(line["instrumentalness"]),
"liveness": float(line["liveness"]),
"speechiness": float(line["speechiness"]),
"danceability": float(line["danceability"]),
"valence": float(line["valence"]),
"loudness": float(line["loudness"]),
"tempo": float(line["tempo"]),
"acousticness": float(line["acousticness"]),
"energy": float(line["energy"]),
"mode": float(line["mode"]),
"key": float(line["key"]),
"artist_id": line["artist_id"].replace(" ", ''),
"track_id": line["track_id"].lower(),
"user_id": line["user_id"],
"id": line["id"],
"created_at": line["created_at"] # dt.datetime.strptime(line["created_at"], "%Y-%m-%d %H:%M:%S").time()
}
model.addEvent(analyzer, filtered)
model.addArtist(analyzer, filtered)
model.addTrack(analyzer, filtered)
model.addDate(analyzer, filtered)
return analyzer
def loadContext(catalog, contextcontefile):
contextcontentfile = cf.data_dir + contextcontefile
input_file = csv.DictReader(open(contextcontentfile, encoding="utf-8"),
delimiter=",")
for event in input_file:
model.addEvent(catalog, event)
return catalog
def loadData(analyzer, eventsfile):
"""
Carga los datos de los archivos CSV en el modelo
"""
# delta_time = -1.0
# delta_memory = -1.0
# tracemalloc.start()
# start_time = getTime()
# start_memory = getMemory()
eventsfile = cf.data_dir + eventsfile
input_file = csv.DictReader(open(eventsfile, encoding="utf-8"),
delimiter=",")
for event in input_file:
model.addEvent(analyzer, event)
# stop_memory = getMemory()
# stop_time = getTime()
# tracemalloc.stop()
# delta_time = stop_time - start_time
# delta_memory = deltaMemory(start_memory, stop_memory)
return analyzer, 0, 0
def loadEvents(analyzer):
crimesfile = cf.data_dir + 'context_content_features/context_content_features-small.csv'
input_file = csv.DictReader(open(crimesfile, encoding="utf-8"),
delimiter=",")
for crime in input_file:
model.addEvent(analyzer, crime)
return analyzer
def loadEvents(analyzer):
"""
Carga los eventos del archivo csv.
"""
eventsfile = cf.data_dir + 'subsamples-small/context_content_features-small.csv'
input_file = csv.DictReader(open(eventsfile, encoding='utf-8'))
for event in input_file:
model.addEvent(analyzer, event)
def loadEvents(analyzer):
"""
Carga los eventos del archivo csv. Por cada evento se indica al
modelo que debe adicionarlo al analizador
"""
eventsfile = cf.data_dir + 'subsamples-small/context_content_features-small.csv'
input_file = csv.DictReader(open(eventsfile, encoding='utf-8'))
for event in input_file:
model.addEvent(analyzer, event)
def loadEvents(analyzer, file):
"""
Itera cada elemento del archivo csv
"""
analysis_file = cf.data_dir + file
input_file = csv.DictReader(open(analysis_file, encoding="utf-8"),
delimiter=",")
for event in input_file:
model.addEvent(analyzer, event)
def loadData(analyzer, crimesfile):
"""
Carga los datos de los archivos CSV en el modelo
"""
crimesfile = cf.data_dir + crimesfile
input_file = csv.DictReader(open(crimesfile, encoding="utf-8"),
delimiter=",")
for event in input_file:
model.addEvent(analyzer, event)
def loadData(catalogo):
"""
Carga los datos de los archivos CSV en el modelo
"""
files = cf.data_dir + 'context_content_features-small.csv'
input_file = csv.DictReader(open(files, encoding="utf-8"),
delimiter=",")
files2 = cf.data_dir + 'sentiment_values.csv'
input_file2 = csv.DictReader(open(files, encoding="utf-8"),
delimiter=",")
for evento in input_file:
model.addEvent(catalogo, evento)
for hashtag in input_file2:
model.createHashtag(catalogo, hashtag)
return catalogo
def loadData(catalog):
TSfile = cf.data_dir + 'user_track_hashtag_timestamp-small.csv'
ts_sub = csv.DictReader(open(TSfile, encoding='utf-8'))
for register in ts_sub:
model.createmap2file(catalog, register, 'track')
HVfile = cf.data_dir + 'sentiment_values.csv'
sv_file = csv.DictReader(open(HVfile, encoding='utf-8'))
for pair in sv_file:
model.addSentiment(catalog, pair)
Dfile = cf.data_dir + 'context_content_features-small.csv'
main_file = csv.DictReader(open(Dfile, encoding='utf-8'))
for event in main_file:
model.addEvent(catalog, event)
def loadData(analyzer, hashtag, sentiments, context):
"""
Carga los datos de los archivos CSV en el modelo
"""
hashtagsfile = cf.data_dir + hashtag
hashtag_file = csv.DictReader(open(hashtagsfile, encoding="utf-8"),
delimiter=",")
contextfile = cf.data_dir + context
context_file = csv.DictReader(open(contextfile, encoding="utf-8"),
delimiter=",")
sentimentsfile = cf.data_dir + sentiments
sentiments_file = csv.DictReader(open(sentimentsfile, encoding="utf-8"),
delimiter=",")
for event in context_file:
model.addEvent(analyzer, event)
posEvent = 1
for hastag in hashtag_file:
posEvent = model.addHashtag(analyzer, hastag, posEvent)
model.crearArboles(analyzer)
for sentiment in sentiments_file:
model.addSentiment(analyzer, sentiment)
return analyzer
def loadEvent(analyzer):
eventfile = cf.data_dir + 'context_content_features-small.csv'
input_file = csv.DictReader(open(eventfile, encoding="utf-8"),
delimiter=",")
for event in input_file:
model.addEvent(analyzer, event)
