MCPcopy Index your code
hub / github.com/FinancialComputingUCL/LOBFrame / save_dataset_info

Function save_dataset_info

utils.py:221–278  ·  view source on GitHub ↗

Save all the days used in the training, validation and test sets. Args: experiment_id (str): ID of the experiment. general_hyperparameters (dict): General hyperparameters. Returns: None.

(
    experiment_id: str,
    general_hyperparameters: dict[str, Any],
)

Source from the content-addressed store, hash-verified

219
220
221def save_dataset_info(
222 experiment_id: str,
223 general_hyperparameters: dict[str, Any],
224) -> None:
225 """
226 Save all the days used in the training, validation and test sets.
227 Args:
228 experiment_id (str): ID of the experiment.
229 general_hyperparameters (dict): General hyperparameters.
230
231 Returns:
232 None.
233 """
234 # Access the training data folder and list all the files.
235 training_days_temp = glob.glob(
236 f"./data/{general_hyperparameters['dataset']}/scaled_data/training/*.csv"
237 )
238 # Access the validation data folder and list all the files.
239 validation_days_temp = glob.glob(
240 f"./data/{general_hyperparameters['dataset']}/scaled_data/validation/*.csv"
241 )
242 # Access the test data folder and list all the files.
243 test_days_temp = glob.glob(
244 f"./data/{general_hyperparameters['dataset']}/scaled_data/test/*.csv"
245 )
246
247 training_days = []
248 validation_days = []
249 test_days = []
250
251 # Extract the dates from the file names (training data).
252 for i in training_days_temp:
253 i = i.split("/")[-1].split("_")[-1]
254 training_days.append(i)
255
256 # Extract the dates from the file names (validation data).
257 for i in validation_days_temp:
258 i = i.split("/")[-1].split("_")[-1]
259 validation_days.append(i)
260
261 # Extract the dates from the file names (test data).
262 for i in test_days_temp:
263 i = i.split("/")[-1].split("_")[-1]
264 test_days.append(i)
265
266 # Create a dictionary containing the training, validation and test days.
267 dataset_info = {
268 "training_days": sorted(set(training_days)),
269 "validation_days": sorted(set(validation_days)),
270 "test_days": sorted(set(test_days)),
271 }
272
273 # Save the dictionary as a YAML file.
274 logger.logger(
275 experiment_id=experiment_id,
276 header="dataset_info",
277 contents=dataset_info,
278 )

Callers 1

main.pyFile · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected