cat_counts['year'] = patent_year
df_counts = pd.DataFrame(cat_counts)
grouped_counts = df_counts.groupby('year')
summed_counts = grouped_counts.agg(sum)
summed_counts['country'] = country
return summed_counts
country_files = os.listdir('./data')
country_files = [f for f in country_files if 'tsv' in f]
## Read in and group the gre en IPC codes per the WIPO definition
green_ipcs = pd.read_csv('./data/ipc_green_inventory_tags_8dig.csv')
## Clean the ipc codes to match those in the PATSTAT output
ipc_clean = psCleanup.ipc_clean(green_ipcs['ipc'])
green_ipcs['ipc'] = ipc_clean
del ipc_clean
## Categorize at the top level the IPC codes
green_energy_cats = {}
for idx, d in enumerate(green_ipcs.l1):
if d in green_energy_cats:
green_energy_cats[d].append(green_ipcs.ipc[idx])
else:
green_energy_cats[d] = [green_ipcs.ipc[idx]]
## Translate the ipc codes into regex for searching
cat_regex = psCleanup.make_regex(green_energy_cats)
## Clean the data
print time.strftime('%c', time.localtime())
print 'Coauthors aggregated'
ipc_list = [
ipc_output.xs(appln_id) if appln_id in ipc_output.index else ''
for appln_id in name_output['appln_id']
]
## Clean and join the IPC codes
ipc_split = []
for ipc in ipc_list:
if len(ipc) > 0:
ipc_split.append(ipc[0].split('**'))
else:
ipc_split.append('')
clean_ipc = [psCleanup.ipc_clean(ipc) for ipc in ipc_split]
name_output['ipc_codes'] = [psCleanup.get_max(ipc) for ipc in clean_ipc]
## Write out files by country-year
name_clean_finish = time.time()
print 'Cleaning time per name + address + ipc code'
print(name_clean_finish - name_clean_time) / float(len(name_output))
end_time = time.time()
elapsed_time = end_time - start_time
n_records = str(len(name_output))
print 'Time elapsed for ' + year + ' and ' + n_records + ' records: ' + str(
numpy.round(elapsed_time, 0))
grouped_country = name_output.groupby('person_ctry_code')
print time.strftime('%c', time.localtime())
print 'Coauthors aggregated'
ipc_list = [ipc_output.xs(appln_id) if appln_id in ipc_output.index else ''
for appln_id in name_output['appln_id']
]
## Clean and join the IPC codes
ipc_split = []
for ipc in ipc_list:
if len(ipc) > 0:
ipc_split.append(ipc[0].split('**'))
else:
ipc_split.append('')
clean_ipc = [psCleanup.ipc_clean(ipc) for ipc in ipc_split]
name_output['ipc_codes'] = [psCleanup.get_max(ipc) for ipc in clean_ipc]
## Write out files by country-year
name_clean_finish = time.time()
print 'Cleaning time per name + address + ipc code'
print (name_clean_finish - name_clean_time) / float(len(name_output))
end_time = time.time()
elapsed_time = end_time - start_time
n_records = str(len(name_output))
print 'Time elapsed for ' + year + ' and ' + n_records + ' records: ' + str(numpy.round(elapsed_time, 0))
grouped_country = name_output.groupby('person_ctry_code')
for country, group in grouped_country:
def tuple_clean(query_output):
"""
Cleans, formats, outputs the query data.
Collects summary statistics per country: number of records,
number of nonblank address lines and average number of coauthors
and ipc codes per country.
Args:
query_output: tuple of unformated person_appln tuples
Returns:
Files of cleaned person_appln rows written out by country.
File of summary statistics written out one row per country.
"""
auth_patent_n = len(query_output)
addresses_n = 0
coauths = list()
ipc = list()
name_clean_time = time.time()
names = [q[2] for q in query_output]
names = psCleanup.name_clean(names, psCleanup.name_address_dict_list)
names_ids = [psCleanup.get_legal_ids(n, psCleanup.legal_regex) for n in names]
addresses = [q[3] for q in query_output]
addresses = psCleanup.name_clean(addresses, psCleanup.name_address_dict_list)
coauthors = [q[5] for q in query_output]
coauthors = psCleanup.name_clean(coauthors, psCleanup.coauth_dict_list)
name_clean_finish = time.time()
print 'Cleaning time per name + address'
print (name_clean_finish - name_clean_time) / float(len(names))
for idx, record in enumerate(query_output):
clean_time_start = time.time()
## Unpack the tuple
appln_id, person_id, person_name, person_address, person_ctry_code, \
coauth, ipc_codes = record
## Separate out the authors and ipcs for cleaning
coauthors_split = coauthors[idx].split('**')
ipc_split = ipc_codes.split('**')
## Drop the co-author that is this author
clean_coauthors = [name for name in coauthors_split if name != person_name]
## Generate some summary statistics
addresses_n += len(person_address) > 0
coauths.append(len(clean_coauthors))
ipc.append(len(ipc_split))
appln_id = str(appln_id)
person_id = str(person_id)
## Clean the person name, then break out the
## legal identifiers
preclean_time = time.time()
## print preclean_time - clean_time_start
# raw_name = psCleanup.name_clean([person_name])[0]
clean_name, firm_legal_ids = names_ids[idx]
# intermediate_clean_time = time.time()
# print intermediate_clean_time - clean_time_start
clean_ipcs = psCleanup.ipc_clean(ipc_split)
# intermediate_clean_time_2 = time.time()
# print intermediate_clean_time_2 - intermediate_clean_time
coauthors_final = psCleanup.get_max(clean_coauthors)
ipc_codes_final = psCleanup.get_max(clean_ipcs)
legal_ids_final = psCleanup.get_max([firm_legal_ids])
clean_time_end = time.time()
print appln_id, person_id, clean_name, legal_ids_final, addresses[idx], person_ctry_code, coauthors_final, ipc_codes_final
print 'Record clean time:'
print clean_time_end - clean_time_start
# filename = outpathname + record[4]+'_out'
# with open(filename, 'a') as tabfile:
# cleanwriter = csv.writer(tabfile, delimiter ='\t')
# cleanwriter.writerow(appln_id,
# person_id,
# clean_name,
# addresses[idx],
# legal_ids_final,
# person_ctry_code,
# coauthors_final,
# ipc_codes_final,
# year
# )
# coauth_mean = numpy.mean(coauths)
# ipc_mean = numpy.mean(ipc)
# with open(outpathname+'summary_stats', 'a') as csvfile:
# statswriter = csv.writer(csvfile)
# statswriter.writerow([year, auth_patent_n, addresses_n, coauth_mean, ipc_mean])
return None
cat_counts['year'] = patent_year
df_counts = pd.DataFrame(cat_counts)
grouped_counts = df_counts.groupby('year')
summed_counts = grouped_counts.agg(sum)
summed_counts['country'] = country
return summed_counts
country_files = os.listdir('./data')
country_files = [f for f in country_files if 'tsv' in f]
## Read in and group the gre en IPC codes per the WIPO definition
green_ipcs = pd.read_csv('./data/ipc_green_inventory_tags_8dig.csv')
## Clean the ipc codes to match those in the PATSTAT output
ipc_clean = psCleanup.ipc_clean(green_ipcs['ipc'])
green_ipcs['ipc'] = ipc_clean
del ipc_clean
## Categorize at the top level the IPC codes
green_energy_cats = {}
for idx, d in enumerate(green_ipcs.l1):
if d in green_energy_cats:
green_energy_cats[d].append(green_ipcs.ipc[idx])
else:
green_energy_cats[d] = [green_ipcs.ipc[idx]]
## Translate the ipc codes into regex for searching
cat_regex = psCleanup.make_regex(green_energy_cats)
## Clean the data
