data.entsoe_loader

data.entsoe_loader

ENTSO-E interim-CSV data loaders.

Config-driven loaders for the merged ENTSO-E interim CSV, suitable for the data_loader / test_data_loader hooks on ConfigEntsoe. Ported from spotforecast2.tasks.task_entsoe ahead of that subpackage’s removal.

Functions

Name	Description
entsoe_data_loader	Read the merged interim ENTSO-E CSV that `config.data_filename` points at.
entsoe_test_data_loader	Return the merged ENTSO-E CSV sliced to the forecast horizon.

entsoe_data_loader

data.entsoe_loader.entsoe_data_loader(config)

Read the merged interim ENTSO-E CSV that config.data_filename points at.

Parameters

Name	Type	Description	Default
config	`ConfigEntsoe`	A `ConfigEntsoe` with `data_filename` set. Relative paths are resolved against `spotforecast2_safe.data.fetch_data.get_data_home`.	required

Returns

Name	Type	Description
	pd.DataFrame	DataFrame indexed by the ENTSO-E timestamp column (`Time (UTC)`)
	pd.DataFrame	with the load columns as data columns.

Raises

Name	Type	Description
	FileNotFoundError	If the merged CSV does not exist. Run `spotforecast2-entsoe download` and `merge` first.

Examples

import os
import tempfile

import pandas as pd
from spotforecast2_safe.configurator import ConfigEntsoe
from spotforecast2_safe.data.entsoe_loader import entsoe_data_loader

# Build a tiny synthetic interim CSV in a temp directory.
tmp = tempfile.mkdtemp()
csv_path = os.path.join(tmp, "energy_load.csv")
idx = pd.date_range(
    "2025-01-01", periods=48, freq="h", tz="UTC", name="Time (UTC)"
)
pd.DataFrame({"Actual Load": range(48)}, index=idx).to_csv(csv_path)

# Absolute path bypasses get_data_home; loader returns the full frame.
config = ConfigEntsoe()
config.data_filename = csv_path
df = entsoe_data_loader(config)

print(df.shape)
assert df.shape == (48, 1)
assert df.index.name == "Time (UTC)"

(48, 1)

entsoe_test_data_loader

data.entsoe_loader.entsoe_test_data_loader(config)

Return the merged ENTSO-E CSV sliced to the forecast horizon.

The slice spans (end_train, end_train + predict_size * 1 h] so that build_prediction_package’s test_actual = ts.reindex(future_pred.index) matches the hourly forecast row-for-row. end_train is taken from config.end_train_default (treated as the inclusive last training timestamp, the same convention the forecaster uses), and the step is assumed to be 1 h after the pipeline’s hourly resampling.

For the live ENTSO-E exemplar with end_train_default = D-2 23:00 UTC and predict_size = 24, this returns the rows for [D-1 00:00, D 00:00) — i.e., y_{-1}. For backtests at an arbitrary end_train_default, it returns the post-cutoff window the model is actually predicting, rather than always “yesterday in wall-clock UTC”.

Parameters

Name	Type	Description	Default
config	`ConfigEntsoe`	A `ConfigEntsoe` with `data_filename`, `end_train_default`, and `predict_size` set; the merged interim CSV must already contain data covering the forecast horizon (run `spotforecast2-entsoe download` first).	required

Returns

Name	Type	Description
	pd.DataFrame	DataFrame indexed by `Time (UTC)` with the rows the forecast will be
	pd.DataFrame	scored against.

Examples

import os
import tempfile

import pandas as pd
from spotforecast2_safe.configurator import ConfigEntsoe
from spotforecast2_safe.data.entsoe_loader import entsoe_test_data_loader

# Synthetic interim CSV spanning the forecast window.
tmp = tempfile.mkdtemp()
csv_path = os.path.join(tmp, "energy_load.csv")
idx = pd.date_range(
    "2025-12-29 00:00", periods=120, freq="h", tz="UTC", name="Time (UTC)"
)
pd.DataFrame({"Actual Load": range(120)}, index=idx).to_csv(csv_path)

config = ConfigEntsoe()
config.data_filename = csv_path
config.end_train_default = "2025-12-31 00:00+00:00"
config.predict_size = 24

test_df = entsoe_test_data_loader(config)

# The slice covers exactly predict_size hourly steps after end_train.
print(test_df.shape)
assert test_df.shape == (24, 1)
assert test_df.index[0] == pd.Timestamp("2025-12-31 01:00", tz="UTC")

(24, 1)