def create_time_series(resampling_methods, chunk_ids, chunk_type, original_chunks, parameter,
window_idx, configs, mean=0, std=1):
# Apply filler as some time series have missing measurements what would lead to ValueError in prediction
filler = MissingValuesFiller()
for resampling in resampling_methods:
series_per_resampling = dict()
pred_scalers = dict()
for chunk_id in chunk_ids:
current_chunk = original_chunks[original_chunks['CHUNK_ID_FILLED_TH'] == chunk_id]
# Scale chunk values if it is configured and create filled time series
if configs.scaling_method == 'standard':
current_chunk[f'SCALED_{resampling}'] = apply_standard_scaling(
current_chunk[f'VITAL_PARAMTER_VALUE_{resampling}_RESAMPLING'], mean, std)
series_per_resampling[chunk_id] = filler.transform(TimeSeries.from_dataframe(
df=current_chunk,
time_col='CHARTTIME',
value_cols=[f'SCALED_{resampling}'],
freq='H'))
elif configs.scaling_method == 'min-max':
# Darts uses MinMaxScaler by default
current_scaler = Scaler()
series_per_resampling[chunk_id] = current_scaler.fit_transform(filler.transform(
TimeSeries.from_dataframe(
df=current_chunk,
time_col='CHARTTIME',
value_cols=[f'VITAL_PARAMTER_VALUE_{resampling}_RESAMPLING'],
freq='H')))
if chunk_type == 'pred' and \
((configs.with_exogenous_input and resampling != 'MEDIAN') or not configs.with_exogenous_input):
pred_scalers[chunk_id] = current_scaler
else: # apply no scaling
series_per_resampling[chunk_id] = filler.transform(TimeSeries.from_dataframe(
df=current_chunk,
time_col='CHARTTIME',
value_cols=[f'VITAL_PARAMTER_VALUE_{resampling}_RESAMPLING'],
freq='H'))
# Save series dict
path = get_script_path(configs)
write_pickle_file(f'{path}/time_series/time_series_{parameter}_win{window_idx}_{chunk_type}_'
f'{resampling.capitalize()}.pickle', series_per_resampling)
# Save scaler dict if it was filled
if pred_scalers:
write_pickle_file(f'{path}/scalers/scalers_{parameter}_win{window_idx}_{resampling.capitalize()}.pickle',
pred_scalers)
'N_HIGH_ALARMS', 'N_LOW_ALARMS', 'N_CHUNKS', 'N_ITERATIONS'
])
# Note: Not changeable, see other scripts ending with "covariates" for MAX and MIN
endogenous_input = 'Median'
exogenous_input = np.nan
if style == 'all':
n_windows = 5
elif style == '20_percent':
n_windows = 1
else:
raise ValueError('The style has to be "all" or "20_percent".')
# Note: Only use filler for now, remove after resampling script is fixed
filler = MissingValuesFiller()
for model_type in model_types:
print(
f'\n##############################\nCurrent Model Type: {model_type}\n##############################\n',
file=sys.stderr)
# Create sub folder for each model type
if not os.path.isdir(
f'./data/{approach}/{n_chunks}_chunks/{style}/{model_type}'):
os.mkdir(f'./data/{approach}/{n_chunks}_chunks/{style}/{model_type}')
# Create model per model type
model = RNNModel(
model=model_type,
input_chunk_length=input_length,
def test_fill_lin_series_with_auto_value(self):
auto_transformer = MissingValuesFiller()
transformed = auto_transformer.transform(self.lin_series_with_holes)
self.assertEqual(self.lin_series, transformed)
def test_fill_const_series_with_const_value(self):
const_transformer = MissingValuesFiller(fill=2.0)
transformed = const_transformer.transform(self.const_series_with_holes)
self.assertEqual(self.const_series, transformed)
#select the time series variable
ts_var = 'CPU_Used'
time_df = df.filter(['date', ts_var])
#convert variable from object dtype to numeric dtype
time_df[ts_var] = pd.to_numeric(time_df[ts_var], errors='coerce')
#remove duplicates
time_df.sort_values("date", inplace=True)
time_df.drop_duplicates(subset="date", keep=False, inplace=True)
#generate time series using darts
series = TimeSeries.from_dataframe(time_df, 'date', ts_var, freq='T')
#treat missing values
filler = MissingValuesFiller()
series = filler.transform(series)
#training and testing dataset
train, val = series.split_after(pd.Timestamp('2019-10-23 19:41:50'))
#FFT model
model = FFT(required_matches=set(), nr_freqs_to_keep=None)
model.fit(train)
pred_val = model.predict(len(val))
#Evaluation metrics
series.plot(label='actual')
pred_val.plot(label='forecast', lw=3)
plt.legend()
print("MAPE:", mape(pred_val, val))