def _to_std(self):
_log('Translating to standard format')
xlator = utils.FormatTranslator()
self.model = (
xlator.to_std(df=self.model.copy(), set_metadata=True)
.set_index(utils.df_idx)
.sort_index()
)
self.hist = (
xlator.to_std(df=self.hist.copy(), set_metadata=False)
.set_index(utils.df_idx)
.sort_index()
)
# override with special cases if more are found in history
self.hist = self.hist[~self.hist.index.duplicated(keep='last')]
# hackery required because unit needed for df_idx
if self.overrides.empty:
self.overrides = None
else:
self.overrides['Unit'] = 'kt'
self.overrides = (
xlator.to_std(df=self.overrides.copy(), set_metadata=False)
.set_index(utils.df_idx)
.sort_index()
)
self.overrides.columns = self.overrides.columns.str.lower()
self.overrides = self.overrides['method']
def test_formatter_to_std():
df = pd.DataFrame({
'Variable': [
'CEDS+|9+ Sectors|Emissions|BC|foo|Unharmonized',
'Emissions|BC|bar|baz',
],
'Region': ['a', 'b'],
'2010': [5.0, 2.0],
'2020': [-1.0, 3.0],
'Unit': ['Mt foo/yr'] * 2,
'Model': ['foo'] * 2,
'Scenario': ['foo'] * 2,
})
fmt = utils.FormatTranslator(df.copy())
obs = fmt.to_std()
exp = pd.DataFrame({
'sector': [
'CEDS+|9+ Sectors|foo|Unharmonized',
'bar|baz',
],
'region': ['a', 'b'],
'2010': [5000.0, 2000.0],
'2020': [-1000.0, 3000.0],
'units': ['kt'] * 2,
'gas': ['BC'] * 2,
})
pdt.assert_frame_equal(obs.set_index(utils.df_idx),
exp.set_index(utils.df_idx))
def __init__(self, rc, hist, model, overrides, regions):
"""Parameters
----------
rc : aneris.RunControl
hist : pd.DataFrame
history in IAMC format
model : pd.DataFrame
model data in IAMC format
overrides : pd.DataFrame
harmonization overrides in IAMC format
regions : pd.DataFrame
regional aggregation mapping (ISO -> model regions)
"""
self.prefix = rc['prefix']
self.suffix = rc['suffix']
self.config = rc['config']
self.add_5regions = rc['add_5regions']
self.exog_files = rc['exogenous'] if 'exogenous' in rc else []
self.model = model
self.hist = hist
self.overrides = overrides
self.regions = regions
if not self.regions['ISO Code'].isin(['World']).any():
glb = {
'ISO Code': 'World',
'Country': 'World',
'Native Region Code': 'World',
}
_log('Manually adding global regional definition: {}'.format(glb))
self.regions = self.regions.append(glb, ignore_index=True)
model_names = self.model.Model.unique()
if len(model_names) > 1:
raise ValueError('Can not have more than one model to harmonize')
self.model_name = model_names[0]
self._xlator = utils.FormatTranslator(prefix=self.prefix,
suffix=self.suffix)
self._model_dfs = []
self._metadata_dfs = []
self._diagnostic_dfs = []
self.exogenous_trajectories = self._exogenous_trajectories()
# TODO better type checking?
self.config['harmonize_year'] = str(self.config['harmonize_year'])
y = self.config['harmonize_year']
if y not in model.columns:
msg = 'Base year {} not found in model data. Existing columns are {}.'
raise ValueError(msg.format(y, model.columns))
if y not in hist.columns:
msg = 'Base year {} not found in hist data. Existing columns are {}.'
raise ValueError(msg.format(y, hist.columns))
def test_formatter_to_template():
df = pd.DataFrame({
'Variable': [
'CEDS+|9+ Sectors|Emissions|BC|foo|Unharmonized',
'CEDS+|9+ Sectors|Emissions|BC|bar|Unharmonized',
],
'Region': ['a', 'b'],
'2010': [5.0, 2.0],
'2020': [-1.0, 3.0],
'Unit': ['Mt BC/yr'] * 2,
'Model': ['foo'] * 2,
'Scenario': ['foo'] * 2,
}).set_index(utils.iamc_idx)
fmt = utils.FormatTranslator(df,
prefix='CEDS+|9+ Sectors',
suffix='Unharmonized')
fmt.to_std()
obs = fmt.to_template()
exp = df.reindex_axis(obs.columns, axis=1)
pdt.assert_frame_equal(obs, exp)
