def run():
test = literal_eval(os.environ["BATCHPAR_test"])
bucket = os.environ['BATCHPAR_bucket']
batch_file = os.environ['BATCHPAR_batch_file']
db_name = os.environ["BATCHPAR_db_name"]
es_host = os.environ['BATCHPAR_outinfo']
es_port = int(os.environ['BATCHPAR_out_port'])
es_index = os.environ['BATCHPAR_out_index']
es_type = os.environ['BATCHPAR_out_type']
entity_type = os.environ["BATCHPAR_entity_type"]
aws_auth_region = os.environ["BATCHPAR_aws_auth_region"]
# database setup
logging.info('Retrieving engine connection')
engine = get_mysql_engine("BATCHPAR_config", "mysqldb", db_name)
logging.info('Building FOS lookup')
fos_lookup = build_fos_lookup(engine, max_lvl=6)
nf = NutsFinder()
# es setup
logging.info('Connecting to ES')
strans_kwargs = {
'filename': 'eurito/arxiv-eu.json',
'from_key': 'tier_0',
'to_key': 'tier_1',
'ignore': ['id']
}
es = ElasticsearchPlus(hosts=es_host,
port=es_port,
aws_auth_region=aws_auth_region,
no_commit=("AWSBATCHTEST" in os.environ),
entity_type=entity_type,
strans_kwargs=strans_kwargs,
null_empty_str=True,
coordinates_as_floats=True,
listify_terms=True,
do_sort=False,
ngram_fields=['textBody_abstract_article'])
# collect file
logging.info('Retrieving article ids')
nrows = 20 if test else None
s3 = boto3.resource('s3')
obj = s3.Object(bucket, batch_file)
art_ids = json.loads(obj.get()['Body']._raw_stream.read())
logging.info(f"{len(art_ids)} article IDs " "retrieved from s3")
# Get all grid countries
# and country: continent lookup
logging.info('Doing country lookup')
country_lookup = get_country_region_lookup()
eu_countries = get_eu_countries()
with db_session(engine) as session:
grid_regions = {
obj.id: country_lookup[obj.country_code]
for obj in session.query(Inst).all()
if obj.country_code is not None
}
grid_countries = {
obj.id: obj.country_code
for obj in session.query(Inst).all()
if obj.country_code is not None
}
grid_institutes = {
obj.id: obj.name
for obj in session.query(Inst).all()
}
grid_latlon = {
obj.id: (obj.latitude, obj.longitude)
for obj in session.query(Inst).all()
}
#
logging.info('Processing rows')
with db_session(engine) as session:
for count, obj in enumerate(
(session.query(Art).filter(Art.id.in_(art_ids)).all())):
row = object_to_dict(obj)
# Extract year from date
if row['created'] is not None:
row['year'] = row['created'].year
# Normalise citation count for searchkit
if row['citation_count'] is None:
row['citation_count'] = 0
# Extract field of study
row['fields_of_study'] = make_fos_tree(row['fields_of_study'],
fos_lookup)
row['_fields_of_study'] = [
f for fields in row['fields_of_study']['nodes'] for f in fields
if f != []
]
# Format hierarchical fields as expected by searchkit
row['categories'] = [
cat['description'] for cat in row.pop('categories')
]
institutes = row.pop('institutes')
good_institutes = [
i['institute_id'] for i in institutes
if i['matching_score'] > 0.9
]
# Add NUTS regions
for inst_id in good_institutes:
if inst_id not in grid_latlon:
continue
lat, lon = grid_latlon[inst_id]
if lat is None or lon is None:
continue
nuts = nf.find(lat=lat, lon=lon)
for i in range(0, 4):
name = f'nuts_{i}'
if name not in row:
row[name] = set()
for nut in nuts:
if nut['LEVL_CODE'] != i:
continue
row[name].add(nut['NUTS_ID'])
for i in range(0, 4):
name = f'nuts_{i}'
if name in row:
row[name] = list(row[name])
# Add other geographies
countries = set(grid_countries[inst_id]
for inst_id in good_institutes
if inst_id in grid_countries)
regions = set(grid_regions[inst_id] for inst_id in good_institutes
if inst_id in grid_countries)
row['countries'] = list(countries) #[c for c, r in countries]
row['regions'] = [r for c, r in regions]
row['is_eu'] = any(c in eu_countries for c in countries)
# Pull out international institute info
has_mn = any(
is_multinational(inst, grid_countries.values())
for inst in good_institutes)
row['has_multinational'] = has_mn
# Generate author & institute properties
mag_authors = row.pop('mag_authors')
if mag_authors is None:
row['authors'] = None
row['institutes'] = None
else:
if all('author_order' in a for a in mag_authors):
mag_authors = sorted(mag_authors,
key=lambda a: a['author_order'])
row['authors'] = [
author['author_name'].title() for author in mag_authors
]
gids = [
author['affiliation_grid_id'] for author in mag_authors
if 'affiliation_grid_id' in author
]
row['institutes'] = [
grid_institutes[g].title() for g in gids
if g in grid_institutes and g in good_institutes
]
if row['institutes'] in (None, []):
row['institutes'] = [
grid_institutes[g].title() for g in good_institutes
]
uid = row.pop('id')
_row = es.index(index=es_index, doc_type=es_type, id=uid, body=row)
if not count % 1000:
logging.info(f"{count} rows loaded to " "elasticsearch")
logging.warning("Batch job complete.")
def run():
test = literal_eval(os.environ["BATCHPAR_test"])
bucket = os.environ['BATCHPAR_bucket']
batch_file = os.environ['BATCHPAR_batch_file']
db_name = os.environ["BATCHPAR_db_name"]
es_host = os.environ['BATCHPAR_outinfo']
es_port = int(os.environ['BATCHPAR_out_port'])
es_index = os.environ['BATCHPAR_out_index']
es_type = os.environ['BATCHPAR_out_type']
entity_type = os.environ["BATCHPAR_entity_type"]
aws_auth_region = os.environ["BATCHPAR_aws_auth_region"]
# database setup
engine = get_mysql_engine("BATCHPAR_config", "mysqldb", db_name)
static_engine = get_mysql_engine("BATCHPAR_config", "mysqldb",
"static_data")
states_lookup = {
row['state_code']: row['state_name']
for _, row in pd.read_sql_table('us_states_lookup',
static_engine).iterrows()
}
states_lookup["AE"] = "Armed Forces (Canada, Europe, Middle East)"
states_lookup["AA"] = "Armed Forces (Americas)"
states_lookup["AP"] = "Armed Forces (Pacific)"
states_lookup[None] = None # default lookup for non-US countries
# Get continent lookup
url = "https://nesta-open-data.s3.eu-west-2.amazonaws.com/rwjf-viz/continent_codes_names.json"
continent_lookup = {
row["Code"]: row["Name"]
for row in requests.get(url).json()
}
continent_lookup[None] = None
eu_countries = get_eu_countries()
# es setup
strans_kwargs = {
'filename': 'eurito/crunchbase-eu.json',
'from_key': 'tier_0',
'to_key': 'tier_1',
'ignore': ['id']
}
es = ElasticsearchPlus(
hosts=es_host,
port=es_port,
aws_auth_region=aws_auth_region,
no_commit=("AWSBATCHTEST" in os.environ),
entity_type=entity_type,
strans_kwargs=strans_kwargs,
null_empty_str=True,
coordinates_as_floats=True,
country_detection=True,
listify_terms=True,
terms_delimiters=("|", ),
null_pairs={"currency_of_funding": "cost_of_funding"},
ngram_fields=[
'textBody_summary_organisation',
'textBody_descriptive_organisation'
])
# collect file
nrows = 20 if test else None
s3 = boto3.resource('s3')
obj = s3.Object(bucket, batch_file)
org_ids = json.loads(obj.get()['Body']._raw_stream.read())
logging.info(f"{len(org_ids)} organisations retrieved from s3")
org_fields = set(c.name for c in Organization.__table__.columns)
geo_fields = [
'country_alpha_2', 'country_alpha_3', 'country_numeric', 'continent',
'latitude', 'longitude'
]
# First get all funders
investor_names = defaultdict(list)
with db_session(engine) as session:
rows = (session.query(Organization, FundingRound).join(
FundingRound, Organization.id == FundingRound.company_id).filter(
Organization.id.in_(org_ids)).all())
for row in rows:
_id = row.Organization.id
_investor_names = row.FundingRound.investor_names
investor_names[_id] += parse_investor_names(_investor_names)
# Pipe orgs to ES
with db_session(engine) as session:
rows = (session.query(Organization, Geographic).join(
Geographic, Organization.location_id == Geographic.id).filter(
Organization.id.in_(org_ids)).limit(nrows).all())
for count, row in enumerate(rows, 1):
# convert sqlalchemy to dictionary
row_combined = {
k: v
for k, v in row.Organization.__dict__.items()
if k in org_fields
}
row_combined[
'currency_of_funding'] = 'USD' # all values are from 'funding_total_usd'
row_combined.update({
k: v
for k, v in row.Geographic.__dict__.items() if k in geo_fields
})
row_combined['investor_names'] = list(
set(investor_names[row_combined['id']]))
row_combined['is_eu'] = row_combined[
'country_alpha_2'] in eu_countries
# reformat coordinates
row_combined['coordinates'] = {
'lat': row_combined.pop('latitude'),
'lon': row_combined.pop('longitude')
}
# iterate through categories and groups
row_combined['category_list'] = []
row_combined['category_group_list'] = []
for category in (session.query(CategoryGroup).select_from(
OrganizationCategory).join(CategoryGroup).filter(
OrganizationCategory.organization_id ==
row.Organization.id).all()):
row_combined['category_list'].append(category.category_name)
row_combined['category_group_list'] += [
group
for group in str(category.category_group_list).split('|')
if group is not 'None'
]
# Add a field for US state name
state_code = row_combined['state_code']
row_combined['placeName_state_organisation'] = states_lookup[
state_code]
continent_code = row_combined['continent']
row_combined[
'placeName_continent_organisation'] = continent_lookup[
continent_code]
row_combined['updated_at'] = row_combined['updated_at'].strftime(
'%Y-%m-%d')
uid = row_combined.pop('id')
_row = es.index(index=es_index,
doc_type=es_type,
id=uid,
body=row_combined)
if not count % 1000:
logging.info(f"{count} rows loaded to elasticsearch")
logging.warning("Batch job complete.")
def run():
test = literal_eval(os.environ["BATCHPAR_test"])
bucket = os.environ['BATCHPAR_bucket']
batch_file = os.environ['BATCHPAR_batch_file']
db_name = os.environ["BATCHPAR_db_name"]
es_host = os.environ['BATCHPAR_outinfo']
es_port = int(os.environ['BATCHPAR_out_port'])
es_index = os.environ['BATCHPAR_out_index']
es_type = os.environ['BATCHPAR_out_type']
entity_type = os.environ["BATCHPAR_entity_type"]
aws_auth_region = os.environ["BATCHPAR_aws_auth_region"]
# database setup
logging.info('Retrieving engine connection')
engine = get_mysql_engine("BATCHPAR_config", "mysqldb", db_name)
_engine = get_mysql_engine("BATCHPAR_config", "readonly",
"patstat_2019_05_13")
# es setup
logging.info('Connecting to ES')
strans_kwargs = {
'filename': 'eurito/patstat-eu.json',
'from_key': 'tier_0',
'to_key': 'tier_1',
'ignore': ['id']
}
es = ElasticsearchPlus(hosts=es_host,
port=es_port,
aws_auth_region=aws_auth_region,
no_commit=("AWSBATCHTEST" in os.environ),
entity_type=entity_type,
strans_kwargs=strans_kwargs,
auto_translate=True,
auto_translate_kwargs={'min_len': 20},
null_empty_str=True,
coordinates_as_floats=True,
do_sort=True,
ngram_fields=['textBody_abstract_patent'])
# collect file
logging.info('Retrieving patent family ids')
nrows = 20 if test else None
s3 = boto3.resource('s3')
obj = s3.Object(bucket, batch_file)
docdb_fam_ids = json.loads(obj.get()['Body']._raw_stream.read())
logging.info(f"{len(docdb_fam_ids)} patent family IDs "
"retrieved from s3")
eu_countries = get_eu_countries()
logging.info('Processing rows')
_filter = ApplnFamily.docdb_family_id.in_(docdb_fam_ids)
with db_session(engine) as session:
for obj in session.query(ApplnFamily).filter(_filter).all():
row = object_to_dict(obj)
appln_ids = row.pop('appln_id')
with db_session(_engine) as _session:
_titles = metadata(Tls202ApplnTitle, _session, appln_ids)
_abstrs = metadata(Tls203ApplnAbstr, _session, appln_ids)
ipcs = metadata(Tls209ApplnIpc, _session, appln_ids)
nace2s = metadata(Tls229ApplnNace2, _session, appln_ids)
techs = metadata(Tls230ApplnTechnField, _session, appln_ids)
# Get persons
_pers_applns = metadata(Tls207PersAppln, _session, appln_ids)
pers_ids = set(pa['person_id'] for pa in _pers_applns)
persons = metadata(Tls906Person,
_session,
pers_ids,
field_selector=Tls906Person.person_id)
title = select_text(_titles, 'appln_title_lg', 'appln_title')
abstr = select_text(_abstrs, 'appln_abstract_lg', 'appln_abstract')
# Get names from lookups
ipcs = list(set(i['ipc_class_symbol'].split()[0] for i in ipcs))
nace2s = list(set(n['nace2_code'] for n in nace2s))
techs = list(set(t['techn_field_nr'] for t in techs))
ctrys = list(set(p['person_ctry_code'] for p in persons))
nuts = list(set(p['nuts'] for p in persons))
is_eu = any(c in eu_countries for c in ctrys)
# Index the data
row = dict(title=title,
abstract=abstr,
ipc=ipcs,
nace2=nace2s,
tech=techs,
ctry=ctrys,
nuts=nuts,
is_eu=is_eu,
**row)
uid = row.pop('docdb_family_id')
_row = es.index(index=es_index, doc_type=es_type, id=uid, body=row)
logging.warning("Batch job complete.")