def _main():
config = get_config(CONFIG_PATH)
check_ssl_expire_date(config)
get_twitter(config)
memo = Memo(config)
if memo.is_exist_today_memo():
print("Today's memo file has been created already.")
else:
print("Today's memo file does not exist.\n"
"The latest memo will be copied.")
try:
memo.copy_memo_from_newest()
except MemoError as err:
print('Failed to copy memo file: {}'.format(err))
exit(1)
print("Did you fill out yesterday's attendance?")
memo.open_excel()
memo.open_website_url()
memo.open_today_memo()
exit(0)
def test_twitter():
class loc(object):
pass
loc.lat = '37.7833'
loc.lng = '-122.4167'
response = get_twitter("San Francisco", loc)
date = response[0][0]['date']
text = response[0][1]['text']
assert((date != None and text != None) == True) # "test_twitter test 1"
loc.lat = '40.7127'
loc.lng = '-74.0059'
response = get_twitter("New York", loc)
date = response[0][0]['date']
text = response[0][1]['text']
assert((date != None and text != None) == True) # "test_twitter test 2"
def evaluate_model(model_name="als"):
"""evaluate the model by cross-validation"""
# train the model based off input params
artists, users, plays = get_twitter()
# create a model from the input data
model = get_model(model_name)
# split data_set to train set and testing set
train, testing = train_test_split(plays)
# evaluation
result = precision_at_k(model=model, train_user_items=train, test_user_items=testing)
print('precision@k = ', result)
def calculate_similar_artists(output_filename, model_name="als"):
""" generates a list of similar artists in lastfm by utiliizing the 'similar_items'
api of the models """
artists, users, plays = get_twitter()
# create a model from the input data
model = get_model(model_name)
# if we're training an ALS based model, weight input for last.fm
# by bm25
if issubclass(model.__class__, AlternatingLeastSquares):
# lets weight these models by bm25weight.
logging.debug("weighting matrix by bm25_weight")
plays = bm25_weight(plays, K1=100, B=0.8)
# also disable building approximate recommend index
model.approximate_recommend = False
# this is actually disturbingly expensive:
plays = plays.tocsr()
logging.debug("training model %s", model_name)
start = time.time()
model.fit(plays)
logging.debug("trained model '%s' in %0.2fs", model_name, time.time() - start)
# write out similar artists by popularity
start = time.time()
logging.debug("calculating top artists")
user_count = np.ediff1d(plays.indptr)
to_generate = sorted(np.arange(len(artists)), key=lambda x: -user_count[x])
# write out as a TSV of artistid, otherartistid, score
logging.debug("writing similar items")
with tqdm.tqdm(total=len(to_generate)) as progress:
with codecs.open(output_filename, "w", "utf8") as o:
for artistid in to_generate:
artist = artists[artistid]
for other, score in model.similar_items(artistid, 11):
o.write("%s\t%s\t%s\n" % (artist, artists[other], score))
progress.update(1)
logging.debug("generated similar artists in %0.2fs", time.time() - start)
def calculate_recommendations(output_filename, model_name="als"):
""" Generates artist recommendations for each user in the dataset """
# train the model based off input params
artists, users, plays = get_twitter()
# create a model from the input data
model = get_model(model_name)
# if we're training an ALS based model, weight input for last.fm
# by bm25
if issubclass(model.__class__, AlternatingLeastSquares):
# lets weight these models by bm25weight.
logging.debug("weighting matrix by bm25_weight")
plays = bm25_weight(plays, K1=100, B=0.8)
# also disable building approximate recommend index
model.approximate_similar_items = False
# this is actually disturbingly expensive:
plays = plays.tocsr()
logging.debug("training model %s", model_name)
start = time.time()
model.fit(plays)
logging.debug("trained model '%s' in %0.2fs", model_name, time.time() - start)
# generate recommendations for each user and write out to a file
start = time.time()
user_plays = plays.T.tocsr()
with tqdm.tqdm(total=len(users)) as progress:
with codecs.open(output_filename, "w", "utf8") as o:
for userid, username in enumerate(users):
for artistid, score in model.recommend(userid, user_plays):
o.write("%s\t%s\t%s\n" % (username, artists[artistid], score))
progress.update(1)
logging.debug("generated recommendations in %0.2fs", time.time() - start)
def _lookup_twitter(city, location):
return twitter.get_twitter(city, location)
