From a1815b4921c20f9fa885c8900cdf937a17704ae5 Mon Sep 17 00:00:00 2001
From: leufen1 <l.leufen@fz-juelich.de>
Date: Wed, 31 Mar 2021 11:11:27 +0200
Subject: [PATCH] updated docs

---
 docs/_source/defaults.rst             |  2 +
 mlair/run_modules/experiment_setup.py | 72 +++++++++++----------------
 2 files changed, 30 insertions(+), 44 deletions(-)

diff --git a/docs/_source/defaults.rst b/docs/_source/defaults.rst
index 775134f5..e95cf10e 100644
--- a/docs/_source/defaults.rst
+++ b/docs/_source/defaults.rst
@@ -17,6 +17,7 @@ create_new_model
 data_handler
 data_origin
 data_path
+debug                             -               MLAir checks if it is running in debug mode and stores this
 dimensions
 end
 epochs
@@ -57,6 +58,7 @@ train_start
 transformation                    :py:`{}`        implement all further transformation functionality
                                                   inside your custom data handler
 use_all_stations_on_all_data_sets
+use_multiprocessing               :py:`True`      is set to False if MLAir is running in debug mode
 upsampling
 val_end
 val_min_length
diff --git a/mlair/run_modules/experiment_setup.py b/mlair/run_modules/experiment_setup.py
index f51cee8a..c777bcc4 100644
--- a/mlair/run_modules/experiment_setup.py
+++ b/mlair/run_modules/experiment_setup.py
@@ -64,48 +64,6 @@ class ExperimentSetup(RunEnvironment):
         * `target_dim` [.]
         * `window_lead_time` [.]
 
-        # interpolation
-        self._set_param("dimensions", dimensions, default={'new_index': ['datetime', 'Stations']})
-        self._set_param("time_dim", time_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
-        self._set_param("start", train_start, default="1997-01-01", scope="train")
-        self._set_param("end", train_end, default="2007-12-31", scope="train")
-        self._set_param("min_length", train_min_length, default=90, scope="train")
-
-        # validation set parameters
-        self._set_param("start", val_start, default="2008-01-01", scope="val")
-        self._set_param("end", val_end, default="2009-12-31", scope="val")
-        self._set_param("min_length", val_min_length, default=90, scope="val")
-
-        # test set parameters
-        self._set_param("start", test_start, default="2010-01-01", scope="test")
-        self._set_param("end", test_end, default="2017-12-31", scope="test")
-        self._set_param("min_length", test_min_length, default=90, scope="test")
-
-        # train_val set parameters
-        self._set_param("start", self.data_store.get("start", "train"), scope="train_val")
-        self._set_param("end", self.data_store.get("end", "val"), scope="train_val")
-        train_val_min_length = sum([self.data_store.get("min_length", s) for s in ["train", "val"]])
-        self._set_param("min_length", train_val_min_length, default=180, scope="train_val")
-
-        # use all stations on all data sets (train, val, test)
-        self._set_param("use_all_stations_on_all_data_sets", use_all_stations_on_all_data_sets, default=True)
-
-        # set post-processing instructions
-        self._set_param("evaluate_bootstraps", evaluate_bootstraps, scope="general.postprocessing")
-        create_new_bootstraps = max([self.data_store.get("train_model", "general"), create_new_bootstraps or False])
-        self._set_param("create_new_bootstraps", create_new_bootstraps, scope="general.postprocessing")
-        self._set_param("number_of_bootstraps", number_of_bootstraps, default=20, scope="general.postprocessing")
-        self._set_param("plot_list", plot_list, default=DEFAULT_PLOT_LIST, scope="general.postprocessing")
-
-        # check variables, statistics and target variable
-        self._check_target_var()
-        self._compare_variables_and_statistics()
-
-
     Creates
         * plot of model architecture in `<model_name>.pdf`
 
@@ -137,8 +95,11 @@ class ExperimentSetup(RunEnvironment):
         predicted.
     :param dimensions:
     :param time_dim:
-    :param interpolation_method:
-    :param limit_nan_fill:
+    :param interpolation_method: The method to use for interpolation.
+    :param interpolation_limit: The maximum number of subsequent time steps in a gap to fill by interpolation. If the
+        gap exceeds this number, the gap is not filled by interpolation at all. The value of time steps is an arbitrary
+        number that is applied depending on the `sampling` frequency. A limit of 2 means that either 2 hours or 2 days
+        are allowed to be interpolated in dependency of the set sampling rate.
     :param train_start:
     :param train_end:
     :param val_start:
@@ -199,6 +160,29 @@ class ExperimentSetup(RunEnvironment):
     :param data_path: path to find and store meteorological and environmental / air quality data. Leave this parameter
         empty, if your host system is known and a suitable path was already hardcoded in the program (see
         :py:func:`prepare host <src.configuration.path_config.prepare_host>`).
+    :param experiment_date:
+    :param window_dim: "Temporal" dimension of the input and target data, that is provided for each sample. The number
+        of samples provided in this dimension can be set using `window_history_size` for inputs and `window_lead_time`
+        on target site.
+    :param iter_dim:
+    :param batch_path:
+    :param login_nodes:
+    :param hpc_hosts:
+    :param model:
+    :param batch_size:
+    :param epochs: Number of epochs used in training. If a training is resumed and the number of epochs of the already
+        (partly) trained model is lower than this parameter, training is continue. In case this number is higher than
+        the given epochs parameter, no training is resumed. Epochs is set to 20 per default, but this value is just a
+        placeholder that should be adjusted for a meaningful training.
+    :param data_handler:
+    :param data_origin:
+    :param competitors: Provide names of reference models trained by MLAir that can be found in the `competitor_path`.
+        These models will be used in the postprocessing for comparison.
+    :param competitor_path: The path where MLAir can find competing models. If not provided, this path is assumed to be
+        in the ´data_path´ directory as a subdirectory called `competitors` (default).
+    :param use_multiprocessing: Enable parallel preprocessing (postprocessing not implemented yet) by setting this
+        parameter to `True` (default). If set to `False` the computation is performed in an serial approach.
+        Multiprocessing is disabled when running in debug mode and cannot be switched on.
 
     """
 
-- 
GitLab