gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 23:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

support multiple types in feature engineering (#562)

Browse Source
This commit is contained in:
Tim
2025-02-08 15:21:11 +08:00
committed by GitHub
parent d4c708c709
commit a0e274889b
2 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/data_science/ensemble/eval_tests/ensemble_test.txt
+3
View File
@@ -20,6 +20,9 @@ X, y, test_X, test_ids = load_data()
X, y, test_X = feat_eng(X, y, test_X)
train_X, val_X, train_y, val_y = train_test_split(X, y, test_size=0.2, random_state=42)
# Print the types of train_y and val_y
print(f"train_y type: {type(train_y)}, val_y type: {type(val_y)}")
test_preds_dict = {}
val_preds_dict = {}
{% for mn in model_names %}
rdagent/components/coder/data_science/feature/eval_tests/feature_test.txt
+3 -3
View File
@@ -57,11 +57,11 @@ if isinstance(X, pd.DataFrame) and isinstance(X_test, pd.DataFrame):
assert get_column_list(X) == get_column_list(X_test), "Mismatch in column names of training and test data."
if isinstance(X, pd.DataFrame):
X_dtypes_unique_sorted = sorted(X.dtypes.unique().tolist())
X_loaded_dtypes_unique_sorted = sorted(X_loaded.dtypes.unique().tolist())
X_dtypes_unique_sorted = sorted([str(dt) for dt in X.dtypes.unique()])
X_loaded_dtypes_unique_sorted = sorted([str(dt) for dt in X_loaded.dtypes.unique()])
assert (
len(X_loaded_dtypes_unique_sorted) == 1
and (X_loaded_dtypes_unique_sorted[0] == np.float64 or X_loaded_dtypes_unique_sorted[0] == np.float32)
and X_loaded_dtypes_unique_sorted[0] in {np.float64, np.float32}
) or (
X_dtypes_unique_sorted == X_loaded_dtypes_unique_sorted
), f"feature engineering has produced new data types which is not allowed, data loader data types are {X_loaded_dtypes_unique_sorted} and feature engineering data types are {X_dtypes_unique_sorted}"