Refactor code and update docstring

pypots/base.py

@@ -349,7 +349,7 @@ def fit(
         train_set :
             The dataset for model training, should be a dictionary including keys as 'X',
             or a path string locating a data file supported by PyPOTS (e.g. h5 file).
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for training, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -358,7 +358,7 @@ def fit(
         val_set :
             The dataset for model validating, should be a dictionary including keys as 'X',
             or a path string locating a data file supported by PyPOTS (e.g. h5 file).
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for validating, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -383,7 +383,7 @@ def predict(
         test_set :
             The dataset for model validating, should be a dictionary including keys as 'X',
             or a path string locating a data file supported by PyPOTS (e.g. h5 file).
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for validating, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains

pypots/classification/base.py

@@ -81,7 +81,7 @@ def fit(
         train_set :
             The dataset for model training, should be a dictionary including keys as 'X' and 'y',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for training, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -90,7 +90,7 @@ def fit(
         val_set :
             The dataset for model validating, should be a dictionary including keys as 'X' and 'y',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for validating, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -113,15 +113,15 @@ def predict(
     @abstractmethod
     def classify(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Classify the input data with the trained model.
 
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -132,8 +132,7 @@ def classify(
         array-like, shape [n_samples],
             Classification results of the given samples.
         """
-        # this is for old API compatibility, will be removed in the future.
-        # Please implement predict() instead.
+
         raise NotImplementedError
 
 
@@ -395,7 +394,7 @@ def fit(
         train_set :
             The dataset for model training, should be a dictionary including keys as 'X' and 'y',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for training, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -404,7 +403,7 @@ def fit(
         val_set :
             The dataset for model validating, should be a dictionary including keys as 'X' and 'y',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for validating, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -427,19 +426,17 @@ def predict(
     @abstractmethod
     def classify(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Classify the input data with the trained model.
 
-        Warnings
-        --------
-        The method classify is deprecated. Please use `predict()` instead.
+
 
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -450,6 +447,5 @@ def classify(
         array-like, shape [n_samples],
             Classification results of the given samples.
         """
-        # this is for old API compatibility, will be removed in the future.
-        # Please implement predict() instead.
+
         raise NotImplementedError

pypots/classification/brits/data.py

@@ -20,7 +20,7 @@ class DatasetForBRITS(DatasetForBRITS_Imputation):
     data :
         The dataset for model input, should be a dictionary including keys as 'X' and 'y',
         or a path string locating a data file.
-        If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+        If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
         which is time-series data for input, can contain missing values, and y should be array-like of shape
         [n_samples], which is classification labels of X.
         If it is a path string, the path should point to a data file, e.g. a h5 file, which contains

pypots/classification/brits/model.py

@@ -17,7 +17,6 @@
 from ..base import BaseNNClassifier
 from ...optim.adam import Adam
 from ...optim.base import Optimizer
-from ...utils.logging import logger
 
 
 class BRITS(BaseNNClassifier):
@@ -257,19 +256,15 @@ def predict(
 
     def classify(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Classify the input data with the trained model.
 
-        Warnings
-        --------
-        The method classify is deprecated. Please use `predict()` instead.
-
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -280,8 +275,6 @@ def classify(
         array-like, shape [n_samples],
             Classification results of the given samples.
         """
-        logger.warning(
-            "🚨DeprecationWarning: The method classify is deprecated. Please use `predict` instead."
-        )
-        result_dict = self.predict(X, file_type=file_type)
+
+        result_dict = self.predict(test_set, file_type=file_type)
         return result_dict["classification"]

pypots/classification/grud/data.py

@@ -23,7 +23,7 @@ class DatasetForGRUD(BaseDataset):
     data :
         The dataset for model input, should be a dictionary including keys as 'X' and 'y',
         or a path string locating a data file.
-        If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+        If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
         which is time-series data for input, can contain missing values, and y should be array-like of shape
         [n_samples], which is classification labels of X.
         If it is a path string, the path should point to a data file, e.g. a h5 file, which contains

pypots/classification/grud/model.py

@@ -18,7 +18,6 @@
 from ..base import BaseNNClassifier
 from ...optim.adam import Adam
 from ...optim.base import Optimizer
-from ...utils.logging import logger
 
 
 class GRUD(BaseNNClassifier):
@@ -234,19 +233,15 @@ def predict(
 
     def classify(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Classify the input data with the trained model.
 
-        Warnings
-        --------
-        The method classify is deprecated. Please use `predict()` instead.
-
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -257,8 +252,6 @@ def classify(
         array-like, shape [n_samples],
             Classification results of the given samples.
         """
-        logger.warning(
-            "🚨DeprecationWarning: The method classify is deprecated. Please use `predict` instead."
-        )
-        result_dict = self.predict(X, file_type=file_type)
+
+        result_dict = self.predict(test_set, file_type=file_type)
         return result_dict["classification"]

pypots/classification/raindrop/data.py

@@ -19,7 +19,7 @@ class DatasetForRaindrop(DatasetForGRUD):
     data :
         The dataset for model input, should be a dictionary including keys as 'X' and 'y',
         or a path string locating a data file.
-        If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+        If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
         which is time-series data for input, can contain missing values, and y should be array-like of shape
         [n_samples], which is classification labels of X.
         If it is a path string, the path should point to a data file, e.g. a h5 file, which contains

pypots/classification/raindrop/model.py

@@ -19,7 +19,6 @@
 from ...classification.base import BaseNNClassifier
 from ...optim.adam import Adam
 from ...optim.base import Optimizer
-from ...utils.logging import logger
 
 
 class Raindrop(BaseNNClassifier):
@@ -279,19 +278,15 @@ def predict(
 
     def classify(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Classify the input data with the trained model.
 
-        Warnings
-        --------
-        The method classify is deprecated. Please use `predict()` instead.
-
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -302,8 +297,6 @@ def classify(
         array-like, shape [n_samples],
             Classification results of the given samples.
         """
-        logger.warning(
-            "🚨DeprecationWarning: The method classify is deprecated. Please use `predict` instead."
-        )
-        result_dict = self.predict(X, file_type=file_type)
+
+        result_dict = self.predict(test_set, file_type=file_type)
         return result_dict["classification"]

pypots/classification/template/model.py

@@ -88,3 +88,10 @@ def predict(
         file_type: str = "hdf5",
     ) -> dict:
         raise NotImplementedError
+
+    def classify(
+        self,
+        test_set: Union[dict, str],
+        file_type: str = "hdf5",
+    ) -> dict:
+        raise NotImplementedError

pypots/clustering/base.py

@@ -81,15 +81,15 @@ def fit(
         train_set :
             The dataset for model training, should be a dictionary including the key 'X',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for training, can contain missing values.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
             key-value pairs like a dict, and it has to include the key 'X'.
 
         val_set :
             The dataset for model validating, should be a dictionary including keys as 'X' and 'y',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for validating, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -112,15 +112,15 @@ def predict(
     @abstractmethod
     def cluster(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Cluster the input with the trained model.
 
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -131,8 +131,7 @@ def cluster(
         array-like,
             Clustering results.
         """
-        # this is for old API compatibility, will be removed in the future.
-        # Please implement predict() instead.
+
         raise NotImplementedError
 
 
@@ -388,15 +387,15 @@ def fit(
         train_set :
             The dataset for model training, should be a dictionary including the key 'X',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for training, can contain missing values.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
             key-value pairs like a dict, and it has to include the key 'X'.
 
         val_set :
             The dataset for model validating, should be a dictionary including keys as 'X' and 'y',
             or a path string locating a data file.
-            If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+            If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
             which is time-series data for validating, can contain missing values, and y should be array-like of shape
             [n_samples], which is classification labels of X.
             If it is a path string, the path should point to a data file, e.g. a h5 file, which contains
@@ -419,19 +418,17 @@ def predict(
     @abstractmethod
     def cluster(
         self,
-        X: Union[dict, str],
+        test_set: Union[dict, str],
         file_type: str = "hdf5",
     ) -> np.ndarray:
         """Cluster the input with the trained model.
 
-        Warnings
-        --------
-        The method cluster is deprecated. Please use `predict()` instead.
+
 
         Parameters
         ----------
-        X :
-            The data samples for testing, should be array-like of shape [n_samples, sequence length (time steps),
+        test_set :
+            The data samples for testing, should be array-like of shape [n_samples, sequence length (n_steps),
             n_features], or a path string locating a data file, e.g. h5 file.
 
         file_type :
@@ -442,6 +439,5 @@ def cluster(
         array-like,
             Clustering results.
         """
-        # this is for old API compatibility, will be removed in the future.
-        # Please implement predict() instead.
+
         raise NotImplementedError

pypots/clustering/crli/data.py

@@ -19,7 +19,7 @@ class DatasetForCRLI(BaseDataset):
     data :
         The dataset for model input, should be a dictionary including keys as 'X' and 'y',
         or a path string locating a data file.
-        If it is a dict, X should be array-like of shape [n_samples, sequence length (time steps), n_features],
+        If it is a dict, X should be array-like of shape [n_samples, sequence length (n_steps), n_features],
         which is time-series data for input, can contain missing values, and y should be array-like of shape
         [n_samples], which is classification labels of X.
         If it is a path string, the path should point to a data file, e.g. a h5 file, which contains