def add_is_off_column(df, metadata):
if 'is_day_off' in df.columns:
return
is_day_off = []
for idx, row in tqdm(df.iterrows(), total=len(df), desc='Adding day off'):
is_day_off.append(
_is_day_off(row['series_id'], row['weekday'], metadata))
df['is_day_off'] = is_day_off
def _prepare_is_day_off(window, df, metadata, series_id):
is_day_off = df.is_holiday.values[::24].tolist()
current_date = df.timestamp.values[-1]
current_weekday = df.weekday.values[-1]
for _ in range(WINDOW_TO_PRED_DAYS[window]):
current_date = _get_next_date(current_date)
current_weekday = _get_next_weekday(current_weekday)
current_day_is_off = _is_day_off(series_id, current_weekday, metadata)
current_day_is_off = current_day_is_off or _is_holiday(current_date)
is_day_off.append(current_day_is_off)
is_day_off = np.array(is_day_off, dtype=np.float32)
is_day_off[is_day_off == 0] = -1
is_day_off = np.expand_dims(is_day_off, axis=0)
return is_day_off
def _prepare_future_day_off(window, df, metadata, series_id):
is_day_off = []
current_date = df.timestamp.values[-1]
current_weekday = df.weekday.values[-1]
for _ in range(WINDOW_TO_PRED_DAYS[window]):
current_date = _get_next_date(current_date)
current_weekday = _get_next_weekday(current_weekday)
current_day_is_off = _is_day_off(series_id, current_weekday, metadata)
current_day_is_off = current_day_is_off or _is_holiday(current_date)
is_day_off.append(current_day_is_off)
is_day_off = np.array(is_day_off, dtype=np.float32)
if window == 'hourly':
is_day_off = np.repeat(is_day_off, 24, axis=0)
if window == 'weekly':
is_day_off = np.reshape(is_day_off, (2, -1))
else:
is_day_off = np.expand_dims(is_day_off, axis=1)
is_day_off = np.expand_dims(is_day_off, axis=0)
return is_day_off
def visualize_idx(idx, train, train_arrange, preds, metadata):
row = train_arrange.loc[idx]
df = train[train.series_id == row['series_id']]
consumption = df.consumption.values[
row['train_start_idx']:row['val_end_idx']]
dates = df.timestamp.values[row['train_start_idx']:row['val_end_idx']]
weekdays = df.weekday.values[row['train_start_idx']:row['val_end_idx']]
if row['window'] == 'hourly':
batch_size = 24
elif row['window'] == 'daily':
batch_size = 1
weekdays = weekdays[::24]
dates = dates[::24]
consumption = group_sum(consumption, 24)
plt.plot(dates[-len(preds[idx]):], preds[idx], color='green', lw=3)
plt.plot(dates[-len(preds[idx]):][::batch_size],
preds[idx][::batch_size],
'o',
color='green',
lw=3)
for i in range(len(dates) // batch_size):
weekday = weekdays[i * batch_size]
if _is_day_off(row['series_id'], weekday, metadata):
color = 'orange'
else:
color = 'blue'
plt.plot(dates[i * batch_size:(i + 1) * batch_size + 1],
consumption[i * batch_size:(i + 1) * batch_size + 1],
color=color)
plt.plot(dates[i * batch_size:(i) * batch_size + 1],
consumption[i * batch_size:(i) * batch_size + 1],
'o',
color=color)
plt.title('%i Nmae: %.3f' % (idx, row['nmae']))
def _is_day_off(self, weekday, series_id, date):
ret = _is_day_off(series_id, weekday, self._metadata)
if self._use_holidays:
ret = ret or _is_holiday(date)
return int(ret)