cartodb4/observatory-extension
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fixed tests for different test points per numerator

Browse Source
This commit is contained in:
Antonio 2017-08-17 16:31:40 +02:00
parent 6ab17bf8be
commit 48ed086fec
1 changed files with 20 additions and 155 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

175
src/python/test/autotest.py
View File

@ -77,7 +77,7 @@ SKIP_COLUMNS = set([
]) ])
MEASURE_COLUMNS = query(''' MEASURE_COLUMNS = query('''
SELECT ARRAY_AGG(DISTINCT numer_id) numer_ids, SELECT FIRST(distinct numer_id) numer_ids,
numer_aggregate, numer_aggregate,
denom_reltype, denom_reltype,
section_tags section_tags
@ -86,53 +86,9 @@ WHERE numer_weight > 0
AND numer_id NOT IN ('{skip}') AND numer_id NOT IN ('{skip}')
AND section_tags IS NOT NULL AND section_tags IS NOT NULL
AND subsection_tags IS NOT NULL AND subsection_tags IS NOT NULL
GROUP BY numer_aggregate, section_tags, denom_reltype GROUP BY numer_id, numer_aggregate, section_tags, denom_reltype
'''.format(skip="', '".join(SKIP_COLUMNS))).fetchall() '''.format(skip="', '".join(SKIP_COLUMNS))).fetchall()
#CATEGORY_COLUMNS = query('''
#SELECT distinct numer_id
#FROM observatory.obs_meta
#WHERE numer_type ILIKE 'text'
#AND numer_weight > 0
#''').fetchall()
#
#BOUNDARY_COLUMNS = query('''
#SELECT id FROM observatory.obs_column
#WHERE type ILIKE 'geometry'
#AND weight > 0
#''').fetchall()
#
#US_CENSUS_MEASURE_COLUMNS = query('''
#SELECT distinct numer_name
#FROM observatory.obs_meta
#WHERE numer_type ILIKE 'numeric'
#AND 'us.census.acs' = ANY (subsection_tags)
#AND numer_weight > 0
#''').fetchall()
#def default_geometry_id(column_id):
# '''
# Returns default test point for the column_id.
# '''
# if column_id == 'whosonfirst.wof_disputed_geom':
# return 'ST_SetSRID(ST_MakePoint(76.57, 33.78), 4326)'
# elif column_id == 'whosonfirst.wof_marinearea_geom':
# return 'ST_SetSRID(ST_MakePoint(-68.47, 43.33), 4326)'
# elif column_id in ('us.census.tiger.school_district_elementary',
# 'us.census.tiger.school_district_secondary',
# 'us.census.tiger.school_district_elementary_clipped',
# 'us.census.tiger.school_district_secondary_clipped'):
# return 'ST_SetSRID(ST_MakePoint(-73.7067, 40.7025), 4326)'
# elif column_id.startswith('es.ine'):
# return 'ST_SetSRID(ST_MakePoint(-2.51141249535454, 42.8226119029222), 4326)'
# elif column_id.startswith('us.zillow'):
# return 'ST_SetSRID(ST_MakePoint(-81.3544048197256, 28.3305906291771), 4326)'
# elif column_id.startswith('ca.'):
# return ''
# else:
# return 'ST_SetSRID(ST_MakePoint(-73.9, 40.7), 4326)'
def default_lonlat(column_id): def default_lonlat(column_id):
''' '''
@ -142,11 +98,6 @@ def default_lonlat(column_id):
return (76.57, 33.78) return (76.57, 33.78)
elif column_id == 'whosonfirst.wof_marinearea_geom': elif column_id == 'whosonfirst.wof_marinearea_geom':
return (-68.47, 43.33) return (-68.47, 43.33)
elif column_id in ('us.census.tiger.school_district_elementary',
'us.census.tiger.school_district_secondary',
'us.census.tiger.school_district_elementary_clipped',
'us.census.tiger.school_district_secondary_clipped'):
return (40.7025, -73.7067)
elif column_id.startswith('uk'): elif column_id.startswith('uk'):
if 'WA' in column_id: if 'WA' in column_id:
return (51.46844551219723, -3.184833526611328) return (51.46844551219723, -3.184833526611328)
@ -178,6 +129,11 @@ def default_lonlat(column_id):
return (48.860875144709475, 2.3613739013671875) return (48.860875144709475, 2.3613739013671875)
elif column_id.startswith('ca.'): elif column_id.startswith('ca.'):
return (43.65594991256823, -79.37965393066406) return (43.65594991256823, -79.37965393066406)
elif column_id in ('us.census.tiger.school_district_elementary',
'us.census.tiger.school_district_secondary',
'us.census.tiger.school_district_elementary_clipped',
'us.census.tiger.school_district_secondary_clipped'):
return (40.7025, -73.7067)
elif column_id.startswith('us.census.'): elif column_id.startswith('us.census.'):
return (28.3305906291771, -81.3544048197256) return (28.3305906291771, -81.3544048197256)
elif column_id.startswith('us.dma.'): elif column_id.startswith('us.dma.'):
@ -217,27 +173,24 @@ def default_area(column_id):
point=point) point=point)
return area return area
#@parameterized(US_CENSUS_MEASURE_COLUMNS)
#def test_get_us_census_measure_points(name):
# resp = query('''
#SELECT * FROM {schema}OBS_GetUSCensusMeasure({point}, '{name}')
# '''.format(name=name.replace("'", "''"),
# schema='cdb_observatory.' if USE_SCHEMA else '',
# point=default_point('')))
# rows = resp.fetchall()
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
def grouped_measure_columns(): def grouped_measure_columns():
groupbypoint = dict()
for numer_ids, numer_aggregate, denom_reltype, section_tags in MEASURE_COLUMNS: for numer_ids, numer_aggregate, denom_reltype, section_tags in MEASURE_COLUMNS:
for colgroup in grouper(numer_ids, 50): point = default_lonlat(numer_ids)
if point in groupbypoint:
groupbypoint[point].append(numer_ids)
else:
groupbypoint[point] = [numer_ids]
for key, value in groupbypoint.iteritems():
for colgroup in grouper(value, 50):
yield [c for c in colgroup if c], numer_aggregate, denom_reltype, section_tags yield [c for c in colgroup if c], numer_aggregate, denom_reltype, section_tags
@parameterized(grouped_measure_columns()) @parameterized(grouped_measure_columns())
def test_get_measure_points(numer_ids, numer_aggregate, denom_reltype, section_tags): def test_get_measure_points(numer_ids, numer_aggregate, denom_reltype, section_tags):
_test_measures(numer_ids, numer_aggregate, section_tags, denom_reltype, default_point(numer_ids[0])) _test_measures(numer_ids, default_point(numer_ids[0]))
@parameterized(grouped_measure_columns()) @parameterized(grouped_measure_columns())
@ -245,13 +198,12 @@ def test_get_measure_areas(numer_ids, numer_aggregate, denom_reltype, section_ta
if numer_aggregate is None or numer_aggregate.lower() not in ('sum', 'median', 'average'): if numer_aggregate is None or numer_aggregate.lower() not in ('sum', 'median', 'average'):
return return
if numer_aggregate.lower() in ('median', 'average') \ if numer_aggregate.lower() in ('median', 'average') \
and (denom_reltype is None \ and (denom_reltype is None or denom_reltype.lower() != 'universe'):
or denom_reltype.lower() != 'universe'):
return return
_test_measures(numer_ids, numer_aggregate, section_tags, denom_reltype, default_area(numer_ids[0])) _test_measures(numer_ids, default_area(numer_ids[0]))
def _test_measures(numer_ids, numer_aggregate, section_tags, denom_reltype, geom): def _test_measures(numer_ids, geom):
in_params = [] in_params = []
for numer_id in numer_ids: for numer_id in numer_ids:
in_params.append({ in_params.append({
@ -284,90 +236,3 @@ def _test_measures(numer_ids, numer_aggregate, section_tags, denom_reltype, geom
assert_equal(len(vals), len(in_params)) assert_equal(len(vals), len(in_params))
for i, val in enumerate(vals): for i, val in enumerate(vals):
assert_is_not_none(val, 'NULL for {}'.format(in_params[i]['numer_id'])) assert_is_not_none(val, 'NULL for {}'.format(in_params[i]['numer_id']))
#@parameterized(CATEGORY_COLUMNS)
#def test_get_category_areas(column_id):
# resp = query('''
#SELECT * FROM {schema}OBS_GetCategory({area}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# area=default_area(column_id)))
# assert_equal(resp.status_code, 200)
# rows = resp.json()['rows']
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
#@parameterized(CATEGORY_COLUMNS)
#def test_get_category_points(column_id):
# if column_id in SKIP_COLUMNS:
# raise SkipTest('Column {} should be skipped'.format(column_id))
# resp = query('''
#SELECT * FROM {schema}OBS_GetCategory({point}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# point=default_point(column_id)))
# rows = resp.fetchall()
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
#@parameterized(BOUNDARY_COLUMNS)
#def test_get_boundaries_by_geometry(column_id):
# resp = query('''
#SELECT * FROM {schema}OBS_GetBoundariesByGeometry({area}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# area=default_area(column_id)))
# assert_equal(resp.status_code, 200)
# rows = resp.json()['rows']
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
#@parameterized(BOUNDARY_COLUMNS)
#def test_get_points_by_geometry(column_id):
# resp = query('''
#SELECT * FROM {schema}OBS_GetPointsByGeometry({area}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# area=default_area(column_id)))
# assert_equal(resp.status_code, 200)
# rows = resp.json()['rows']
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
#@parameterized(BOUNDARY_COLUMNS)
#def test_get_boundary_points(column_id):
# resp = query('''
#SELECT * FROM {schema}OBS_GetBoundary({point}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# point=default_point(column_id)))
# assert_equal(resp.status_code, 200)
# rows = resp.json()['rows']
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
#@parameterized(BOUNDARY_COLUMNS)
#def test_get_boundary_id(column_id):
# resp = query('''
#SELECT * FROM {schema}OBS_GetBoundaryId({point}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# point=default_point(column_id)))
# assert_equal(resp.status_code, 200)
# rows = resp.json()['rows']
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])
#@parameterized(BOUNDARY_COLUMNS)
#def test_get_boundary_by_id(column_id):
# resp = query('''
#SELECT * FROM {schema}OBS_GetBoundaryById({geometry_id}, '{column_id}')
# '''.format(column_id=column_id,
# schema='cdb_observatory.' if USE_SCHEMA else '',
# geometry_id=default_geometry_id(column_id)))
# assert_equal(resp.status_code, 200)
# rows = resp.json()['rows']
# assert_equal(1, len(rows))
# assert_is_not_none(rows[0][0])