Merge branch 'lukas_issue146_refac_rename-interpolate' into 'develop'

Resolve "REFAC: rename parameters interpolate_... with interpolation_...."

See merge request toar/machinelearningtools!120

mlair/configuration/defaults.py

@@ -28,8 +28,8 @@ DEFAULT_TARGET_VAR = "o3"
 DEFAULT_TARGET_DIM = "variables"
 DEFAULT_WINDOW_LEAD_TIME = 3
 DEFAULT_DIMENSIONS = {"new_index": ["datetime", "Stations"]}
-DEFAULT_INTERPOLATE_DIM = "datetime"
-DEFAULT_INTERPOLATE_METHOD = "linear"
+DEFAULT_INTERPOLATION_DIM = "datetime"
+DEFAULT_INTERPOLATION_METHOD = "linear"
 DEFAULT_LIMIT_NAN_FILL = 1
 DEFAULT_TRAIN_START = "1997-01-01"
 DEFAULT_TRAIN_END = "2007-12-31"

mlair/data_handling/data_generator.py

@@ -58,8 +58,8 @@ class DataGenerator(keras.utils.Sequence):
     """
 
     def __init__(self, data_path: str, stations: Union[str, List[str]], variables: List[str],
-                 interpolate_dim: str, target_dim: str, target_var: str, station_type: str = None,
-                 interpolate_method: str = "linear", limit_nan_fill: int = 1, window_history_size: int = 7,
+                 interpolation_dim: str, target_dim: str, target_var: str, station_type: str = None,
+                 interpolation_method: str = "linear", limit_nan_fill: int = 1, window_history_size: int = 7,
                  window_lead_time: int = 4, transformation: Dict = None, extreme_values: num_or_list = None,
                  data_preparation=None, **kwargs):
         """
@@ -68,11 +68,11 @@ class DataGenerator(keras.utils.Sequence):
         :param data_path: path to data
         :param stations: list with all stations to include
         :param variables: list with all used variables
-        :param interpolate_dim: dimension along which interpolation is applied
+        :param interpolation_dim: dimension along which interpolation is applied
         :param target_dim: dimension of target variable
         :param target_var: name of target variable
         :param station_type: TOAR station type classification (background, traffic)
-        :param interpolate_method: method of interpolation
+        :param interpolation_method: method of interpolation
         :param limit_nan_fill: maximum gab in data to fill by interpolation
         :param window_history_size: length of the history window
         :param window_lead_time: lenght of the label window
@@ -87,11 +87,11 @@ class DataGenerator(keras.utils.Sequence):
             os.makedirs(self.data_path_tmp)
         self.stations = helpers.to_list(stations)
         self.variables = variables
-        self.interpolate_dim = interpolate_dim
+        self.interpolation_dim = interpolation_dim
         self.target_dim = target_dim
         self.target_var = target_var
         self.station_type = station_type
-        self.interpolate_method = interpolate_method
+        self.interpolation_method = interpolation_method
         self.limit_nan_fill = limit_nan_fill
         self.window_history_size = window_history_size
         self.window_lead_time = window_lead_time
@@ -104,7 +104,7 @@ class DataGenerator(keras.utils.Sequence):
         """Display all class attributes."""
         return f"DataGenerator(path='{self.data_path}', stations={self.stations}, " \
                f"variables={self.variables}, station_type={self.station_type}, " \
-               f"interpolate_dim='{self.interpolate_dim}', target_dim='{self.target_dim}', " \
+               f"interpolation_dim='{self.interpolation_dim}', target_dim='{self.target_dim}', " \
                f"target_var='{self.target_var}', **{self.kwargs})"
 
     def __len__(self):
@@ -292,11 +292,11 @@ class DataGenerator(keras.utils.Sequence):
                                  **self.kwargs)
             if self.transformation is not None:
                 data.transform("datetime", **helpers.remove_items(self.transformation, "scope"))
-            data.interpolate(self.interpolate_dim, method=self.interpolate_method, limit=self.limit_nan_fill)
-            data.make_history_window(self.target_dim, self.window_history_size, self.interpolate_dim)
-            data.make_labels(self.target_dim, self.target_var, self.interpolate_dim, self.window_lead_time)
-            data.make_observation(self.target_dim, self.target_var, self.interpolate_dim)
-            data.remove_nan(self.interpolate_dim)
+            data.interpolate(self.interpolation_dim, method=self.interpolation_method, limit=self.limit_nan_fill)
+            data.make_history_window(self.target_dim, self.window_history_size, self.interpolation_dim)
+            data.make_labels(self.target_dim, self.target_var, self.interpolation_dim, self.window_lead_time)
+            data.make_observation(self.target_dim, self.target_var, self.interpolation_dim)
+            data.remove_nan(self.interpolation_dim)
             if self.extreme_values is not None:
                 kwargs = {"extremes_on_right_tail_only": self.kwargs.get("extremes_on_right_tail_only", False)}
                 data.multiply_extremes(self.extreme_values, **kwargs)

mlair/run_modules/experiment_setup.py

@@ -13,7 +13,7 @@ from mlair.configuration.defaults import DEFAULT_STATIONS, DEFAULT_VAR_ALL_DICT,
     DEFAULT_HPC_LOGIN_LIST, DEFAULT_HPC_HOST_LIST, DEFAULT_CREATE_NEW_MODEL, DEFAULT_TRAINABLE, \
     DEFAULT_FRACTION_OF_TRAINING, DEFAULT_EXTREME_VALUES, DEFAULT_EXTREMES_ON_RIGHT_TAIL_ONLY, DEFAULT_PERMUTE_DATA, \
     DEFAULT_BATCH_SIZE, DEFAULT_EPOCHS, DEFAULT_TARGET_VAR, DEFAULT_TARGET_DIM, DEFAULT_WINDOW_LEAD_TIME, \
-    DEFAULT_DIMENSIONS, DEFAULT_INTERPOLATE_DIM, DEFAULT_INTERPOLATE_METHOD, DEFAULT_LIMIT_NAN_FILL, \
+    DEFAULT_DIMENSIONS, DEFAULT_INTERPOLATION_DIM, DEFAULT_INTERPOLATION_METHOD, DEFAULT_LIMIT_NAN_FILL, \
     DEFAULT_TRAIN_START, DEFAULT_TRAIN_END, DEFAULT_TRAIN_MIN_LENGTH, DEFAULT_VAL_START, DEFAULT_VAL_END, \
     DEFAULT_VAL_MIN_LENGTH, DEFAULT_TEST_START, DEFAULT_TEST_END, DEFAULT_TEST_MIN_LENGTH, DEFAULT_TRAIN_VAL_MIN_LENGTH, \
     DEFAULT_USE_ALL_STATIONS_ON_ALL_DATA_SETS, DEFAULT_EVALUATE_BOOTSTRAPS, DEFAULT_CREATE_NEW_BOOTSTRAPS, \
@@ -66,8 +66,8 @@ class ExperimentSetup(RunEnvironment):
 
         # interpolation
         self._set_param("dimensions", dimensions, default={'new_index': ['datetime', 'Stations']})
-        self._set_param("interpolate_dim", interpolate_dim, default='datetime')
-        self._set_param("interpolate_method", interpolate_method, default='linear')
+        self._set_param("interpolation_dim", interpolation_dim, default='datetime')
+        self._set_param("interpolation_method", interpolation_method, default='linear')
         self._set_param("limit_nan_fill", limit_nan_fill, default=1)
 
         # train set parameters
@@ -140,8 +140,8 @@ class ExperimentSetup(RunEnvironment):
     :param window_lead_time: number of time steps to predict by model (default 3). Time steps `t_0+1` to `t_0+w` are
         predicted.
     :param dimensions:
-    :param interpolate_dim:
-    :param interpolate_method:
+    :param interpolation_dim:
+    :param interpolation_method:
     :param limit_nan_fill:
     :param train_start:
     :param train_end:
@@ -220,8 +220,8 @@ class ExperimentSetup(RunEnvironment):
                  target_dim=None,
                  window_lead_time: int = None,
                  dimensions=None,
-                 interpolate_dim=None,
-                 interpolate_method=None,
+                 interpolation_dim=None,
+                 interpolation_method=None,
                  limit_nan_fill=None, train_start=None, train_end=None, val_start=None, val_end=None, test_start=None,
                  test_end=None, use_all_stations_on_all_data_sets=None, trainable: bool = None, fraction_of_train: float = None,
                  experiment_path=None, plot_path: str = None, forecast_path: str = None, overwrite_local_data = None, sampling: str = "daily",
@@ -306,8 +306,8 @@ class ExperimentSetup(RunEnvironment):
 
         # interpolation
         self._set_param("dimensions", dimensions, default=DEFAULT_DIMENSIONS)
-        self._set_param("interpolate_dim", interpolate_dim, default=DEFAULT_INTERPOLATE_DIM)
-        self._set_param("interpolate_method", interpolate_method, default=DEFAULT_INTERPOLATE_METHOD)
+        self._set_param("interpolation_dim", interpolation_dim, default=DEFAULT_INTERPOLATION_DIM)
+        self._set_param("interpolation_method", interpolation_method, default=DEFAULT_INTERPOLATION_METHOD)
         self._set_param("limit_nan_fill", limit_nan_fill, default=DEFAULT_LIMIT_NAN_FILL)
 
         # train set parameters

mlair/run_modules/pre_processing.py

@@ -16,7 +16,7 @@ from mlair.configuration import path_config
 from mlair.helpers.join import EmptyQueryResult
 from mlair.run_modules.run_environment import RunEnvironment
 
-DEFAULT_ARGS_LIST = ["data_path", "stations", "variables", "interpolate_dim", "target_dim", "target_var"]
+DEFAULT_ARGS_LIST = ["data_path", "stations", "variables", "interpolation_dim", "target_dim", "target_var"]
 DEFAULT_KWARGS_LIST = ["limit_nan_fill", "window_history_size", "window_lead_time", "statistics_per_var", "min_length",
                        "station_type", "overwrite_local_data", "start", "end", "sampling", "transformation",
                        "extreme_values", "extremes_on_right_tail_only", "network", "data_preparation"]
@@ -225,8 +225,8 @@ class PreProcessing(RunEnvironment):
         loading time are logged in debug mode.
 
         :param args: Dictionary with required parameters for DataGenerator class (`data_path`, `network`, `stations`,
-            `variables`, `interpolate_dim`, `target_dim`, `target_var`).
-        :param kwargs: positional parameters for the DataGenerator class (e.g. `start`, `interpolate_method`,
+            `variables`, `interpolation_dim`, `target_dim`, `target_var`).
+        :param kwargs: positional parameters for the DataGenerator class (e.g. `start`, `interpolation_method`,
             `window_lead_time`).
         :param all_stations: All stations to check.
         :param name: name to display in the logging info message

test/test_data_handling/test_data_generator.py

@@ -80,10 +80,10 @@ class TestDataGenerator:
         assert gen.stations == ['DEBW107']
         assert gen.variables == ['o3', 'temp']
         assert gen.station_type is None
-        assert gen.interpolate_dim == 'datetime'
+        assert gen.interpolation_dim == 'datetime'
         assert gen.target_dim == 'variables'
         assert gen.target_var == 'o3'
-        assert gen.interpolate_method == "linear"
+        assert gen.interpolation_method == "linear"
         assert gen.limit_nan_fill == 1
         assert gen.window_history_size == 7
         assert gen.window_lead_time == 4
@@ -93,7 +93,7 @@ class TestDataGenerator:
     def test_repr(self, gen):
         path = os.path.join(os.path.dirname(__file__), 'data')
         assert gen.__repr__().rstrip() == f"DataGenerator(path='{path}', stations=['DEBW107'], " \
-                                          f"variables=['o3', 'temp'], station_type=None, interpolate_dim='datetime', " \
+                                          f"variables=['o3', 'temp'], station_type=None, interpolation_dim='datetime', " \
                                           f"target_dim='variables', target_var='o3', **{{'start': 2010, 'end': 2014}})" \
             .rstrip()
 

test/test_modules/test_experiment_setup.py

@@ -64,8 +64,8 @@ class TestExperimentSetup:
         assert data_store.get("window_lead_time", "general") == 3
         # interpolation
         assert data_store.get("dimensions", "general") == {'new_index': ['datetime', 'Stations']}
-        assert data_store.get("interpolate_dim", "general") == "datetime"
-        assert data_store.get("interpolate_method", "general") == "linear"
+        assert data_store.get("interpolation_dim", "general") == "datetime"
+        assert data_store.get("interpolation_method", "general") == "linear"
         assert data_store.get("limit_nan_fill", "general") == 1
         # train parameters
         assert data_store.get("start", "general.train") == "1997-01-01"
@@ -93,7 +93,7 @@ class TestExperimentSetup:
                       stations=['DEBY053', 'DEBW059', 'DEBW027'], network="INTERNET", station_type="background",
                       variables=["o3", "temp"], start="1999-01-01", end="2001-01-01", window_history_size=4,
                       target_var="relhum", target_dim="target", window_lead_time=10, dimensions="dim1",
-                      interpolate_dim="int_dim", interpolate_method="cubic", limit_nan_fill=5, train_start="2000-01-01",
+                      interpolation_dim="int_dim", interpolation_method="cubic", limit_nan_fill=5, train_start="2000-01-01",
                       train_end="2000-01-02", val_start="2000-01-03", val_end="2000-01-04", test_start="2000-01-05",
                       test_end="2000-01-06", use_all_stations_on_all_data_sets=False, trainable=False,
                       fraction_of_train=0.5, experiment_path=experiment_path, create_new_model=True, val_min_length=20)
@@ -125,8 +125,8 @@ class TestExperimentSetup:
         assert data_store.get("window_lead_time", "general") == 10
         # interpolation
         assert data_store.get("dimensions", "general") == "dim1"
-        assert data_store.get("interpolate_dim", "general") == "int_dim"
-        assert data_store.get("interpolate_method", "general") == "cubic"
+        assert data_store.get("interpolation_dim", "general") == "int_dim"
+        assert data_store.get("interpolation_method", "general") == "cubic"
         assert data_store.get("limit_nan_fill", "general") == 5
         # train parameters
         assert data_store.get("start", "general.train") == "2000-01-01"