def test_exposure_string_is_provided___file_content_is_loaded(self, data):
columns=['first', 'second']
exposure_str = _unicode(pd.DataFrame(columns=columns, data=data).to_csv(index=False))
res_str = olf.get_exposure(source_exposure=exposure_str).to_csv(index=False)
self.assertEqual(exposure_str, res_str)
def safe_decode(s, encoding=None):
'''Similar to bytes `decode` method returning unicode.
Decodes `s` using the given `encoding`, or determining one from the system.
Returning type depend on python version; if 2.x is `unicode` if 3.x `str`.
.. versionadded:: 1.1.3
'''
if isinstance(s, _unicode):
return s
else:
encoding = force_encoding(encoding)
try:
# In Python 3 str(b'm') returns the string "b'm'" and not just "m",
# this fixes this.
return _unicode(s, encoding, 'replace')
except:
# For numbers and other stuff.
return _unicode(s)
def test_file_is_provided___file_content_is_loaded(self, data):
columns = ['first', 'second']
exposure_str = _unicode(pd.DataFrame(columns=columns, data=data).to_csv(index=False))
with NamedTemporaryFile('w') as f:
f.writelines(exposure_str)
f.flush()
res_str = olf.get_exposure(source_exposure_fp=f.name).to_csv(index=False)
self.assertEqual(exposure_str, res_str)
def safe_encode(u, encoding=None):
'''Similar to unicode `encode` method returning bytes.
Encodes `u` using the given `encoding`, or determining one from the system.
Returning type is always `bytes`; but in python 2.x is also `str`.
.. versionadded:: 1.1.3
'''
if isinstance(u, bytes):
return u
else:
encoding = force_encoding(encoding)
try:
if isinstance(u, _str_base):
# In Python 2.x bytes does not allows an encoding argument.
return bytes(u)
else:
return _unicode(u).encode(encoding, 'replace')
except:
return _unicode(u).encode(encoding, 'replace')
def test_file_is_provided___file_content_is_loaded(self, data):
columns = ['first', 'second']
exposure_str = _unicode(
pd.DataFrame(columns=columns, data=data).to_csv(index=False))
f = NamedTemporaryFile('w', delete=False)
try:
f.writelines(exposure_str)
f.close()
res_str = olf.get_exposure(source_exposure_fp=f.name).to_csv(
index=False)
self.assertEqual(exposure_str, res_str)
finally:
os.remove(f.name)
def generate_oasis_files(
self,
target_dir,
exposure_fp,
exposure_profile=None,
exposure_profile_fp=None,
keys_fp=None,
lookup_config=None,
lookup_config_fp=None,
keys_data_fp=None,
model_version_fp=None,
lookup_package_fp=None,
supported_oed_coverage_types=None,
accounts_fp=None,
accounts_profile=None,
accounts_profile_fp=None,
fm_aggregation_profile=None,
fm_aggregation_profile_fp=None,
ri_info_fp=None,
ri_scope_fp=None,
oasis_files_prefixes=None
):
# Check whether the invocation indicates a deterministic or model
# analysis/run - the CLI supports deterministic analyses via a command
# `oasislmf exposure run` which requires a preexisting input files
# directory, which is usually the same as the analysis/output directory
deterministic = not(keys_fp or (lookup_config or lookup_config_fp) or (keys_data_fp and model_version_fp and lookup_package_fp))
# Prepare the target directory and copy the source files, profiles and
# model version file into it
target_dir = prepare_input_files_directory(
target_dir,
exposure_fp,
exposure_profile_fp=exposure_profile_fp,
keys_fp=keys_fp,
lookup_config_fp=lookup_config_fp,
model_version_fp=model_version_fp,
accounts_fp=accounts_fp,
accounts_profile_fp=accounts_profile_fp,
fm_aggregation_profile_fp=fm_aggregation_profile_fp,
ri_info_fp=ri_info_fp,
ri_scope_fp=ri_scope_fp
)
# Get the profiles defining the exposure and accounts files, ID related
# terms in these files, and FM aggregation hierarchy
exposure_profile = exposure_profile or (get_json(src_fp=exposure_profile_fp) if exposure_profile_fp else self.exposure_profile)
accounts_profile = accounts_profile or (get_json(src_fp=accounts_profile_fp) if accounts_profile_fp else self.accounts_profile)
id_terms = unified_id_terms(profiles=(exposure_profile, accounts_profile,))
loc_id = id_terms['locid']
acc_id = id_terms['accid']
portfolio_num = id_terms['portid']
fm_aggregation_profile = (
fm_aggregation_profile or
({int(k): v for k, v in viewitems(get_json(src_fp=fm_aggregation_profile_fp))} if fm_aggregation_profile_fp else {}) or
self.fm_aggregation_profile
)
# If a pre-generated keys file path has not been provided,
# then it is asssumed some model lookup assets have been provided, so
# as to allow the lookup to be instantiated and called to generated
# the keys file. Otherwise if no model keys file path or lookup assets
# were provided then a "deterministic" keys file is generated.
_keys_fp = _keys_errors_fp = None
if not keys_fp:
_keys_fp = os.path.join(target_dir, 'keys.csv')
_keys_errors_fp = os.path.join(target_dir, 'keys-errors.csv')
cov_types = supported_oed_coverage_types or self.supported_oed_coverage_types
if deterministic:
loc_numbers = (loc_num[loc_id] for _, loc_num in get_dataframe(
src_fp=exposure_fp,
col_dtypes={loc_id: 'str', acc_id: 'str', portfolio_num: 'str'},
empty_data_error_msg='No exposure found in the source exposure (loc.) file'
)[[loc_id]].iterrows())
keys = [
{loc_id: loc_num, 'peril_id': 1, 'coverage_type': cov_type, 'area_peril_id': i + 1, 'vulnerability_id': i + 1}
for i, (loc_num, cov_type) in enumerate(product(loc_numbers, cov_types))
]
_, _ = olf.write_oasis_keys_file(keys, _keys_fp)
else:
lookup_config = get_json(src_fp=lookup_config_fp) if lookup_config_fp else lookup_config
if lookup_config:
lookup_config['keys_data_path'] = os.path.abspath(os.path.dirname(lookup_config_fp))
_, lookup = olf.create(
lookup_config=lookup_config,
model_keys_data_path=keys_data_fp,
model_version_file_path=model_version_fp,
lookup_package_path=lookup_package_fp
)
f1, n1, f2, n2 = olf.save_results(
lookup,
loc_id_col=loc_id,
successes_fp=_keys_fp,
errors_fp=_keys_errors_fp,
source_exposure_fp=exposure_fp
)
else:
_keys_fp = os.path.join(target_dir, os.path.basename(keys_fp))
# Get the GUL input items and exposure dataframes
gul_inputs_df, exposure_df = get_gul_input_items(
exposure_fp, _keys_fp, exposure_profile=exposure_profile
)
# Write the GUL input files
files_prefixes = oasis_files_prefixes or self.oasis_files_prefixes
gul_input_files = write_gul_input_files(
gul_inputs_df,
target_dir,
oasis_files_prefixes=files_prefixes['gul']
)
# If no source accounts file path has been provided assume that IL
# input files, and therefore also RI input files, are not needed
if not accounts_fp:
return gul_input_files
# Get the IL input items
il_inputs_df, _ = get_il_input_items(
exposure_df,
gul_inputs_df,
accounts_fp=accounts_fp,
exposure_profile=exposure_profile,
accounts_profile=accounts_profile,
fm_aggregation_profile=fm_aggregation_profile
)
# Write the IL/FM input files
il_input_files = write_il_input_files(
il_inputs_df,
target_dir,
oasis_files_prefixes=files_prefixes['il']
)
# Combine the GUL and IL input file paths into a single dict (for convenience)
oasis_files = {k: v for k, v in chain(gul_input_files.items(), il_input_files.items())}
# If no RI input file paths (info. and scope) have been provided then
# no RI input files are needed, just return the GUL and IL Oasis files
if not (ri_info_fp or ri_scope_fp):
return oasis_files
# Write the RI input files, and write the returned RI layer info. as a
# file, which can be reused by the model runner (in the model execution
# stage) to set the number of RI iterations
ri_layers = write_ri_input_files(
exposure_fp,
accounts_fp,
oasis_files['items'],
oasis_files['coverages'],
oasis_files['gulsummaryxref'],
oasis_files['fm_xref'],
oasis_files['fmsummaryxref'],
ri_info_fp,
ri_scope_fp,
target_dir
)
with io_open(os.path.join(target_dir, 'ri_layers.json'), 'w', encoding='utf-8') as f:
f.write(_unicode(json.dumps(ri_layers, ensure_ascii=False, indent=4)))
oasis_files['ri_layers'] = os.path.abspath(f.name)
for layer, layer_info in viewitems(ri_layers):
oasis_files['RI_{}'.format(layer)] = layer_info['directory']
return oasis_files