Source code for tobler.dasymetric.models
-from ..area_weighted.vectorized_raster_interpolation import (
+"""Model-based methods for areal interpolation."""
+
+import numpy as np
+import statsmodels.formula.api as smf
+from statsmodels.genmod.families import Gaussian, NegativeBinomial, Poisson
+
+from ..area_weighted.vectorized_raster_interpolation import (
+ _check_presence_of_crs,
calculate_interpolated_population_from_correspondence_table,
- return_weights_from_regression,
create_non_zero_population_by_pixels_locations,
- _check_presence_of_crs,
+ fast_append_profile_in_gdf,
+ return_weights_from_regression,
)
-from ..data import fetch_quilt_path
-import rasterio
-import warnings
+from tobler.util import project_gdf
-[docs]def linear_model(
+[docs]def glm_pixel_adjusted(
source_df=None,
target_df=None,
raster="nlcd_2011",
@@ -131,8 +136,13 @@ Source code for tobler.dasymetric.models
formula=None,
likelihood="poisson",
force_crs_match=True,
+ **kwargs,
):
- """Interpolate data between two polygonal datasets using an auxiliary raster to as inut to a linear regression model.
+ """Estimate interpolated values using raster data as input to a generalized linear model, then apply an adjustmnent factor based on pixel values.
+
+ Unlike the regular `glm` function, this version applies an experimental pixel-level adjustment
+ subsequent to fitting the model. This has the benefit of making sure local control totals are
+ respected, but can also induce unknown error. Use with caution.
Parameters
----------
@@ -145,8 +155,8 @@ Source code for tobler.dasymetric.models
i.e. a coefficients refer to the relationship between pixel counts and population counts.
Defaults to 2011 NLCD
raster_codes : list, required (default =[21, 22, 23, 24])
- list of inteegers that represent different types of raster cells. Defaults to [21, 22, 23, 24] which
- are considered developed land types in the NLCD
+ list of integers that represent different types of raster cells.
+ Defaults to [21, 22, 23, 24] whichare considered developed land types in the NLCD
variable : str, required
name of the variable (column) to be modeled from the `source_df`
formula : str, optional
@@ -156,35 +166,124 @@ Source code for tobler.dasymetric.models
Returns
--------
- interpolated: geopandas.GeoDataFrame
- a new geopandas dataframe with boundaries from `target_df` and modeled attribute data from the `source_df`
+ interpolated : geopandas.GeoDataFrame
+ a new geopandas dataframe with boundaries from `target_df` and modeled attribute data
+ from the `source_df`
"""
if not raster_codes:
raster_codes = [21, 22, 23, 24]
- # build weights from raster and vector data
- weights = return_weights_from_regression(
- geodataframe=source_df,
- raster_path=raster,
- pop_string=variable,
- formula_string=formula,
- codes=raster_codes,
- force_crs_match=force_crs_match,
- likelihood=likelihood,
- )
+ # build weights from raster and vector data
+ weights = return_weights_from_regression(
+ geodataframe=source_df,
+ raster_path=raster,
+ pop_string=variable,
+ formula_string=formula,
+ codes=raster_codes,
+ force_crs_match=force_crs_match,
+ likelihood=likelihood,
+ na_value=255,
+ ReLU=False,
+ )
- # match vector population to pixel counts
- correspondence_table = create_non_zero_population_by_pixels_locations(
- geodataframe=source_df, raster=raster, pop_string=variable, weights=weights
- )
+ # match vector population to pixel counts
+ correspondence_table = create_non_zero_population_by_pixels_locations(
+ geodataframe=source_df, raster=raster, pop_string=variable, weights=weights
+ )
- # estimate the model
- interpolated = calculate_interpolated_population_from_correspondence_table(
- target_df, raster, correspondence_table
- )
+ # estimate the model
+ interpolated = calculate_interpolated_population_from_correspondence_table(
+ target_df, raster, correspondence_table, variable_name=variable
+ )
return interpolated
+
+
+[docs]def glm(
+ source_df=None,
+ target_df=None,
+ raster="nlcd_2011",
+ raster_codes=None,
+ variable=None,
+ formula=None,
+ likelihood="poisson",
+ force_crs_match=True,
+ return_model=False,
+):
+ """Estimate interpolated values using raster data as input to a generalized linear model.
+
+ Parameters
+ ----------
+ source_df : geopandas.GeoDataFrame, required
+ geodataframe containing source original data to be represented by another geometry
+ target_df : geopandas.GeoDataFrame, required
+ geodataframe containing target boundaries that will be used to represent the source data
+ raster : str, required (default="nlcd_2011")
+ path to raster file that will be used to input data to the regression model.
+ i.e. a coefficients refer to the relationship between pixel counts and population counts.
+ Defaults to 2011 NLCD
+ raster_codes : list, required (default =[21, 22, 23, 24, 41, 42, 52])
+ list of integers that represent different types of raster cells. If no formula is given,
+ the model will be fit from a linear combination of the logged count of each cell type
+ listed here. Defaults to [21, 22, 23, 24, 41, 42, 52] which
+ are informative land type cells from the NLCD
+ variable : str, required
+ name of the variable (column) to be modeled from the `source_df`
+ formula : str, optional
+ patsy-style model formula that specifies the model. Raster codes should be prefixed with
+ "Type_", e.g. `"n_total_pop ~ -1 + np.log1p(Type_21) + np.log1p(Type_22)`
+ likelihood : str, {'poisson', 'gaussian', 'neg_binomial'} (default = "poisson")
+ the likelihood function used in the model
+ force_crs_match : bool
+ whether to coerce geodataframe and raster to the same CRS
+ return model : bool
+ whether to return the fitted model in addition to the interpolated geodataframe.
+ If true, this will return (geodataframe, model)
+
+ Returns
+ --------
+ interpolated : geopandas.GeoDataFrame
+ a new geopandas dataframe with boundaries from `target_df` and modeled attribute
+ data from the `source_df`. If `return_model` is true, the function will also return
+ the fitted regression model for further diagnostics
+
+
+ """
+ _check_presence_of_crs(source_df)
+ liks = {"poisson": Poisson, "gaussian": Gaussian, "neg_binomial": NegativeBinomial}
+
+ if likelihood not in liks.keys():
+ raise ValueError(f"likelihood must one of {liks.keys()}")
+
+ if not raster_codes:
+ raster_codes = [21, 22, 23, 24, 41, 42, 52]
+ raster_codes = ["Type_" + str(i) for i in raster_codes]
+
+ if not formula:
+ formula = (
+ variable
+ + "~ -1 +"
+ + "+".join(["np.log1p(" + code + ")" for code in raster_codes])
+ )
+ source_df["area"] = project_gdf(source_df.copy()).area
+
+ profiled_df = fast_append_profile_in_gdf(
+ source_df[["geometry", variable, "area"]], raster, force_crs_match
+ )
+
+ results = smf.glm(formula, data=profiled_df, family=liks[likelihood]()).fit()
+
+ out = target_df.copy()[["geometry"]]
+ temp = fast_append_profile_in_gdf(out[["geometry"]], raster, force_crs_match)
+ temp["area"] = project_gdf(out.copy()).area
+
+ out[variable] = results.predict(temp.drop(columns=["geometry"]).fillna(0))
+
+ if return_model:
+ return out, results
+
+ return out
diff --git a/docs/_modules/tobler/data.html b/docs/_modules/tobler/data.html
index 06b64a4..f544dc4 100644
--- a/docs/_modules/tobler/data.html
+++ b/docs/_modules/tobler/data.html
@@ -112,6 +112,8 @@
Source code for tobler.data
from urllib.parse import unquote, urlparse
+from warnings import warn
+from requests.exceptions import Timeout
import quilt3
@@ -153,12 +155,12 @@ Source code for tobler.data
full_path = unquote(nlcd[path + ".tif"].get())
full_path = urlparse(full_path).path
+
except ImportError:
- raise IOError(
+ warn(
"Unable to locate local raster data. If you would like to use "
"raster data from the National Land Cover Database, you can "
- "store it locally using the `data.store_rasters()` function"
- )
+ "store it locally using the `data.store_rasters()` function")
else:
return path
diff --git a/docs/_sources/api.rst.txt b/docs/_sources/api.rst.txt
index 93cc826..cdf78d6 100644
--- a/docs/_sources/api.rst.txt
+++ b/docs/_sources/api.rst.txt
@@ -34,7 +34,8 @@ variables being assigned to the target
.. autosummary::
:toctree: generated/
- linear_model
+ glm
+ glm_pixel_adjusted
masked_area_interpolate
diff --git a/docs/_sources/generated/tobler.dasymetric.glm.rst.txt b/docs/_sources/generated/tobler.dasymetric.glm.rst.txt
new file mode 100644
index 0000000..fac89c4
--- /dev/null
+++ b/docs/_sources/generated/tobler.dasymetric.glm.rst.txt
@@ -0,0 +1,6 @@
+tobler.dasymetric.glm
+=====================
+
+.. currentmodule:: tobler.dasymetric
+
+.. autofunction:: glm
\ No newline at end of file
diff --git a/docs/_sources/generated/tobler.dasymetric.glm_pixel_adjusted.rst.txt b/docs/_sources/generated/tobler.dasymetric.glm_pixel_adjusted.rst.txt
new file mode 100644
index 0000000..f8f2fb4
--- /dev/null
+++ b/docs/_sources/generated/tobler.dasymetric.glm_pixel_adjusted.rst.txt
@@ -0,0 +1,6 @@
+tobler.dasymetric.glm\_pixel\_adjusted
+======================================
+
+.. currentmodule:: tobler.dasymetric
+
+.. autofunction:: glm_pixel_adjusted
\ No newline at end of file
diff --git a/docs/_sources/generated/tobler.dasymetric.linear_model.rst.txt b/docs/_sources/generated/tobler.dasymetric.linear_model.rst.txt
deleted file mode 100644
index 6e42281..0000000
--- a/docs/_sources/generated/tobler.dasymetric.linear_model.rst.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-tobler.dasymetric.linear\_model
-===============================
-
-.. currentmodule:: tobler.dasymetric
-
-.. autofunction:: linear_model
\ No newline at end of file
diff --git a/docs/api.html b/docs/api.html
index da4d265..c9ea0d9 100644
--- a/docs/api.html
+++ b/docs/api.html
@@ -157,10 +157,13 @@ Dasymetric
-linear_model([source_df, target_df, raster, …])
Interpolate data between two polygonal datasets using an auxiliary raster to as inut to a linear regression model.
glm([source_df, target_df, raster, …])
Estimate interpolated values using raster data as input to a generalized linear model.
masked_area_interpolate(source_df, target_df)
glm_pixel_adjusted([source_df, target_df, …])
Estimate interpolated values using raster data as input to a generalized linear model, then apply an adjustmnent factor based on pixel values.
masked_area_interpolate(source_df, target_df)
Interpolate data between two polygonal datasets using an auxiliary raster to mask out uninhabited land.
tobler.area_weighted.area_interpolate¶
-
-
tobler.area_weighted.area_interpolate(source_df, target_df, extensive_variables=[], intensive_variables=[], table=None, allocate_total=True)[source]¶
+tobler.area_weighted.area_interpolate(source_df, target_df, extensive_variables=None, intensive_variables=None, table=None, allocate_total=True)[source]¶
Area interpolation for extensive and intensive variables.
- Parameters
-- source_df
geopandas.GeoDataFrame
-- target_df
geopandas.GeoDataFrame
+- source_df
geopandas.GeoDataFrame
+- target_df
geopandas.GeoDataFrame
- extensive_variables
list columns in dataframes for extensive variables
- intensive_variables
list columns in dataframes for intensive variables
- table
scipy.sparse.dok_matrix
+- table
scipy.sparse.dok_matrix
- allocate_totalbool
True if total value of source area should be allocated.
False if denominator is area of i. Note that the two cases
would be identical when the area of the source polygon is
@@ -140,8 +140,8 @@
tobler.area_weighted.area_interpolateReturns
-- estimates
tuple (2) (extensive variable array, intensive variables array)
-Each is of shape n,v where n is number of target units and v is the number of variables for each variable type.
+- estimates
geopandas.GeoDataFrame new geodaraframe with interpolated variables as columns and target_df geometry
+as output geometry
tobler.area_weighted.area_tables
- Parameters
-- source_df
geopandas.GeoDataFrame
-- target_df
geopandas.GeoDataFrame
+- source_df
geopandas.GeoDataFrame
+- target_df
geopandas.GeoDataFrame
- Returns
diff --git a/docs/generated/tobler.area_weighted.area_tables_binning.html b/docs/generated/tobler.area_weighted.area_tables_binning.html
index 70e8f6b..59aced5 100644
--- a/docs/generated/tobler.area_weighted.area_tables_binning.html
+++ b/docs/generated/tobler.area_weighted.area_tables_binning.html
@@ -124,7 +124,7 @@ tobler.area_weighted.area_tables_binning
- Parameters
-- source_df
geopandas.GeoDataFrame GeoDataFrame containing input data and polygons
+- source_df
geopandas.GeoDataFrame GeoDataFrame containing input data and polygons
- target_df
geopandas.GeoDataFramee GeoDataFrame defining the output geometries
tobler.area_weighted.area_tables_binningReturns
-- tables
scipy.sparse.dok_matrix
+- tables
scipy.sparse.dok_matrix
diff --git a/docs/generated/tobler.area_weighted.area_tables_raster.html b/docs/generated/tobler.area_weighted.area_tables_raster.html
index 8af0278..60e2fd2 100644
--- a/docs/generated/tobler.area_weighted.area_tables_raster.html
+++ b/docs/generated/tobler.area_weighted.area_tables_raster.html
@@ -15,7 +15,7 @@
-
+
@@ -124,9 +124,9 @@ tobler.area_weighted.area_tables_raster
- Parameters
-- source_df
geopandas.GeoDataFrame geeodataframe with geometry column of polygon type
+- source_df
geopandas.GeoDataFrame geeodataframe with geometry column of polygon type
- target_df
geopandas.GeoDataFrame geodataframe with geometry column of polygon type
+- target_df
geopandas.GeoDataFrame geodataframe with geometry column of polygon type
- raster_path
str the path to the associated raster image.
tobler.dasymetric.glm — tobler v0.1.0 Manual
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+tobler.dasymetric.glm¶
+
+-
+
tobler.dasymetric.glm(source_df=None, target_df=None, raster='nlcd_2011', raster_codes=None, variable=None, formula=None, likelihood='poisson', force_crs_match=True, return_model=False)[source]¶
+Estimate interpolated values using raster data as input to a generalized linear model.
+
+- Parameters
+
+- source_df
geopandas.GeoDataFrame, required geodataframe containing source original data to be represented by another geometry
+- target_df
geopandas.GeoDataFrame, required geodataframe containing target boundaries that will be used to represent the source data
+- raster
str, required (default=”nlcd_2011”) path to raster file that will be used to input data to the regression model.
+i.e. a coefficients refer to the relationship between pixel counts and population counts.
+Defaults to 2011 NLCD
+- raster_codes
list, required (default =[21, 22, 23, 24, 41, 42, 52]) list of integers that represent different types of raster cells. If no formula is given,
+the model will be fit from a linear combination of the logged count of each cell type
+listed here. Defaults to [21, 22, 23, 24, 41, 42, 52] which
+are informative land type cells from the NLCD
+- variable
str, required name of the variable (column) to be modeled from the source_df
+- formula
str, optional patsy-style model formula that specifies the model. Raster codes should be prefixed with
+“Type_”, e.g. “n_total_pop ~ -1 + np.log1p(Type_21) + np.log1p(Type_22)
+- likelihood
str, {‘poisson’, ‘gaussian’, ‘neg_binomial’} (default = “poisson”) the likelihood function used in the model
+- force_crs_matchbool
whether to coerce geodataframe and raster to the same CRS
+- return modelbool
whether to return the fitted model in addition to the interpolated geodataframe.
+If true, this will return (geodataframe, model)
+
+- Returns
+
+- interpolated
geopandas.GeoDataFrame a new geopandas dataframe with boundaries from target_df and modeled attribute
+data from the source_df. If return_model is true, the function will also return
+the fitted regression model for further diagnostics
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/docs/generated/tobler.dasymetric.linear_model.html b/docs/generated/tobler.dasymetric.glm_pixel_adjusted.html
similarity index 76%
rename from docs/generated/tobler.dasymetric.linear_model.html
rename to docs/generated/tobler.dasymetric.glm_pixel_adjusted.html
index 430434e..36dc514 100644
--- a/docs/generated/tobler.dasymetric.linear_model.html
+++ b/docs/generated/tobler.dasymetric.glm_pixel_adjusted.html
@@ -3,7 +3,7 @@
- tobler.dasymetric.linear_model — tobler v0.1.0 Manual
+ tobler.dasymetric.glm_pixel_adjusted — tobler v0.1.0 Manual
@@ -16,7 +16,7 @@
-
+
@@ -85,7 +85,7 @@
@@ -115,25 +115,28 @@
-
-tobler.dasymetric.linear_model¶
+
+tobler.dasymetric.glm_pixel_adjusted¶
--
-
tobler.dasymetric.linear_model(source_df=None, target_df=None, raster='nlcd_2011', raster_codes=None, variable=None, formula=None, likelihood='poisson', force_crs_match=True)[source]¶
-Interpolate data between two polygonal datasets using an auxiliary raster to as inut to a linear regression model.
+-
+
tobler.dasymetric.glm_pixel_adjusted(source_df=None, target_df=None, raster='nlcd_2011', raster_codes=None, variable=None, formula=None, likelihood='poisson', force_crs_match=True, **kwargs)[source]¶
+Estimate interpolated values using raster data as input to a generalized linear model, then apply an adjustmnent factor based on pixel values.
+Unlike the regular glm function, this version applies an experimental pixel-level adjustment
+subsequent to fitting the model. This has the benefit of making sure local control totals are
+respected, but can also induce unknown error. Use with caution.
- Parameters
-- source_df
geopandas.GeoDataFrame, required geodataframe containing source original data to be represented by another geometry
+- source_df
geopandas.GeoDataFrame, required geodataframe containing source original data to be represented by another geometry
- target_df
geopandas.GeoDataFrame, required geodataframe containing target boundaries that will be used to represent the source data
+- target_df
geopandas.GeoDataFrame, required geodataframe containing target boundaries that will be used to represent the source data
- raster
str, required (default=”nlcd_2011”) path to raster file that will be used to input data to the regression model.
i.e. a coefficients refer to the relationship between pixel counts and population counts.
Defaults to 2011 NLCD
- raster_codes
list, required (default =[21, 22, 23, 24]) list of inteegers that represent different types of raster cells. Defaults to [21, 22, 23, 24] which
-are considered developed land types in the NLCD
+- raster_codes
list, required (default =[21, 22, 23, 24]) list of integers that represent different types of raster cells.
+Defaults to [21, 22, 23, 24] whichare considered developed land types in the NLCD
- variable
str, required name of the variable (column) to be modeled from the source_df
tobler.dasymetric.linear_modelReturns
-
-- interpolated:
geopandas.GeoDataFrame a new geopandas dataframe with boundaries from target_df and modeled attribute data from the source_df
+
+- interpolated
geopandas.GeoDataFrame a new geopandas dataframe with boundaries from target_df and modeled attribute data
+from the source_df
tobler.dasymetric.linear_model
- Source
diff --git a/docs/generated/tobler.dasymetric.masked_area_interpolate.html b/docs/generated/tobler.dasymetric.masked_area_interpolate.html
index da2fcb2..d6b2df2 100644
--- a/docs/generated/tobler.dasymetric.masked_area_interpolate.html
+++ b/docs/generated/tobler.dasymetric.masked_area_interpolate.html
@@ -16,7 +16,7 @@
-
+
@@ -119,16 +119,16 @@
tobler.dasymetric.masked_area_interpolate¶
-
-
tobler.dasymetric.masked_area_interpolate(source_df, target_df, raster_path='nlcd_2011', codes=None, force_crs_match=True, extensive_variables=None, intensive_variables=None, allocate_total=True, tables=None)[source]¶
+tobler.dasymetric.masked_area_interpolate(source_df, target_df, raster='nlcd_2011', codes=None, force_crs_match=True, extensive_variables=None, intensive_variables=None, allocate_total=True, tables=None)[source]¶
Interpolate data between two polygonal datasets using an auxiliary raster to mask out uninhabited land.
- Parameters
-- source_df
geopandas.GeoDataFrame source data to be converted to another geometric representation.
+- source_df
geopandas.GeoDataFrame source data to be converted to another geometric representation.
- target_df
geopandas.GeoDataFrame target geometries that will form the new representation of the input data
+- target_df
geopandas.GeoDataFrame target geometries that will form the new representation of the input data
- raster_path
str path to raster file that contains ancillary data.
+
- raster
str path to raster file that contains ancillary data.
alternatively a user can pass ncld_2001 or nlcd_2011 to use built-in data from the
National Land Cover Database
tobler.dasymetric.masked_area_interpolateReturns
-geopandas.GeoDataFrameGeoDataFrame with geometries matching the target_df and extensive and intensive
+
geopandas.GeoDataFrameGeoDataFrame with geometries matching the target_df and extensive and intensive
variables as the columns
diff --git a/docs/genindex.html b/docs/genindex.html
index 739bd0f..db2d587 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -116,7 +116,7 @@ Index
A
- | L
+ | G
| M
| S
@@ -137,10 +137,14 @@ A
-L
+G
diff --git a/docs/objects.inv b/docs/objects.inv
index b674a78..a14cada 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 55c5256..e6f4c18 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["api","generated/tobler.area_weighted.area_interpolate","generated/tobler.area_weighted.area_tables","generated/tobler.area_weighted.area_tables_binning","generated/tobler.area_weighted.area_tables_raster","generated/tobler.dasymetric.linear_model","generated/tobler.dasymetric.masked_area_interpolate","generated/tobler.data.store_rasters","index","installation","references"],envversion:{"sphinx.domains.c":1,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":1,"sphinx.domains.javascript":1,"sphinx.domains.math":2,"sphinx.domains.python":1,"sphinx.domains.rst":1,"sphinx.domains.std":1,"sphinx.ext.intersphinx":1,"sphinx.ext.viewcode":1,sphinx:56},filenames:["api.rst","generated/tobler.area_weighted.area_interpolate.rst","generated/tobler.area_weighted.area_tables.rst","generated/tobler.area_weighted.area_tables_binning.rst","generated/tobler.area_weighted.area_tables_raster.rst","generated/tobler.dasymetric.linear_model.rst","generated/tobler.dasymetric.masked_area_interpolate.rst","generated/tobler.data.store_rasters.rst","index.rst","installation.rst","references.rst"],objects:{"tobler.area_weighted":{area_interpolate:[1,0,1,""],area_tables:[2,0,1,""],area_tables_binning:[3,0,1,""],area_tables_raster:[4,0,1,""]},"tobler.dasymetric":{linear_model:[5,0,1,""],masked_area_interpolate:[6,0,1,""]},"tobler.data":{store_rasters:[7,0,1,""]}},objnames:{"0":["py","function","Python function"]},objtypes:{"0":"py:function"},terms:{"case":1,"default":[1,4,5,6],"function":[5,7],"int":6,"new":[5,6],"return":[1,2,3,4,5,6,7],"true":[1,4,5,6],CRS:[4,6],For:1,The:[1,2,4,8,9],a_i:1,accord:4,activ:9,addit:0,alloc:[1,2,3,4,6],allocate_tot:[1,6],also:9,altern:6,anaconda:9,ancillari:6,anoth:[5,6],anselin:10,approach:[0,3],area:[1,2,3,4,10],area_tables_rast:6,area_weight:6,areal:8,argument:4,arrai:[1,2,4,6],arriba:10,assign:0,associ:4,assumpt:[1,2,4],attribut:[1,5],auxiliari:[0,5,6],avail:7,base:4,being:0,bel:10,between:[0,5,6],binari:[2,4],bool:[1,4,6],both:[1,2,4],boundari:5,built:6,can:[4,6,9],cell:5,chang:9,clone:9,code:[4,6],coeffici:5,column:[1,4,5,6],command:9,complet:1,conda:9,consid:[4,5,6],consider:4,construct:[2,3,4],contain:[3,5,6],contribut:9,convert:6,coordin:[1,2,4],correspond:[2,3,4],count:5,cover:[4,6],creat:9,daniel:10,dasymetr:8,data:[3,5,6],databas:[4,6],datafram:[1,2,4,5,6],dataset:[5,6],david:10,defin:3,denomin:1,descript:4,detail:1,develop:[4,5,6,10],differ:5,directori:9,doi:10,dok_matrix:[1,3],download:9,draw:4,dynam:10,each:[1,4],econom:10,env:9,environ:9,estim:1,exhaust:1,extens:[1,6],extensive_vari:[1,6],fals:1,file:[4,5,6],folch:10,follow:[1,9],forc:6,force_crs_match:[4,5,6],fork:9,form:[2,4,6],formula:5,found:4,from:[5,6,7],gaussian:5,geeodatafram:4,gener:6,geodatafram:[1,2,3,4,5,6],geodataframe:3,geograph:8,geometr:6,geometri:[0,2,3,4,5,6],geopanda:[1,2,3,4,5,6],get:9,gov:4,guti:10,harmon:[4,7],have:[1,2,4],here:4,high:4,homag:8,html:4,http:[4,10],ident:1,imag:4,index:3,input:[3,5,6],inspir:4,inteeg:5,integ:4,intens:[1,4,6],intensive_vari:[1,6],interlant:10,interpol:[1,5,6,7,8],intersect:[1,2,4],inut:5,land:[4,5,6],landcov:4,legendari:8,let:4,librari:8,likelihood:5,lindsei:10,linear:5,list:[1,4,5,6],local:[7,9],low:4,luc:10,make:9,manual:9,map:[2,4,8],mask:6,match:6,measur:10,medium:4,metadata:4,method:9,metropolitan:10,model:5,modul:7,more:1,mrlc:4,myrna:10,name:[5,8],nation:[4,6],ncld_2001:6,nlcd:[4,5,6],nlcd_2011:[5,6],none:[1,5,6,7],note:[1,2,4],nov:10,number:1,numpi:[2,4,6],onli:[4,9],open:4,oper:9,option:[2,4,5,6],org:10,origin:5,out:6,output:3,overlap:0,packag:7,paramet:[1,2,3,4,5,6],part:6,pass:6,path:[4,5,6],patsi:5,pip:9,pixel:[5,6],pleas:9,poisson:5,polygon:[1,3,4,5,6],popul:[4,5],pull:9,pysal:9,python:9,quarterli:10,quilt:7,raf:10,raster:[4,5,6,7],raster_cod:5,raster_path:[4,6],reason:1,recommend:[4,9],refer:[1,2,4,5],registri:7,regress:5,rei:10,relationship:5,repo:9,repositori:9,repres:5,represent:6,reproject:4,request:9,requir:5,rrez:10,run:9,same:[1,2,4,6],sastr:10,save:7,scipi:[1,3],see:1,sergio:10,set:1,setup:9,shape:1,share:6,should:[1,4,6],sinc:4,site:4,sourc:[0,1,2,3,4,5,6,7,9],source_df:[1,2,3,4,5,6],space:4,spars:[1,3],spatial:[3,10],start:9,storag:7,str:[4,5,6],style:5,submit:9,sum_i:1,sum_k:1,support:9,sure:9,system:[1,2,4],tabl:[1,2,3,4,6],taken:4,target:[0,1,2,3,4,5,6],target_df:[1,2,3,4,5,6],thi:[4,6,9],tobler:9,total:[1,6],tupl:[1,2,4,6],two:[1,2,4,5,6],type:[1,4,5],uninhabit:6,union:[2,4],unit:1,url:10,use:[0,1,6,7],used:5,user:6,using:[3,4,5,6],v_i:1,v_j:1,valu:[1,4,6],variabl:[0,1,5,6],weight:1,when:1,where:1,whether:[4,6],which:[5,6],would:1,www:4,yml:9,you:9,your:9},titles:["API reference","tobler.area_weighted.area_interpolate","tobler.area_weighted.area_tables","tobler.area_weighted.area_tables_binning","tobler.area_weighted.area_tables_raster","tobler.dasymetric.linear_model","tobler.dasymetric.masked_area_interpolate","tobler.data.store_rasters","Tobler","Installation","References"],titleterms:{api:0,area:0,area_interpol:1,area_t:2,area_tables_bin:3,area_tables_rast:4,area_weight:[1,2,3,4],dasymetr:[0,5,6],data:[0,7],develop:9,instal:9,linear_model:5,masked_area_interpol:6,refer:[0,10],releas:9,store_rast:7,tobler:[1,2,3,4,5,6,7,8],version:9,weight:0}})
\ No newline at end of file
+Search.setIndex({docnames:["api","generated/tobler.area_weighted.area_interpolate","generated/tobler.area_weighted.area_tables","generated/tobler.area_weighted.area_tables_binning","generated/tobler.area_weighted.area_tables_raster","generated/tobler.dasymetric.glm","generated/tobler.dasymetric.glm_pixel_adjusted","generated/tobler.dasymetric.masked_area_interpolate","generated/tobler.data.store_rasters","index","installation","references"],envversion:{"sphinx.domains.c":1,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":1,"sphinx.domains.javascript":1,"sphinx.domains.math":2,"sphinx.domains.python":1,"sphinx.domains.rst":1,"sphinx.domains.std":1,"sphinx.ext.intersphinx":1,"sphinx.ext.viewcode":1,sphinx:56},filenames:["api.rst","generated/tobler.area_weighted.area_interpolate.rst","generated/tobler.area_weighted.area_tables.rst","generated/tobler.area_weighted.area_tables_binning.rst","generated/tobler.area_weighted.area_tables_raster.rst","generated/tobler.dasymetric.glm.rst","generated/tobler.dasymetric.glm_pixel_adjusted.rst","generated/tobler.dasymetric.masked_area_interpolate.rst","generated/tobler.data.store_rasters.rst","index.rst","installation.rst","references.rst"],objects:{"tobler.area_weighted":{area_interpolate:[1,0,1,""],area_tables:[2,0,1,""],area_tables_binning:[3,0,1,""],area_tables_raster:[4,0,1,""]},"tobler.dasymetric":{glm:[5,0,1,""],glm_pixel_adjusted:[6,0,1,""],masked_area_interpolate:[7,0,1,""]},"tobler.data":{store_rasters:[8,0,1,""]}},objnames:{"0":["py","function","Python function"]},objtypes:{"0":"py:function"},terms:{"case":1,"default":[1,4,5,6,7],"function":[5,6,8],"int":7,"new":[1,5,6,7],"return":[1,2,3,4,5,6,7,8],"true":[1,4,5,6,7],CRS:[4,5,7],For:1,The:[1,2,4,9,10],Use:6,a_i:1,accord:4,activ:10,addit:[0,5],adjust:6,adjustmn:6,alloc:[1,2,3,4,7],allocate_tot:[1,7],also:[5,6,10],altern:7,anaconda:10,ancillari:7,anoth:[5,6,7],anselin:11,appli:6,approach:[0,3],area:[1,2,3,4,11],area_tables_rast:7,area_weight:7,areal:9,argument:4,arrai:[2,4,7],arriba:11,assign:0,associ:4,assumpt:[1,2,4],attribut:[1,5,6],auxiliari:[0,7],avail:8,base:[4,6],being:0,bel:11,benefit:6,between:[0,5,6,7],binari:[2,4],bool:[1,4,5,7],both:[1,2,4],boundari:[5,6],built:7,can:[4,6,7,10],caution:6,cell:[5,6],chang:10,clone:10,code:[4,5,7],coeffici:[5,6],coerc:5,column:[1,4,5,6,7],combin:5,command:10,complet:1,conda:10,consid:[4,6,7],consider:4,construct:[2,3,4],contain:[3,5,6,7],contribut:10,control:6,convert:7,coordin:[1,2,4],correspond:[2,3,4],count:[5,6],cover:[4,7],creat:10,daniel:11,dasymetr:9,data:[3,5,6,7],databas:[4,7],datafram:[1,2,4,5,6,7],dataset:7,david:11,defin:3,denomin:1,descript:4,detail:1,develop:[4,6,7,11],diagnost:5,differ:[5,6],directori:10,doi:11,dok_matrix:[1,3],download:10,draw:4,dynam:11,each:[4,5],econom:11,env:10,environ:10,error:6,estim:[1,5,6],exhaust:1,experiment:6,extens:[1,7],extensive_vari:[1,7],factor:6,fals:[1,5],file:[4,5,6,7],fit:[5,6],folch:11,follow:[1,10],forc:7,force_crs_match:[4,5,6,7],fork:10,form:[2,4,7],formula:[5,6],found:4,from:[5,6,7,8],further:5,gaussian:[5,6],geeodatafram:4,gener:[5,6,7],geodarafram:1,geodatafram:[1,2,3,4,5,6,7],geodataframe:3,geograph:9,geometr:7,geometri:[0,1,2,3,4,5,6,7],geopanda:[1,2,3,4,5,6,7],get:10,given:5,glm:6,gov:4,guti:11,harmon:[4,8],has:6,have:[1,2,4],here:[4,5],high:4,homag:9,html:4,http:[4,11],ident:1,imag:4,index:3,induc:6,inform:5,input:[3,5,6,7],inspir:4,integ:[4,5,6],intens:[1,4,7],intensive_vari:[1,7],interlant:11,interpol:[1,5,6,7,8,9],intersect:[1,2,4],kwarg:6,land:[4,5,6,7],landcov:4,legendari:9,let:4,level:6,librari:9,likelihood:[5,6],lindsei:11,linear:[5,6],list:[1,4,5,6,7],local:[6,8,10],log1p:5,log:5,low:4,luc:11,make:[6,10],manual:10,map:[2,4,9],mask:7,match:7,measur:11,medium:4,metadata:4,method:10,metropolitan:11,model:[5,6],modul:8,more:1,mrlc:4,myrna:11,n_total_pop:5,name:[5,6,9],nation:[4,7],ncld_2001:7,neg_binomi:5,nlcd:[4,5,6,7],nlcd_2011:[5,6,7],none:[1,5,6,7,8],note:[1,2,4],nov:11,numpi:[2,4,7],onli:[4,10],open:4,oper:10,option:[2,4,5,6,7],org:11,origin:[5,6],out:7,output:[1,3],overlap:0,packag:8,paramet:[1,2,3,4,5,6,7],part:7,pass:7,path:[4,5,6,7],patsi:[5,6],pip:10,pixel:[5,6,7],pleas:10,poisson:[5,6],polygon:[1,3,4,7],popul:[4,5,6],prefix:5,pull:10,pysal:10,python:10,quarterli:11,quilt:8,raf:11,raster:[4,5,6,7,8],raster_cod:[5,6],raster_path:4,reason:1,recommend:[4,10],refer:[1,2,4,5,6],registri:8,regress:[5,6],regular:6,rei:11,relationship:[5,6],repo:10,repositori:10,repres:[5,6],represent:7,reproject:4,request:10,requir:[5,6],respect:6,return_model:5,rrez:11,run:10,same:[1,2,4,5,7],sastr:11,save:8,scipi:[1,3],see:1,sergio:11,set:1,setup:10,share:7,should:[1,4,5,7],sinc:4,site:4,sourc:[0,1,2,3,4,5,6,7,8,10],source_df:[1,2,3,4,5,6,7],space:4,spars:[1,3],spatial:[3,11],specifi:5,start:10,storag:8,str:[4,5,6,7],style:[5,6],submit:10,subsequ:6,sum_i:1,sum_k:1,support:10,sure:[6,10],system:[1,2,4],tabl:[1,2,3,4,7],taken:4,target:[0,1,2,3,4,5,6,7],target_df:[1,2,3,4,5,6,7],thi:[4,5,6,7,10],tobler:10,total:[1,6,7],tupl:[2,4,7],two:[1,2,4,7],type:[4,5,6],type_21:5,type_22:5,type_:5,uninhabit:7,union:[2,4],unknown:6,unlik:6,url:11,use:[0,1,7,8],used:[5,6],user:7,using:[3,4,5,6,7],v_i:1,v_j:1,valu:[1,4,5,6,7],variabl:[0,1,5,6,7],version:6,weight:1,when:1,where:1,whether:[4,5,7],which:[5,7],whichar:6,would:1,www:4,yml:10,you:10,your:10},titles:["API reference","tobler.area_weighted.area_interpolate","tobler.area_weighted.area_tables","tobler.area_weighted.area_tables_binning","tobler.area_weighted.area_tables_raster","tobler.dasymetric.glm","tobler.dasymetric.glm_pixel_adjusted","tobler.dasymetric.masked_area_interpolate","tobler.data.store_rasters","Tobler","Installation","References"],titleterms:{api:0,area:0,area_interpol:1,area_t:2,area_tables_bin:3,area_tables_rast:4,area_weight:[1,2,3,4],dasymetr:[0,5,6,7],data:[0,8],develop:10,glm:5,glm_pixel_adjust:6,instal:10,masked_area_interpol:7,refer:[0,11],releas:10,store_rast:8,tobler:[1,2,3,4,5,6,7,8,9],version:10,weight:0}})
\ No newline at end of file
diff --git a/docsrc/api.rst b/docsrc/api.rst
index 93cc826..cdf78d6 100644
--- a/docsrc/api.rst
+++ b/docsrc/api.rst
@@ -34,7 +34,8 @@ variables being assigned to the target
.. autosummary::
:toctree: generated/
- linear_model
+ glm
+ glm_pixel_adjusted
masked_area_interpolate