TimeSeriesSplit और प्रति-क्षितिज त्रुटि विश्लेषण के साथ पूर्वानुमानों का सत्यापन

import numpy as np
from sklearn.model_selection import TimeSeriesSplit
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error

X = np.arange(12).reshape(-1, 1)
y = np.array([1.0, 1.8, 3.2, 4.1, 5.0, 5.9, 6.8, 7.7, 8.6, 9.5, 10.4, 11.3])

tscv = TimeSeriesSplit(n_splits=3, test_size=2)
for fold, (train_idx, test_idx) in enumerate(tscv.split(X), start=1):
    X_train, X_test = X[train_idx], X[test_idx]
    y_train, y_test = y[train_idx], y[test_idx]
    model = LinearRegression()
    model.fit(X_train, y_train)
    pred = model.predict(X_test)
    print(f"Fold {fold}: test indices {test_idx}, MAE {mean_absolute_error(y_test, pred):.3f}")

from sklearn.metrics import mean_absolute_error

# y_true and y_pred are aligned per horizon
horizon_errors = {}
for horizon in range(1, max_horizon + 1):
    mask = (horizon_index == horizon)
    horizon_errors[horizon] = mean_absolute_error(y_true[mask], y_pred[mask])

from sklearn.metrics import mean_absolute_error, mean_squared_error

# Strictly consistent scoring functions for point forecasts
mae = mean_absolute_error(y_true, y_pred)  # aligns with median target
mse = mean_squared_error(y_true, y_pred)   # aligns with mean target

from sklearn.metrics import mean_absolute_error

# Example: 12 monthly samples, 3 folds, test_size=2
# Fold 1 test indices: 6,7; Fold 2 test indices: 8,9; Fold 3 test indices: 10,11
# Per-horizon MAE: horizon 1 = 1.2, horizon 2 = 1.9, horizon 3 = 2.8
# Decision: restrict forecast to horizon 2 or improve long-horizon features