Adriano Dal Pastro
b6539802e0
- mv src/multi_swarm → src/multi_swarm_core/multi_swarm_core (member layout) - sed-replace globale degli import: from/import multi_swarm.* → multi_swarm_core.* - 115 occorrenze aggiornate in src/ scripts/ tests/ - multi_swarm_coevolutive (nome repo) preservato dal word boundary Pre-condizione per il setup uv workspace della Fase 3. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
41 lines
1.2 KiB
Python
41 lines
1.2 KiB
Python
import pandas as pd
|
|
import pytest
|
|
|
|
from multi_swarm_core.data.splits import expanding_walk_forward
|
|
|
|
|
|
@pytest.fixture
|
|
def daily_index():
|
|
return pd.date_range("2024-01-01", "2024-12-31", freq="D", tz="UTC")
|
|
|
|
|
|
def test_expanding_split_count(daily_index: pd.DatetimeIndex):
|
|
splits = expanding_walk_forward(
|
|
daily_index, train_ratio=0.7, n_folds=4, min_train_days=30
|
|
)
|
|
assert len(splits) == 4
|
|
|
|
|
|
def test_expanding_split_train_grows(daily_index: pd.DatetimeIndex):
|
|
splits = expanding_walk_forward(
|
|
daily_index, train_ratio=0.7, n_folds=4, min_train_days=30
|
|
)
|
|
train_lengths = [len(s.train_idx) for s in splits]
|
|
assert train_lengths == sorted(train_lengths)
|
|
assert train_lengths[0] < train_lengths[-1]
|
|
|
|
|
|
def test_no_overlap_train_test(daily_index: pd.DatetimeIndex):
|
|
splits = expanding_walk_forward(
|
|
daily_index, train_ratio=0.7, n_folds=4, min_train_days=30
|
|
)
|
|
for s in splits:
|
|
assert s.train_idx[-1] < s.test_idx[0]
|
|
|
|
|
|
def test_min_train_days_respected():
|
|
idx = pd.date_range("2024-01-01", "2024-02-15", freq="D", tz="UTC")
|
|
splits = expanding_walk_forward(idx, train_ratio=0.7, n_folds=2, min_train_days=20)
|
|
for s in splits:
|
|
assert len(s.train_idx) >= 20
|