def test_doc_index1():
"""First code example in index.rst."""
estat = Request('ESTAT')
flow_response = estat.dataflow('une_rt_a')
with pytest.raises(TypeError):
# This presumes the DataStructureDefinition instance can conduct a
# network request for its own content
structure_response = flow_response.dataflow.une_rt_a.structure(
request=True, target_only=False)
# Same effect
structure_response = estat.get(
'datastructure', flow_response.dataflow.une_rt_a.structure.id)
# Even better: Request.get(…) should examine the class and ID of the object
# structure = estat.get(flow_response.dataflow.une_rt_a.structure)
# Show some codelists
s = sdmx.to_pandas(structure_response)
expected = pd.Series({
'AT': 'Austria',
'BE': 'Belgium',
'BG': 'Bulgaria',
'CH': 'Switzerland',
'CY': 'Cyprus',
}, name='GEO') \
.rename_axis('CL_GEO')
# Codelists are converted to a DictLike
assert isinstance(s.codelist, DictLike)
# Same effect
assert_pd_equal(s.codelist['CL_GEO'].sort_index().head(), expected)
def dump_structure(data_source: sdmx.Request, dataset_name: str, debug=False):
print(f"Exploring {dataset_name}...")
dataset_msg = data_source.dataflow(dataset_name)
dataset = getattr(dataset_msg.dataflow, dataset_name)
if debug:
print(dataset)
dsd = dataset.structure
if debug:
print(dsd)
assert isinstance(dsd, sdmx.model.DataStructureDefinition)
return dsd
def test_doc_index1():
"""First code example in index.rst."""
estat = Request("ESTAT")
flow_response = estat.dataflow("une_rt_a")
with pytest.raises(TypeError):
# This presumes the DataStructureDefinition instance can conduct a
# network request for its own content
structure_response = flow_response.dataflow.une_rt_a.structure(
request=True, target_only=False
)
# Same effect
structure_response = estat.get(
"datastructure", flow_response.dataflow.une_rt_a.structure.id
)
# Even better: Request.get(…) should examine the class and ID of the object
# structure = estat.get(flow_response.dataflow.une_rt_a.structure)
# Show some codelists
s = pandasdmx.to_pandas(structure_response)
expected = pd.Series(
{
"AT": "Austria",
"BE": "Belgium",
"BG": "Bulgaria",
"CH": "Switzerland",
"CY": "Cyprus",
},
name="GEO",
).rename_axis("CL_GEO")
# Codelists are converted to a DictLike
assert isinstance(s.codelist, DictLike)
# Same effect
assert_pd_equal(s.codelist["CL_GEO"].sort_index().head(), expected)
def test_doc_usage_structure():
"""Code examples in walkthrough.rst."""
ecb = Request("ECB")
ecb_via_proxy = Request("ECB", proxies={"http": "http://1.2.3.4:5678"})
assert all(
getattr(ecb_via_proxy.session, k) == v for k, v in (
("proxies", {
"http": "http://1.2.3.4:5678"
}),
("stream", False),
("timeout", 30.1),
))
msg1 = ecb.categoryscheme()
assert msg1.response.url == (
"http://sdw-wsrest.ecb.int/service/categoryscheme/ECB/latest"
"?references=parentsandsiblings")
# Check specific headers
headers = msg1.response.headers
assert headers["Content-Type"] == ("application/vnd.sdmx.structure+xml; "
"version=2.1")
assert all(k in headers for k in ["Connection", "Date", "Server"])
# Removed: in pandaSDMX 0.x this was a convenience method that (for this
# structure message) returned two DataStructureDefinitions. Contra the
# spec, that assumes:
# - There is 1 Categorization using the CategoryScheme; there could be
# many.
# - The Categorization maps DataStructureDefinitions to Categories, when
# there could be many.
# list(cat_response.category_scheme['MOBILE_NAVI']['07'])
dfs = pandasdmx.to_pandas(msg1.dataflow).head()
assert len(dfs) == 2
flows = ecb.dataflow() # noqa: F841
dsd_id = flows.dataflow.EXR.structure.id
assert dsd_id == "ECB_EXR1"
refs = dict(references="all")
msg2 = ecb.datastructure(resource_id=dsd_id, params=refs)
dsd = msg2.structure[dsd_id]
assert pandasdmx.to_pandas(dsd.dimensions) == [
"FREQ",
"CURRENCY",
"CURRENCY_DENOM",
"EXR_TYPE",
"EXR_SUFFIX",
"TIME_PERIOD",
]
cl = pandasdmx.to_pandas(msg2.codelist["CL_CURRENCY"]).sort_index()
expected = pd.Series(
{
"ADF": "Andorran Franc (1-1 peg to the French franc)",
"ADP": "Andorran Peseta (1-1 peg to the Spanish peseta)",
"AED": "United Arab Emirates dirham",
"AFA": "Afghanistan afghani (old)",
"AFN": "Afghanistan, Afghanis",
},
name="Currency code list",
).rename_axis("CL_CURRENCY")
assert_pd_equal(cl.head(), expected)
from pandasdmx import Request
from pprint import pprint
estat = Request('ESTAT')
table_code = 'teilm020'
flow_response = estat.dataflow(table_code)
structure_response = flow_response.dataflow[table_code].structure(
request=True, target_only=False)
metadata = structure_response.write()
# List of of available keys
metadata.codelist.index.levels[0]
# List of names for potential key vaulues
metadata.codelist.loc['GEO']['name'].to_dict()
#resp = estat.data(table_code, key={'GEO': 'EL+ES+IE'}, params={'startPeriod': '2007'})
resp = estat.data(table_code)
data = resp.write()
## Accessing data by key
# Keys order
data.keys().names
# Available key values
[x.name + "= " + str([n for n in x]) for x in data.keys().levels]
## Accessing data by date
# List of available dates:
def test_doc_usage_structure():
"""Code examples in walkthrough.rst."""
ecb = Request('ECB')
ecb_via_proxy = Request('ECB', proxies={'http': 'http://1.2.3.4:5678'})
assert all(
getattr(ecb_via_proxy.session, k) == v for k, v in (
('proxies', {
'http': 'http://1.2.3.4:5678'
}),
('stream', False),
('timeout', 30.1),
))
msg1 = ecb.categoryscheme()
assert msg1.response.url == (
'http://sdw-wsrest.ecb.int/service/categoryscheme/ECB/latest'
'?references=parentsandsiblings')
# Check specific headers
headers = msg1.response.headers
assert headers['Content-Type'] == ('application/vnd.sdmx.structure+xml; '
'version=2.1')
assert all(k in headers for k in ['Connection', 'Date', 'Server'])
# Removed: in pandaSDMX 0.x this was a convenience method that (for this
# structure message) returned two DataStructureDefinitions. Contra the
# spec, that assumes:
# - There is 1 Categorization using the CategoryScheme; there could be
# many.
# - The Categorization maps DataStructureDefintions to Categories, when
# there could be many.
# list(cat_response.category_scheme['MOBILE_NAVI']['07'])
dfs = sdmx.to_pandas(msg1.dataflow).head()
expected = pd.Series({
'AME':
'AMECO',
'BKN':
'Banknotes statistics',
'BLS':
'Bank Lending Survey Statistics',
'BOP': ('Euro Area Balance of Payments and International Investment '
'Position Statistics'),
'BSI':
'Balance Sheet Items',
})
assert_pd_equal(dfs, expected)
flows = ecb.dataflow() # noqa: F841
dsd_id = msg1.dataflow.EXR.structure.id
assert dsd_id == 'ECB_EXR1'
refs = dict(references='all')
msg2 = ecb.datastructure(resource_id=dsd_id, params=refs)
dsd = msg2.structure[dsd_id]
assert sdmx.to_pandas(dsd.dimensions) == [
'FREQ', 'CURRENCY', 'CURRENCY_DENOM', 'EXR_TYPE', 'EXR_SUFFIX',
'TIME_PERIOD'
]
cl = sdmx.to_pandas(msg2.codelist['CL_CURRENCY']).sort_index()
expected = pd.Series({
'ADF': 'Andorran Franc (1-1 peg to the French franc)',
'ADP': 'Andorran Peseta (1-1 peg to the Spanish peseta)',
'AED': 'United Arab Emirates dirham',
'AFA': 'Afghanistan afghani (old)',
'AFN': 'Afghanistan, Afghanis',
}, name='Currency code list') \
.rename_axis('CL_CURRENCY')
assert_pd_equal(cl.head(), expected)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 15 18:47:27 2020
@author: Peter Jakobsen
"""
from pandasdmx import Request
estat = Request('ESTAT')
# Download the metadata and expose it as a dict mapping resource names to pandas DataFrames
flow_response = estat.dataflow('une_rt_a')
structure_response = flow_response.dataflow.une_rt_a.structure(request=True, target_only=False)
# Show some code lists.
structure_response.write().codelist.loc['GEO'].head()
#We use codes from the code list ‘GEO’ to obtain data on Greece, Ireland and Spain only.
resp = estat.data('une_rt_a', key={'GEO': 'EL+ES+IE'}, params={'startPeriod': '2007'})
# We use a generator expression to select some columns
# and write them to a pandas DataFrame
data = resp.write(s for s in resp.data.series if s.key.AGE == 'TOTAL')
def dump_flows(data_source: sdmx.Request):
flows = data_source.dataflow()
df = sdmx.to_pandas(flows.dataflow)
print(df)
from pandasdmx import Request
# Connecting to the Eurostat web service
estat = Request('ESTAT')
# Downloading the dataflow definitions
flows = estat.dataflow()
# Getting information about the dataflow
flows.url
flows.http_headers
# Exporting the dataflow definitions to a pandas DataFrame
dflows = flows.write().dataflow
# Listing tables from the high tech database and the description of a single table
ht_tabs = dflows[dflows.index.str.startswith('htec') == True]
kia_emp = dflows.loc['htec_kia_emp2'][0]
# Dataflow definition
df_def = flows.dataflow.htec_kia_emp2
# Database's datastructure id
dsd_id = df_def.structure.id
# Creating a support dict
refs = dict(references = 'all')
# Calling the table
dsd_response = estat.get(url = 'http://ec.europa.eu/eurostat/SDMX/diss-web/rest/datastructure/ESTAT/' + dsd_id)
# Getting informatou about the datastructure