def algo11(db, ref):
#Column L: must be in Reference>Target
db_col_loc = etl.find_in_header(db, 'Targeting')
ref_col_loc = etl.find_in_header(ref, 'Target')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, 'Targets not in Referece\n' + ','.join(missing_names)
def algo6(db, ref):
#Column G: must be in Reference>District
db_col_loc = etl.find_in_header(db, 'District')
ref_col_loc = etl.find_in_header(ref, 'Admin1_District')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, 'Districts not in the reference:\n' + ','.join(
missing_names)
def algo17(db,ref):
#column R: must be in reference>Status
db_col_loc = etl.find_in_header(db, 'Activity Status')
ref_col_loc = etl.find_in_header(ref,'Status')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, return_message('Activity Status not in Reference' ,missing_names)
def algo9(db, ref):
#column J: must be in reference>Type of Activity
db_col_loc = etl.find_in_header(db, 'Action type')
ref_col_loc = etl.find_in_header(ref, 'Action_Type')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, 'Incorrect Action types:\n' + ','.join(missing_names)
def algo11(db,ref):
#Column L: must be in Reference>Target
db_col_loc = etl.find_in_header(db, 'Targeting')
ref_col_loc = etl.find_in_header(ref,'Target')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, return_message('Targets not in Referece' ,missing_names)
def algo1(db, ref):
#***Column A must be in Reference>ImplementingAgency if not: make a note
db_col_loc = etl.find_in_header(db, 'Implementing agency')
ref_col_loc = etl.find_in_header(ref,'Implementing_Agency_Name')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, return_message('Agencies not in the reference:' ,missing_names)
def algo9(db,ref):
#column J: must be in reference>Type of Activity
db_col_loc = etl.find_in_header(db, 'Action type')
ref_col_loc = etl.find_in_header(ref,'Action_Type')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, return_message('Incorrect Action types:' ,missing_names)
def algo3(db, ref):
#* what return? change?
#Column C: must be in Reference>LocalPartnerAgency
#If not: Check if mispelling (like '%agencyname%)
db_col_loc = etl.find_in_header(db, 'Local partner agency')
ref_col_loc = etl.find_in_header(ref, 'Local_Partner_Agency')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
def algo17(db, ref):
#column R: must be in reference>Status
db_col_loc = etl.find_in_header(db, 'Activity Status')
ref_col_loc = etl.find_in_header(ref, 'Status')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, 'Activity Status not in Referece\n' + ','.join(
missing_names)
def algo1(db, ref):
#***Column A must be in Reference>ImplementingAgency if not: make a note
db_col_loc = etl.find_in_header(db, 'Implementing agency')
ref_col_loc = etl.find_in_header(ref, 'Implementing_Agency_Name')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, 'Agencies not in the reference:\n' + ','.join(
missing_names)
def algo3(db,ref):
#* what return? change?
#Column C: must be in Reference>LocalPartnerAgency
#If not: Check if mispelling (like '%agencyname%)
db_col_loc = etl.find_in_header(db, 'Local partner agency')
ref_col_loc = etl.find_in_header(ref,'Local_Partner_Agency')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
def match_vdcs():
#notes...
#1651 VDCs without exact match
w = etl.pull_wb("/Users/ewanog/Downloads/ward_level_data.xlsx", "local")
#w = etl.pull_wb("/Users/ewanog/Downloads/test.xlsx", "local")
#from cbs: col 1 (dist), col 2 (vdc), col 3 (ward)
#from new: H (dist), N (VDC), O (ward)
cbs = w.get_sheet_by_name("cbs")
new = w.get_sheet_by_name("new")
cbs_dist = etl.get_values(cbs.columns[0][1:])
cbs_vdc = etl.get_values(cbs.columns[1][1:])
cbs_ward = etl.get_values(cbs.columns[2][1:])
new_dist = etl.get_values(new.columns[7][1:])
new_vdc = etl.get_values(new.columns[13][1:])
new_ward = etl.get_values(new.columns[14][1:])
ns = set(new_vdc)
#see vdc matches
cb_zip = zip(cbs_dist, cbs_vdc)
new_zip = zip(new_dist, new_vdc)
print len(set(etl.colvals_notincol(cbs,'B',new,'N')))
print len(set(cbs_vdc))
for v in set(etl.colvals_notincol(cbs,'B',new,'N')):
r = process.extract(v, [r for r in new_zip if r[1] == ])
print r[0][1]
if __name__ == '__main__':
read = False
if read:
for ws in w.worksheets:
if ws['A44'].value:
r = get_vals(ws)
print r[-1][0]
#pr(r)
else:
match_vdcs()
def algo8(db, ref):
#Column I: must be in reference>Ward or a number or numbers separated by commas
#take all into missing names and trim from there
db_col_loc = etl.find_in_header(db, 'Municipal Ward')
ref_col_loc = etl.find_in_header(ref, 'Wards')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
#trim missing_names to see if they contain any forbidden chars
invalid = []
for v in missing_names:
for letter in v:
#if we've found an illegal letter
if letter not in set(string.digits + ' ' + ','):
invalid.append('(' + v + ')')
break
return db, ref, 'Malformed wards: \n' + ','.join(invalid)
def algo8(db,ref):
#Column I: must be in reference>Ward or a number or numbers separated by commas
#take all into missing names and trim from there
db_col_loc = etl.find_in_header(db, 'Municipal Ward')
ref_col_loc = etl.find_in_header(ref,'Wards')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
#trim missing_names to see if they contain any forbidden chars
invalid = []
for v in missing_names:
for letter in v:
#if we've found an illegal letter
if letter not in set(string.digits + ' ' + ','):
invalid.append('(' + v + ')')
break
return db, ref, return_message('Malformed wards: ' ,invalid)
def test_colvals_notincol(self):
self.assertEqual(tuple(etl.colvals_notincol(db, 'A', ref, 'A')),
tuple(['notincluded1','notincluded2','notincluded3']))
def algo6(db,ref):
#Column G: must be in Reference>District
db_col_loc = etl.find_in_header(db, 'District')
ref_col_loc = etl.find_in_header(ref,'Admin1_District')
missing_names = etl.colvals_notincol(db, db_col_loc, ref, ref_col_loc)
return db, ref, return_message('Districts not in the reference:' ,missing_names)
