def test_wdi_download_str(self):
# These are the expected results, rounded (robust against
# data revisions in the future).
expected = {
"NY.GDP.PCAP.CD": {
("Japan", "2004"): 38000.0,
("Japan", "2003"): 35000.0,
("Japan", "2002"): 32000.0,
("Japan", "2001"): 34000.0,
("Japan", "2000"): 39000.0,
}
}
expected = pd.DataFrame(expected)
expected = expected.sort_index()
cntry_codes = "JP"
inds = "NY.GDP.PCAP.CD"
result = download(
country=cntry_codes, indicator=inds, start=2000, end=2004, errors="ignore"
)
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ["country", "year"]
tm.assert_frame_equal(result, expected)
result = WorldBankReader(
inds, countries=cntry_codes, start=2000, end=2004, errors="ignore"
).read()
result = result.sort_index()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_str(self):
expected = {
'NY.GDP.PCAP.CD': {
('Japan', '2004'): 36441.50449394,
('Japan', '2003'): 33690.93772972,
('Japan', '2002'): 31235.58818439,
('Japan', '2001'): 32716.41867489,
('Japan', '2000'): 37299.64412913
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'JP'
inds = 'NY.GDP.PCAP.CD'
result = download(country=cntry_codes,
indicator=inds,
start=2000,
end=2004,
errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2000,
end=2004,
errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_get_countries(self):
result1 = get_countries()
result2 = WorldBankReader().get_countries()
session = requests.Session()
result3 = get_countries(session=session)
result4 = WorldBankReader(session=session).get_countries()
for result in [result1, result2, result3, result4]:
assert 'Zimbabwe' in list(result['name'])
assert len(result) > 100
assert pd.notnull(result.latitude.mean())
assert pd.notnull(result.longitude.mean())
def test_wdi_get_indicators(self):
result1 = get_indicators()
result2 = WorldBankReader().get_indicators()
session = requests.Session()
result3 = get_indicators(session=session)
result4 = WorldBankReader(session=session).get_indicators()
for result in [result1, result2, result3, result4]:
exp_col = pd.Index(['id', 'name', 'source', 'sourceNote', 'sourceOrganization', 'topics'])
# assert_index_equal doesn't exists
self.assertTrue(result.columns.equals(exp_col))
self.assertTrue(len(result) > 10000)
def test_wdi_download_monthly(self):
expected = {'COPPER': {('World', '2012M01'): 8040.47,
('World', '2011M12'): 7565.48,
('World', '2011M11'): 7581.02,
('World', '2011M10'): 7394.19,
('World', '2011M09'): 8300.14,
('World', '2011M08'): 9000.76,
('World', '2011M07'): 9650.46,
('World', '2011M06'): 9066.85,
('World', '2011M05'): 8959.90,
('World', '2011M04'): 9492.79,
('World', '2011M03'): 9503.36,
('World', '2011M02'): 9867.60,
('World', '2011M01'): 9555.70}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'ALL'
inds = 'COPPER'
result = download(country=cntry_codes, indicator=inds,
start=2011, end=2012, freq='M',errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds, countries=cntry_codes,
start=2011, end=2012, freq='M', errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_monthly(self):
expected = {
"COPPER": {
("World", "2012M01"): 8040.47,
("World", "2011M12"): 7565.48,
("World", "2011M11"): 7581.02,
("World", "2011M10"): 7394.19,
("World", "2011M09"): 8300.14,
("World", "2011M08"): 9000.76,
("World", "2011M07"): 9650.46,
("World", "2011M06"): 9066.85,
("World", "2011M05"): 8959.90,
("World", "2011M04"): 9492.79,
("World", "2011M03"): 9503.36,
("World", "2011M02"): 9867.60,
("World", "2011M01"): 9555.70,
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
expected = expected.sort_index()
cntry_codes = "ALL"
inds = "COPPER"
result = download(
country=cntry_codes,
indicator=inds,
start=2011,
end=2012,
freq="M",
errors="ignore",
)
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ["country", "year"]
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2011,
end=2012,
freq="M",
errors="ignore").read()
result = result.sort_index()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_monthly(self):
expected = {
'COPPER': {
('World', '2012M01'): 8040.47,
('World', '2011M12'): 7565.48,
('World', '2011M11'): 7581.02,
('World', '2011M10'): 7394.19,
('World', '2011M09'): 8300.14,
('World', '2011M08'): 9000.76,
('World', '2011M07'): 9650.46,
('World', '2011M06'): 9066.85,
('World', '2011M05'): 8959.90,
('World', '2011M04'): 9492.79,
('World', '2011M03'): 9503.36,
('World', '2011M02'): 9867.60,
('World', '2011M01'): 9555.70
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
expected = expected.sort_index()
cntry_codes = 'ALL'
inds = 'COPPER'
result = download(country=cntry_codes,
indicator=inds,
start=2011,
end=2012,
freq='M',
errors='ignore')
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ['country', 'year']
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2011,
end=2012,
freq='M',
errors='ignore').read()
result = result.sort_index()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_str(self):
expected = {'NY.GDP.PCAP.CD': {('Japan', '2004'): 36441.50449394,
('Japan', '2003'): 33690.93772972,
('Japan', '2002'): 31235.58818439,
('Japan', '2001'): 32716.41867489,
('Japan', '2000'): 37299.64412913}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'JP'
inds = 'NY.GDP.PCAP.CD'
result = download(country=cntry_codes, indicator=inds,
start=2000, end=2004, errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds, countries=cntry_codes,
start=2000, end=2004, errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_quarterly(self):
expected = {'DT.DOD.PUBS.CD.US': {('Albania', '2012Q1'): 3240539817.18,
('Albania', '2011Q4'): 3213979715.15,
('Albania', '2011Q3'): 3187681048.95,
('Albania', '2011Q2'): 3248041513.86,
('Albania', '2011Q1'): 3137210567.92}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'ALB'
inds = 'DT.DOD.PUBS.CD.US'
result = download(country=cntry_codes, indicator=inds,
start=2011, end=2012, freq='Q', errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds, countries=cntry_codes,
start=2011, end=2012, freq='Q', errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-1)
tm.assert_frame_equal(result, expected)
def test_wdi_search(self):
# Test that a name column exists, and that some results were returned
# ...without being too strict about what the actual contents of the
# results actually are. The fact that there are some, is good enough.
result = search('gdp.*capita.*constant')
self.assertTrue(result.name.str.contains('GDP').any())
# check cache returns the results within 0.5 sec
current_time = time.time()
result = search('gdp.*capita.*constant')
self.assertTrue(result.name.str.contains('GDP').any())
self.assertTrue(time.time() - current_time < 0.5)
result2 = WorldBankReader().search('gdp.*capita.*constant')
session = requests.Session()
result3 = search('gdp.*capita.*constant', session=session)
result4 = WorldBankReader(session=session).search('gdp.*capita.*constant')
for result in [result2, result3, result4]:
self.assertTrue(result.name.str.contains('GDP').any())
def test_wdi_get_indicators(self):
result1 = get_indicators()
result2 = WorldBankReader().get_indicators()
session = requests.Session()
result3 = get_indicators(session=session)
result4 = WorldBankReader(session=session).get_indicators()
for result in [result1, result2, result3, result4]:
exp_col = pd.Index([
"id",
"name",
"unit",
"source",
"sourceNote",
"sourceOrganization",
"topics",
])
# Column order is version dependent, so check columns are present
assert sorted(result.columns) == sorted(exp_col)
assert len(result) > 10000
def test_wdi_download_quarterly(self):
code = "DT.DOD.PUBS.CD.US"
expected = {
code: {
("Albania", "2012Q1"): 3240539817.18,
("Albania", "2011Q4"): 3213979715.15,
("Albania", "2011Q3"): 3187681048.95,
("Albania", "2011Q2"): 3248041513.86,
("Albania", "2011Q1"): 3137210567.92,
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
expected = expected.sort_index()
cntry_codes = "ALB"
inds = "DT.DOD.PUBS.CD.US"
result = download(
country=cntry_codes,
indicator=inds,
start=2011,
end=2012,
freq="Q",
errors="ignore",
)
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ["country", "year"]
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2011,
end=2012,
freq="Q",
errors="ignore").read()
result = result.sort_index()
result = np.round(result, decimals=-1)
tm.assert_frame_equal(result, expected)
def test_wdi_download_quarterly(self):
code = 'DT.DOD.PUBS.CD.US'
expected = {
code: {
('Albania', '2012Q1'): 3240539817.18,
('Albania', '2011Q4'): 3213979715.15,
('Albania', '2011Q3'): 3187681048.95,
('Albania', '2011Q2'): 3248041513.86,
('Albania', '2011Q1'): 3137210567.92
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
expected = expected.sort_index()
cntry_codes = 'ALB'
inds = 'DT.DOD.PUBS.CD.US'
result = download(country=cntry_codes,
indicator=inds,
start=2011,
end=2012,
freq='Q',
errors='ignore')
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ['country', 'year']
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2011,
end=2012,
freq='Q',
errors='ignore').read()
result = result.sort_index()
result = np.round(result, decimals=-1)
tm.assert_frame_equal(result, expected)
def test_wdi_download_str(self):
# These are the expected results, rounded (robust against
# data revisions in the future).
expected = {
'NY.GDP.PCAP.CD': {
('Japan', '2004'): 38000.0,
('Japan', '2003'): 35000.0,
('Japan', '2002'): 32000.0,
('Japan', '2001'): 34000.0,
('Japan', '2000'): 39000.0
}
}
expected = pd.DataFrame(expected)
expected = expected.sort_index()
cntry_codes = 'JP'
inds = 'NY.GDP.PCAP.CD'
result = download(country=cntry_codes,
indicator=inds,
start=2000,
end=2004,
errors='ignore')
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ['country', 'year']
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2000,
end=2004,
errors='ignore').read()
result = result.sort_index()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
