def build_allocation_df(self):
df = DataFrame()
exchange_df = self.build_exchange_df()
for alloc in self.dataset.flowData.iterchildren(tag = tag_prefix + 'allocation'):
baseline = {0: {'referenceToCoProduct': alloc.get('referenceToCoProduct'),
'CoProductName': exchange_df.loc[int(alloc.get('referenceToCoProduct')), 'name'],
'allocationMethod': int(alloc.get('allocationMethod')),
'fraction': float(alloc.get('fraction'))/100.}}
for r in alloc.iterchildren(tag = tag_prefix + 'referenceToInputOutput'):
to_add = deepcopy(baseline)
sel = exchange_df.loc[int(r.text)]
to_add[0].update({'referenceToInputOutput': r.text,
'exchange': sel['name']})
for attr in ['category', 'subCategory', 'group']:
to_add[0].update({attr: sel[attr]})
df = gff.update_df(df, to_add)
return df
def convertion_template(self, MD, folder_template, rosettas, new_MD):
#mapping[attribute_name_spold2] = attribute_name_spold1
metainfo_attribute_mapping = {
'geographyShortname': 'geographyShortname',
'generalComment': 'generalComment',
'includedActivitiesStart': 'includedProcesses',
'geographyComments': 'geographyComment',
'technologyComments': 'technologyComment',
'timePeriodComments': 'timePeriodComment',
'samplingProcedure': 'samplingProcedure',
'extrapolations': 'extrapolations',
'synonyms': 'synonym',
'activityName': 'name'
}
metainfo_attribute_without_mapping = ['includedActivitiesEnd',
'allocationComments', 'technologyLevel', 'macroEconomicComment',
'tags']
line_for_metainfo_template = {}
for attr in metainfo_attribute_mapping:
line_for_metainfo_template[attr] = getattr(self, metainfo_attribute_mapping[attr])
if (line_for_metainfo_template['geographyShortname'] not in
set(MD['geographies']['shortname'])):
line_for_metainfo_template['geographyShortname'] += ' is no longer valid. Please replace with valid geography shortname from current MasterData.'
line_for_metainfo_template.update(dict(zip(metainfo_attribute_without_mapping,
['']*len(metainfo_attribute_without_mapping))))
line_for_metainfo_template['startDate'] = '%s-01-01' % self.startYear
line_for_metainfo_template['endDate'] = '%s-12-31' % self.endYear
line_for_metainfo_template['id'] = str(uuid4())
line_for_metainfo_template['dataEntryBy'] = ''
line_for_metainfo_template['dataGenerator'] = ''
if self.name not in MD['ActivityNames'].index:
if len(new_MD['ActivityNames']) == 0 or self.name not in new_MD['ActivityNames'].index:
to_add = {len(new_MD['ActivityNames']): {
'original activityName': self.name,
'activityName': 'fix me',
'id': str(uuid4())}}
new_MD['ActivityNames'] = gff.update_df(new_MD['ActivityNames'], to_add)
line_for_metainfo_template['activityName'] = 'fix me'
line_for_metainfo_template['activityName source'] = self.name
for p in self.persons:
for field1, field2 in [('dataEntryBy', 'dataEntryBy'),
('dataGenerator', 'dataGeneratorPerson')]:
if p.number == getattr(self, field2):
line_for_metainfo_template[field1] = p.name
if p.name not in set(MD['persons']['name']):
if len(new_MD['persons']) == 0 or p.name not in set(new_MD['persons']['name']):
if len(new_MD['persons']) > 0:
1/0
to_add = {}
for field in ['name', 'address', 'telephone', 'telefax',
'email', 'companyCode']:
to_add[field] = getattr(p, field)
if p.companyCode not in MD['companies']['code']:
if (len(new_MD['companies']) == 0 or
p.companyCode not in set(new_MD['companies']['code'])):
to_add2 = {'id': str(uuid4()),
'name': '',
'code': p.companyCode,
'website': '',
'comment': ''}
new_MD['companies'] = gff.update_df(
new_MD['companies'], {len(
new_MD['companies']): to_add2})
to_add['id'] = to_add2['id']
else:
to_add['id'] = new_MD['companies'][new_MD['companies']['code'] == p.companyCode].iloc[0]['id']
else:
to_add['id'] = MD['companies']['codes'][MD['companies']['codes'] == p.companyCode].iloc[0]['id']
new_MD['persons'] = gff.update_df(new_MD['persons'], {len(new_MD['persons']): to_add})
for s in self.sources:
fields = gff.list_attributes(s)
fields.remove('text')
fields.remove('number')
if len(new_MD['Sources']) == 0 or s.title not in set(new_MD['Sources']['title']):
to_add = {}
for field in fields:
to_add[field] = getattr(s, field)
to_add['comment'] = ''
to_add['id'] = str(uuid4())
new_MD['Sources'] = gff.update_df(new_MD['Sources'],
{len(new_MD['Sources']): to_add})
if s.number == self.referenceToPublishedSource:
try:
uuid = to_add['id']
except:
uuid = new_MD['Sources'][new_MD['Sources']['title'] == s.title].iloc[0]['id']
line_for_metainfo_template['publishedSourceId'] = uuid
line_for_metainfo_template['dataPublishedIn'] = self.dataPublishedIn
line_for_metainfo_template = DataFrame({0: line_for_metainfo_template}).transpose()
exchanges_template = DataFrame()
properties_template = DataFrame()
exchange_attribute_mapping = {'group': 'group', 'name': 'name',
'compartment': 'category', 'subcompartment': 'subCategory',
'unitName': 'unit', 'amount': 'meanValue', 'comments': 'generalComment',
}
pedigree_fields = ['reliability', 'completeness', 'temporalCorrelation',
'geographicalCorrelation', 'furtherTechnologyCorrelation']
exchange_attribute_without_mapping = ['activityLink activityName',
'activityLink geography', 'variableName', 'mathematicalRelation',
'productionVolumeAmount', 'productionVolumeComment',
'productionVolumeSourceId', 'productionVolumeMathematicalRelation',
'uncertainty comments', 'uncertainty type production volume',
'variance production volume', 'uncertainty comments production volume',
'reliability production volume', 'completeness production volume',
'temporalCorrelation production volume', 'geographicalCorrelation production volume',
'furtherTechnologyCorrelation production volume', ]
for group in group_list:
for exc in getattr(self, group):
exchange_attributes = {}
for attr in exchange_attribute_mapping:
exchange_attributes[attr] = getattr(exc, exchange_attribute_mapping[attr])
if 'Environment' in group:
if exchange_attributes['compartment'] == 'air':
exchange_attributes['compartment'] = 'Air'
elif exchange_attributes['compartment'] == 'water':
exchange_attributes['compartment'] = 'Water'
elif exchange_attributes['compartment'] == 'soil':
exchange_attributes['compartment'] = 'Soil'
elif exchange_attributes['compartment'] == 'Non material emissions':
pass
else:
1/0
if exchange_attributes['subcompartment'] == 'unspecified':
exchange_attributes['subcompartment'] = '(unspecified)'
ee = (exchange_attributes['name'],
exchange_attributes['compartment'],
exchange_attributes['subcompartment'])
if ee not in set(rosettas['ee'].index):
for field in ['name', 'compartment', 'subcompartment']:
exchange_attributes['original %s' % field] = deepcopy(exchange_attributes[field])
exchange_attributes[field] = 'fix me'
if len(new_MD['ElementaryExchanges']) == 0 or gff.merge(ee, ', ') not in set(new_MD['ElementaryExchanges']['index']):
to_add = {0: {'nameUUID': str(uuid4()),
'name source': ee[0],
'name': '',
'compartment source': ee[1],
'compartment': '',
'subcompartment source': ee[2],
'subcompartment': '',
'unitName': rosettas['unit'].loc[exc.unit,'name'],
'casNumber': '',
'formula': '',
'synonyms': '',
'index': gff.merge(ee, ', ')}}
new_MD['ElementaryExchanges'] = gff.update_df(
new_MD['ElementaryExchanges'], to_add)
exchange_attributes['unitName'] = rosettas['unit'].loc[exc.unit,'name']
else:
sel = rosettas['ee'].loc[ee]
if type(sel) != pandas.core.frame.DataFrame:
1/0
if len(sel) != 1:
1/0
sel = sel.iloc[0]
for field in ['name', 'compartment', 'subcompartment']:
exchange_attributes[field] = sel['%s ecoinvent' % field]
exchange_attributes['original %s' % field] = ''
if not sel['unit equal']:
1/0
else:#intermediate exchange
if exchange_attributes['name'] not in set(rosettas['ie'].index):
exchange_attributes['original name'] = deepcopy(exchange_attributes['name'])
for field in ['compartment', 'subcompartment']:
exchange_attributes[field] = ''
exchange_attributes['name'] = 'fix me'
if len(new_MD['IntermediateExchanges']) == 0 or exchange_attributes['spold1 name'] not in set(new_MD['IntermediateExchanges']['name spold1']):
to_add = {0: {'nameUUID': str(uuid4()),
'name source': exchange_attributes['original name'],
'name': '',
'CAS': '',
'comment': '',
'By-product classification': '',
'CPC': '',
'ISIC rev.4 ecoinvent': '',
'synonyms': '',
'unitName': rosettas['unit'].loc[exc.unit,'name']}}
new_MD['IntermediateExchanges'] = gff.update_df(
new_MD['IntermediateExchanges'], to_add)
exchange_attributes['unitName'] = rosettas['unit'].loc[exc.unit,'name']
else:
for field in ['name', 'compartment', 'subcompartment']:
exchange_attributes['original %s' % field] = ''
sel = rosettas['ie'].loc[exchange_attributes['name']]
exchange_attributes['name'] = sel['ecoinvent product name']
exchange_attributes['potential activityLink activityName'] = sel['ecoinvent activityLink activityName']
exchange_attributes['potential activityLink geography'] = sel['ecoinvent activityLink geography']
new_unit = MD['IntermediateExchanges'][
MD['IntermediateExchanges']['name'] ==
exchange_attributes['name']].iloc[0]['unitName']
if new_unit != exchange_attributes['unitName']:
if new_unit == 'unit' and exchange_attributes['unitName'] == 'p':
exchange_attributes['unitName'] = new_unit
elif new_unit == 'm*year' and exchange_attributes['unitName'] == 'my':
exchange_attributes['unitName'] = new_unit
else:
1/0
exchange_attributes['variance'] = ''
if not gff.isempty(exchange_attributes['comments']):
if ',BU:' in exchange_attributes['comments']:
pedigreeMatrix, rest = exchange_attributes['comments'].split(',BU:')
pedigreeMatrix = pedigreeMatrix[1:].split(',')[:5]
exchange_attributes['variance'] = np.log(float(rest.split(');')[0]))**2.
if exchange_attributes['variance'] > 5.:
1/0
exchange_attributes['comments'] = gff.merge(rest.split(');')[1:], ');')
else:
m = pedigree_re.search(exchange_attributes['comments'])
if m:
1/0
else:
pedigreeMatrix = 5*['']
if gff.isempty(exc.uncertaintyType) or exc.group == 'ReferenceProduct':
exchange_attributes['uncertainty type'] = ''
elif exc.uncertaintyType == 0:
exchange_attributes['uncertainty type'] = 'undefined'
exchange_attributes['variance'] = ''
elif exc.uncertaintyType == 1:
exchange_attributes['uncertainty type'] = 'lognormal'
elif exc.uncertaintyType == 2:
1/0
elif exc.uncertaintyType == 3:
1/0
elif exc.uncertaintyType == 4:
1/0
else:
1/0
#add info in log about missing pedigree
for i in range(len(pedigree_fields)):
if pedigreeMatrix[i] == '':
exchange_attributes[pedigree_fields[i]] = ''
elif pedigreeMatrix[i] in ['1', '2', '3', '4', '5']:
exchange_attributes[pedigree_fields[i]] = int(pedigreeMatrix[i])
else:
1/0
exchange_attributes.update(dict(zip(
exchange_attribute_without_mapping,
['']*len(exchange_attribute_without_mapping))))
for field in ['sourceId', 'pageNumbers',]:
exchange_attributes[field] = ''
if not gff.isempty(exc.referenceToSource):
1/0
exchanges_template = gff.update_df(exchanges_template,
{len(exchanges_template): exchange_attributes})
cols = ['group', 'name', 'compartment', 'subcompartment', 'activityLink activityName',
'activityLink geography', 'unitName', 'amount', 'variableName',
'mathematicalRelation', 'sourceId', 'pageNumbers', 'comments',
'productionVolumeAmount', 'productionVolumeComment', 'productionVolumeSourceId',
'productionVolumeMathematicalRelation', 'uncertainty type', 'variance',
'uncertainty comments', 'reliability', 'completeness', 'temporalCorrelation',
'geographicalCorrelation', 'furtherTechnologyCorrelation', 'uncertainty type production volume',
'variance production volume', 'uncertainty comments production volume',
'reliability production volume', 'completeness production volume', 'temporalCorrelation production volume',
'geographicalCorrelation production volume', 'furtherTechnologyCorrelation production volume']
cols.extend(['original name', 'original compartment', 'original subcompartment',
'potential activityLink activityName', 'potential activityLink geography'])
if 'potential activityLink activityName' not in exchanges_template.columns:
1/0
dfs = [{'df': exchanges_template, 'cols': cols, 'sheetname': 'exchanges'}]
df_new_exchanges = exchanges_template[exchanges_template['name'] == 'fix me']
if len(df_new_exchanges) > 0:
for index in df_new_exchanges.index:
sel = df_new_exchanges.loc[index]
fields = ['group', 'name', 'compartment', 'subcompartment',
'activityLink activityName', 'activityLink geography']
baseline = dict(zip(fields, list(sel[fields])))
fields2 = ['group', 'original name', 'original compartment', 'original subcompartment']
baseline.update(dict(zip(fields, list(sel[fields2]))))
cols = ['group', 'name', 'compartment', 'subcompartment', 'activityLink activityName',
'activityLink geography', 'property name', 'unitName', 'amount',
'comment', 'sourceId', 'mathematicalRelation', 'variableName']
#dfs.append({'df': '', 'cols': cols, 'sheetname': 'properties'})
else:
pass
logs = DataFrame()
for index in exchanges_template.index:
sel = exchanges_template.loc[index]
fields = ['group', 'name', 'compartment', 'subcompartment',
'activityLink activityName', 'activityLink geography']
baseline = dict(zip(fields, list(sel[fields])))
gravity = 'error'
if sel['name'] == 'fix me':
fields2 = ['group', 'original name', 'original compartment', 'original subcompartment']
baseline.update(dict(zip(fields, list(sel[fields2]))))
if 'Environment' in sel['group']:
message = 'Find appropriate exchange in MasterData'
elif 'FromTechnoslphere' == sel['group']:
message = 'Find appropriate exchange in MasterData, and maybe activityLink activityName and geography'
else:
message = 'Find appropriate exchange in MasterData and enter production volume'
to_add = {'gravity': gravity,
'line': index + 2,
'message': message}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
to_add = {'gravity': gravity,
'line': index + 2,
'message': 'If exchange is new, properties have to be entered in the "properties" tab'}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
#warnings
gravity = 'warning'
if not gff.isempty(sel['variance']) and sel['variance'] == .0006:
to_add = {'gravity': gravity,
'line': index + 2,
'message': 'additional variance by pedigreeMatrix > basic uncertainty. Variance set to 0.0006. Check pedigree matrix and variance.'}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
if gff.isempty(sel['sourceId']):
to_add = {'gravity': gravity,
'line': index + 2,
'message': 'consider entering original information'}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
if gff.isempty(sel['comments']):
to_add = {'gravity': gravity,
'line': index + 2,
'message': 'consider entering comment'}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
if sel['group'] == 'ReferenceProduct':
for field in ['productionVolumeAmount', 'productionVolumeComment',
'productionVolumeSourceId']:
if gff.isempty(sel[field]):
to_add = {'gravity': gravity,
'line': index + 2,
'message': 'consider entering %s' % field}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
if gff.isempty(sel['uncertainty type production volume']):
to_add = {'gravity': gravity,
'line': index + 2,
'message': 'consider entering uncertainty information for production volume'}
to_add.update(baseline)
logs = gff.update_df(logs, {len(logs): to_add})
else:
for field in ['variance production volume',
'uncertainty comments', 'production volume',
'reliability production volume', 'completeness production volume',
'temporalCorrelation production volume', 'geographicalCorrelation production volume',
'furtherTechnologyCorrelation production volume']:
if gff.isempty(sel[field]):
1/0
else:
if gff.isempty(sel['uncertainty type']):
1/0
else:
fields = ['variance']
fields.extend(pedigree_fields)
for field in fields:
if gff.isempty(sel[field]):
1/0
cols = ['gravity', 'line', 'group', 'name',
'compartment', 'subcompartment', 'message']
dfs.append({'df': logs, 'cols': cols, 'sheetname': 'logs'})
if not gff.isempty(exchanges_template.iloc[0]['original name']):
filename = exchanges_template.iloc[0]['original name'].split('|')[0]
filename += '.xlsx'
else:
1/0
print 'saving', filename
gff.write_DataFrame(dfs, folder_template, filename)
line_for_metainfo_template['exchange template filename'] = filename
return (line_for_metainfo_template, exchanges_template,
properties_template, new_MD)
def read_Simapro_export(folder, filename, tabname):
if '.csv' in filename:
1/0
elif '.xlsx':
wb = load_workbook(filename = os.path.join(folder, filename), use_iterators = True)
ws = wb.get_sheet_by_name(name = tabname)
row_offset = -1
for row in ws.iter_rows(): #skipping header
row_offset += 1
if row[0].value == 'Process':
start = deepcopy(row_offset)
break
dim = ws.calculate_dimension()
dataset_positions = []
for row in ws.iter_rows(range_string = dim, row_offset = row_offset):
if row[0].value == 'End':
dataset_positions.append((start, deepcopy(row_offset)))
break
else:
row_offset += 1
projectInputParametersPosition = False
projectCalculatedParameters = False
for row in ws.iter_rows(range_string = dim, row_offset = row_offset):
#positioning for next process
if row[0].value == 'Process':
start = deepcopy(row_offset)
break
elif row[0].value == 'Project Input parameters':
projectInputParametersPosition = deepcopy(row_offset)
elif row[0].value == 'Project Calculated parameters':
projectCalculatedParameters = deepcopy(row_offset)
else:
row_offset += 1
if row_offset == ws.max_row:
pass
#last UP
parameters = DataFrame()
if projectInputParametersPosition and projectCalculatedParameters:
for row in ws.iter_rows(range_string = dim, row_offset = projectInputParametersPosition+1):
if row[0].value == None:
break
else:
to_add = {'variableName': str(row[0].value),
'amount': float(row[1].value),
'uncertaintyType': str(row[2].value),
'variance': float(row[3].value),
'comment': str(row[9].value),
'variableNameLength': len(str(row[0].value))}
parameters = gff.update_df(parameters, {len(parameters): to_add})
if len(parameters) > 0:
parameters.sort(columns = 'variableNameLength', ascending = False, inplace = True)
for row in ws.iter_rows(range_string = dim, row_offset = projectCalculatedParameters+1):
if row[0].value == None:
break
elif row[0].value == 'Project Calculated parameters':
pass
else:
1/0 #to fix later if it occurs
if len(parameters) == 0:
to_add = {'variableName': 'LUC_crop_specific',
'amount': 1.,
'uncertaintyType': 'Undefined',
'variance': '',
'comment': 'dummy value, please edit',
'variableNameLength': 10}
parameters = gff.update_df(parameters, {len(parameters): to_add})
datasets = []
for start, end in dataset_positions:
rows = []
counter = start
for row in ws.iter_rows(range_string = dim, row_offset = start):
counter += 1
if counter == end:
break
line = []
for cell in row:
line.append(cell.value)
rows.append(line)
datasets.append(Dataset(rows, filename, parameters = parameters))
else:
1/0
if len(datasets) == 0:
1/0
elif len(datasets) == 1:
datasets = datasets[0]
return datasets
def convertion_template(self, MD, folder_template, rosettas, new_MD, unit_conflicts):
metainfo_attribute_mapping = {
'geographyShortname': 'geography',
'generalComment': 'comment',
'technologyComments': 'technology',
'samplingProcedure': 'collectionMethod',
}
metainfo_attribute_without_mapping = ['includedActivitiesEnd',
'allocationComments', 'technologyLevel', 'macroEconomicComment',
'tags', 'includedActivitiesStart', 'geographyComments',
'timePeriodComments', 'extrapolations', 'synonyms']
line_for_metainfo_template = {}
for attr in metainfo_attribute_mapping:
line_for_metainfo_template[attr] = getattr(self, metainfo_attribute_mapping[attr])
line_for_metainfo_template.update(dict(zip(metainfo_attribute_without_mapping,
['']*len(metainfo_attribute_without_mapping))))
for field in ['startDate', 'endDate', 'dataEntryBy', 'dataGenerator']:
if hasattr(self, field):
line_for_metainfo_template[field] = getattr(self, field)
else:
line_for_metainfo_template[field] = ''
line_for_metainfo_template['id'] = str(uuid4())
line_for_metainfo_template['activityName original'] = self.processName
if self.processName not in set(rosettas['activityName'].index):
1/0
self.activityName = rosettas['activityName'].loc[self.processName, 'ecoinvent name']
if not self.activityName in MD['ActivityNames'].index:
if len(new_MD['ActivityNames']) == 0 or self.activityName not in set(new_MD['ActivityNames']['activityName']):
to_add = {len(new_MD['ActivityNames']): {
'original activityName': self.processName,
'activityName': self.activityName,
'id': str(uuid4())}}
new_MD['ActivityNames'] = gff.update_df(new_MD['ActivityNames'], to_add)
#f.processName = rosettas['ie'].loc[self.ReferenceProduct[0].name, 'ecoinvent activityLink activityName']
line_for_metainfo_template['activityName'] = self.activityName
line_for_metainfo_template['accessRestrictedTo'] = 'Licensees'
line_for_metainfo_template['technologyLevel'] = 'Current'
line_for_metainfo_template['dataEntryBy'] = line_for_metainfo_template['dataEntryBy'].strip()
line_for_metainfo_template = DataFrame({0: line_for_metainfo_template}).transpose()
for field in ['dataEntryBy', 'dataGenerator']:
personName = line_for_metainfo_template.iloc[0][field]
if not gff.isempty(personName) and personName not in set(MD['persons']['name']):
if len(new_MD['persons']) == 0 or personName not in set(new_MD['persons']['name']):
to_add = {'id': str(uuid4()),
'name': personName}
cols = ['address', 'companyCode', 'companyName', 'email', 'telefax', 'telephone']
to_add.update(dict(zip(cols, ['']*len(cols))))
new_MD['persons'] = gff.update_df(new_MD['persons'],
{len(new_MD['persons']): to_add})
exchanges_template = DataFrame()
properties_template = DataFrame()
exchange_attribute_mapping = {'group': 'group', 'name': 'name',
'compartment': 'compartment', 'subcompartment': 'subcompartment',
'unitName': 'unitName', 'amount': 'amount', 'comments': 'comment',
'mathematicalRelation': 'mathematicalRelation',
'variableName': 'variableName', 'variance': 'variance',
'sourceId': 'sourceId',
'original name': 'name', 'original compartment': 'compartment',
'original subcompartment': 'subcompartment'
}
pedigree_fields = ['reliability', 'completeness', 'temporalCorrelation',
'geographicalCorrelation', 'furtherTechnologyCorrelation']
exchange_attribute_without_mapping = ['activityLink activityName',
'activityLink geography',
'productionVolumeAmount', 'productionVolumeComment',
'productionVolumeSourceId', 'productionVolumeMathematicalRelation',
'uncertainty comments', 'uncertainty type production volume',
'variance production volume', 'uncertainty comments production volume',
'reliability production volume', 'completeness production volume',
'temporalCorrelation production volume', 'geographicalCorrelation production volume',
'furtherTechnologyCorrelation production volume', ]
group_list = ['ReferenceProduct', 'ByProduct', 'FromTechnosphere', 'ToEnvironment',
'FromEnvironment']
for group in group_list:
for exc in getattr(self, group):
exchange_attributes = {}
for attr in exchange_attribute_mapping:
exchange_attributes[attr] = getattr(exc, exchange_attribute_mapping[attr])
if 'Environment' in group:
if exchange_attributes['compartment'] == 'air':
exchange_attributes['compartment'] = 'Air'
elif exchange_attributes['compartment'] == 'water':
exchange_attributes['compartment'] = 'Water'
elif exchange_attributes['compartment'] == 'soil':
exchange_attributes['compartment'] = 'Soil'
elif exchange_attributes['compartment'] == 'Non material emissions':
pass
elif exchange_attributes['compartment'] == 'natural resources':
exchange_attributes['compartment'] = 'Raw'
else:
1/0
if exchange_attributes['subcompartment'] == 'unspecified':
exchange_attributes['subcompartment'] = '(unspecified)'
ee = (exchange_attributes['name'],
exchange_attributes['compartment'],
exchange_attributes['subcompartment'])
if ee not in set(rosettas['ee'].index):
print ee
1/0
else:
sel = rosettas['ee'].loc[ee]
if type(sel) == pandas.core.series.Series:
sel = DataFrame(sel).transpose()
ee_ = tuple(sel.iloc[0][['name ecoinvent',
'compartment ecoinvent', 'subcompartment ecoinvent']])
if ee_ in set(MD['ElementaryExchanges'].index):
cols = ['name', 'compartment', 'subcompartment', 'unitName']
exchange_attributes.update(dict(zip(cols,
list(MD['ElementaryExchanges'].loc[ee_, cols]))))
else:
if len(new_MD['ElementaryExchanges']) == 0 or gff.merge(ee_, ', ') not in set(new_MD['ElementaryExchanges']['index']):
to_add = {0: {'nameUUID': str(uuid4()),
'name': ee_[0],
'compartment': ee_[1],
'subcompartment': ee_[2],
'unitName': rosettas['unit'].loc[exc.unitName,'name'],
'casNumber': '',
'formula': '',
'synonyms': '',
'index': gff.merge(ee_, ', '),
'name original': ee[0],
'compartment original': ee[1],
'subcompartment original': ee[2]}}
new_MD['ElementaryExchanges'] = gff.update_df(
new_MD['ElementaryExchanges'], to_add)
sel2 = new_MD['ElementaryExchanges'][new_MD['ElementaryExchanges']['index'] ==
gff.merge(ee_, ', ')].iloc[0]
cols = ['name', 'compartment', 'subcompartment', 'unitName']
exchange_attributes.update(dict(zip(cols, list(sel2[cols]))))
if type(sel) != pandas.core.frame.DataFrame:
1/0
if len(sel) != 1:
1/0
sel = sel.iloc[0]
else:#intermediate exchange
if exchange_attributes['name'] not in set(rosettas['ie'].index):
print self.filename
print exchange_attributes['name']
1/0
else:
sel = rosettas['ie'].loc[exchange_attributes['name']]
if sel['ecoinvent product name'] in set(MD['IntermediateExchanges'].index):
exchange_attributes['name'] = sel['ecoinvent product name']
exchange_attributes['potential activityLink activityName'] = sel['ecoinvent activityLink activityName']
exchange_attributes['potential activityLink geography'] = sel['ecoinvent activityLink geography']
exchange_attributes['unitName'] = MD['IntermediateExchanges'].loc[exchange_attributes['name'], 'unitName']
else:
exchange_attributes['name'] = sel['ecoinvent product name']
exchange_attributes['potential activityLink activityName'] = sel['ecoinvent activityLink activityName']
exchange_attributes['potential activityLink geography'] = sel['ecoinvent activityLink geography']
exchange_attributes['unitName'] = rosettas['unit'].loc[exc.unitName,'name']
if (len(new_MD['IntermediateExchanges']) == 0 or
sel['ecoinvent product name'] not in
set(new_MD['IntermediateExchanges']['name'])):
to_add = {0: {'nameUUID': str(uuid4()),
'name original': exchange_attributes['original name'],
'name': sel['ecoinvent product name'],
'CAS': '',
'comment': '',
'By-product classification': '',
'CPC': '',
'ISIC rev.4 ecoinvent': '',
'synonyms': '',
'unitName': rosettas['unit'].loc[exc.unitName,'name']}}
new_MD['IntermediateExchanges'] = gff.update_df(
new_MD['IntermediateExchanges'], to_add)
else:
pass #already in new_MD
if len(exc.pedigreeMatrix) == 5:
for i in range(len(pedigree_fields)):
exchange_attributes[pedigree_fields[i]] = exc.pedigreeMatrix[i]
exchange_attributes.update(dict(zip(
exchange_attribute_without_mapping,
['']*len(exchange_attribute_without_mapping))))
for field in ['pageNumbers']:
exchange_attributes[field] = ''
if exc.unitName != exchange_attributes['unitName']:
if exchange_attributes['unitName'] == rosettas['unit'].loc[exc.unitName,'name']:
exchange_attributes['amount'] = exchange_attributes['amount'] * rosettas['unit'].loc[exc.unitName,'conversion']
elif exc.unitName == 'kg' and exchange_attributes['unitName'] == 'm3' and 'Water' in exc.name:
exchange_attributes['amount'] = exchange_attributes['amount']/1000.
else:
to_add = {'filename': self.filename,
'group': exc.group,
'ecoinvent name': exchange_attributes['name'],
'ecoinvent compartment': exchange_attributes['compartment'],
'ecoinvent subcompartment': exchange_attributes['subcompartment'],
'original unit': exc.unitName,
'ecoinvent unit': exchange_attributes['unitName']}
unit_conflicts = gff.update_df(unit_conflicts, to_add)
for field in ['productionVolumeAmount', 'productionVolumeComment',
'productionVolumeSourceId', 'productionVolumeMathematicalRelation']:
if hasattr(exc, field) and not gff.isempty(getattr(exc, field)):
exchange_attributes[field] = getattr(exc, field)
exchanges_template = gff.update_df(exchanges_template, exchange_attributes)
cols = ['group', 'original name', 'name', 'compartment', 'subcompartment', 'activityLink activityName',
'activityLink geography', 'unitName', 'amount', 'variableName',
'mathematicalRelation', 'sourceId', 'pageNumbers', 'comments',
'productionVolumeAmount', 'productionVolumeComment', 'productionVolumeSourceId',
'productionVolumeMathematicalRelation', 'uncertainty type', 'variance',
'uncertainty comments', 'reliability', 'completeness', 'temporalCorrelation',
'geographicalCorrelation', 'furtherTechnologyCorrelation', 'uncertainty type production volume',
'variance production volume', 'uncertainty comments production volume',
'reliability production volume', 'completeness production volume', 'temporalCorrelation production volume',
'geographicalCorrelation production volume', 'furtherTechnologyCorrelation production volume',
'original compartment', 'original subcompartment',
'potential activityLink activityName', 'potential activityLink geography']
if 'potential activityLink activityName' not in exchanges_template.columns:
exchanges_template['potential activityLink activityName'] = ''
exchanges_template['potential activityLink geography'] = ''
dfs = [{'df': exchanges_template, 'cols': cols, 'sheetname': 'exchanges'}]
parameters_template = DataFrame()
for p in self.parameters:
to_add = {}
for attr in gff.list_attributes(p):
to_add[attr] = getattr(p, attr)
parameters_template = gff.update_df(parameters_template,
{len(parameters_template): to_add})
if p.name not in set(MD['parameters'].index):
if 'parameters' not in new_MD:
new_MD['parameters'] = DataFrame()
if len(new_MD['parameters']) == 0 or p.name not in set(new_MD['parameters']['name']):
to_add = {'name': p.name,
'defaultVariableName': p.variableName,
'unitName': p.unitName,
'comment': '',
'id': str(uuid4())}
new_MD['parameters'] = gff.update_df(new_MD['parameters'], to_add)
cols = ['name', 'variableName', 'amount', 'unitName', 'uncertaintyType', 'comment']
cols.extend(pedigree_fields)
for col in cols:
if col not in parameters_template.columns:
parameters_template[col] = ''
dfs.append({'df': parameters_template, 'cols': cols, 'sheetname': 'parameters'})
if not gff.isempty(exchanges_template.iloc[0]['original name']):
filename = exchanges_template.iloc[0]['original name'].split('|')[0]
for c in ['/']:
filename = filename.replace(c, '_')
filename += '.xlsx'
else:
1/0
print 'saving', filename
gff.write_DataFrame(dfs, folder_template, filename)
line_for_metainfo_template['exchange template filename'] = filename
sources = set(exchanges_template['sourceId'])
if 'publishedSourceId' in set(line_for_metainfo_template.columns) and not gff.isempty(line_for_metainfo_template['publishedSourceId']):
1/0
sources.add(line_for_metainfo_template['publishedSourceId'])
if '' in sources:
sources.remove('')
if len(sources) > 0:
if 'Sources' not in new_MD:
new_MD['Sources'] = DataFrame()
elif 'id' in list(new_MD['Sources'].columns):
sources = sources.difference(set(new_MD['Sources']['id']))
if len(sources) > 0:
cols = ['sourceType', 'title', 'firstAuthor', 'additionalAuthors', 'year',
'pageNumbers', 'nameOfEditors', 'titleOfAnthology',
'placeOfPublications', 'publisher', 'journal', 'volumeNo',
'issueNo', 'generalComment']
for s in sources:
to_add = dict(zip(cols, ['']*len(cols)))
to_add['id'] = s
new_MD['Sources'] = gff.update_df(new_MD['Sources'], to_add)
return (line_for_metainfo_template, exchanges_template,
properties_template, new_MD, unit_conflicts)
def __init__(self, rows, filename, parameters = DataFrame()):
self.filename = filename
headers = ['Products', 'Materials/fuels',
'Electricity/heat', 'Waste to treatment']
positions_ie = dict(zip(headers, [0]*len(headers)))
headers = ['Resources', 'Emissions to air', 'Emissions to water',
'Emissions to soil']
positions_ee = dict(zip(headers, [0]*len(headers)))
headers = ['Avoided products', 'Final waste flows', 'Non material emissions',
'Social issues', 'Economic issues']
positions_should_be_empty = dict(zip(headers, [0]*len(headers)))
for i in range(len(rows)):
if rows[i][0] in headers_metainfo:
if rows[i+1][0] == None:
setattr(self, headers_metainfo[rows[i][0]], '')
else:
setattr(self, headers_metainfo[rows[i][0]], rows[i+1][0])
elif rows[i][0] in positions_ie:
positions_ie[rows[i][0]] = i
elif rows[i][0] in positions_ee:
positions_ee[rows[i][0]] = i
elif rows[i][0] in positions_should_be_empty:
positions_should_be_empty[rows[i][0]] = i
if rows[i+1][0] != None:
1/0
elif rows[i][0] == 'Input parameters':
InputParametersPosition = i
elif rows[i][0] == 'Calculated parameters':
CalculatedParameters = i
for row in rows[InputParametersPosition+1:]:
if row[0] == None:
break
else:
to_add = {'variableName': str(row[0]),
'amount': float(row[1]),
'uncertaintyType': str(row[2]),
'variance': float(row[3]),
'comment': str(row[9]),
'variableNameLength': len(str(row[0]))}
parameters = gff.update_df(parameters, {len(parameters): to_add})
if len(parameters) > 0:
parameters.sort(columns = 'variableNameLength', ascending = False, inplace = True)
for row in rows[CalculatedParameters+1:]:
if row[0] == None:
break
else:
1/0 #to fix later if it occurs
for group in ['ReferenceProduct', 'FromEnvironment', 'ToEnvironment',
'FromTechnosphere', 'ByProduct']:
setattr(self, group, [])
for i in range(positions_ie['Products']+1,
positions_should_be_empty['Avoided products']-1):
if rows[i][0] != None:
ref_exc = Exchange(rows[i], 'ReferenceProduct')
self.ReferenceProduct.append(ref_exc)
for i in range(positions_ie['Materials/fuels']+1,
positions_ee['Emissions to air']-1):
if rows[i][0] != None and i != positions_ie['Electricity/heat']:
exc = Exchange(rows[i], 'FromTechnosphere', parameters = parameters)
self.FromTechnosphere.append(exc)
for i in range(positions_ee['Resources']+1, positions_ie['Materials/fuels']-1):
if not gff.isempty(rows[i][0]):
exc = Exchange(rows[i], 'FromEnvironment', parameters = parameters)
self.FromEnvironment.append(exc)
for i in range(positions_ie['Waste to treatment']+1,
InputParametersPosition-1):
if rows[i][0] != None:
exc = Exchange(rows[i], 'ByProduct', parameters = parameters)
self.FromTechnosphere.append(exc)
for i in range(positions_ee['Emissions to air'],
positions_should_be_empty['Final waste flows']-1):
if gff.isempty(rows[i][0]):
pass
elif rows[i][0] in positions_ee:
group = rows[i][0]
else:
exc = Exchange(rows[i], group, parameters = parameters)
self.ToEnvironment.append(exc)
self.parameters = []
parameters.set_index('variableName', inplace = True)
for variableName in parameters.index:
self.parameters.append(Parameter(parameters.loc[variableName]))
