Skip to main content

Features

WRSI Features represent derived weather metrics and regime classifications that underpin the signals.

forecast_skill publishes skill_score as a ratio, 1 - MAE / climatology MAE (above 0 beats climatology), not a 0-100 score. Climatology is point-in-time: the same calendar day in earlier years only, with at least three years.

Typical use cases​

They are designed for:

  • Research
  • Regime-aware modelling
  • Cross-season comparison

Accessing WRSI Features​

from snowtrail import Snowtrail
client = Snowtrail(api_key="your-api-key")

# Fetch WRSI features (e.g. forecast dynamics)
df = client.wrsi.forecast_dynamics(date_from="2024-01-01")

# All methods return pandas DataFrames
print(df.head())