def segment_driver(driver_id):
''' this generated the segments in settings.SEGMENTS_FOLDER[1] '''
da = DataAccess()
for ride_id_minus_1, ride in enumerate(da.get_rides(driver_id)):
ride_id = ride_id_minus_1 + 1
if da.skip_segment(driver_id, ride_id):
continue
# apply the Ramer-Douglas-Peucker algorithm
ride = [p + [i] for i, p in enumerate(smoothen(ride))] # enrich with timestamp
ride = rdp(ride, epsilon=10)
lengths = [util.euclidian_distance(ride[i-1], ride[i]) for i in xrange(1, len(ride))]
times = [ride[i][2] - ride[i-1][2] for i in xrange(1, len(ride))]
angles = [util.get_angle(ride[i-2], ride[i-1], ride[i]) for i in xrange(2, len(ride))]
# bucket the values
lengths = util.bucket(np.log(lengths), 25, [2.2,8]) # [int(l) for l in lengths]
times = util.bucket(np.log(times), 20, [1,5.5]) # [int(t) for t in times]
angles = util.bucket(angles, 30, [0,180]) # [int(a) for a in angles]
# write results
da.write_ride_segments(driver_id, ride_id, lengths, times, angles)
logging.info('finished segmenting driver %s' % driver_id)
def get_data_heading(model_id, driver_id, repeat, test=False, moving_average_window=3, stops=False, version=1):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
if test:
raise Exception
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train # used for training
set2 = driver_test + other_test # used for testing
set1 = [heading.get_ride_heading(ride, variations=True, \
moving_average_window=moving_average_window, stops=stops, version=version) for ride in set1]
set2 = [util.get_list_string(heading.get_ride_heading(ride, \
moving_average_window=moving_average_window, stops=stops, version=version)) for ride in set2]
set1 = list(itertools.chain(*set1))
set1 = [util.get_list_string(r) for r in set1]
vectorizer = CountVectorizer(min_df=2, ngram_range=(1,15), max_df=1000000)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_heading(model_id,
driver_id,
repeat,
test=False,
moving_average_window=3,
stops=False,
version=1):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
if test:
raise Exception
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train # used for training
set2 = driver_test + other_test # used for testing
set1 = [heading.get_ride_heading(ride, variations=True, \
moving_average_window=moving_average_window, stops=stops, version=version) for ride in set1]
set2 = [util.get_list_string(heading.get_ride_heading(ride, \
moving_average_window=moving_average_window, stops=stops, version=version)) for ride in set2]
set1 = list(itertools.chain(*set1))
set1 = [util.get_list_string(r) for r in set1]
vectorizer = CountVectorizer(min_df=2, ngram_range=(1, 15), max_df=1000000)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def save_threads(youtube: YouTube,
da: DataAccess,
from_vid: str,
dry_run: bool = True):
for video in da.gen_all_videos_in_order(from_vid):
vid = video["id"]
vtitle = video["snippet"]["title"]
print()
print(f"Processing {vtitle}...")
if da.have_comments_for_video(vid):
print(f'We\'ve already got comments for "{vtitle}".')
print("Skipping...")
continue
if not dry_run:
threads = youtube.get_comment_threads_for_video(vid)
with open(os.path.join(ROOT_DIR, "db", "commentThreads",
f"{vid}.json"),
mode="w") as f:
f.write(json.dumps(threads))
else:
print("\t(Dry run)")
print(f'Threads for "{vtitle}" saved.')
print()
print("------------------------------------------------------------")
# Give a little delay between batches.
# - DOS paranoia.
sleep(1)
def export_video_ids_json(self):
da = DataAccess()
videos = da.get_all_videos(sort=True)
vids = [video["id"] for video in videos]
with open(os.path.join(self.export_dir, "video_ids.txt"), mode="w") as f:
f.write(json.dumps(vids, indent=2))
def test_model_heading(model_id, driver_id, Model, get_data, repeat):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
set1 = list(da.get_rides(driver_id)) # first half of the train set
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
seed=seed)) # second half of the train set
moving_average_window = 6 if get_data == get_data_heading_v2 else 3
set1 = [heading.get_ride_heading(ride, variations=True, \
moving_average_window=moving_average_window) for ride in set1]
set2 = [heading.get_ride_heading(ride, variations=True, \
moving_average_window=moving_average_window) for ride in set2]
set1 = [[util.get_list_string(r) for r in four_pack] for four_pack in set1]
set2 = [[util.get_list_string(r) for r in four_pack] for four_pack in set2]
vectorizer = CountVectorizer(min_df=2, ngram_range=(1, 15), max_df=1000000)
vectorizer.fit([r[0] for r in set1])
rides = [[vectorizer.transform([r])[0] for r in four_pack]
for four_pack in set1]
other_rides = [[vectorizer.transform([r])[0] for r in four_pack]
for four_pack in set2]
other_rides = list(itertools.chain(*other_rides))
rides = np.array(rides)
trainY = [1] * settings.BIG_CHUNK_TEST * 4 * repeat + [
0
] * settings.BIG_CHUNK_TEST * 4 * repeat
kf = KFold(200,
n_folds=settings.FOLDS,
shuffle=True,
random_state=driver_id)
predictions = ['bug'] * 200
for train_fold, test_fold in kf:
trainX = rides[train_fold]
trainX = scipy.sparse.vstack(
list(itertools.chain(*trainX)) * repeat + \
other_rides
)
testX = scipy.sparse.vstack([r[0] for r in rides[test_fold]])
assert (trainX.shape[0] == len(trainY))
assert (testX.shape[0] == settings.SMALL_CHUNK_TEST)
model = Model(trainX, trainY, driver_id)
fold_predictions = model.predict(testX)
for i, v in enumerate(test_fold):
predictions[v] = fold_predictions[i]
predictions = np.array(predictions)
if settings.ENABLE_CACHE:
util.cache_results(Model, get_data, driver_id, True, predictions,
repeat)
return driver_id, predictions
def export_video_ids_tsv(self):
da = DataAccess()
videos = da.get_all_videos(sort=True)
with open(
os.path.join(self.export_dir, "vids.tsv"), mode="w", encoding="utf-8"
) as f:
f.write(f"video_id\tvideo_title\n")
for video in videos:
vtitle = video["snippet"]["title"]
f.write(f"{video['id']}\t{vtitle}\n")
def evaluate_iex_stocks():
print('Started evaluating IEX stocks ...', flush=True)
filename = 'sandp_top_250'
os.environ["IEX_API_KEY"] = config.data_iex_api_key
data_access = DataAccess(filename)
global iex_stocks
iex_stocks = evaluate_stocks('iex', f'{filename}.csv', data_access)
def test_model_heading(model_id, driver_id, Model, get_data, repeat):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
set1 = list(da.get_rides(driver_id)) # first half of the train set
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, seed=seed)) # second half of the train set
moving_average_window = 6 if get_data == get_data_heading_v2 else 3
set1 = [heading.get_ride_heading(ride, variations=True, \
moving_average_window=moving_average_window) for ride in set1]
set2 = [heading.get_ride_heading(ride, variations=True, \
moving_average_window=moving_average_window) for ride in set2]
set1 = [[util.get_list_string(r) for r in four_pack] for four_pack in set1]
set2 = [[util.get_list_string(r) for r in four_pack] for four_pack in set2]
vectorizer = CountVectorizer(min_df=2, ngram_range=(1,15), max_df=1000000)
vectorizer.fit([r[0] for r in set1])
rides = [[vectorizer.transform([r])[0] for r in four_pack] for four_pack in set1]
other_rides = [[vectorizer.transform([r])[0] for r in four_pack] for four_pack in set2]
other_rides = list(itertools.chain(*other_rides))
rides = np.array(rides)
trainY = [1] * settings.BIG_CHUNK_TEST * 4 * repeat + [0] * settings.BIG_CHUNK_TEST * 4 * repeat
kf = KFold(200, n_folds=settings.FOLDS, shuffle=True, random_state=driver_id)
predictions = ['bug'] * 200
for train_fold, test_fold in kf:
trainX = rides[train_fold]
trainX = scipy.sparse.vstack(
list(itertools.chain(*trainX)) * repeat + \
other_rides
)
testX = scipy.sparse.vstack([r[0] for r in rides[test_fold]])
assert(trainX.shape[0] == len(trainY))
assert(testX.shape[0] == settings.SMALL_CHUNK_TEST)
model = Model(trainX, trainY, driver_id)
fold_predictions = model.predict(testX)
for i, v in enumerate(test_fold):
predictions[v] = fold_predictions[i]
predictions = np.array(predictions)
if settings.ENABLE_CACHE:
util.cache_results(Model, get_data, driver_id, True, predictions, repeat)
return driver_id, predictions
def test_sum_expeneses_two_rows(self):
da = DataAccess(database=TEST_DB)
da.insert(**TEST_ROW_1)
da.insert(**TEST_ROW_2)
sum_result = da.sum_expenses()
da.close()
self.assertAlmostEqual(sum_result, 26.99)
def get_data_fft(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train
set2 = driver_test + other_test
if version == 1:
set1 = [util.fft(ride) for ride in set1]
set2 = [util.fft(ride) for ride in set2]
else:
set1 = [util.fft_strip(ride) for ride in set1]
set2 = [util.fft_strip(ride) for ride in set2]
return np.array(set1), np.array(set2)
def get_data_g_forces_v6(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id)) # first half of the train set
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
seed=seed)) # second half of the train set
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train # used for training
set2 = driver_test + other_test # used for testing
set1 = [util.get_g_forces_v4(ride, version=version) for ride in set1]
set2 = [util.get_g_forces_v4(ride, version=version) for ride in set2]
vectorizer = CountVectorizer(min_df=1, ngram_range=(1, 20))
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_basic_accel(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train
set2 = driver_test + other_test
set1 = [util.build_features_acc(ride, version=version) for ride in set1]
set2 = [util.build_features_acc(ride, version=version) for ride in set2]
return np.array(set1), np.array(set2)
def get_data_acc4acc(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train
set2 = driver_test + other_test
set1 = [
util.get_acc4acc_words(ride, step=3, version=version) for ride in set1
]
set2 = [
util.get_acc4acc_words(ride, step=3, version=version) for ride in set2
]
max_ngram = 15 if version == 1 else 20
vectorizer = CountVectorizer(min_df=1, ngram_range=(1, max_ngram))
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def del_user():
if request.method == 'GET':
uuid = session['user']['user_id']
if DA.delete_user_from_uuid(uuid):
user = session['user']['user_id']
session.pop('user', None)
return redirect(url_for('auth.login'))
else:
flash("Errore nella cancellazione del profilo!")
def get_videos_for_pitems(self, pitems: List) -> List:
print("Requesting videos for playlist items.")
vids: List[str] = [
pitem["contentDetails"]["videoId"] for pitem in pitems
]
data = []
# Filter out videos we already have.
da = DataAccess()
vids = [vid for vid in vids if not da.have_video(vid)]
for items in gen_resources_for_ids(
self.youtube.videos,
vids,
part="snippet,statistics",
):
data += items
return data
def segment_driver(driver_id):
''' this generated the segments in settings.SEGMENTS_FOLDER[1] '''
da = DataAccess()
for ride_id_minus_1, ride in enumerate(da.get_rides(driver_id)):
ride_id = ride_id_minus_1 + 1
if da.skip_segment(driver_id, ride_id):
continue
# apply the Ramer-Douglas-Peucker algorithm
ride = [p + [i]
for i, p in enumerate(smoothen(ride))] # enrich with timestamp
ride = rdp(ride, epsilon=10)
lengths = [
util.euclidian_distance(ride[i - 1], ride[i])
for i in xrange(1, len(ride))
]
times = [ride[i][2] - ride[i - 1][2] for i in xrange(1, len(ride))]
angles = [
util.get_angle(ride[i - 2], ride[i - 1], ride[i])
for i in xrange(2, len(ride))
]
# bucket the values
lengths = util.bucket(np.log(lengths), 25,
[2.2, 8]) # [int(l) for l in lengths]
times = util.bucket(np.log(times), 20,
[1, 5.5]) # [int(t) for t in times]
angles = util.bucket(angles, 30, [0, 180]) # [int(a) for a in angles]
# write results
da.write_ride_segments(driver_id, ride_id, lengths, times, angles)
logging.info('finished segmenting driver %s' % driver_id)
def get_data_segment_angles(model_id,
driver_id,
repeat,
test=False,
segment_version=1,
extra=((1, 1), 2)):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
ngram_range, min_df = extra
if test:
set1 = list(da.get_rides_segments(driver_id, version=segment_version))
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK,
segments=True,
version=segment_version)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed))
other_test = list(
da.get_random_rides(settings.SMALL_CHUNK,
driver_id,
segments=True,
version=segment_version))
set1 = driver_train + other_train
set2 = driver_test + other_test
# create features for each (segment, angle, segment) tuple
set1 = [[
'%s_%s_%s' % (d[0][i - 1], d[1][i - 1], d[0][i])
for i in xrange(1, len(d[0]))
] for d in set1]
set2 = [[
'%s_%s_%s' % (d[0][i - 1], d[1][i - 1], d[0][i])
for i in xrange(1, len(d[0]))
] for d in set2]
set1 = [util.get_list_string(d) for d in set1]
set2 = [util.get_list_string(d) for d in set2]
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_g_forces_v1(model_id, driver_id, repeat, test=False, min_df=1, ngram_range=(1,10), digitize=0):
def process(ride, digitize):
g_forces = util.get_g_forces(ride)
if digitize:
g_forces = np.digitize(g_forces, range(0, 800, digitize))
return util.get_list_string(g_forces)
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id)) # first half of the train set
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, seed=seed)) # second half of the train set
else:
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train # used for training
set2 = driver_test + other_test # used for testing
set1 = [process(ride, digitize) for ride in set1]
set2 = [process(ride, digitize) for ride in set2]
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_movements_accel(model_id, driver_id, repeat, test=False, step=3, tf=False, extra=((1,15),2), version=1):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
ngram_range, min_df = extra
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, segments=False, seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK, segments=False)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, segments=False, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id, segments=False))
set1 = driver_train + other_train
set2 = driver_test + other_test
set1 = [util.build_features4(r, step=step, version=version) for r in set1]
set2 = [util.build_features4(r, step=step, version=version) for r in set2]
if tf:
vectorizer = TfidfVectorizer(min_df=min_df, ngram_range=ngram_range)
else:
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def main():
# Disable OAuthlib's HTTPS verification when running locally.
# *DO NOT* leave this option enabled in production.
os.environ["OAUTHLIB_INSECURE_TRANSPORT"] = "1"
# Get the API key as a CLI arg.
api_key = sys.argv[1]
if not api_key:
raise Exception("No API key provided.")
# Get credentials and create an API client
youtube = YouTube(api_key)
# Do stuff.
da = DataAccess()
pitems_dict = da.get_pitems_dict(OTHER_PLAYLIST_IDS)
current_vid = "lM28rfsHge0"
# save_threads(youtube, da, from_vid=current_vid, dry_run=False)
# save_all_playlist_items(youtube, OTHER_PLAYLIST_IDS, dry_run=False)
save_all_videos(youtube, pitems_dict, dry_run=False)
def segment_driver_v2(driver_id):
''' this generated the segments in settings.SEGMENTS_FOLDER[2] '''
da = DataAccess()
for ride_id_minus_1, ride in enumerate(da.get_rides(driver_id)):
ride_id = ride_id_minus_1 + 1
if da.skip_segment(driver_id, ride_id, version=2):
continue
# apply the Ramer-Douglas-Peucker algorithm
ride = [p + [i] for i, p in enumerate(ride)] # enrich with timestamp
ride = rdp(ride, epsilon=4)
lengths = [util.euclidian_distance(ride[i-1], ride[i]) for i in xrange(1, len(ride))]
times = [ride[i][2] - ride[i-1][2] for i in xrange(1, len(ride))]
angles = [util.get_angle(ride[i-2], ride[i-1], ride[i]) for i in xrange(2, len(ride))]
lengths = np.histogram(lengths, bins=range(0, 700, 20) + [1000000000])[0]
times = np.histogram(times, bins=range(0, 60, 4) + [1000000000])[0]
angles = np.histogram(angles, bins=range(0, 181, 20))[0]
# write results
da.write_ride_segments(driver_id, ride_id, lengths, times, angles, version=2)
logging.info('finished segmenting driver %s' % driver_id)
def get_data_segment_lengths(model_id,
driver_id,
repeat,
test=False,
segment_version=1,
extra=((1, 8), 1)):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
ngram_range, min_df = extra
if test:
set1 = list(da.get_rides_segments(driver_id, version=segment_version))
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK,
segments=True,
version=segment_version)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed))
other_test = list(
da.get_random_rides(settings.SMALL_CHUNK,
driver_id,
segments=True,
version=segment_version))
set1 = driver_train + other_train
set2 = driver_test + other_test
# keep only lengths
set1 = [d[0] for d in set1]
set2 = [d[0] for d in set2]
# convert to text
set1 = [util.get_list_string(d) for d in set1]
set2 = [util.get_list_string(d) for d in set2]
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_movements_v1(model_id,
driver_id,
repeat,
test=False,
step=5,
tf=False,
version=1,
extra=((1, 5), 2)):
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
ngram_range, min_df = extra
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
segments=False,
seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK,
segments=False)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
segments=False,
seed=seed))
other_test = list(
da.get_random_rides(settings.SMALL_CHUNK,
driver_id,
segments=False))
set1 = driver_train + other_train
set2 = driver_test + other_test
# keep only lengths and convert to text
set1 = [util.build_features3(r, step=step, version=version) for r in set1]
set2 = [util.build_features3(r, step=step, version=version) for r in set2]
if tf:
vectorizer = TfidfVectorizer(min_df=min_df, ngram_range=ngram_range)
else:
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def insert_expense(self):
insert_data_access = DataAccess()
insert_dict = {
'description': self.description.get(),
'amount': self.amount.get(),
'file_path': self.receipt.get(),
'date': self.date.get(),
}
insert_data_access.insert(**insert_dict)
insert_data_access.close()
self.sum += float(self.amount.get())
self.sum_label.set(format_sum_string(self.sum))
self.add_window.destroy()
def get_data_segment_lengths(model_id, driver_id, repeat, test=False, segment_version=1, extra=((1,8),1)):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
ngram_range, min_df = extra
if test:
set1 = list(da.get_rides_segments(driver_id, version=segment_version))
set2 = list(da.get_random_rides(
settings.BIG_CHUNK_TEST * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed
))
else:
driver_train, driver_test = da.get_rides_split(
driver_id,
settings.BIG_CHUNK,
segments=True,
version=segment_version
)
other_train = list(da.get_random_rides(
settings.BIG_CHUNK * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed
))
other_test = list(da.get_random_rides(
settings.SMALL_CHUNK,
driver_id,
segments=True,
version=segment_version
))
set1 = driver_train + other_train
set2 = driver_test + other_test
# keep only lengths
set1 = [d[0] for d in set1]
set2 = [d[0] for d in set2]
# convert to text
set1 = [util.get_list_string(d) for d in set1]
set2 = [util.get_list_string(d) for d in set2]
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_segment_angles_v2(model_id, driver_id, repeat, test=False, segment_version=1, extra=((1,3),1)):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
ngram_range, min_df = extra
if test:
set1 = list(da.get_rides_segments(driver_id, version=segment_version))
set2 = list(da.get_random_rides(
settings.BIG_CHUNK_TEST * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed
))
else:
driver_train, driver_test = da.get_rides_split(
driver_id,
settings.BIG_CHUNK,
segments=True,
version=segment_version
)
other_train = list(da.get_random_rides(
settings.BIG_CHUNK * repeat,
driver_id,
segments=True,
version=segment_version,
seed=seed
))
other_test = list(da.get_random_rides(
settings.SMALL_CHUNK,
driver_id,
segments=True,
version=segment_version
))
set1 = driver_train + other_train
set2 = driver_test + other_test
# create features for each (segment, angle, segment) tuple
set1 = [['%s_%s' % (d[0][i-1], d[1][i-1]) for i in xrange(1, len(d[0]))] for d in set1]
set2 = [['%s_%s' % (d[0][i-1], d[1][i-1]) for i in xrange(1, len(d[0]))] for d in set2]
set1 = [util.get_list_string(d) for d in set1]
set2 = [util.get_list_string(d) for d in set2]
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_g_forces_v1(model_id,
driver_id,
repeat,
test=False,
min_df=1,
ngram_range=(1, 10),
digitize=0):
def process(ride, digitize):
g_forces = util.get_g_forces(ride)
if digitize:
g_forces = np.digitize(g_forces, range(0, 800, digitize))
return util.get_list_string(g_forces)
seed = random.Random(x=driver_id + model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id)) # first half of the train set
set2 = list(
da.get_random_rides(settings.BIG_CHUNK_TEST * repeat,
driver_id,
seed=seed)) # second half of the train set
else:
driver_train, driver_test = da.get_rides_split(driver_id,
settings.BIG_CHUNK)
other_train = list(
da.get_random_rides(settings.BIG_CHUNK * repeat,
driver_id,
seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train # used for training
set2 = driver_test + other_test # used for testing
set1 = [process(ride, digitize) for ride in set1]
set2 = [process(ride, digitize) for ride in set2]
vectorizer = CountVectorizer(min_df=min_df, ngram_range=ngram_range)
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_basic_accel(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train
set2 = driver_test + other_test
set1 = [util.build_features_acc(ride, version=version) for ride in set1]
set2 = [util.build_features_acc(ride, version=version) for ride in set2]
return np.array(set1), np.array(set2)
def get_data_g_forces_v6(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id)) # first half of the train set
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, seed=seed)) # second half of the train set
else:
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train # used for training
set2 = driver_test + other_test # used for testing
set1 = [util.get_g_forces_v4(ride, version=version) for ride in set1]
set2 = [util.get_g_forces_v4(ride, version=version) for ride in set2]
vectorizer = CountVectorizer(min_df=1, ngram_range=(1,20))
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_dist_acc(model_id, driver_id, repeat, test=False):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train
set2 = driver_test + other_test
set1 = [util.get_distance_acc_words(ride, step=3) for ride in set1]
set2 = [util.get_distance_acc_words(ride, step=3) for ride in set2]
vectorizer = CountVectorizer(min_df=1, ngram_range=(1,15))
set1 = vectorizer.fit_transform(set1)
set2 = vectorizer.transform(set2)
return set1, set2
def get_data_fft(model_id, driver_id, repeat, test=False, version=1):
seed = random.Random(x=driver_id+model_id)
da = DataAccess()
if test:
set1 = list(da.get_rides(driver_id))
set2 = list(da.get_random_rides(settings.BIG_CHUNK_TEST * repeat, driver_id, seed=seed))
else:
driver_train, driver_test = da.get_rides_split(driver_id, settings.BIG_CHUNK)
other_train = list(da.get_random_rides(settings.BIG_CHUNK * repeat, driver_id, seed=seed))
other_test = list(da.get_random_rides(settings.SMALL_CHUNK, driver_id))
set1 = driver_train + other_train
set2 = driver_test + other_test
if version == 1:
set1 = [util.fft(ride) for ride in set1]
set2 = [util.fft(ride) for ride in set2]
else:
set1 = [util.fft_strip(ride) for ride in set1]
set2 = [util.fft_strip(ride) for ride in set2]
return np.array(set1), np.array(set2)
def segment_driver_v2(driver_id):
''' this generated the segments in settings.SEGMENTS_FOLDER[2] '''
da = DataAccess()
for ride_id_minus_1, ride in enumerate(da.get_rides(driver_id)):
ride_id = ride_id_minus_1 + 1
if da.skip_segment(driver_id, ride_id, version=2):
continue
# apply the Ramer-Douglas-Peucker algorithm
ride = [p + [i] for i, p in enumerate(ride)] # enrich with timestamp
ride = rdp(ride, epsilon=4)
lengths = [
util.euclidian_distance(ride[i - 1], ride[i])
for i in range(1, len(ride))
]
times = [ride[i][2] - ride[i - 1][2] for i in range(1, len(ride))]
angles = [
util.get_angle(ride[i - 2], ride[i - 1], ride[i])
for i in range(2, len(ride))
]
lengths = np.histogram(lengths,
bins=list(range(0, 700, 20)) + [1000000000])[0]
times = np.histogram(times,
bins=list(range(0, 60, 4)) + [1000000000])[0]
angles = np.histogram(angles, bins=list(range(0, 181, 20)))[0]
# write results
da.write_ride_segments(driver_id,
ride_id,
lengths,
times,
angles,
version=2)
logging.info('finished segmenting driver %s' % driver_id)
def mod_targa():
targa = request.form['targa']
uuid = session['user']['user_id']
if not DA.change_targa(uuid, targa):
flash("Errore in modifica targa!")
return redirect(url_for('main.profilo'))
def test_insert_extra_fields(self):
da = DataAccess(database=TEST_DB)
da.insert(**TEST_ROW_3)
self.assertEqual(_get_row_count(), 1)
def test_insert_no_kwargs_raises_InvalidDataError(self):
da = DataAccess(database=TEST_DB)
self.assertRaises(InvalidDataError, da.insert)
def test_sum_expenses_one_row(self):
da = DataAccess(database=TEST_DB)
da.insert(**TEST_ROW_1)
sum_result = da.sum_expenses()
da.close()
self.assertEqual(sum_result, 12.75)
def __init__(self):
connection_string = SvcConfig.db_connection_str
data_access = DataAccess(connection_string)
self.data_access = data_access
def __init__(self, db, model_table_name, model_table, hh_table_name, hh_table, pp_table_name, pp_table,
land_table_name, land_table, business_sector_table_name, business_sector_table,
policy_table_name, policy_table, stat_table_name, stat_table, start_year):
'''
Initialize the society class;
'''
# Set the start year and current time stamps
self.start_year = start_year
self.current_year = start_year
# Create a dictionary to store model parameters, indexed by Variable_Name, and contents are Variable_Value
self.model_parameters_dict = dict()
# Fill in the model parameters dictionary from the model table (fetched from DB)
for record in model_table:
self.model_parameters_dict[record.Variable_Name] = record.Variable_Value
# Get the variable lists for household, person, land, business sector, policy, and statistics classes
self.hh_var_list = DataAccess.get_var_list(db, hh_table_name)
self.pp_var_list = DataAccess.get_var_list(db, pp_table_name)
self.land_var_list = DataAccess.get_var_list(db, land_table_name)
self.business_sector_var_list = DataAccess.get_var_list(db, business_sector_table_name)
self.policy_var_list = DataAccess.get_var_list(db, policy_table_name)
self.stat_var_list = DataAccess.get_var_list(db, stat_table_name)
# Initialize the land instances, and create a land dictionary to store all the land parcels
# Note that the land parcels here do not necessarily belong to any household. i.e. land_parcel.HID could be "None".
self.land_dict = dict()
for land in land_table:
land_parcel = Land(land, self.land_var_list, self.current_year)
self.land_dict[land_parcel.ParcelID] = land_parcel # Indexed by ParcelID
# Initialize the household instances (household capital property and land class instances are initialized at the initialization of household class);
# And create a dictionary to store them, indexed by HID.
self.hh_dict = dict()
# Add household instances to hh_dict
for hh in hh_table:
hh_temp = Household(hh, self.hh_var_list, self.current_year, db, pp_table_name, pp_table,
self.land_dict, self.model_parameters_dict)
self.hh_dict[hh_temp.HID] = hh_temp # Indexed by HID
# Initialize the business sector instances;
# And create a dictionary to store them, indexed by sector name.
self.business_sector_dict = dict()
for sector in business_sector_table:
sector_temp = BusinessSector(sector, self.business_sector_var_list)
self.business_sector_dict[sector_temp.SectorName] = sector_temp # Indexed by SectorName
# Initialize the policy program instances;
# And create a dictionary to store them, indexed by policy program type.
self.policy_dict = dict()
for program in policy_table:
program_temp = Policy(program, self.policy_var_list)
self.policy_dict[program_temp.PolicyType] = program_temp # Indexed by PolicyType
# Create a statistics dictionary; indexed by Variable Names.To be filled later in Statistics Class.
self.stat_dict = dict()
# Create some variables to record the confiscated (due to ownerlessness) money and land
self.ownerless_land = list()
self.ownerless_money = 0
def evaluate_sandp500_stocks():
print('Started evaluating STOOQ.com stocks ...', flush=True)
data_access = DataAccess('sandp500')
global sandp500_stocks
sandp500_stocks = evaluate_stocks('stooq', 'sandp500.csv', data_access)
def evaluate_fse_stocks():
print('Started evaluating QUANDL stocks ...', flush=True)
data_access = DataAccess('quandl_fse_stocks')
global fse_stocks
fse_stocks = evaluate_stocks('quandl', 'quandl_fse_stocks.csv',
data_access)
def get_sum():
sum_data_access = DataAccess()
sum_result = sum_data_access.sum_expenses()
sum_data_access.close()
return sum_result
def __init__(self, record, VarList, current_year, db, pp_table_name, pp_table, land_dict, model_parameters):
'''
Construct the household class from the household table in the DB, and then add some other user-defined attributes.
record - a record in the household table in the DB.
VarList - the variable (or field) list of the household table in the DB
VarList = {paramName1: paramOrder1, paramName2: paramOrder2, ...}
Also initialize the household's own person instances here from the person table in the DB.
Also initialize the household's capital properties instance here.
'''
# Set the attributes (var) and their values (record) from the household table in the DB.
for var in VarList:
setattr(self, var[0], record[var[1]])
# Set the household and person variables (attributes) lists
self.hh_var_list = VarList
self.pp_var_list = DataAccess.get_var_list(db, pp_table_name)
# Set the current time stamp
self.StatDate = current_year
# Define own persons (members) dict of the household, indexed by PID
self.own_pp_dict = dict()
# Add respective persons into the persons dict of the household
for pp in pp_table:
if pp.HID == self.HID:
pp_temp = Person(pp, self.pp_var_list, current_year)
self.own_pp_dict[pp_temp.PID] = pp_temp # Indexed by PID
# Initialize the household's capital properties class instance
self.own_capital_properties = CapitalProperty(self, land_dict, model_parameters)
# Define an empty list of available business sectors,
# and another empty list of the business sectors that the household is in in the current year
self.own_av_business_sectors = list()
self.own_current_sectors = list()
# Define an empty list of participant policy programs
self.own_policy_programs = list()
# Initialize the household's energy class instance
self.energy = Energy()
# Define a variable indicating the household's preference type
'''
1 - Max Labor, Min Risk;
2 - Min Labor, Min Risk;
3 - Max Labor, Max Risk;
4 - Min Labor, Max Risk;
'''
self.hh_preference_type = int()
# Also define a variable indicating the preference toward risks
'''
True - risk aversion; False - risk appetite;
'''
self.hh_risk_type = True
# Define a variable indicating the household's business type
'''
0 - agriculture only
1 - agriculture and another business sectors; or one business sector which is not agriculture
2 - agriculture and more than one other business sectors
'''
self.business_type = int()
# Define a switch variable indicating whether the household is dissolved in the current year
self.is_dissolved_this_year = False
def init_db():
try:
global db_client
db_client = DataAccess.get_instance().get_db_client()
except Exception as e:
logging.critical("Problem occured while connecting db. {}".format(e))
