max_depth=0.1)
for idx in ids:
metadata = ismn_reader.metadata[idx]
jobs.append((idx, metadata['longitude'], metadata['latitude']))
print("Jobs (gpi, lon, lat):")
print(jobs)
# For this small test dataset it is only one job
#
# It is important here that the ISMN reader has a read_ts function that works by just using the `dataset_id`. In this
# way the validation framework can go through the jobs and read the correct time series.
# In[6]:
data = ismn_reader.read_ts(ids[0])
print('ISMN data example:')
print(data.head())
# ## Initialize the Validation class
#
# The Validation class is the heart of the validation framwork. It contains the information about which datasets to
# read using which arguments or keywords and if they are spatially compatible. It also contains the settings about
# which metric calculators to use and how to perform the scaling into the reference data space. It is initialized in
# the following way:
# In[7]:
datasets = {
'ISMN': {
'class': ismn_reader,
jobs = []
ids = ismn_reader.get_dataset_ids(variable='soil moisture', min_depth=0, max_depth=0.1)
for idx in ids:
metadata = ismn_reader.metadata[idx]
jobs.append((idx, metadata['longitude'], metadata['latitude']))
print jobs
# For this small test dataset it is only one job
#
# It is important here that the ISMN reader has a read_ts function that works by just using the `dataset_id`. In this way the validation framework can go through the jobs and read the correct time series.
# In[5]:
data = ismn_reader.read_ts(ids[0])
print data.head()
# ## Initialize the Validation class
#
# The Validation class is the heart of the validation framwork. It contains the information about which datasets to read using which arguments or keywords and if they are spatially compatible. It also contains the settings about which metric calculators to use and how to perform the scaling into the reference data space. It is initialized in the following way:
# In[11]:
datasets = {'ISMN': {'class': ismn_reader,
'columns': ['soil moisture']},
'ASCAT': {'class': ascat_reader, 'columns': ['sm'],
'kwargs': {'mask_frozen_prob': 80,
'mask_snow_prob': 80,
'mask_ssf': True}}
