diff --git a/src/configuration/defaults.py b/src/configuration/defaults.py
new file mode 100644
index 0000000000000000000000000000000000000000..7ce96cfce515e7f32d98444e6a9542c9fbd7b4f4
--- /dev/null
+++ b/src/configuration/defaults.py
@@ -0,0 +1,64 @@
+__author__ = "Lukas Leufen"
+__date__ = '2020-06-25'
+
+
+DEFAULT_STATIONS = ['DEBW107', 'DEBY081', 'DEBW013', 'DEBW076', 'DEBW087', 'DEBY052', 'DEBY032', 'DEBW022', 'DEBY004',
+ 'DEBY020', 'DEBW030', 'DEBW037', 'DEBW031', 'DEBW015', 'DEBW073', 'DEBY039', 'DEBW038', 'DEBW081',
+ 'DEBY075', 'DEBW040', 'DEBY053', 'DEBW059', 'DEBW027', 'DEBY072', 'DEBW042', 'DEBW039', 'DEBY001',
+ 'DEBY113', 'DEBY089', 'DEBW024', 'DEBW004', 'DEBY037', 'DEBW056', 'DEBW029', 'DEBY068', 'DEBW010',
+ 'DEBW026', 'DEBY002', 'DEBY079', 'DEBW084', 'DEBY049', 'DEBY031', 'DEBW019', 'DEBW001', 'DEBY063',
+ 'DEBY005', 'DEBW046', 'DEBW103', 'DEBW052', 'DEBW034', 'DEBY088', ]
+DEFAULT_VAR_ALL_DICT = {'o3': 'dma8eu', 'relhum': 'average_values', 'temp': 'maximum', 'u': 'average_values',
+ 'v': 'average_values', 'no': 'dma8eu', 'no2': 'dma8eu', 'cloudcover': 'average_values',
+ 'pblheight': 'maximum'}
+DEFAULT_NETWORK = "AIRBASE"
+DEFAULT_STATION_TYPE = "background"
+DEFAULT_VARIABLES = DEFAULT_VAR_ALL_DICT.keys()
+DEFAULT_START = "1997-01-01"
+DEFAULT_END = "2017-12-31"
+DEFAULT_WINDOW_HISTORY_SIZE = 13
+DEFAULT_OVERWRITE_LOCAL_DATA = False
+DEFAULT_TRANSFORMATION = {"scope": "data", "method": "standardise", "mean": "estimate"}
+DEFAULT_HPC_LOGIN_LIST = ["ju", "hdfmll"] # ju[wels} #hdfmll(ogin)
+DEFAULT_HPC_HOST_LIST = ["jw", "hdfmlc"] # first part of node names for Juwels (jw[comp], hdfmlc(ompute).
+DEFAULT_CREATE_NEW_MODEL = True
+DEFAULT_TRAINABLE = True
+DEFAULT_FRACTION_OF_TRAINING = 0.8
+DEFAULT_EXTREME_VALUES = None
+DEFAULT_EXTREMES_ON_RIGHT_TAIL_ONLY = False
+DEFAULT_PERMUTE_DATA = False
+DEFAULT_BATCH_SIZE = int(256 * 2)
+DEFAULT_EPOCHS = 20
+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_LIMIT_NAN_FILL = 1
+DEFAULT_TRAIN_START = "1997-01-01"
+DEFAULT_TRAIN_END = "2007-12-31"
+DEFAULT_TRAIN_MIN_LENGTH = 90
+DEFAULT_VAL_START = "2008-01-01"
+DEFAULT_VAL_END = "2009-12-31"
+DEFAULT_VAL_MIN_LENGTH = 90
+DEFAULT_TEST_START = "2010-01-01"
+DEFAULT_TEST_END = "2017-12-31"
+DEFAULT_TEST_MIN_LENGTH = 90
+DEFAULT_TRAIN_VAL_MIN_LENGTH = 180
+DEFAULT_USE_ALL_STATIONS_ON_ALL_DATA_SETS = True
+DEFAULT_EVALUATE_BOOTSTRAPS = True
+DEFAULT_CREATE_NEW_BOOTSTRAPS = False
+DEFAULT_NUMBER_OF_BOOTSTRAPS = 20
+DEFAULT_PLOT_LIST = ["PlotMonthlySummary", "PlotStationMap", "PlotClimatologicalSkillScore", "PlotTimeSeries",
+ "PlotCompetitiveSkillScore", "PlotBootstrapSkillScore", "PlotConditionalQuantiles",
+ "PlotAvailability"]
+
+
+def get_defaults():
+ """Return all default parameters set in defaults.py"""
+ return {key: value for key, value in globals().items() if key.startswith('DEFAULT')}
+
+
+if __name__ == "__main__":
+ print(get_defaults())
\ No newline at end of file
diff --git a/src/run.py b/src/run.py
index 11029817a978b872d0f99954a50ab5f5b93aa012..cd97217efd74b81bcaf79b4b2351c4c063efcbf0 100644
--- a/src/run.py
+++ b/src/run.py
@@ -4,33 +4,33 @@ import argparse
import inspect
-def run(stations=['DEBW107', 'DEBY081', 'DEBW013', 'DEBW076', 'DEBW087', 'DEBW001'],
- station_type='background',
- trainable=False, create_new_model=True,
- window_history_size=6,
+def run(stations=None,
+ station_type=None,
+ trainable=None, create_new_model=None,
+ window_history_size=None,
experiment_date="testrun",
network=None,
variables=None, statistics_per_var=None,
start=None, end=None,
- target_var="o3", target_dim=None,
+ target_var=None, target_dim=None,
window_lead_time=None,
dimensions=None,
interpolate_method=None, interpolate_dim=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=True, fraction_of_train=None,
+ use_all_stations_on_all_data_sets=None, fraction_of_train=None,
experiment_path=None, plot_path=None, forecast_path=None, bootstrap_path=None, overwrite_local_data=None,
- sampling="daily",
- permute_data_on_training=False, extreme_values=None, extremes_on_right_tail_only=None,
+ sampling=None,
+ permute_data_on_training=None, extreme_values=None, extremes_on_right_tail_only=None,
transformation=None,
train_min_length=None, val_min_length=None, test_min_length=None,
- evaluate_bootstraps=True, number_of_bootstraps=None, create_new_bootstraps=False,
+ evaluate_bootstraps=None, number_of_bootstraps=None, create_new_bootstraps=None,
plot_list=None,
model=None,
batch_size=None,
epochs=None):
params = inspect.getfullargspec(ExperimentSetup).args
- kwargs = {k: v for k, v in locals().items() if k in params}
+ kwargs = {k: v for k, v in locals().items() if k in params and v is not None}
parser = argparse.ArgumentParser()
parser.add_argument('--experiment_date', metavar='--exp_date', type=str, default="testrun",
diff --git a/src/run_modules/experiment_setup.py b/src/run_modules/experiment_setup.py
index ff6fec842714d599696b8726e9d25aa22e55583f..e89926a67ea4d63847fdc3eab71d56c45a99f6b3 100644
--- a/src/run_modules/experiment_setup.py
+++ b/src/run_modules/experiment_setup.py
@@ -8,25 +8,19 @@ from typing import Union, Dict, Any, List
from src.configuration import path_config
from src import helpers
+from src.configuration.defaults import DEFAULT_STATIONS, DEFAULT_VAR_ALL_DICT, DEFAULT_NETWORK, DEFAULT_STATION_TYPE, \
+ DEFAULT_START, DEFAULT_END, DEFAULT_WINDOW_HISTORY_SIZE, DEFAULT_OVERWRITE_LOCAL_DATA, DEFAULT_TRANSFORMATION, \
+ 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_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, \
+ DEFAULT_NUMBER_OF_BOOTSTRAPS, DEFAULT_PLOT_LIST
from src.run_modules.run_environment import RunEnvironment
from src.model_modules.model_class import MyLittleModel as VanillaModel
-DEFAULT_STATIONS = ['DEBW107', 'DEBY081', 'DEBW013', 'DEBW076', 'DEBW087', 'DEBY052', 'DEBY032', 'DEBW022', 'DEBY004',
- 'DEBY020', 'DEBW030', 'DEBW037', 'DEBW031', 'DEBW015', 'DEBW073', 'DEBY039', 'DEBW038', 'DEBW081',
- 'DEBY075', 'DEBW040', 'DEBY053', 'DEBW059', 'DEBW027', 'DEBY072', 'DEBW042', 'DEBW039', 'DEBY001',
- 'DEBY113', 'DEBY089', 'DEBW024', 'DEBW004', 'DEBY037', 'DEBW056', 'DEBW029', 'DEBY068', 'DEBW010',
- 'DEBW026', 'DEBY002', 'DEBY079', 'DEBW084', 'DEBY049', 'DEBY031', 'DEBW019', 'DEBW001', 'DEBY063',
- 'DEBY005', 'DEBW046', 'DEBW103', 'DEBW052', 'DEBW034', 'DEBY088', ]
-DEFAULT_VAR_ALL_DICT = {'o3': 'dma8eu', 'relhum': 'average_values', 'temp': 'maximum', 'u': 'average_values',
- 'v': 'average_values', 'no': 'dma8eu', 'no2': 'dma8eu', 'cloudcover': 'average_values',
- 'pblheight': 'maximum'}
-DEFAULT_TRANSFORMATION = {"scope": "data", "method": "standardise", "mean": "estimate"}
-DEFAULT_PLOT_LIST = ["PlotMonthlySummary", "PlotStationMap", "PlotClimatologicalSkillScore", "PlotTimeSeries",
- "PlotCompetitiveSkillScore", "PlotBootstrapSkillScore", "PlotConditionalQuantiles",
- "PlotAvailability"]
-DEFAULT_HPC_LOGIN_LIST = ["ju", "hdfmll"] # ju[wels} #hdfmll(ogin)
-DEFAULT_HPC_HOST_LIST = ["jw", "hdfmlc"] # first part of node names for Juwels (jw[comp], hdfmlc(ompute).
-
class ExperimentSetup(RunEnvironment):
"""
@@ -228,11 +222,11 @@ class ExperimentSetup(RunEnvironment):
interpolate_dim=None,
interpolate_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=True, trainable: bool = None, fraction_of_train: float = None,
- experiment_path=None, plot_path: str = None, forecast_path: str = None, overwrite_local_data: bool = None, sampling: str = "daily",
- create_new_model: bool = None, bootstrap_path=None, permute_data_on_training: bool = None, transformation=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",
+ create_new_model = None, bootstrap_path=None, permute_data_on_training = None, transformation=None,
train_min_length=None, val_min_length=None, test_min_length=None, extreme_values: list = None,
- extremes_on_right_tail_only: bool = None, evaluate_bootstraps=True, plot_list=None, number_of_bootstraps=None,
+ extremes_on_right_tail_only: bool = None, evaluate_bootstraps=None, plot_list=None, number_of_bootstraps=None,
create_new_bootstraps=None, data_path: str = None, login_nodes=None, hpc_hosts=None, model=None,
batch_size=None, epochs=None):
@@ -244,22 +238,23 @@ class ExperimentSetup(RunEnvironment):
self._set_param("hostname", path_config.get_host())
self._set_param("hpc_hosts", hpc_hosts, default=DEFAULT_HPC_HOST_LIST + DEFAULT_HPC_LOGIN_LIST)
self._set_param("login_nodes", login_nodes, default=DEFAULT_HPC_LOGIN_LIST)
- self._set_param("create_new_model", create_new_model, default=True)
+ self._set_param("create_new_model", create_new_model, default=DEFAULT_CREATE_NEW_MODEL)
if self.data_store.get("create_new_model"):
trainable = True
data_path = self.data_store.get("data_path")
bootstrap_path = path_config.set_bootstrap_path(bootstrap_path, data_path, sampling)
self._set_param("bootstrap_path", bootstrap_path)
- self._set_param("trainable", trainable, default=True)
- self._set_param("fraction_of_training", fraction_of_train, default=0.8)
- self._set_param("extreme_values", extreme_values, default=None, scope="train")
- self._set_param("extremes_on_right_tail_only", extremes_on_right_tail_only, default=False, scope="train")
+ self._set_param("trainable", trainable, default=DEFAULT_TRAINABLE)
+ self._set_param("fraction_of_training", fraction_of_train, default=DEFAULT_FRACTION_OF_TRAINING)
+ self._set_param("extreme_values", extreme_values, default=DEFAULT_EXTREME_VALUES, scope="train")
+ self._set_param("extremes_on_right_tail_only", extremes_on_right_tail_only,
+ default=DEFAULT_EXTREMES_ON_RIGHT_TAIL_ONLY, scope="train")
self._set_param("upsampling", extreme_values is not None, scope="train")
upsampling = self.data_store.get("upsampling", "train")
- permute_data = False if permute_data_on_training is None else permute_data_on_training
+ permute_data = DEFAULT_PERMUTE_DATA if permute_data_on_training is None else permute_data_on_training
self._set_param("permute_data", permute_data or upsampling, scope="train")
- self._set_param("batch_size", batch_size, default=int(256 * 2))
- self._set_param("epochs", epochs, default=20)
+ self._set_param("batch_size", batch_size, default=DEFAULT_BATCH_SIZE)
+ self._set_param("epochs", epochs, default=DEFAULT_EPOCHS)
# set experiment name
exp_date = self._get_parser_args(parser_args).get("experiment_date")
@@ -290,58 +285,63 @@ class ExperimentSetup(RunEnvironment):
# setup for data
self._set_param("stations", stations, default=DEFAULT_STATIONS)
- self._set_param("network", network, default="AIRBASE")
- self._set_param("station_type", station_type, default=None)
+ self._set_param("network", network, default=DEFAULT_NETWORK)
+ self._set_param("station_type", station_type, default=DEFAULT_STATION_TYPE)
self._set_param("statistics_per_var", statistics_per_var, default=DEFAULT_VAR_ALL_DICT)
self._set_param("variables", variables, default=list(self.data_store.get("statistics_per_var").keys()))
- self._set_param("start", start, default="1997-01-01")
- self._set_param("end", end, default="2017-12-31")
- self._set_param("window_history_size", window_history_size, default=13)
- self._set_param("overwrite_local_data", overwrite_local_data, default=False, scope="preprocessing")
+ self._set_param("start", start, default=DEFAULT_START)
+ self._set_param("end", end, default=DEFAULT_END)
+ self._set_param("window_history_size", window_history_size, default=DEFAULT_WINDOW_HISTORY_SIZE)
+ self._set_param("overwrite_local_data", overwrite_local_data, default=DEFAULT_OVERWRITE_LOCAL_DATA,
+ scope="preprocessing")
self._set_param("sampling", sampling)
self._set_param("transformation", transformation, default=DEFAULT_TRANSFORMATION)
self._set_param("transformation", None, scope="preprocessing")
# target
- self._set_param("target_var", target_var, default="o3")
- self._set_param("target_dim", target_dim, default='variables')
- self._set_param("window_lead_time", window_lead_time, default=3)
+ self._set_param("target_var", target_var, default=DEFAULT_TARGET_VAR)
+ self._set_param("target_dim", target_dim, default=DEFAULT_TARGET_DIM)
+ self._set_param("window_lead_time", window_lead_time, default=DEFAULT_WINDOW_LEAD_TIME)
# 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("limit_nan_fill", limit_nan_fill, default=1)
+ 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("limit_nan_fill", limit_nan_fill, default=DEFAULT_LIMIT_NAN_FILL)
# 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")
+ self._set_param("start", train_start, default=DEFAULT_TRAIN_START, scope="train")
+ self._set_param("end", train_end, default=DEFAULT_TRAIN_END, scope="train")
+ self._set_param("min_length", train_min_length, default=DEFAULT_TRAIN_MIN_LENGTH, 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")
+ self._set_param("start", val_start, default=DEFAULT_VAL_START, scope="val")
+ self._set_param("end", val_end, default=DEFAULT_VAL_END, scope="val")
+ self._set_param("min_length", val_min_length, default=DEFAULT_VAL_MIN_LENGTH, 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")
+ self._set_param("start", test_start, default=DEFAULT_TEST_START, scope="test")
+ self._set_param("end", test_end, default=DEFAULT_TEST_END, scope="test")
+ self._set_param("min_length", test_min_length, default=DEFAULT_TEST_MIN_LENGTH, 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")
+ self._set_param("min_length", train_val_min_length, default=DEFAULT_TRAIN_VAL_MIN_LENGTH, 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)
+ self._set_param("use_all_stations_on_all_data_sets", use_all_stations_on_all_data_sets,
+ default=DEFAULT_USE_ALL_STATIONS_ON_ALL_DATA_SETS)
# set post-processing instructions
- self._set_param("evaluate_bootstraps", evaluate_bootstraps, scope="general.postprocessing")
- create_new_bootstraps = max([self.data_store.get("trainable", "general"), create_new_bootstraps or False])
+ self._set_param("evaluate_bootstraps", evaluate_bootstraps, default=DEFAULT_EVALUATE_BOOTSTRAPS,
+ scope="general.postprocessing")
+ create_new_bootstraps = max([self.data_store.get("trainable", "general"),
+ create_new_bootstraps or DEFAULT_CREATE_NEW_BOOTSTRAPS])
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("number_of_bootstraps", number_of_bootstraps, default=DEFAULT_NUMBER_OF_BOOTSTRAPS,
+ scope="general.postprocessing")
self._set_param("plot_list", plot_list, default=DEFAULT_PLOT_LIST, scope="general.postprocessing")
# check variables, statistics and target variable