def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"), open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
dtype = {
'time_id': 'UInt32',
'trade_flow_id': 'UInt8',
'reporter_id': 'UInt32',
'partner_id': 'UInt32',
'qty_unit_id': 'String',
'qty_unit': 'String',
'qty': 'Float64',
'netweight_kg': 'Float64',
'trade_value_us_dollars': 'UInt64',
'hs6_id': 'UInt32'
}
download_data = DownloadStep(connector=source_connector)
unzip_step = UnzipStep(pattern=r"\.csv$")
extract_step = ExtractStep()
load_step = LoadStep(
"trade_i_comtrade_m_hs", db_connector, if_exists="append", dtype=dtype,
pk=['reporter_id', 'trade_flow_id', 'time_id'],
nullable_list=['qty', 'trade_value_us_dollars']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).foreach(unzip_step).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(
params.get("source_connector"),
open("etl/countries/russia/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"),
open("etl/conns.yaml"))
dtype = copy.deepcopy(DTYPE)
dtype['hs6_id'] = 'String'
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep("trade_s_rus_m_hs",
db_connector,
if_exists="append",
dtype=dtype,
pk=[
'trade_flow_id', 'time_id', 'country_id',
'region_id', 'district_id', 'hs10_id'
],
nullable_list=['unit_short_name'])
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"),
open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"),
open("etl/conns.yaml"))
dtype = {
'id': 'String',
'id_num': 'UInt32',
'iso3': 'String',
'iso2': 'String',
'continent': 'String',
'color': 'String',
'name': 'String',
}
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep("dim_shared_countries",
db_connector,
if_exists="append",
dtype=dtype,
pk=['id_num'])
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"), open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
dtype = {
'year': 'UInt32',
'hs6_id': 'UInt32',
'exporter': 'UInt32',
'importer': 'UInt32',
'trade_value_thou_us_dollars': 'Float64',
'trade_value_us_dollars': 'Float64',
'qty_tons': 'Float64',
}
download_data = DownloadStep(connector=source_connector)
unzip_step = UnzipStep(pattern=r"\.csv$")
extract_step = ExtractStep()
load_step = LoadStep(
"trade_i_baci_a_{}".format(params['hs_code']), db_connector, if_exists="append", dtype=dtype,
pk=['exporter', 'importer', 'year'], nullable_list=['qty_tons']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).foreach(unzip_step).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"), open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
dtype = {
'chapter': 'String',
'chapter_name': 'String',
'chapter_id': 'UInt8',
'hs2': 'String',
'hs2_name': 'String',
'hs2_id': 'UInt8',
'hs4': 'String',
'hs4_name': 'String',
'hs4_id': 'UInt16',
'hs6': 'String',
'hs6_name': 'String',
'hs6_id': 'UInt32',
}
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep(
"dim_shared_hs{}".format(params['hs_code']), db_connector,
if_exists="append", dtype=dtype,
pk=['hs6_id']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"),
open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"),
open("etl/conns.yaml"))
dtype = {
'year': 'UInt16',
'trade_flow_id': 'UInt8',
'reporter_id': 'UInt32',
'partner_id': 'UInt32',
'service_id': 'UInt16',
'trade_value_us_dollars': 'Int64',
}
download_data = DownloadStep(connector=source_connector)
unzip_step = UnzipStep(pattern=r"\.csv$")
extract_step = ExtractStep()
load_step = LoadStep("services_i_comtrade_a_eb02",
db_connector,
if_exists="append",
dtype=dtype,
pk=['reporter_id', 'trade_flow_id', 'year'],
nullable_list=['trade_value_us_dollars'])
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).foreach(unzip_step).next(
extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"),
open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"),
open("etl/conns.yaml"))
dtype = {
'aggregate_level': 'UInt8',
'service_id': 'UInt16',
'service': 'String',
}
download_data = DownloadStep(connector=source_connector)
unzip_step = UnzipStep(pattern=r"\.csv$")
extract_step = ExtractStep()
consolidation_step = ConsolidationStep()
load_step = LoadStep("dim_shared_eb02",
db_connector,
if_exists="append",
dtype=dtype,
pk=['service_id'],
nullable_list=['aggregate_level'])
for year in range(2000, 2017 + 1):
params['year'] = year
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).foreach(unzip_step).next(extract_step)
pp.run_pipeline()
pp = AdvancedPipelineExecutor(params)
pp = pp.next(consolidation_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"),
open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"),
open("etl/conns.yaml"))
dtype = {
'geo_id': 'String',
'short_name': 'String',
'table_name': 'String',
'long_name': 'String',
'two_alpha_code': 'String',
'two_alpha_code_lower': 'String',
'currency_unit': 'String',
'special_notes': 'String',
'region': 'String',
'income_group': 'String',
'wb_2_code': 'String',
'national_accounts_base_year': 'String',
'national_accounts_reference_year': 'String',
'sna_price_valuation': 'String',
'lending_category': 'String',
'other_groups': 'String',
'system_of_national_accounts': 'String',
'alternative_conversion_factor': 'String',
'ppp_survey_year': 'String',
'balance_of_payments_manual_in_use': 'String',
'external_debt_reporting_status': 'String',
'system_of_trade': 'String',
'government_accounting_concept': 'String',
'imf_data_dissemination_standard': 'String',
'latest_population_census': 'String',
'latest_household_survey': 'String',
'income_and_expenditure_source': 'String',
'vital_registration_complete': 'String',
'latest_agricultural_census': 'String',
'latest_industrial_data': 'UInt32',
'latest_trade_data': 'UInt32',
}
nullable_list = list(dtype.keys())[3:]
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep("dim_shared_geo",
db_connector,
if_exists="append",
dtype=dtype,
pk=['geo_id'],
nullable_list=nullable_list)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = grab_connector(__file__,
params.get("source-connector"))
postgres_connector = grab_connector(__file__, "postgres-local")
step1 = DownloadStep(connector=source_connector)
step2 = TransformStep()
step3 = LoadStep("brazil_ncm", postgres_connector, if_exists="append")
pipeline = AdvancedPipelineExecutor(params)
pipeline = pipeline.next(step1).next(step2).next(step3)
return pipeline.run_pipeline()
def run(params, **kwargs):
source_connector = grab_connector(__file__,
params.get("source-connector"))
postgres_connector = grab_connector(__file__, "postgres-local")
step1 = DownloadStep(connector=source_connector)
step2 = LoadStep(params.get("dim") + "_table",
postgres_connector,
if_exists="replace")
pipeline = AdvancedPipelineExecutor(params)
pipeline = pipeline.next(step1).next(step2)
return pipeline.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"), open("etl/countries/russia/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep(
"dim_rus_countries", db_connector, if_exists="append", dtype=DTYPE, pk=['id'], nullable_list=['name']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = grab_connector(__file__, params.get("source"))
db_connector = grab_connector(__file__, params.get("db"))
step1 = DownloadStep(connector=source_connector)
step2 = TransformStep()
step3 = LoadStep("trade_i_mdic_m_hs",
db_connector,
if_exists="append",
pk=["time_id"])
pipeline = AdvancedPipelineExecutor(params)
pipeline = pipeline.next(step1).next(step2).next(step3)
return pipeline.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"), open("etl/countries/sweden/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep(
"trade_s_swe_m_hs", db_connector, if_exists="append", dtype=DTYPE,
pk=['hs6_id', 'trade_flow_id', 'partner_iso3'],
nullable_list=['amount']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
dtype = {
'trade_flow_id': 'UInt8',
'trade_flow_name': 'String',
}
extract_step = ExtractStep()
load_step = LoadStep(
"dim_shared_trade_flow", db_connector,
if_exists="append", dtype=dtype, pk=['trade_flow_id']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"),
open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"),
open("etl/conns.yaml"))
dtype = {
'indicator_id': 'String',
'topic': 'String',
'indicator_name': 'String',
'short_definition': 'String',
'long_definition': 'String',
'unit_of_measure': 'String',
'periodicity': 'String',
'base_period': 'String',
'other_notes': 'String',
'aggregation_method': 'String',
'limitations_and_expectations': 'String',
'notes_from_original_source': 'String',
'general_comments': 'String',
'source': 'String',
'statistical_concept_and_methodology': 'String',
'development_relevance': 'String',
'related_source_links': 'String',
'other_web_links': 'String',
'related_indicators': 'String',
'license_type': 'String'
}
nullable_list = list(dtype.keys())[2:]
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep("dim_shared_indicators",
db_connector,
if_exists="append",
dtype=dtype,
pk=['indicator_id'],
nullable_list=nullable_list)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()
def run(params, **kwargs):
db_connector = grab_connector(__file__, params.get("db"))
step1 = TimeCreationStep()
step2 = LoadStep("dim_shared_time",
db_connector,
if_exists="replace",
pk=["time_id"])
step3 = ProductCreationStep()
step4 = LoadStep("dim_shared_products",
db_connector,
if_exists="replace",
pk=["hs4_id"])
step5 = CountryCreationStep()
step6 = LoadStep("dim_shared_countries",
db_connector,
if_exists="replace",
pk=["id"])
step7 = StateCreationStep()
step8 = LoadStep("dim_shared_states",
db_connector,
if_exists="replace",
pk=["state_id"])
step9 = MunicipalityCreationStep()
step10 = LoadStep("dim_shared_municipalities",
db_connector,
if_exists="replace",
pk=["municipality_id"])
step11 = FlowCreationStep()
step12 = LoadStep("dim_shared_flow",
db_connector,
if_exists="replace",
pk=["flow_id"])
pipeline = AdvancedPipelineExecutor(params)
pipeline = pipeline.next(step1).next(step2).next(step3).next(
step4).next(step5).next(step6).next(step7).next(step8).next(
step9).next(step10).next(step11).next(step12)
return pipeline.run_pipeline()
def run(params, **kwargs):
source_connector = Connector.fetch(params.get("source_connector"), open("etl/conns.yaml"))
db_connector = Connector.fetch(params.get("db_connector"), open("etl/conns.yaml"))
dtype = {
'geo_id': 'String',
'indicator_id': 'String',
'year': 'UInt32',
'mea': 'Float64'
}
download_data = DownloadStep(connector=source_connector)
extract_step = ExtractStep()
load_step = LoadStep(
"indicators_i_wdi_a", db_connector, if_exists="append", dtype=dtype,
pk=['geo_id'], nullable_list=['mea']
)
pp = AdvancedPipelineExecutor(params)
pp = pp.next(download_data).next(extract_step).next(load_step)
return pp.run_pipeline()