Merge pull request #19 from WenjieDu/dev

Add random walk dataset and release v0.3

.pre-commit-config.yaml

@@ -0,0 +1,26 @@
+repos:
+    # hooks for checking files
+    -   repo: https://github.com/pre-commit/pre-commit-hooks
+        rev: v4.6.0
+        hooks:
+            -   id: trailing-whitespace
+            -   id: end-of-file-fixer
+            -   id: check-yaml
+
+    # hooks for linting code
+    -   repo: https://github.com/psf/black
+        rev: 24.8.0
+        hooks:
+            -   id: black
+                args: [
+                    --line-length=120, # refer to pyproject.toml
+                ]
+
+    -   repo: https://github.com/PyCQA/flake8
+        rev: 7.1.1
+        hooks:
+            -   id: flake8
+                args: [
+                    --max-line-length=120, # refer to pyproject.toml
+                    --extend-ignore=E203,E231
+                ]

benchpots/datasets/__init__.py

@@ -14,6 +14,7 @@
 from .physionet_2019 import preprocess_physionet2019
 from .ucr_uea_datasets import preprocess_ucr_uea_datasets
 from .solar_alabama import preprocess_solar_alabama
+from .random_walk import preprocess_random_walk
 
 __all__ = [
     "preprocess_physionet2012",
@@ -25,4 +26,5 @@
     "preprocess_pems_traffic",
     "preprocess_ucr_uea_datasets",
     "preprocess_solar_alabama",
+    "preprocess_random_walk",
 ]

benchpots/datasets/beijing_multisite_air_quality.py

@@ -140,7 +140,6 @@ def preprocess_beijing_air_quality(
         processed_dataset["val_X_ori"] = val_X_ori
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
         processed_dataset["test_X_ori"] = test_X_ori
     else:
         logger.warning("rate is 0, no missing values are artificially added.")

benchpots/datasets/electricity_load_diagrams.py

@@ -108,7 +108,6 @@ def preprocess_electricity_load_diagrams(
         processed_dataset["val_X_ori"] = val_X_ori
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
         processed_dataset["test_X_ori"] = test_X_ori
     else:
         logger.warning("rate is 0, no missing values are artificially added.")

benchpots/datasets/electricity_transformer_temperature.py

@@ -115,7 +115,7 @@ def preprocess_ett(
         processed_dataset["val_X_ori"] = val_X_ori
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
+
         processed_dataset["test_X_ori"] = test_X_ori
     else:
         logger.warning("rate is 0, no missing values are artificially added.")

benchpots/datasets/italy_air_quality.py

@@ -99,7 +99,6 @@ def preprocess_italy_air_quality(
         processed_dataset["val_X_ori"] = val_X_ori
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
         processed_dataset["test_X_ori"] = test_X_ori
     else:
         logger.warning("rate is 0, no missing values are artificially added.")

benchpots/datasets/pems_traffic.py

@@ -110,7 +110,6 @@ def preprocess_pems_traffic(
         processed_dataset["val_X_ori"] = val_X_ori
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
         processed_dataset["test_X_ori"] = test_X_ori
     else:
         logger.warning("rate is 0, no missing values are artificially added.")

benchpots/datasets/physionet_2012.py

@@ -227,7 +227,6 @@ def apply_func(df_temp):  # pad and truncate to set the max length of samples as
         )
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
         processed_dataset["test_X_ori"] = test_X_ori
 
         test_X_indicating_mask = np.isnan(test_X_ori) ^ np.isnan(test_X)

benchpots/datasets/physionet_2019.py

@@ -192,7 +192,6 @@ def apply_func(df_temp):  # pad and truncate to set the max length of samples as
         processed_dataset["val_X_ori"] = val_X_ori
 
         processed_dataset["test_X"] = test_X
-        # test_X_ori is for error calc, not for model input, hence mustn't have NaNs
         processed_dataset["test_X_ori"] = test_X_ori
 
         test_X_indicating_mask = np.isnan(test_X_ori) ^ np.isnan(test_X)