Merge branch 'develop' into update-markov-docs-null
This commit is contained in:
Andy Eschbacher
+22
-11
@@ -43,8 +43,10 @@ SELECT
|
||||
aoi.quads,
|
||||
aoi.significance,
|
||||
c.num_cyclists_per_total_population
|
||||
FROM CDB_AreasOfInterestLocal('SELECT * FROM commute_data',
|
||||
'num_cyclists_per_total_population') As aoi
|
||||
FROM
|
||||
cdb_crankshaft.CDB_AreasOfInterestLocal(
|
||||
'SELECT * FROM commute_data'
|
||||
'num_cyclists_per_total_population') As aoi
|
||||
JOIN commute_data As c
|
||||
ON c.cartodb_id = aoi.rowid;
|
||||
```
|
||||
@@ -77,8 +79,12 @@ A table with the following columns.
|
||||
#### Examples
|
||||
|
||||
```sql
|
||||
SELECT *
|
||||
FROM CDB_AreasOfInterestGlobal('SELECT * FROM commute_data', 'num_cyclists_per_total_population')
|
||||
SELECT
|
||||
*
|
||||
FROM
|
||||
cdb_crankshaft.CDB_AreasOfInterestGlobal(
|
||||
'SELECT * FROM commute_data',
|
||||
'num_cyclists_per_total_population')
|
||||
```
|
||||
|
||||
### CDB_AreasOfInterestLocalRate(subquery text, numerator_column text, denominator_column text)
|
||||
@@ -125,9 +131,11 @@ SELECT
|
||||
aoi.quads,
|
||||
aoi.significance,
|
||||
c.cyclists_per_total_population
|
||||
FROM CDB_AreasOfInterestLocalRate('SELECT * FROM commute_data'
|
||||
'num_cyclists',
|
||||
'total_population') As aoi
|
||||
FROM
|
||||
cdb_crankshaft.CDB_AreasOfInterestLocalRate(
|
||||
'SELECT * FROM commute_data'
|
||||
'num_cyclists',
|
||||
'total_population') As aoi
|
||||
JOIN commute_data As c
|
||||
ON c.cartodb_id = aoi.rowid;
|
||||
```
|
||||
@@ -161,10 +169,13 @@ A table with the following columns.
|
||||
#### Examples
|
||||
|
||||
```sql
|
||||
SELECT *
|
||||
FROM CDB_AreasOfInterestGlobalRate('SELECT * FROM commute_data',
|
||||
'num_cyclists',
|
||||
'total_population')
|
||||
SELECT
|
||||
*
|
||||
FROM
|
||||
cdb_crankshaft.CDB_AreasOfInterestGlobalRate(
|
||||
'SELECT * FROM commute_data',
|
||||
'num_cyclists',
|
||||
'total_population')
|
||||
```
|
||||
|
||||
## Hotspot, Coldspot, and Outlier Functions
|
||||
|
||||
+6
-2
@@ -47,8 +47,12 @@ SELECT
|
||||
m.trend_up,
|
||||
m.trend_down,
|
||||
m.volatility
|
||||
FROM CDB_SpatialMarkovTrend('SELECT * FROM nyc_real_estate'
|
||||
Array['m03y2009','m03y2010','m03y2011','m03y2012','m03y2013','m03y2014','m03y2015','m03y2016']) As m
|
||||
FROM
|
||||
cdb_crankshaft.CDB_SpatialMarkovTrend(
|
||||
'SELECT * FROM nyc_real_estate'
|
||||
Array['m03y2009', 'm03y2010', 'm03y2011',
|
||||
'm03y2012', 'm03y2013', 'm03y2014',
|
||||
'm03y2015','m03y2016']) As m
|
||||
JOIN nyc_real_estate As c
|
||||
ON c.cartodb_id = m.rowid;
|
||||
```
|
||||
|
||||
+9
-6
@@ -54,9 +54,9 @@ with t as (
|
||||
SELECT
|
||||
array_agg(cartodb_id::bigint) as id,
|
||||
array_agg(the_geom) as g,
|
||||
array_agg(coalesce(gla,0)::numeric) as w
|
||||
array_agg(coalesce(gla, 0)::numeric) as w
|
||||
FROM
|
||||
abel.centros_comerciales_de_madrid
|
||||
centros_comerciales_de_madrid
|
||||
WHERE not no_cc
|
||||
),
|
||||
s as (
|
||||
@@ -67,12 +67,15 @@ SELECT
|
||||
FROM
|
||||
sscc_madrid
|
||||
)
|
||||
select
|
||||
SELECT
|
||||
g.the_geom,
|
||||
trunc(g.h,2) as h,
|
||||
trunc(g.h, 2) as h,
|
||||
round(g.hpop) as hpop,
|
||||
trunc(g.dist/1000,2) as dist_km
|
||||
FROM t, s, CDB_Gravity1(t.id, t.g, t.w, s.id, s.g, s.p, newmall_ID, 100000, 5000) g
|
||||
trunc(g.dist/1000, 2) as dist_km
|
||||
FROM
|
||||
t,
|
||||
s,
|
||||
cdb_crankshaft.CDB_Gravity(t.id, t.g, t.w, s.id, s.g, s.p, newmall_ID, 100000, 5000) as g
|
||||
```
|
||||
|
||||
|
||||
|
||||
+11
-4
@@ -44,11 +44,18 @@ Default values:
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
with a as (
|
||||
select
|
||||
WITH a as (
|
||||
SELECT
|
||||
array_agg(the_geom) as geomin,
|
||||
array_agg(temp::numeric) as colin
|
||||
from table_4804232032
|
||||
FROM table_4804232032
|
||||
)
|
||||
SELECT CDB_SpatialInterpolation(geomin, colin, CDB_latlng(41.38, 2.15),1) FROM a;
|
||||
SELECT
|
||||
cdb_crankshaft.CDB_SpatialInterpolation(
|
||||
geomin,
|
||||
colin,
|
||||
CDB_latlng(41.38, 2.15),
|
||||
1)
|
||||
FROM
|
||||
a
|
||||
```
|
||||
|
||||
+13
-5
@@ -27,12 +27,20 @@ PostGIS wil include this in future versions ([doc for dev branch](http://postgis
|
||||
```sql
|
||||
WITH a AS (
|
||||
SELECT
|
||||
ARRAY[ST_GeomFromText('POINT(2.1744 41.403)', 4326),ST_GeomFromText('POINT(2.1228 41.380)', 4326),ST_GeomFromText('POINT(2.1511 41.374)', 4326),ST_GeomFromText('POINT(2.1528 41.413)', 4326),ST_GeomFromText('POINT(2.165 41.391)', 4326),ST_GeomFromText('POINT(2.1498 41.371)', 4326),ST_GeomFromText('POINT(2.1533 41.368)', 4326),ST_GeomFromText('POINT(2.131386 41.41399)', 4326)] AS geomin
|
||||
ARRAY[
|
||||
ST_GeomFromText('POINT(2.1744 41.403)', 4326),
|
||||
ST_GeomFromText('POINT(2.1228 41.380)', 4326),
|
||||
ST_GeomFromText('POINT(2.1511 41.374)', 4326),
|
||||
ST_GeomFromText('POINT(2.1528 41.413)', 4326),
|
||||
ST_GeomFromText('POINT(2.165 41.391)', 4326),
|
||||
ST_GeomFromText('POINT(2.1498 41.371)', 4326),
|
||||
ST_GeomFromText('POINT(2.1533 41.368)', 4326),
|
||||
ST_GeomFromText('POINT(2.131386 41.41399)', 4326)
|
||||
] AS geomin
|
||||
)
|
||||
SELECT
|
||||
st_transform(
|
||||
(st_dump(CDB_voronoi(geomin, 0.2, 1e-9)
|
||||
)).geom
|
||||
, 3857) as the_geom_webmercator
|
||||
ST_TRANSFORM(
|
||||
(ST_Dump(cdb_crankshaft.CDB_Voronoi(geomin, 0.2, 1e-9))).geom,
|
||||
3857) as the_geom_webmercator
|
||||
FROM a;
|
||||
```
|
||||
|
||||
+22
-14
@@ -1,8 +1,8 @@
|
||||
## K-Means Functions
|
||||
|
||||
### CDB_KMeans(subquery text, no_clusters INTEGER)
|
||||
### CDB_KMeans(subquery text, no_clusters integer)
|
||||
|
||||
This function attempts to find n clusters within the input data. It will return a table to CartoDB ids and
|
||||
This function attempts to find n clusters within the input data. It will return a table to CartoDB ids and
|
||||
the number of the cluster each point in the input was assigend to.
|
||||
|
||||
|
||||
@@ -26,18 +26,20 @@ A table with the following columns.
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
SELECT
|
||||
customers.*,
|
||||
km.cluster_no
|
||||
FROM cdb_crankshaft.CDB_Kmeans('SELECT * from customers' , 6) km, customers_3
|
||||
WHERE customers.cartodb_id = km.cartodb_id
|
||||
SELECT
|
||||
customers.*,
|
||||
km.cluster_no
|
||||
FROM
|
||||
cdb_crankshaft.CDB_Kmeans('SELECT * from customers' , 6) km, customers_3
|
||||
WHERE
|
||||
customers.cartodb_id = km.cartodb_id
|
||||
```
|
||||
|
||||
### CDB_WeightedMean(subquery text, weight_column text, category_column text)
|
||||
|
||||
Function that computes the weighted centroid of a number of clusters by some weight column.
|
||||
|
||||
### Arguments
|
||||
### Arguments
|
||||
|
||||
| Name | Type | Description |
|
||||
|------|------|-------------|
|
||||
@@ -45,18 +47,24 @@ Function that computes the weighted centroid of a number of clusters by some wei
|
||||
| weight\_column | TEXT | The name of the column to use as a weight |
|
||||
| category\_column | TEXT | The name of the column to use as a category |
|
||||
|
||||
### Returns
|
||||
### Returns
|
||||
|
||||
A table with the following columns.
|
||||
|
||||
| Column Name | Type | Description |
|
||||
|-------------|------|-------------|
|
||||
| the\_geom | GEOMETRY | A point for the weighted cluster center |
|
||||
| class | INTEGER | The cluster class |
|
||||
| class | INTEGER | The cluster class |
|
||||
|
||||
### Example Usage
|
||||
### Example Usage
|
||||
|
||||
```sql
|
||||
SELECT ST_TRANSFORM(the_geom, 3857) as the_geom_webmercator, class
|
||||
FROM cdb_weighted_mean('SELECT *, customer_value FROM customers','customer_value','cluster_no')
|
||||
```sql
|
||||
SELECT
|
||||
ST_Transform(m.the_geom, 3857) AS the_geom_webmercator,
|
||||
m.class
|
||||
FROM
|
||||
cdb_crankshaft.cdb_WeightedMean(
|
||||
'SELECT * FROM customers',
|
||||
'customer_value',
|
||||
'cluster_no') AS m
|
||||
```
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
### CDB_CreateAndPredictSegment(query TEXT, variable_name TEXT, target_query TEXT)
|
||||
|
||||
This function trains a [Gradient Boosting](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html) model to attempt to predict the target data and then generates predictions for new data.
|
||||
This function trains a [Gradient Boosting](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html) model to attempt to predict the target data and then generates predictions for new data.
|
||||
|
||||
#### Arguments
|
||||
|
||||
@@ -34,12 +34,12 @@ A table with the following columns.
|
||||
SELECT * from cdb_crankshaft.CDB_CreateAndPredictSegment(
|
||||
'SELECT agg, median_rent::numeric, male_pop::numeric, female_pop::numeric FROM late_night_agg',
|
||||
'agg',
|
||||
'SELECT row_number() OVER () As cartodb_id, median_rent, male_pop, female_pop FROM ml_learning_ny');
|
||||
'SELECT row_number() OVER () As cartodb_id, median_rent, male_pop, female_pop FROM ml_learning_ny');
|
||||
```
|
||||
|
||||
### CDB_CreateAndPredictSegment(target numeric[], train_features numeric[], prediction_features numeric[], prediction_ids numeric[])
|
||||
|
||||
This function trains a [Gradient Boosting](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html) model to attempt to predict the target data and then generates predictions for new data.
|
||||
This function trains a [Gradient Boosting](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html) model to attempt to predict the target data and then generates predictions for new data.
|
||||
|
||||
|
||||
#### Arguments
|
||||
@@ -76,7 +76,7 @@ WITH training As (
|
||||
FROM late_night_agg),
|
||||
target AS (
|
||||
SELECT cdb_crankshaft.CDB_PyAgg(Array[median_rent, male_pop, female_pop]::Numeric[]) As features,
|
||||
array_agg(cartodb_id) As cartodb_ids FROM late_night_agg)
|
||||
array_agg(cartodb_id) As cartodb_ids FROM late_night_agg)
|
||||
|
||||
SELECT cdb_crankshaft.CDB_CreateAndPredictSegment(training.target, training.features, target.features, target.cartodb_ids)
|
||||
FROM training, target;
|
||||
|
||||
+10
-4
@@ -23,11 +23,17 @@ Function to find the [PIA](https://en.wikipedia.org/wiki/Pole_of_inaccessibility
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
with a as(
|
||||
select st_geomfromtext('POLYGON((-432540.453078056 4949775.20452642,-432329.947920966 4951361.232584,-431245.028163694 4952223.31516671,-429131.071033529 4951768.00415574,-424622.07505895 4952843.13503987,-423688.327170174 4953499.20752423,-424086.294349759 4954968.38274191,-423068.388925945 4954378.63345336,-423387.653225542 4953355.67417084,-420594.869840519 4953781.00230592,-416026.095299382 4951484.06849063,-412483.018546414 4951024.5410983,-410490.399661215 4954502.24032205,-408186.197521284 4956398.91417441,-407627.262358013 4959300.94633864,-406948.770061627 4959874.85407739,-404949.583326472 4959047.74518163,-402570.908447199 4953743.46829807,-400971.358683991 4952193.11680804,-403533.488084088 4949649.89857885,-406335.177028373 4950193.19571096,-407790.456731515 4952391.46015616,-412060.672398345 4950381.2389307,-410716.93482498 4949156.7509561,-408464.162289794 4943912.8940387,-409350.599394983 4942819.84896006,-408087.791091424 4942451.6711778,-407274.045613725 4940572.4807777,-404446.196589102 4939976.71501489,-402422.964843936 4940450.3670813,-401010.654464241 4939054.8061663,-397647.247369412 4940679.80737878,-395658.413346901 4940528.84765185,-395536.852462953 4938829.79565997,-394268.923462818 4938003.7277717,-393388.720249116 4934757.80596815,-392393.301362444 4934326.71675815,-392573.527618037 4932323.40974412,-393464.640141837 4931903.10653605,-393085.597275686 4931094.7353605,-398426.261165985 4929156.87541607,-398261.174361137 4926238.00816416,-394045.059966834 4925765.18668498,-392982.960705174 4926391.81893628,-393090.272694301 4927176.84692181,-391648.240010564 4924626.06386961,-391889.914625075 4923086.14787613,-394345.177314013 4923235.086036,-395550.878718795 4917812.79243978,-399009.463978251 4912927.7157945,-398948.794855767 4911941.91010796,-398092.636652078 4911806.57392519,-401991.601817112 4911722.9204501,-406225.972607907 4914505.47286319,-411104.994569885 4912569.26941163,-412925.513522316 4913030.3608866,-414630.148884835 4914436.69169949,-414207.691417276 4919205.78028405,-418306.141109809 4917994.9580478,-424184.700779621 4918938.12432889,-426816.961458921 4923664.37379373,-420956.324227126 4923381.98014807,-420186.661267781 4924286.48693378,-420943.411166194 4926812.76394433,-419779.45457046 4928527.43466337,-419768.767899344 4930681.94459216,-421911.668097113 4930432.40620397,-423482.386112205 4933451.28047252,-427272.814773717 4934151.56473242,-427144.908678797 4939731.77191996,-428982.125554848 4940522.84445172,-428986.133056516 4942437.17281266,-431237.792396792 4947309.68284815,-432476.889648814 4947791.74800037,-432540.453078056 4949775.20452642))', 3857) as g
|
||||
WITH a as (
|
||||
SELECT
|
||||
ST_GeomFromText(
|
||||
'POLYGON((-432540.453078056 4949775.20452642,-432329.947920966 4951361.232584,-431245.028163694 4952223.31516671,-429131.071033529 4951768.00415574,-424622.07505895 4952843.13503987,-423688.327170174 4953499.20752423,-424086.294349759 4954968.38274191,-423068.388925945 4954378.63345336,-423387.653225542 4953355.67417084,-420594.869840519 4953781.00230592,-416026.095299382 4951484.06849063,-412483.018546414 4951024.5410983,-410490.399661215 4954502.24032205,-408186.197521284 4956398.91417441,-407627.262358013 4959300.94633864,-406948.770061627 4959874.85407739,-404949.583326472 4959047.74518163,-402570.908447199 4953743.46829807,-400971.358683991 4952193.11680804,-403533.488084088 4949649.89857885,-406335.177028373 4950193.19571096,-407790.456731515 4952391.46015616,-412060.672398345 4950381.2389307,-410716.93482498 4949156.7509561,-408464.162289794 4943912.8940387,-409350.599394983 4942819.84896006,-408087.791091424 4942451.6711778,-407274.045613725 4940572.4807777,-404446.196589102 4939976.71501489,-402422.964843936 4940450.3670813,-401010.654464241 4939054.8061663,-397647.247369412 4940679.80737878,-395658.413346901 4940528.84765185,-395536.852462953 4938829.79565997,-394268.923462818 4938003.7277717,-393388.720249116 4934757.80596815,-392393.301362444 4934326.71675815,-392573.527618037 4932323.40974412,-393464.640141837 4931903.10653605,-393085.597275686 4931094.7353605,-398426.261165985 4929156.87541607,-398261.174361137 4926238.00816416,-394045.059966834 4925765.18668498,-392982.960705174 4926391.81893628,-393090.272694301 4927176.84692181,-391648.240010564 4924626.06386961,-391889.914625075 4923086.14787613,-394345.177314013 4923235.086036,-395550.878718795 4917812.79243978,-399009.463978251 4912927.7157945,-398948.794855767 4911941.91010796,-398092.636652078 4911806.57392519,-401991.601817112 4911722.9204501,-406225.972607907 4914505.47286319,-411104.994569885 4912569.26941163,-412925.513522316 4913030.3608866,-414630.148884835 4914436.69169949,-414207.691417276 4919205.78028405,-418306.141109809 4917994.9580478,-424184.700779621 4918938.12432889,-426816.961458921 4923664.37379373,-420956.324227126 4923381.98014807,-420186.661267781 4924286.48693378,-420943.411166194 4926812.76394433,-419779.45457046 4928527.43466337,-419768.767899344 4930681.94459216,-421911.668097113 4930432.40620397,-423482.386112205 4933451.28047252,-427272.814773717 4934151.56473242,-427144.908678797 4939731.77191996,-428982.125554848 4940522.84445172,-428986.133056516 4942437.17281266,-431237.792396792 4947309.68284815,-432476.889648814 4947791.74800037,-432540.453078056 4949775.20452642))',
|
||||
3857) as g
|
||||
),
|
||||
b as (
|
||||
select ST_Transform(g, 4326) as g from a
|
||||
SELECT ST_Transform(g, 4326) as g
|
||||
FROM a
|
||||
)
|
||||
SELECT st_astext(CDB_PIA(g)) from b;
|
||||
SELECT
|
||||
ST_AsText(cdb_crankshaft.CDB_PIA(g))
|
||||
FROM b
|
||||
```
|
||||
|
||||
+15
-5
@@ -24,12 +24,22 @@ Returns a table object
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
with data as (
|
||||
select
|
||||
ARRAY[7.0,8.0,1.0,2.0,3.0,5.0,6.0,4.0] as colin,
|
||||
ARRAY[ST_GeomFromText('POINT(2.1744 41.4036)'),ST_GeomFromText('POINT(2.1228 41.3809)'),ST_GeomFromText('POINT(2.1511 41.3742)'),ST_GeomFromText('POINT(2.1528 41.4136)'),ST_GeomFromText('POINT(2.165 41.3917)'),ST_GeomFromText('POINT(2.1498 41.3713)'),ST_GeomFromText('POINT(2.1533 41.3683)'),ST_GeomFromText('POINT(2.131386 41.413998)')] as geomin
|
||||
WITH data as (
|
||||
SELECT
|
||||
ARRAY[7.0,8.0,1.0,2.0,3.0,5.0,6.0,4.0] as colin,
|
||||
ARRAY[
|
||||
ST_GeomFromText('POINT(2.1744 41.4036)'),
|
||||
ST_GeomFromText('POINT(2.1228 41.3809)'),
|
||||
ST_GeomFromText('POINT(2.1511 41.3742)'),
|
||||
ST_GeomFromText('POINT(2.1528 41.4136)'),
|
||||
ST_GeomFromText('POINT(2.165 41.3917)'),
|
||||
ST_GeomFromText('POINT(2.1498 41.3713)'),
|
||||
ST_GeomFromText('POINT(2.1533 41.3683)'),
|
||||
ST_GeomFromText('POINT(2.131386 41.413998)')
|
||||
] as geomin
|
||||
)
|
||||
select CDB_Densify(geomin, colin, 2) from data;
|
||||
SELECT cdb_crankshaft.CDB_Densify(geomin, colin, 2)
|
||||
FROM data
|
||||
```
|
||||
|
||||
|
||||
|
||||
+13
-5
@@ -26,11 +26,19 @@ Returns a table object
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
with data as (
|
||||
select
|
||||
ARRAY[7.0,8.0,1.0,2.0,3.0,5.0,6.0,4.0] as colin,
|
||||
ARRAY[ST_GeomFromText('POINT(2.1744 41.4036)'),ST_GeomFromText('POINT(2.1228 41.3809)'),ST_GeomFromText('POINT(2.1511 41.3742)'),ST_GeomFromText('POINT(2.1528 41.4136)'),ST_GeomFromText('POINT(2.165 41.3917)'),ST_GeomFromText('POINT(2.1498 41.3713)'),ST_GeomFromText('POINT(2.1533 41.3683)'),ST_GeomFromText('POINT(2.131386 41.413998)')] as geomin
|
||||
WITH data as (
|
||||
SELECT
|
||||
ARRAY[7.0,8.0,1.0,2.0,3.0,5.0,6.0,4.0] as colin,
|
||||
ARRAY[ST_GeomFromText('POINT(2.1744 41.4036)'),
|
||||
ST_GeomFromText('POINT(2.1228 41.3809)'),
|
||||
ST_GeomFromText('POINT(2.1511 41.3742)'),
|
||||
ST_GeomFromText('POINT(2.1528 41.4136)'),
|
||||
ST_GeomFromText('POINT(2.165 41.3917)'),
|
||||
ST_GeomFromText('POINT(2.1498 41.3713)'),
|
||||
ST_GeomFromText('POINT(2.1533 41.3683)'),
|
||||
ST_GeomFromText('POINT(2.131386 41.413998)')] as geomin
|
||||
)
|
||||
select CDB_TINmap(geomin, colin, 2) from data;
|
||||
SELECT cdb_crankshaft.CDB_TINmap(geomin, colin, 2)
|
||||
FROM data
|
||||
```
|
||||
|
||||
|
||||
+3
-3
@@ -43,7 +43,7 @@ With a table `website_visits` and a column of the number of website visits in un
|
||||
```sql
|
||||
SELECT
|
||||
id,
|
||||
CDB_StaticOutlier(visits_10k, 11.0) As outlier,
|
||||
cdb_crankshaft.CDB_StaticOutlier(visits_10k, 11.0) As outlier,
|
||||
visits_10k
|
||||
FROM website_visits
|
||||
```
|
||||
@@ -93,7 +93,7 @@ WITH cte As (
|
||||
unnest(Array[1,3,5,1,32,3,57,2]) As visits_10k
|
||||
)
|
||||
SELECT
|
||||
(CDB_PercentOutlier(array_agg(visits_10k), 2.0, array_agg(id))).*
|
||||
(cdb_crankshaft.CDB_PercentOutlier(array_agg(visits_10k), 2.0, array_agg(id))).*
|
||||
FROM cte;
|
||||
```
|
||||
|
||||
@@ -144,7 +144,7 @@ WITH cte As (
|
||||
unnest(Array[1,3,5,1,32,3,57,2]) As visits_10k
|
||||
)
|
||||
SELECT
|
||||
(CDB_StdDevOutlier(array_agg(visits_10k), 2.0, array_agg(id))).*
|
||||
(cdb_crankshaft.CDB_StdDevOutlier(array_agg(visits_10k), 2.0, array_agg(id))).*
|
||||
FROM cte;
|
||||
```
|
||||
|
||||
|
||||
+128
@@ -0,0 +1,128 @@
|
||||
## Regression
|
||||
|
||||
### Predictive geographically weighted regression (GWR)
|
||||
|
||||
Predictive GWR generates estimates of the dependent variable at locations where it has not been observed. It predicts these unknown values by first using the GWR model estimation analysis with known data values of the dependent and independent variables sampled from around the prediction location(s) to build a geographically weighted, spatially-varying regression model. It then uses this model and known values of the independent variables at the prediction locations to predict the value of the dependent variable where it is otherwise unknown.
|
||||
|
||||
For predictive GWR to work, a dataset needs known independent variables, some known dependent variables, and some unknown dependent variables. The dataset also needs to have geometry data (e.g., point, lines, or polygons).
|
||||
|
||||
#### Arguments
|
||||
|
||||
| Name | Type | Description |
|
||||
|------|------|-------------|
|
||||
| subquery | TEXT | SQL query that expose the data to be analyzed (e.g., `SELECT * FROM regression_inputs`). This query must have the geometry column name (see the optional `geom_col` for default), the id column name (see `id_col`), and the dependent (`dep_var`) and independent (`ind_vars`) column names. |
|
||||
| dep_var | TEXT | Name of the dependent variable in the regression model |
|
||||
| ind_vars | TEXT[] | Text array of independent variable column names used in the model to describe the dependent variable. |
|
||||
| bw (optional) | NUMERIC | Value of bandwidth. If `NULL` then select optimal (default). |
|
||||
| fixed (optional) | BOOLEAN | True for distance based kernel function and False (default) for adaptive (nearest neighbor) kernel function. Defaults to `False`. |
|
||||
| kernel (optional)| TEXT | Type of kernel function used to weight observations. One of `gaussian`, `bisquare` (default), or `exponential`. |
|
||||
|
||||
|
||||
#### Returns
|
||||
|
||||
| Column Name | Type | Description |
|
||||
|-------------|------|-------------|
|
||||
| coeffs | JSON | JSON object with parameter estimates for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the parameter estimate. |
|
||||
| stand_errs | JSON | Standard errors for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the respective standard errors. |
|
||||
| t_vals | JSON | T-values for each of the dependent variables. The keys of the JSON object are the dependent variable names, with values corresponding to the respective t-value. |
|
||||
| predicted | NUMERIC | predicted value of y |
|
||||
| residuals | NUMERIC | residuals of the response |
|
||||
| r_squared | NUMERIC | R-squared for the parameter fit |
|
||||
| bandwidth | NUMERIC | bandwidth value consisting of either a distance or N nearest neighbors |
|
||||
| rowid | INTEGER | row id of the original row |
|
||||
|
||||
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
SELECT
|
||||
g.cartodb_id,
|
||||
g.the_geom,
|
||||
g.the_geom_webmercator,
|
||||
(gwr.coeffs->>'pctblack')::numeric as coeff_pctblack,
|
||||
(gwr.coeffs->>'pctrural')::numeric as coeff_pctrural,
|
||||
(gwr.coeffs->>'pcteld')::numeric as coeff_pcteld,
|
||||
(gwr.coeffs->>'pctpov')::numeric as coeff_pctpov,
|
||||
gwr.residuals
|
||||
FROM cdb_crankshaft.CDB_GWR_Predict('select * from g_utm'::text,
|
||||
'pctbach'::text,
|
||||
Array['pctblack', 'pctrural', 'pcteld', 'pctpov']) As gwr
|
||||
JOIN g_utm as g
|
||||
on g.cartodb_id = gwr.rowid
|
||||
```
|
||||
|
||||
Note: See [PostgreSQL syntax for parsing JSON objects](https://www.postgresql.org/docs/9.5/static/functions-json.html).
|
||||
|
||||
### Geographically weighted regression model estimation
|
||||
|
||||
This analysis generates the model coefficients for a geographically weighted, spatially-varying regression. The model coefficients, along with their respective statistics, allow one to make inferences or describe a dependent variable based on a set of independent variables. Similar to traditional linear regression, GWR takes a linear combination of independent variables and a known dependent variable to estimate an optimal set of coefficients. The model coefficients are spatially varying (controlled by the `bandwidth` and `fixed` parameters), so that the model output is allowed to vary from geometry to geometry. This allows GWR to capture non-stationarity -- that is, how local processes vary over space. In contrast, coefficients obtained from estimating a traditional linear regression model assume that processes are constant over space.
|
||||
|
||||
#### Arguments
|
||||
|
||||
| Name | Type | Description |
|
||||
|------|------|-------------|
|
||||
| subquery | TEXT | SQL query that expose the data to be analyzed (e.g., `SELECT * FROM regression_inputs`). This query must have the geometry column name (see the optional `geom_col` for default), the id column name (see `id_col`), dependent and independent column names. |
|
||||
| dep_var | TEXT | name of the dependent variable in the regression model |
|
||||
| ind_vars | TEXT[] | Text array of independent variables used in the model to describe the dependent variable |
|
||||
| bw (optional) | NUMERIC | Value of bandwidth. If `NULL` then select optimal (default). |
|
||||
| fixed (optional) | BOOLEAN | True for distance based kernel function and False for adaptive (nearest neighbor) kernel function (default). Defaults to false. |
|
||||
| kernel | TEXT | Type of kernel function used to weight observations. One of `gaussian`, `bisquare` (default), or `exponential`. |
|
||||
|
||||
|
||||
#### Returns
|
||||
|
||||
| Column Name | Type | Description |
|
||||
|-------------|------|-------------|
|
||||
| coeffs | JSON | JSON object with parameter estimates for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the parameter estimate. |
|
||||
| stand_errs | JSON | Standard errors for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the respective standard errors. |
|
||||
| t_vals | JSON | T-values for each of the dependent variables. The keys of the JSON object are the dependent variable names, with values corresponding to the respective t-value. |
|
||||
| predicted | NUMERIC | predicted value of y |
|
||||
| residuals | NUMERIC | residuals of the response |
|
||||
| r_squared | NUMERIC | R-squared for the parameter fit |
|
||||
| bandwidth | NUMERIC | bandwidth value consisting of either a distance or N nearest neighbors |
|
||||
| rowid | INTEGER | row id of the original row |
|
||||
|
||||
|
||||
#### Example Usage
|
||||
|
||||
```sql
|
||||
SELECT
|
||||
g.cartodb_id,
|
||||
g.the_geom,
|
||||
g.the_geom_webmercator,
|
||||
(gwr.coeffs->>'pctblack')::numeric as coeff_pctblack,
|
||||
(gwr.coeffs->>'pctrural')::numeric as coeff_pctrural,
|
||||
(gwr.coeffs->>'pcteld')::numeric as coeff_pcteld,
|
||||
(gwr.coeffs->>'pctpov')::numeric as coeff_pctpov,
|
||||
gwr.residuals
|
||||
FROM cdb_crankshaft.CDB_GWR('select * from g_utm'::text, 'pctbach'::text, Array['pctblack', 'pctrural', 'pcteld', 'pctpov']) As gwr
|
||||
JOIN g_utm as g
|
||||
on g.cartodb_id = gwr.rowid
|
||||
```
|
||||
|
||||
Note: See [PostgreSQL syntax for parsing JSON objects](https://www.postgresql.org/docs/9.5/static/functions-json.html).
|
||||
|
||||
|
||||
## Advanced reading
|
||||
|
||||
* Fotheringham, A. Stewart, Chris Brunsdon, and Martin Charlton. 2002. Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. John Wiley & Sons. <http://www.wiley.com/WileyCDA/WileyTitle/productCd-0471496162.html>
|
||||
|
||||
* Brunsdon, Chris, A. Stewart Fotheringham, and Martin E. Charlton. 1996. "Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity." Geographical Analysis 28 (4): 281–98. <http://onlinelibrary.wiley.com/doi/10.1111/j.1538-4632.1996.tb00936.x/abstract>
|
||||
|
||||
* Brunsdon, Chris, Stewart Fotheringham, and Martin Charlton. 1998. "Geographically Weighted Regression." Journal of the Royal Statistical Society: Series D (The Statistician) 47 (3): 431–43. <http://onlinelibrary.wiley.com/doi/10.1111/1467-9884.00145/abstract>
|
||||
|
||||
* Fotheringham, A. S., M. E. Charlton, and C. Brunsdon. 1998. "Geographically Weighted Regression: A Natural Evolution of the Expansion Method for Spatial Data Analysis." Environment and Planning A 30 (11): 1905–27. doi:10.1068/a301905. <https://www.researchgate.net/publication/23538637_Geographically_Weighted_Regression_A_Natural_Evolution_Of_The_Expansion_Method_for_Spatial_Data_Analysis>
|
||||
|
||||
### GWR for prediction
|
||||
|
||||
* Harris, P., A. S. Fotheringham, R. Crespo, and M. Charlton. 2010. "The Use of Geographically Weighted Regression for Spatial Prediction: An Evaluation of Models Using Simulated Data Sets." Mathematical Geosciences 42 (6): 657–80. doi:10.1007/s11004-010-9284-7. <https://www.researchgate.net/publication/225757830_The_Use_of_Geographically_Weighted_Regression_for_Spatial_Prediction_An_Evaluation_of_Models_Using_Simulated_Data_Sets>
|
||||
|
||||
### GWR in application
|
||||
|
||||
* Cahill, Meagan, and Gordon Mulligan. 2007. "Using Geographically Weighted Regression to Explore Local Crime Patterns." Social Science Computer Review 25 (2): 174–93. doi:10.1177/0894439307298925. <http://isites.harvard.edu/fs/docs/icb.topic923297.files/174.pdf>
|
||||
|
||||
* Gilbert, Angela, and Jayajit Chakraborty. 2011. "Using Geographically Weighted Regression for Environmental Justice Analysis: Cumulative Cancer Risks from Air Toxics in Florida." Social Science Research 40 (1): 273–86. doi:10.1016/j.ssresearch.2010.08.006. <http://scholarcommons.usf.edu/cgi/viewcontent.cgi?article=2985&context=etd>
|
||||
|
||||
* Ali, Kamar, Mark D. Partridge, and M. Rose Olfert. 2007. "Can Geographically Weighted Regressions Improve Regional Analysis and Policy Making?" International Regional Science Review 30 (3): 300–329. doi:10.1177/0160017607301609. <https://www.researchgate.net/publication/249682503_Can_Geographically_Weighted_Regressions_Improve_Regional_Analysis_and_Policy_Making>
|
||||
|
||||
* Lu, Binbin, Martin Charlton, and A. Stewart Fotheringhama. 2011. "Geographically Weighted Regression Using a Non-Euclidean Distance Metric with a Study on London House Price Data." Procedia Environmental Sciences, Spatial Statistics 2011: Mapping Global Change, 7: 92–97. doi:10.1016/j.proenv.2011.07.017. <https://www.researchgate.net/publication/261960122_Geographically_weighted_regression_with_a_non-Euclidean_distance_metric_A_case_study_using_hedonic_house_price_data>
|
||||
Reference in New Issue
Block a user