Quick Start

This guide shows you how to download electricity data and run a simple forecast in just a few steps.

Set up environment

import os

# Set your ENTSOE API key
os.environ["ENTSOE_API_KEY"] = "your-api-key-here"

# Optional: Configure multithreading (requires Python 3.13t+)
os.environ["PYTHON_GIL"] = "0"
os.environ["MAX_THREADS"] = "16"

Download data with DataPipeline

from epftoolbox2.pipelines import DataPipeline
from epftoolbox2.data.sources import EntsoeSource, OpenMeteoSource, CalendarSource
from epftoolbox2.data.transformers import ResampleTransformer, LagTransformer
from epftoolbox2.data.validators import NullCheckValidator

pipeline = (
    DataPipeline()
    .add_source(EntsoeSource(
        country_code="PL",
        api_key=os.environ["ENTSOE_API_KEY"],
        type=["load", "price"]
    ))
    .add_source(OpenMeteoSource(
        latitude=52.2297,
        longitude=21.0122,
        horizon=7,
        prefix="warsaw"
    ))
    .add_source(CalendarSource(
        country="PL",
        holidays="binary",
        weekday="onehot",
        daylight_hours=True
    ))
    .add_transformer(ResampleTransformer(freq="1h"))
    .add_transformer(LagTransformer(
        columns=["load_actual"],
        lags=[1, 2, 7],
        freq="day"
    ))
    .add_validator(NullCheckValidator(columns=["load_actual", "price"]))
)

df = pipeline.run(start="2023-01-01", end="2024-04-01", cache=True)
print(f"Downloaded {len(df)} rows with {len(df.columns)} columns")

Train models with ModelPipeline

from epftoolbox2.pipelines import ModelPipeline
from epftoolbox2.models import OLSModel, LassoCVModel
from epftoolbox2.evaluators import MAEEvaluator
from epftoolbox2.exporters import ExcelExporter, TerminalExporter

predictors = [
    "load_actual",
    "is_monday_d+{horizon}",
    "is_tuesday_d+{horizon}",
    "is_wednesday_d+{horizon}",
    "is_thursday_d+{horizon}",
    "is_friday_d+{horizon}",
    "is_saturday_d+{horizon}",
    "is_sunday_d+{horizon}",
    "is_holiday_d+{horizon}",
    "daylight_hours_d+{horizon}",
    "load_actual_d-1",
    "load_actual_d-7",
    "warsaw_temperature_2m_d+{horizon}",
]

pipeline = (
    ModelPipeline()
    .add_model(OLSModel(predictors=predictors, training_window=365, name="OLS"))
    .add_model(LassoCVModel(predictors=predictors, training_window=365, cv=5, name="LassoCV"))
    .add_evaluator(MAEEvaluator())
    .add_exporter(TerminalExporter())
    .add_exporter(ExcelExporter("results.xlsx"))
)

report = pipeline.run(
    data=df,
    test_start="2024-02-01",
    test_end="2024-03-01",
    target="price",
    horizon=7,
    save_dir="results",
)

Analyze results

# Overall summary
print(report.summary())

# By forecast horizon
print(report.by_horizon())

# By hour of day
print(report.by_hour())

Expected Output

Summary
┏━━━━━━━━━━┳━━━━━━━━━┓
┃ model    ┃ MAE     ┃
┡━━━━━━━━━━╇━━━━━━━━━┩
│ OLS      │ 26.0199 │
│ LassoCV  │ 28.1098 │
└──────────┴─────────┘

What’s Next?

Data Pipeline Overview Learn about sources, transformers, and validators

Model Pipeline Overview Configure models, evaluators, and exporters