Merge pull request #314 from CartoDB/develop

Release 1.8.0

.travis.yml

@@ -1,4 +1,5 @@
 language: c
+dist: precise
 
 env:
   global:

NEWS.md

@@ -1,3 +1,10 @@
+1.8.0 (2017-10-18)
+------------------
+
+__Improvements__
+
+* Add `number_geometries` field to `OBS_GetAvailableGeometries` in order to provide the number of geometries from the source data to be used in the score calculation ([#313](https://github.com/CartoDB/observatory-extension/issues/313))
+
 1.7.0 (2017-08-18)
 ------------------
 

doc/boundary_functions.md

@@ -2,7 +2,7 @@
 
 Use the following functions to retrieve [Boundary](https://carto.com/docs/carto-engine/data/overview/#boundary-data) data. Data ranges from small areas (e.g. US Census Block Groups) to large areas (e.g. Countries). You can access boundaries by point location lookup, bounding box lookup, direct ID access and several other methods described below.
 
-You can [access](https://carto.com/docs/carto-engine/data/accessing) boundaries through CARTO Builder. The same methods will work if you are using the CARTO Engine to develop your application. We [encourage you](http://docs/carto-engine/data/accessing/#best-practices) to use table modifying methods (UPDATE and INSERT) over dynamic methods (SELECT).
+You can [access](https://carto.com/docs/carto-engine/data/accessing) boundaries through CARTO Builder. The same methods will work if you are using the CARTO Engine to develop your application. We [encourage you](https://carto.com/docs/carto-engine/data/accessing/#best-practices) to use table modifying methods (UPDATE and INSERT) over dynamic methods (SELECT).
 
 ## OBS_GetBoundariesByGeometry(geom geometry, geometry_id text)
 
@@ -123,7 +123,7 @@ SET the_geom = OBS_GetBoundary(the_geom, 'us.census.tiger.block_group')
 
 ## OBS_GetBoundaryId(point_geometry, boundary_id)
 
-The ```OBS_GetBoundaryId(point_geometry, boundary_id)``` returns a unique geometry_id for the boundary geometry that contains a given point geometry. See the [Boundary ID Glossary](http://docs/carto-engine/data/glossary/#boundary-ids). The method can be combined with ```OBS_GetBoundaryById(geometry_id)``` to create a point aggregation workflow.
+The ```OBS_GetBoundaryId(point_geometry, boundary_id)``` returns a unique geometry_id for the boundary geometry that contains a given point geometry. See the [Boundary ID Glossary](https://carto.com/docs/carto-engine/data/glossary/#boundary-ids). The method can be combined with ```OBS_GetBoundaryById(geometry_id)``` to create a point aggregation workflow.
 
 #### Arguments
 

doc/discovery_functions.md

@@ -228,7 +228,7 @@ SELECT * FROM cdb_observatory.OBS_GetAvailableDenominators(
 WHERE valid_timespan IS True;
 ```
 
-## OBS_GetAvailableGeometries(bounds, filter_tags, numer_id, denom_id, timespan)
+## OBS_GetAvailableGeometries(bounds, filter_tags, numer_id, denom_id, timespan, number_geometries)
 
 Return available geometries within a boundary and with the specified
 `filter_tags`.
@@ -242,6 +242,7 @@ filter_tags | Text[] | a list of filters.  Only geometries for which all of thes
 numer_id | Text | the ID of a numerator to check whether the geometry is valid against.  Will not reduce length of returned table, but will change values for `valid_numer` (optional)
 denom_id | Text | the ID of a denominator to check whether the geometry is valid against.  Will not reduce length of returned table, but will change values for `valid_denom` (optional)
 timespan | Text | the ID of a timespan to check whether the geometry is valid against.  Will not reduce length of returned table, but will change values for `valid_timespan` (optional)
+number_geometries | Integer | Number of geometries of the source data in order to calculate more accurately the score value to know which geometry fits better with the provided extent. (optional)
 
 #### Returns
 

release/observatory.control

@@ -1,5 +1,5 @@
 comment = 'CartoDB Observatory backend extension'
-default_version = '1.7.0'
+default_version = '1.8.0'
 requires = 'postgis'
 superuser = true
 schema = cdb_observatory

src/pg/observatory.control

@@ -1,5 +1,5 @@
 comment = 'CartoDB Observatory backend extension'
-default_version = '1.7.0'
+default_version = '1.8.0'
 requires = 'postgis'
 superuser = true
 schema = cdb_observatory

src/pg/sql/42_observatory_exploration.sql

@@ -323,7 +323,8 @@ CREATE OR REPLACE FUNCTION cdb_observatory.OBS_GetAvailableGeometries(
   filter_tags TEXT[] DEFAULT NULL,
   numer_id TEXT DEFAULT NULL,
   denom_id TEXT DEFAULT NULL,
-  timespan TEXT DEFAULT NULL
+  timespan TEXT DEFAULT NULL,
+  number_geoms INTEGER DEFAULT NULL
 ) RETURNS TABLE (
   geom_id TEXT,
   geom_name TEXT,
@@ -390,15 +391,16 @@ BEGIN
       FROM observatory.obs_meta_geom o
       WHERE %s (geom_tags ?& $4 OR CARDINALITY($4) = 0)
     ), scores AS (
-      SELECT * FROM cdb_observatory._OBS_GetGeometryScores($5,
-        (SELECT ARRAY_AGG(geom_id) FROM available_geoms)
+      SELECT * FROM cdb_observatory._OBS_GetGeometryScores(bounds => $5,
+        filter_geom_ids => (SELECT ARRAY_AGG(geom_id) FROM available_geoms),
+        desired_num_geoms => $6::integer
       )
     ) SELECT DISTINCT ON (geom_id) available_geoms.*, score, numtiles, notnull_percent, numgeoms,
              percentfill, estnumgeoms, meanmediansize
       FROM available_geoms, scores
       WHERE available_geoms.geom_id = scores.column_id
   $string$, geom_clause)
-  USING numer_id, denom_id, timespan, filter_tags, bounds;
+  USING numer_id, denom_id, timespan, filter_tags, bounds, number_geoms;
   RETURN;
 END
 $$ LANGUAGE plpgsql;

src/python/test/perftest.py

@@ -44,33 +44,7 @@ for q in (
                                  -73.81885528564453,41.745696344339564, 4326),
                  'us.census.tiger.county_clipped')) foo
            ORDER BY ST_NPoints(the_geom) DESC
-           LIMIT 50;''',
-        'DROP TABLE IF EXISTS obs_perftest_country_simple',
-        '''CREATE TABLE obs_perftest_country_simple (cartodb_id SERIAL PRIMARY KEY,
-           geom GEOMETRY,
-           name TEXT) ''',
-        '''INSERT INTO obs_perftest_country_simple (geom, name)
-           SELECT the_geom geom,
-                  geom_refs AS name
-           FROM (SELECT * FROM {schema}OBS_GetBoundariesByGeometry(
-                 st_makeenvelope(-179,-89, 179,89, 4326),
-                 'whosonfirst.wof_country_geom')) foo
-           ORDER BY ST_NPoints(the_geom) ASC
-           LIMIT 50;''',
-        'DROP TABLE IF EXISTS obs_perftest_country_complex',
-        '''CREATE TABLE obs_perftest_country_complex (cartodb_id SERIAL PRIMARY KEY,
-           geom GEOMETRY,
-           name TEXT) ''',
-        '''INSERT INTO obs_perftest_country_complex (geom, name)
-           SELECT the_geom geom,
-                  geom_refs AS name
-           FROM (SELECT * FROM {schema}OBS_GetBoundariesByGeometry(
-                 st_makeenvelope(-179,-89, 179,89, 4326),
-                 'whosonfirst.wof_country_geom')) foo
-           ORDER BY ST_NPoints(the_geom) DESC
-           LIMIT 50;''',
-        #'''SET statement_timeout = 5000;'''
-):
+           LIMIT 50;'''):
     q_formatted = q.format(
         schema='cdb_observatory.' if USE_SCHEMA else '',
     )
@@ -118,15 +92,7 @@ def record(params, results):
 
     ('complex', '_OBS_GetGeometryScores', 'NULL', 1),
     ('complex', '_OBS_GetGeometryScores', 'NULL', 500),
-    ('complex', '_OBS_GetGeometryScores', 'NULL', 3000),
-
-    ('country_simple', '_OBS_GetGeometryScores', 'NULL', 1),
-    ('country_simple', '_OBS_GetGeometryScores', 'NULL', 500),
-    ('country_simple', '_OBS_GetGeometryScores', 'NULL', 5000),
-
-    ('country_complex', '_OBS_GetGeometryScores', 'NULL', 1),
-    ('country_complex', '_OBS_GetGeometryScores', 'NULL', 500),
-    ('country_complex', '_OBS_GetGeometryScores', 'NULL', 5000),
+    ('complex', '_OBS_GetGeometryScores', 'NULL', 3000)
 ])
 def test_getgeometryscores_performance(geom_complexity, api_method, filters, target_geoms):
     print api_method, geom_complexity, filters, target_geoms