new data handler that combines kz filter and mixed sampling types

mlair/data_handler/data_handler_kz_filter.py

@@ -24,7 +24,7 @@ class DataHandlerKzFilterSingleStation(DataHandlerSingleStation):
     _requirements = remove_items(inspect.getfullargspec(DataHandlerSingleStation).args, ["self", "station"])
 
     def __init__(self, *args, kz_filter_length, kz_filter_iter, **kwargs):
-        assert kwargs.get("sampling") == "hourly"  # This data handler requires hourly data resolution
+        self._check_sampling(**kwargs)
         kz_filter_length = to_list(kz_filter_length)
         kz_filter_iter = to_list(kz_filter_iter)
         # self.original_data = None  # ToDo: implement here something to store unfiltered data
@@ -34,6 +34,9 @@ class DataHandlerKzFilterSingleStation(DataHandlerSingleStation):
         self.cutoff_period_days = None
         super().__init__(*args, **kwargs)
 
+    def _check_sampling(self, **kwargs):
+        assert kwargs.get("sampling") == "hourly"  # This data handler requires hourly data resolution
+
     def setup_samples(self):
         """
         Setup samples. This method prepares and creates samples X, and labels Y.

mlair/data_handler/data_handler_mixed_sampling.py

@@ -2,6 +2,7 @@ __author__ = 'Lukas Leufen'
 __date__ = '2020-11-05'
 
 from mlair.data_handler.data_handler_single_station import DataHandlerSingleStation
+from mlair.data_handler.data_handler_kz_filter import DataHandlerKzFilterSingleStation
 from mlair.data_handler import DefaultDataHandler
 from mlair.configuration import path_config
 from mlair import helpers
@@ -59,3 +60,38 @@ class DataHandlerMixedSampling(DefaultDataHandler):
     data_handler = DataHandlerMixedSamplingSingleStation
     data_handler_transformation = DataHandlerMixedSamplingSingleStation
     _requirements = data_handler.requirements()
+
+
+class DataHandlerMixedSamplingWithFilterSingleStation(DataHandlerMixedSamplingSingleStation,
+                                                      DataHandlerKzFilterSingleStation):
+    _requirements1 = DataHandlerKzFilterSingleStation.requirements()
+    _requirements2 = DataHandlerMixedSamplingSingleStation.requirements()
+    _requirements = list(set(_requirements1 + _requirements2))
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    def _check_sampling(self, **kwargs):
+        assert kwargs.get("sampling") == ("hourly", "daily")
+
+    def setup_samples(self):
+        """
+        Setup samples. This method prepares and creates samples X, and labels Y.
+
+        A KZ filter is applied on the input data that has hourly resolution. Lables Y are provided as aggregated values
+        with daily resolution.
+        """
+        self._data = list(map(self.load_and_interpolate, [0, 1]))  # load input (0) and target (1) data
+        self.set_inputs_and_targets()
+        self.apply_kz_filter()
+        if self.do_transformation is True:
+            self.call_transform()
+        self.make_samples()
+
+
+class DataHandlerMixedSamplingWithFilter(DefaultDataHandler):
+    """Data handler using mixed sampling for input and target. Inputs are temporal filtered."""
+
+    data_handler = DataHandlerMixedSamplingWithFilterSingleStation
+    data_handler_transformation = DataHandlerMixedSamplingWithFilterSingleStation
+    _requirements = data_handler.requirements()

run_mixed_sampling.py

@@ -4,7 +4,7 @@ __date__ = '2019-11-14'
 import argparse
 
 from mlair.workflows import DefaultWorkflow
-from mlair.data_handler.data_handler_mixed_sampling import DataHandlerMixedSampling
+from mlair.data_handler.data_handler_mixed_sampling import DataHandlerMixedSampling, DataHandlerMixedSamplingWithFilter
 
 
 def main(parser_args):
@@ -12,7 +12,9 @@ def main(parser_args):
                 sampling_inputs="hourly",
                 window_history_size=72,
                 **parser_args.__dict__,
-                data_handler=DataHandlerMixedSampling,
+                data_handler=DataHandlerMixedSampling,  # WithFilter,
+                kz_filter_length=[365 * 24, 20 * 24],
+                kz_filter_iter=[3, 5],
                 start="2006-01-01",
                 train_start="2006-01-01",
                 end="2011-12-31",