# OSGP: Measuring Geographic Distributions – Standard Distance

(Open Source Geospatial Python)

The ‘What is it?’

The Standard Distance, also know as the Standard Distance Deviation, is the average distance all features vary from the Mean Center and measures the compactness of a distribution. The Standard Distance is a value representing the distance in units from the Mean Center and is usually plotted on a map as a circle for a visual indication of dispersion, the Standard Distance is the radius.

The Standard Distance works best in the absence of a strong directional trend. According to Andy Mitchell, if a directional trend is present you are better off using the Standard Deviational Ellipse.

You can use the Standard Distance to compare territories between species, which has the wider/broader territory, or to compare changes over time such as the dispersion of burglaries for each calendar month.

In a Normal Distribution you would expect around 68% of all points to fall within the Standard Distance.

The Formula!

The mean x-coordinate is subtracted from the x-coordinate value for each point and the difference is squared. The sum of all the squared values for x minus the x-mean is divided by the number of points. This is also performed for y-coordinates. The resulting values for x and y are summed and then we take the square root of this value to return the value to original distance units.

First we get the mean X and Y…

…and then the Standard Distance

For Point features the X and Y coordinates of each feature is used, for Polygons the centroid of each feature represents the X and Y coordinate to use, and for Linear features the mid-point of each line is used for the X and Y coordinate.

The Code…

```from osgeo import ogr
from shapely.geometry import MultiLineString
from shapely import wkt
import numpy as np
import sys, math

## set the driver for the data
driver = ogr.GetDriverByName("FileGDB")
## path to the FileGDB
gdb = r"C:\Users\Glen B\Documents\ArcGIS\Default.gdb"
## ope the GDB in write mode (1)
ds = driver.Open(gdb, 1)

input_lyr_name = "Birmingham_Burglaries_2016"

output_fc = "{0}_standard_distance".format(input_lyr_name)

## reference the layer using the layers name
if input_lyr_name in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
lyr = ds.GetLayerByName(input_lyr_name)
print "{0} found in {1}".format(input_lyr_name, gdb)

if output_fc in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

try:
## for points and polygons we use the centroid
first_feat = lyr.GetFeature(1)
if first_feat.geometry().GetGeometryName() in ["POINT", "MULTIPOINT", "POLYGON", "MULTIPOLYGON"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, pt in enumerate(lyr):
ft_geom = pt.geometry()
xy_arr[i] = (ft_geom.Centroid().GetX(), ft_geom.Centroid().GetY())

## for lines we get the midpoint of a line
elif first_feat.geometry().GetGeometryName() in ["LINESTRING", "MULTILINESTRING"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, ln in enumerate(lyr):
line_geom = ln.geometry().ExportToWkt()
midpoint = shapely_line.interpolate(shapely_line.length/2)
xy_arr[i] = (midpoint.x, midpoint.y)

except Exception:
print "Unknown geometry for {}".format(input_lyr_name)
sys.exit()

avg_x, avg_y = np.mean(xy_arr, axis=0)

print "Mean Center: {0}, {1}".format(avg_x, avg_y)

sum_of_sq_diff_x = 0.0
sum_of_sq_diff_y = 0.0

for x, y in xy_arr:
diff_x = math.pow(x - avg_x, 2)
diff_y = math.pow(y - avg_y, 2)
sum_of_sq_diff_x += diff_x
sum_of_sq_diff_y += diff_y

sum_of_results = (sum_of_sq_diff_x/lyr.GetFeatureCount()) + (sum_of_sq_diff_y/lyr.GetFeatureCount())
standard_distance = math.sqrt(sum_of_results)
print "Standard Distance: {0}". format(standard_distance)

## create a point with the mean center
## and buffer by the standard distance
pnt = ogr.Geometry(ogr.wkbPoint)
polygon = pnt.Buffer(standard_distance, 90)

## create a new polygon layer with the same spatial ref as lyr
out_lyr = ds.CreateLayer(output_fc, lyr.GetSpatialRef(), ogr.wkbPolygon)

## define and create new fields
x_fld = ogr.FieldDefn("X", ogr.OFTReal)
y_fld = ogr.FieldDefn("Y", ogr.OFTReal)
stnd_dst = ogr.FieldDefn("Standard_Distance", ogr.OFTReal)
out_lyr.CreateField(x_fld)
out_lyr.CreateField(y_fld)
out_lyr.CreateField(stnd_dst)

## add the standard distance buffer to the layer
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(polygon)
feat.SetField("X", avg_x)
feat.SetField("Y", avg_y)
feat.SetField("Standard_Distance", standard_distance)
out_lyr.CreateFeature(feat)

print "Created {0}".format(output_fc)

## free up resources
del feat, ds, lyr, out_lyr```

I’d like to give credit to Logan Byers from GIS StackExchange who aided in speeding up the computational time using NumPy and for forcing me to begin learning the wonders of NumPy (getting there bit by bit).

The Example:

I downloaded crime data from DATA.POLICE.UK for the West Midlands Police from January 2016 to December 2016. I used some Python to extract just the Burglary data and made this into a feature class in the File GDB. Next, I downloaded OS Boundary Line data and clipped the Burglary data to just Birmingham. Everything was now in place to find the Standard Distance of all burglaries for Birmingham in 2016. (see The Other Scripts section at the bottom of this post for processing the data)

Running the script from The Code section above calculates the Standard Distance for burglaries in Birmingham for 2016 and creates a polygon feature class in the File GDB.

OSGP Mean Center:     407926.695396, 286615.428507
ArcGIS Mean Center:    407926.695396, 286615.428507

OSGP Standard Distance:      6416.076596
ArcGIS Standard Distance:    6416.076596

Also See…

The Resources:

ESRI Guide to GIS Volume 2: Chapter 2 (I highly recommend this book)
see book review here.

Geoprocessing with Python

Python GDAL/OGR Cookbook

Setting up GDAL/OGR with FileGDB Driver for Python on Windows

< The Other Scripts >

1. Extract Burglary Data for West Midlands

```import csv, os
from osgeo import ogr, osr

## set the driver for the data
driver = ogr.GetDriverByName("FileGDB")

## path to the FileGDB
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

## ope the GDB in write mode (1)
ds = driver.Open(gdb, 1)

## the coordinates in the csv files are lat/long
source = osr.SpatialReference()
source.ImportFromEPSG(4326)

## we need the data in British National Grid
target = osr.SpatialReference()
target.ImportFromEPSG(27700)

transform = osr.CoordinateTransformation(source, target)

## set the output fc name
output_fc = "WM_Burglaries_2016"

## if the output fc already exists delete it
if output_fc in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

out_lyr = ds.CreateLayer(output_fc, target, ogr.wkbPoint)

## define and create new fields
mnth_fld = ogr.FieldDefn("Month", ogr.OFTString)
rep_by_fld = ogr.FieldDefn("Reported_by", ogr.OFTString)
fls_wthn_fld = ogr.FieldDefn("Falls_within", ogr.OFTString)
loc_fld = ogr.FieldDefn("Location", ogr.OFTString)
lsoa_c_fld = ogr.FieldDefn("LSOA_code", ogr.OFTString)
lsoa_n_fld = ogr.FieldDefn("LSOA_name", ogr.OFTString)
crime_fld = ogr.FieldDefn("Crime_type", ogr.OFTString)
outcome_fld = ogr.FieldDefn("Last_outcome", ogr.OFTString)

out_lyr.CreateField(mnth_fld)
out_lyr.CreateField(rep_by_fld)
out_lyr.CreateField(fls_wthn_fld)
out_lyr.CreateField(loc_fld)
out_lyr.CreateField(lsoa_c_fld)
out_lyr.CreateField(lsoa_n_fld)
out_lyr.CreateField(crime_fld)
out_lyr.CreateField(outcome_fld)

root_folder = r"C:\Users\Glen B\Documents\Crime"

## for each csv
for root,dirs,files in os.walk(root_folder):
for filename in files:
if filename.endswith(".csv"):
csv_path = "{0}\\{1}".format(root, filename)
with open(csv_path, "rb") as csvfile:
## create a point with attributes for each burglary
if row[9] == "Burglary":
pnt = ogr.Geometry(ogr.wkbPoint)
pnt.Transform(transform)
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(pnt)
feat.SetField("Month", row[1])
feat.SetField("Reported_by", row[2])
feat.SetField("Falls_within", row[3])
feat.SetField("Location", row[6])
feat.SetField("LSOA_code", row[7])
feat.SetField("LSOA_name", row[8])
feat.SetField("Crime_type", row[9])
feat.SetField("Last_outcome", row[10])
out_lyr.CreateFeature(feat)

del ds, feat, out_lyr```

2. Birmingham Burglaries Only

```from osgeo import ogr

## required drivers
shp_driver = ogr.GetDriverByName("ESRI Shapefile")
gdb_driver = ogr.GetDriverByName("FileGDB")

## input boundary shapefile and file gdb
shapefile = r"C:\Users\Glen B\Documents\Crime\Data\GB\district_borough_unitary_region.shp"
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

## open the shapefile in read mode and gdb in write mode
shp_ds = shp_driver.Open(shapefile, 0)
gdb_ds = gdb_driver.Open(gdb, 1)

## reference the necessary layers
shp_layer = shp_ds.GetLayer(0)
gdb_layer = gdb_ds.GetLayerByName("WM_Burglaries_2016")

## filter the shapefile
shp_layer.SetAttributeFilter("NAME = 'Birmingham District (B)'")

## set the name for the output feature class
output_fc = "Birmingham_Burglaries_2016"

## if the output already exists then delete it
if output_fc in [gdb_ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(gdb_ds.GetLayerCount())]:
gdb_ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

## create an output layer
out_lyr = gdb_ds.CreateLayer(output_fc, shp_layer.GetSpatialRef(), ogr.wkbPoint)

## copy the schema from the West Midlands burglaries
## and use it for the Birmingham burglaries
lyr_def = gdb_layer.GetLayerDefn()
for i in range(lyr_def.GetFieldCount()):
out_lyr.CreateField (lyr_def.GetFieldDefn(i))

## only get burglaries that intersect the Birmingham region
for shp_feat in shp_layer:
print shp_feat.GetField("NAME")
birm_geom = shp_feat.GetGeometryRef()
for gdb_feat in gdb_layer:
burglary_geom = gdb_feat.GetGeometryRef()
if burglary_geom.Intersects(birm_geom):
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(burglary_geom)

## populate the attribute table
for i in range(lyr_def.GetFieldCount()):
feat.SetField(lyr_def.GetFieldDefn(i).GetNameRef(), gdb_feat.GetField(i))
## create the feature
out_lyr.CreateFeature(feat)
feat.Destroy()

del shp_ds, shp_layer, gdb_ds, gdb_layer```

The Usual 🙂

As always please feel free to comment to help make the code more efficient, highlight errors, or let me know if this was of any use to you.

# OSGP: Measuring Geographic Distributions – Weighted Mean Center

(Open Source Geospatial Python)

The ‘What is it?’

See Mean Center.

The unweighted center is mainly used for events that occur at a place and time such as burglaries. The weighted center, however, is predominantly used for stationary features such as retail outlets or delineated areas for example (such as Census tracts). The Weighted Mean Center does not take into account distance between features in the dataset.

The weight needs to be a numerical attribute. The greater the value, the higher the weight for that feature.

The Formula!

The Weighted Mean Center is calculated by multiplying the x and y coordinate by the weight for that feature and summing all for both x and y individually, and then dividing this by the sum of all the weights.

For Point features the X and Y coordinates of each feature is used, for Polygons the centroid of each feature represents the X and Y coordinate to use, and for Linear features the mid-point of each line is used for the X and Y coordinate.

The Code…

```from osgeo import ogr
from shapely.geometry import MultiLineString
from shapely import wkt
import numpy as np
import sys

## set the driver for the data
driver = ogr.GetDriverByName("ESRI Shapefile")
## folder where the shapefile resides
folder = r"C:\Users\glen.bambrick\Documents\GDAL\shp\\"
## name of the shapefile concatenated with folder
shp = "{0}Census2011_Small_Areas_generalised20m.shp".format(folder)
## open the shapefile
ds = driver.Open(shp, 0)
## reference the only layer in the shapefile
lyr = ds.GetLayer(0)

## create an output data source
out_ds = driver.CreateDataSource("{0}{1}_wgt_mean_center.shp".format(folder,lyr.GetName()))

## output mean center weighted filename
output_fc = "{0}{1}_wgt_mean_center".format(folder,lyr.GetName())

## field that has numerical weight
weight_fld = "TOTAL2011"

try:
first_feat = lyr.GetFeature(1)
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
wgt_arr = np.ndarray((len(lyr), 1), dtype=np.float)
## use the centroid for points and polygons
if first_feat.geometry().GetGeometryName() in ["POINT", "MULTIPOINT", "POLYGON", "MULTIPOLYGON"]:
for i, pt in enumerate(lyr):
ft_geom = pt.geometry()
weight = pt.GetField(weight_fld)
xy_arr[i] = (ft_geom.Centroid().GetX() * weight, ft_geom.Centroid().GetY() * weight)
wgt_arr[i] = weight
## midpoint of lines
elif first_feat.geometry().GetGeometryName() in ["LINESTRING", "MULTILINESTRING"]:
for i, ln in enumerate(lyr):
line_geom = ln.geometry().ExportToWkt()
weight = ln.GetField(weight_fld)
midpoint = shapely_line.interpolate(shapely_line.length/2)
xy_arr[i] = (midpoint.x * weight, midpoint.y * weight)
wgt_arr[i] = weight

except Exception:
print "Unknown geometry or Incorrect field name for {}".format(input_lyr_name)
sys.exit()

## do the maths
sum_x, sum_y = np.sum(xy_arr, axis=0)
sum_wgt = np.sum(wgt_arr)
weighted_x, weighted_y = sum_x/sum_wgt, sum_y/sum_wgt

print "Weighted Mean Center: {0}, {1}".format(weighted_x, weighted_y)

## create a new point layer with the same spatial ref as lyr
out_lyr = out_ds.CreateLayer(output_fc, lyr.GetSpatialRef(), ogr.wkbPoint)

## define and create new fields
x_fld = ogr.FieldDefn("X", ogr.OFTReal)
y_fld = ogr.FieldDefn("Y", ogr.OFTReal)
out_lyr.CreateField(x_fld)
out_lyr.CreateField(y_fld)

## create a new point for the mean center weighted
pnt = ogr.Geometry(ogr.wkbPoint)

## add the mean center weighted to the new layer
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(pnt)
feat.SetField("X", weighted_x)
feat.SetField("Y", weighted_y)
out_lyr.CreateFeature(feat)

print "Created: {0}.shp".format(output_fc)

## free up resources
del ds, out_ds, lyr, first_feat, feat, out_lyr```

I’d like to give credit to Logan Byers from GIS StackExchange who aided in speeding up the computational time using NumPy and for forcing me to begin learning the wonders of NumPy (which is still a work in progress)

The Example:

I downloaded the Small Areas of Ireland from the CSO. You will have to acknowledge a disclaimer. The data contains population information for the 2011 Census. Once downloaded unzip Census2011_Small_Areas_generalised20m.zip to working folder.

Running the script from The Code section above calculates the Weighted Mean Center of all Small Areas based on the population count for each for 2011 and creates a point Shapefile as the output.

OSGP Weighted Mean Center:      238557.427484, 208347.116116
ArcGIS Weighted Mean Center:    238557.427484, 208347.116116

Also See…

The Resources:

ESRI Guide to GIS Volume 2: Chapter 2 (I highly recommend this book)
see book review here.

Geoprocessing with Python

Python GDAL/OGR Cookbook

The Usual 🙂

As always please feel free to comment to help make the code more efficient, highlight errors, or let me know if this was of any use to you.

# OSGP: Measuring Geographic Distributions – Median Center

(Open Source Geospatial Python)

The ‘What is it?’

Also known as the Center of Minimum Distance, the Median Center is a location that is the shortest total distance to all features in the study area (not to be confused with the Central Feature, which is the feature that is the shortest distance to all others). It can be used to find a suitable location for something that needs to be centrally located. The Median Center will gravitate towards an area with the most features.

The Median Center is good for finding the most accessible location.

The Formula!

The is no single formula or equation for calculating an exact Median Center, according to Andy Mitchell it is an iterative process involving calculating the Mean Center, summing the distances from it to each feature, offsetting the center slightly and summing the distances again until it eventually zones in on the optimum location that has the lowest sum.

The code below implements the Yehuda Vardi and Cun-Hui Zhang algorithm or the Weiszfeld algorithm.

The Code…

```import math, sys
import numpy as np
from osgeo import ogr
from scipy.spatial.distance import cdist

## "W" for Weiszfield
## "YC" for Yehuda Vardi and Cun-Hui Zhang
algorithm = "YC"

## Weiszfield
## https://gist.github.com/endolith/2837160
def numersum(test_median,dataPoint):
## Provides the denominator of the weiszfeld algorithm depending on whether
## you are adjusting the candidate x or y
return 1/math.sqrt((test_median[0]-dataPoint[0])**2 + (test_median[1]-dataPoint[1])**2)

def denomsum(test_median, xy_arr):
## Provides the denominator of the weiszfeld algorithm
temp = 0.0
for i in range(0,len(xy_arr)):
temp += 1/math.sqrt((test_median[0] - xy_arr[i][0])**2 + (test_median[1] - xy_arr[i][1])**2)
return temp

## Yehuda Vardi and Cun-Hui Zhang
## http://stackoverflow.com/questions/30299267/geometric-median-of-multidimensional-points
## user: orlp
def geometric_median(X, eps=1e-5):
y = np.mean(X, 0)

while True:
D = cdist(X, [y])
nonzeros = (D != 0)[:, 0]
Dinv = 1 / D[nonzeros]
Dinvs = np.sum(Dinv)
W = Dinv / Dinvs
T = np.sum(W * X[nonzeros], 0)
num_zeros = len(X) - np.sum(nonzeros)
if num_zeros == 0:
y1 = T
elif num_zeros == len(X):
return y
else:
R = (T - y) * Dinvs
r = np.linalg.norm(R)
rinv = 0 if r == 0 else num_zeros/r
y1 = max(0, 1-rinv)*T + min(1, rinv)*y
if np.linalg.norm(y - y1) < eps:
return y1
y = y1

## set the driver for the data
driver = ogr.GetDriverByName("FileGDB")

## path to the FileGDB
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

## ope the GDB in write mode (1)
ds = driver.Open(gdb, 1)

## input feature class
input_lyr_name = "Birmingham_Secondary_Schools"

## name of output feature class
output_fc = "{0}_median_center".format(input_lyr_name)

## reference the layer using the layers name
if input_lyr_name in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
lyr = ds.GetLayerByName(input_lyr_name)
print "{0} found in {1}".format(input_lyr_name, gdb)

## if the output layer already exists then delete it
if output_fc in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

## create an array with coordinates of each feature
try:
first_feat = lyr.GetFeature(1)
## centroid for points and polygons
if first_feat.geometry().GetGeometryName() in ["POINT", "MULTIPOINT", "POLYGON", "MULTIPOLYGON"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, pt in enumerate(lyr):
ft_geom = pt.geometry()
xy_arr[i] = (ft_geom.Centroid().GetX(), ft_geom.Centroid().GetY())

## for lines we get the midpoint of a line
elif first_feat.geometry().GetGeometryName() in ["LINESTRING", "MULTILINESTRING"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, ln in enumerate(lyr):
line_geom = ln.geometry().ExportToWkt()
midpoint = shapely_line.interpolate(shapely_line.length/2)
xy_arr[i] = (midpoint.x, midpoint.y)

except Exception:
print "Unknown geometry for {}".format(input_lyr_name)
sys.exit()

## if using Weiszfield
if algorithm == "W":
## https://gist.github.com/endolith/2837160
avg_x, avg_y = np.mean(xy_arr, axis=0)
test_median = [avg_x, avg_y]
numIter = 50

## minimise the objective function
for x in range(0,numIter):
denom = denomsum(test_median,xy_arr)
nextx = 0.0
nexty = 0.0

for y in range(0,len(xy_arr)):
nextx += (xy_arr[y][0] * numersum(test_median,xy_arr[y]))/denom
nexty += (xy_arr[y][1] * numersum(test_median,xy_arr[y]))/denom

test_median = [nextx,nexty]

## if using Yehuda Vardi and Cun-Hui Zhang
elif algorithm == "YC":
test_median = geometric_median(xy_arr)

print "Median Center: {0}, {1}".format(test_median[0], test_median[1])

## create a new point layer with the same spatial ref as lyr
out_lyr = ds.CreateLayer(output_fc, lyr.GetSpatialRef(), ogr.wkbPoint)

## define and create new fields
x_fld = ogr.FieldDefn("X", ogr.OFTReal)
y_fld = ogr.FieldDefn("Y", ogr.OFTReal)
out_lyr.CreateField(x_fld)
out_lyr.CreateField(y_fld)

## create a new point for the mean center
pnt = ogr.Geometry(ogr.wkbPoint)

## add the mean center to the new layer
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(pnt)
feat.SetField("X", test_median[0])
feat.SetField("Y", test_median[1])
out_lyr.CreateFeature(feat)

print "Created {0}".format(output_fc)

## free up resources
del ds, lyr, first_feat, feat, out_lyr```

I’d like to give credit to…
Logan Byers from GIS StackExchange who aided in speeding up the computational time using NumPy and for forcing me to begin learning the wonders of NumPy.
orlp from Stack Overflow for their implementation of Yehuda Vardi and Cun-Hui Zhang’s algorithm for the geometric median.
Daniel J Lewis (I think) for the implementation of the Weiszfeld algorithm.

The Example:

I downloaded vector data that contains polygons for schools (and other features) from OS Open Map – Local that covered the West Midlands. I also downloaded OS Boundary Line data. Using Python and GDAL/OGR I extracted secondary schools from the data for Birmingham only. Everything was now in place to find the Median Center of all Secondary Schools for Birmingham. (see The Other Scripts section at the bottom of this post for processing the data)

Running the script from The Code section above calculates the coordinates of the Median Center for Secondary Schools in Birmingham and creates a point feature class in the File GDB.

OSGP Median Center (W):        407658.278755, 286696.905759
OSGP Median Center (YC):      407658.278752, 286696.905769
ArcGIS Median Center:             407658.009375, 286697.53996

What’s Next?

Also See…

The Resources:

ESRI Guide to GIS Volume 2: Chapter 2
see book review here.

Geoprocessing with Python

Python GDAL/OGR Cookbook

Setting up GDAL/OGR with FileGDB Driver for Python on Windows

< The Other Scripts >

Birmingham Secondary Schools

```from osgeo import ogr
import os

## necessary drivers
shp_driver = ogr.GetDriverByName("ESRI Shapefile")
gdb_driver = ogr.GetDriverByName("FileGDB")

## input boundary shapefile and file reference file gdb
shapefile = r"C:\Users\Glen B\Documents\Schools\Data\GB\district_borough_unitary_region.shp"
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

shp_ds = shp_driver.Open(shapefile, 0)
gdb_ds = gdb_driver.Open(gdb, 1)

## filter boundary to just Birmingham
shp_layer = shp_ds.GetLayer(0)
shp_layer.SetAttributeFilter("NAME = 'Birmingham District (B)'")

## name the output
output_fc = "Birmingham_Secondary_Schools"

## if the output feature class already exists then delete it
if output_fc in [gdb_ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(gdb_ds.GetLayerCount())]:
gdb_ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

## create the output feature class
out_lyr = gdb_ds.CreateLayer(output_fc, shp_layer.GetSpatialRef(), ogr.wkbPolygon)

## the folder that contains the data to extract Secondary Schools from
root_folder = r"C:\Users\Glen B\Documents\Schools\Vector\data"

## traverse through the folders and find ImportantBuildings files
## copy only those that intersect the Birmingham region
## transfer across attributes
count = 1
for root,dirs,files in os.walk(root_folder):
for filename in files:
if filename.endswith("ImportantBuilding.shp") and filename[0:2] in ["SP", "SO", "SJ", "SK"]:
shp_path = "{0}\\{1}".format(root, filename)
schools_ds = shp_driver.Open(shp_path, 0)
schools_lyr = schools_ds.GetLayer(0)
schools_lyr.SetAttributeFilter("CLASSIFICA = 'Secondary Education'")
lyr_def = schools_lyr.GetLayerDefn()
if count == 1:
for i in range(lyr_def.GetFieldCount()):
out_lyr.CreateField(lyr_def.GetFieldDefn(i))
count += 1
for shp_feat in shp_layer:
birm_geom = shp_feat.GetGeometryRef()

for school_feat in schools_lyr:
school_geom = school_feat.GetGeometryRef()

if school_geom.Intersects(birm_geom):
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(school_geom)
for i in range(lyr_def.GetFieldCount()):
feat.SetField(lyr_def.GetFieldDefn(i).GetNameRef(), school_feat.GetField(i))

out_lyr.CreateFeature(feat)
feat.Destroy()

del shp_ds, shp_layer, gdb_ds```

The Usual 🙂

As always please feel free to comment to help make the code more efficient, highlight errors, or let me know if this was of any use to you.

# OSGP: Measuring Geographic Distributions – Central Feature

(Open Source Geospatial Python)

The ‘What is it?’

The Central Feature is the point that is the shortest distance to all other points in the dataset and thus identifies the most centrally located feature. The Central Feature can be used to find the most accessible feature, for example, the most accessible school to hold a training day for teachers from schools in a given area.

The Formula!

For each feature calculate the total distance to all other features. The feature that has the shortest total distance is the Central Feature.

For Point features the X and Y coordinates of each feature is used, for Polygons the centroid of each feature represents the X and Y coordinate to use, and for Linear features the mid-point of each line is used for the X and Y coordinate

The Code…

```from osgeo import ogr
from shapely.geometry import MultiLineString
from shapely import wkt
import numpy as np

## set the driver for the data
driver = ogr.GetDriverByName("FileGDB")
## path to the FileGDB
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"
## open the GDB in write mode (1)
ds = driver.Open(gdb, 1)

## input layer
input_lyr_name = "Birmingham_Secondary_Schools"

## output layer
output_fc = "{0}_central_feature".format(input_lyr_name)

## reference the layer using the layers name
if input_lyr_name in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
lyr = ds.GetLayerByName(input_lyr_name)
print "{0} found in {1}".format(input_lyr_name, gdb)

## delete the output layer if it already exists
if output_fc in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

## for each point or polygon in the layer
## get the x and y value of the centroid
## and add them into a numpy array
try:
first_feat = lyr.GetFeature(1)
if first_feat.geometry().GetGeometryName() in ["POINT", "MULTIPOINT", "POLYGON", "MULTIPOLYGON"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, pt in enumerate(lyr):
ft_geom = pt.geometry()
xy_arr[i] = (ft_geom.Centroid().GetX(), ft_geom.Centroid().GetY())

## for linear features we get the midpoint of a line
elif first_feat.geometry().GetGeometryName() in ["LINESTRING", "MULTILINESTRING"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, ln in enumerate(lyr):
line_geom = ln.geometry().ExportToWkt()
midpoint = shapely_line.interpolate(shapely_line.length/2)
xy_arr[i] = (midpoint.x, midpoint.y)

## exit gracefully if unknown geometry or input contains no geometry
except Exception:
print "Unknown Geometry for {0}".format(input_lyr_name)

## construct NxN array, this will be the distance matrix
pt_dist_arr = np.ndarray((len(xy_arr), len(xy_arr)), dtype=np.float)

## fill the distance array
for i, a in enumerate(xy_arr):
for j, b in enumerate(xy_arr):
pt_dist_arr[i,j] = np.linalg.norm(a-b)

## sum distances for each point
summed_distances = np.sum(pt_dist_arr, axis=0)

## index of point with minimum summed distances
index_central_feat = np.argmin(summed_distances)

## position of the point with min distance
central_x, central_y = xy_arr[index_central_feat]

print "Central Feature Coords: {0}, {1}".format(central_x, central_y)

## create a new point layer with the same spatial ref as lyr
out_lyr = ds.CreateLayer(output_fc, lyr.GetSpatialRef(), ogr.wkbPoint)

## define and create new fields
x_fld = ogr.FieldDefn("X", ogr.OFTReal)
y_fld = ogr.FieldDefn("Y", ogr.OFTReal)
out_lyr.CreateField(x_fld)
out_lyr.CreateField(y_fld)

## create a new point for the mean center
pnt = ogr.Geometry(ogr.wkbPoint)

## add the mean center to the new layer
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(pnt)
feat.SetField("X", central_x)
feat.SetField("Y", central_y)
out_lyr.CreateFeature(feat)

print "Created: {0}".format(output_fc)

## free up resources
del ds, lyr, first_feat, feat, out_lyr```

I’d like to give credit to Logan Byers from GIS StackExchange who aided in speeding up the computational time using NumPy and for forcing me to begin learning the wonders of NumPy.

At the moment this is significantly slower that performing the same process with ArcGIS for 20,000+ features, but more rapid for a lower amount. 1,000 features processed in 3 seconds.

The Example:

I downloaded vector data that contains polygons for schools from OS Open Map – Local that covered the West Midlands. I also downloaded OS Boundary Line data. Using Python and GDAL/OGR I extracted secondary schools from the data for Birmingham. Everything was now in place to find the Central Feature of all Secondary Schools for Birmingham. (see The Other Scripts section at the bottom of this post for processing the data)

Running the script from The Code section above calculates the coordinates of the Central Feature for all Secondary Schools and creates a point feature class in the File GDB.

OSGP Central Feature:      407726.185, 287215.1
ArcGIS Central Feature:    407726.185, 287215.1

What’s Next?

Median Center (link will be updated once post is complete)

Also see…

Mean Center

The Resources:

ESRI Guide to GIS Volume 2: Chapter 2 (I highly recommend this book)
see book review here.

Geoprocessing with Python

Python GDAL/OGR Cookbook

Setting up GDAL/OGR with FileGDB Driver for Python on Windows

< The Other Scripts >

Birmingham Secondary Schools

```from osgeo import ogr
import os

## necessary drivers
shp_driver = ogr.GetDriverByName("ESRI Shapefile")
gdb_driver = ogr.GetDriverByName("FileGDB")

## input boundary shapefile and file reference file gdb
shapefile = r"C:\Users\Glen B\Documents\Schools\Data\GB\district_borough_unitary_region.shp"
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

shp_ds = shp_driver.Open(shapefile, 0)
gdb_ds = gdb_driver.Open(gdb, 1)

## filter boundary to just Birmingham
shp_layer = shp_ds.GetLayer(0)
shp_layer.SetAttributeFilter("NAME = 'Birmingham District (B)'")

## name the output
output_fc = "Birmingham_Secondary_Schools"

## if the output feature class already exists then delete it
if output_fc in [gdb_ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(gdb_ds.GetLayerCount())]:
gdb_ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

## create the output feature class
out_lyr = gdb_ds.CreateLayer(output_fc, shp_layer.GetSpatialRef(), ogr.wkbPolygon)

## the folder that contains the data to extract Secondary Schools from
root_folder = r"C:\Users\Glen B\Documents\Schools\Vector\data"

## traverse through the folders and find ImportantBuildings files
## copy only those that intersect the Birmingham region
## transfer across attributes
count = 1
for root,dirs,files in os.walk(root_folder):
for filename in files:
if filename.endswith("ImportantBuilding.shp") and filename[0:2] in ["SP", "SO", "SJ", "SK"]:
shp_path = "{0}\\{1}".format(root, filename)
schools_ds = shp_driver.Open(shp_path, 0)
schools_lyr = schools_ds.GetLayer(0)
schools_lyr.SetAttributeFilter("CLASSIFICA = 'Secondary Education'")
lyr_def = schools_lyr.GetLayerDefn()
if count == 1:
for i in range(lyr_def.GetFieldCount()):
out_lyr.CreateField(lyr_def.GetFieldDefn(i))
count += 1
for shp_feat in shp_layer:
birm_geom = shp_feat.GetGeometryRef()

for school_feat in schools_lyr:
school_geom = school_feat.GetGeometryRef()

if school_geom.Intersects(birm_geom):
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(school_geom)
for i in range(lyr_def.GetFieldCount()):
feat.SetField(lyr_def.GetFieldDefn(i).GetNameRef(), school_feat.GetField(i))

out_lyr.CreateFeature(feat)
feat.Destroy()

del shp_ds, shp_layer, gdb_ds```

The Usual 🙂

As always please feel free to comment to help make the code more efficient, highlight errors, or let me know if this was of any use to you.

# OSGP: Measuring Geographic Distributions – Mean Center

(Open Source Geospatial Python)

The ‘What is it?’

The Mean Center is the average X coordinate and Y coordinate for all features in a study area and is the simplest descriptor of a geographic distribution. The Mean Center is generally used to track the changes in a features distribution over time and can also be used to compare the distribution of multiple features.

The Mean Center is also known as the Geographic Center or Center of Concentration for a set of features.

You would calculate the Mean Center for features where there is no travel interaction between the Center and the features of the study. Basically, use it for a study where each event that happens is a recorded location, for example a burglary for crime analysis, or the sighting of wombat for wildlife studies.

The Formula!

For Point features the X and Y coordinates of each feature is used, for Polygons the centroid of each feature represents the X and Y coordinate to use, and for Linear features the mid-point of each line is used for the X and Y coordinate.

The Code…

```from osgeo import ogr
from shapely.geometry import MultiLineString
from shapely import wkt
import numpy as np
import sys

## set the driver for the data
driver = ogr.GetDriverByName("FileGDB")
## path to the FileGDB
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"
## ope the GDB in write mode (1)
ds = driver.Open(gdb, 1)

## input layer
input_lyr_name = "Birmingham_Burglaries_2016"

## the output layer
output_fc = "{0}_mean_center".format(input_lyr_name)

## reference the layer using the layers name
if input_lyr_name in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
lyr = ds.GetLayerByName(input_lyr_name)
print "{0} found in {1}".format(input_lyr_name, gdb)

## delete the output feature class if it already exists
if output_fc in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

try:
## assess the geometry of the input feature class
first_feat = lyr.GetFeature(1)
## for each point or polygon in the layer
## get the x and y value of the centroid
## store in a numpy array
if first_feat.geometry().GetGeometryName() in ["POINT", "MULTIPOINT", "POLYGON", "MULTIPOLYGON"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, pt in enumerate(lyr):
ft_geom = pt.geometry()
xy_arr[i] = (ft_geom.Centroid().GetX(), ft_geom.Centroid().GetY())

## for lineear we get the midpoint of a line
elif first_feat.geometry().GetGeometryName() in ["LINESTRING", "MULTILINESTRING"]:
xy_arr = np.ndarray((len(lyr), 2), dtype=np.float)
for i, ln in enumerate(lyr):
line_geom = ln.geometry().ExportToWkt()
midpoint = shapely_line.interpolate(shapely_line.length/2)
xy_arr[i] = (midpoint.x, midpoint.y)

## exit gracefully if unknown geometry or input contains no geometry
except Exception:
print "Unknown geometry for {0}".format(input_lyr_name)
sys.exit()

avg_x, avg_y = np.mean(xy_arr, axis=0)

print "Mean Center: {0}, {1}".format(avg_x, avg_y)

## create a new point layer with the same spatial ref as input layer
out_lyr = ds.CreateLayer(output_fc, lyr.GetSpatialRef(), ogr.wkbPoint)

## define and create new fields to hold the mean center coordinates
x_fld = ogr.FieldDefn("X", ogr.OFTReal)
y_fld = ogr.FieldDefn("Y", ogr.OFTReal)
out_lyr.CreateField(x_fld)
out_lyr.CreateField(y_fld)

## create a new point geom for the mean center
pnt = ogr.Geometry(ogr.wkbPoint)

## add the mean center point to the new layer with attributes
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(pnt)
feat.SetField("X", avg_x)
feat.SetField("Y", avg_y)
out_lyr.CreateFeature(feat)

print "Created: {0}".format(output_fc)

## free up resources
del ds, lyr, first_feat, feat, out_lyr```

I’d like to give credit to Logan Byers from GIS StackExchange who aided in speeding up the computational time using NumPy and for forcing me to begin learning the wonders of NumPy.

The Example:

I downloaded crime data from DATA.POLICE.UK for the West Midlands Police from January 2016 to December 2016. I used some Python to extract just the Burglary data and made this into a feature class in the File GDB. Next, I downloaded OS Boundary Line data and clipped the Burglary data to just Birmingham. Everything was now in place to find the Mean Center of all burglaries for Birmingham in 2016. (see The Other Scripts section at the bottom of this post for processing the data)

Running the script from The Code section above calculates the Mean Center of all burglaries for 2016 and created a point feature class in the File GDB.

OSGP Mean Center:     407926.695396, 286615.428507
ArcGIS Mean Center:    407926.695396, 286615.428507

What’s Next?…

Central Feature

The Resources:

ESRI Guide to GIS Volume 2: Chapter 2 (I highly recommend this book)
see book review here.

Geoprocessing with Python

Python GDAL/OGR Cookbook

Setting up GDAL/OGR with FileGDB Driver for Python on Windows

< The Other Scripts >

1. Extract Burglary Data for West Midlands

```import csv, os
from osgeo import ogr, osr

## set the driver for the data
driver = ogr.GetDriverByName("FileGDB")

## path to the FileGDB
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

## ope the GDB in write mode (1)
ds = driver.Open(gdb, 1)

## the coordinates in the csv files are lat/long
source = osr.SpatialReference()
source.ImportFromEPSG(4326)

## we need the data in British National Grid
target = osr.SpatialReference()
target.ImportFromEPSG(27700)

transform = osr.CoordinateTransformation(source, target)

## set the output fc name
output_fc = "WM_Burglaries_2016"

## if the output fc already exists delete it
if output_fc in [ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(ds.GetLayerCount())]:
ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

out_lyr = ds.CreateLayer(output_fc, target, ogr.wkbPoint)

## define and create new fields
mnth_fld = ogr.FieldDefn("Month", ogr.OFTString)
rep_by_fld = ogr.FieldDefn("Reported_by", ogr.OFTString)
fls_wthn_fld = ogr.FieldDefn("Falls_within", ogr.OFTString)
loc_fld = ogr.FieldDefn("Location", ogr.OFTString)
lsoa_c_fld = ogr.FieldDefn("LSOA_code", ogr.OFTString)
lsoa_n_fld = ogr.FieldDefn("LSOA_name", ogr.OFTString)
crime_fld = ogr.FieldDefn("Crime_type", ogr.OFTString)
outcome_fld = ogr.FieldDefn("Last_outcome", ogr.OFTString)

out_lyr.CreateField(mnth_fld)
out_lyr.CreateField(rep_by_fld)
out_lyr.CreateField(fls_wthn_fld)
out_lyr.CreateField(loc_fld)
out_lyr.CreateField(lsoa_c_fld)
out_lyr.CreateField(lsoa_n_fld)
out_lyr.CreateField(crime_fld)
out_lyr.CreateField(outcome_fld)

root_folder = r"C:\Users\Glen B\Documents\Crime"

## for each csv
for root,dirs,files in os.walk(root_folder):
for filename in files:
if filename.endswith(".csv"):
csv_path = "{0}\\{1}".format(root, filename)
with open(csv_path, "rb") as csvfile:
## create a point with attributes for each burglary
if row[9] == "Burglary":
pnt = ogr.Geometry(ogr.wkbPoint)
pnt.Transform(transform)
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(pnt)
feat.SetField("Month", row[1])
feat.SetField("Reported_by", row[2])
feat.SetField("Falls_within", row[3])
feat.SetField("Location", row[6])
feat.SetField("LSOA_code", row[7])
feat.SetField("LSOA_name", row[8])
feat.SetField("Crime_type", row[9])
feat.SetField("Last_outcome", row[10])
out_lyr.CreateFeature(feat)

del ds, feat, out_lyr```

2. Birmingham Burglaries Only

```from osgeo import ogr

## required drivers
shp_driver = ogr.GetDriverByName("ESRI Shapefile")
gdb_driver = ogr.GetDriverByName("FileGDB")

## input boundary shapefile and file gdb
shapefile = r"C:\Users\Glen B\Documents\Crime\Data\GB\district_borough_unitary_region.shp"
gdb = r"C:\Users\Glen B\Documents\my_geodata.gdb"

## open the shapefile in read mode and gdb in write mode
shp_ds = shp_driver.Open(shapefile, 0)
gdb_ds = gdb_driver.Open(gdb, 1)

## reference the necessary layers
shp_layer = shp_ds.GetLayer(0)
gdb_layer = gdb_ds.GetLayerByName("WM_Burglaries_2016")

## filter the shapefile
shp_layer.SetAttributeFilter("NAME = 'Birmingham District (B)'")

## set the name for the output feature class
output_fc = "Birmingham_Burglaries_2016"

## if the output already exists then delete it
if output_fc in [gdb_ds.GetLayerByIndex(lyr_name).GetName() for lyr_name in range(gdb_ds.GetLayerCount())]:
gdb_ds.DeleteLayer(output_fc)
print "Deleting: {0}".format(output_fc)

## create an output layer
out_lyr = gdb_ds.CreateLayer(output_fc, shp_layer.GetSpatialRef(), ogr.wkbPoint)

## copy the schema from the West Midlands burglaries
## and use it for the Birmingham burglaries
lyr_def = gdb_layer.GetLayerDefn()
for i in range(lyr_def.GetFieldCount()):
out_lyr.CreateField (lyr_def.GetFieldDefn(i))

## only get burglaries that intersect the Birmingham region
for shp_feat in shp_layer:
print shp_feat.GetField("NAME")
birm_geom = shp_feat.GetGeometryRef()
for gdb_feat in gdb_layer:
burglary_geom = gdb_feat.GetGeometryRef()
if burglary_geom.Intersects(birm_geom):
feat_dfn = out_lyr.GetLayerDefn()
feat = ogr.Feature(feat_dfn)
feat.SetGeometry(burglary_geom)

## populate the attribute table
for i in range(lyr_def.GetFieldCount()):
feat.SetField(lyr_def.GetFieldDefn(i).GetNameRef(), gdb_feat.GetField(i))
## create the feature
out_lyr.CreateFeature(feat)
feat.Destroy()

del shp_ds, shp_layer, gdb_ds, gdb_layer```

The Usual 🙂

As always please feel free to comment to help make the code more efficient, highlight errors, or let me know if this was of any use to you.

# Book Review: The ESRI Guide to GIS Analysis Vol. 2: Spatial Measurements & Statistics

Title: The ESRI Guide to GIS Analysis Vol. 2: Spatial Measurements & Statistics
Author: Andy Mitchell
Publisher: ESRI Press
Year: 2005
Aimed at: GIS/Analysts/Map Designers – intermediate
Purchased from: www.wordery.com

This textbook acts as companion text for GIS Tutorial 2: Spatial Analysis Workbook (for ArcGIS 10.3.x) where you can match up the chapters in each book. Although not a necessity, I would recommend using both texts in tandem to apply the theory and methods discussed with practical tutorials and walkthroughs using ArcGIS. This is the second book of the series and follows on from The ESRI Guide to GIS Analysis Volume 1: Geographic Patterns & Relationships.

The first chapter is, inevitably, an introduction to spatial measurements and statistics. You perform analysis to answer questions and to answer these questions you not only need data but you also need to understand the data. Are you using nominal, ordinal, interval or ratio values, or a combination of these? The type of value(s) will shape the analysis techniques and methods used to calculate the statistics. You will need to interpret the statistics, test their significance and question the results. These elements are briefly visited with the premise of getting more in-depth as the book progresses. The chapter ends with a section on ‘Understanding data distributions’ which is essentially a brief introduction to data exploratory techniques such as describing frequency distributions, spatial distributions, and the presence of outliers and how they can affect analysis.

Chapter 2 discusses measuring geographic distributions with the bulk of the chapter focused on finding the center (mean, meridian, central feature), and measuring compactness (standard distance), orientation and direction of distributions (spatial trends). These are discussed for points, lines, and areal features and also using weighted factors based on attributes. These are useful for adding statistical confidence to patterns derived from a map. Formulas and equations begin to surface and although not necessary to learn them off by heart, because the GIS does all the heavy lifting for you, it gives insight into what goes on under the hood, and knowing the underlying theory and formulas can often aid in troubleshooting and producing accurate analysis. The last section of this chapter is fundamental to the rest of the text, testing statistical significance. This allows you to measure a confidence level for your analysis using the null hypothesis, p-value, and z-score. This can be a difficult topic to comprehend and may require further reading.

The third chapter, a lengthy one, is based around using statistical analysis to identify patterns, to enhance and backup the visual analysis of the map with confidence or to find patterns not may not have been immediately obvious. The human eye will often see patterns that do not really exist, so alternatively, statistical analysis might indicate what you thought was a strong pattern was actually quite weak. The statistical analysis methods are beginning to heat up and here we are introduced to; the Kolmorogov-Smirnov test and Chi Square test for quadrat analysis in identifying patterns in areas of equal size; the nearest neighbour index for calculating the average distance between features and identifying clustering or dispersion; and the K-function as an alternative to the nearest neighbour index, each used to measure the pattern of feature locations. These are followed by measuring the spatial pattern of feature values using; the join count statistic for areas with categories; Geary’s c and Moran’s I for measuring the similarity of nearby features, and the General-G statistic for measuring the concentration of high and low values for features having continuous values. The formulas for each are presented along with testing the significance of and interpreting the results. The final section of this chapter discusses defining spatial neighbourhoods and weights when analysing patterns. There are a few things to consider such as local or regional influences, thresholds of influence, interaction between adjacent features, and the rate of regional decline of influence.

Chapter 4 is titled ‘Identifying Clusters’ with a main focus on hotspot analysis. First, we are introduced to nearest neighbour hierarchical clustering which is heavily used in crime analysis. While Chapter 3 discussed global methods for identifying patterns and returns a single statistic, this chapter focuses on local statistics to show where these patterns exist within the global setting. Geary’s c and Moran’s I both have local versions and their definition, implementation, and factors influencing the results are discussed and critiqued along with Art Getis’ and Keith Ord’s Gi* method for identifying hot and cold spots.While the methods in Chapter 3 enforced that there are patterns in the data (or not), the methods in Chapter 4 highlight where these clustered patterns are. The last section of Chapter 4 discusses using statistics with geographic data; how the very nature of geographic data affects your analysis, how geographic data is represented in a GIS affects your data analysis, the influence of the study area boundary, and GIS data and errors.

“To the extent you’re confident in the quality of your GIS data, you can be confident in the quality of your analysis results.”

The last chapter ventures away from identifying patterns and clusters and focuses on analysing geographic relationships and using statistics to analyse such. Geographic relationships and processes are used to predict where something is likely to occur and examining why things occur where they do. Chapter 5 looks at statistical methods for identifying geographical relationships with a Pearson’s correlation coefficient and Spearman’s correlation coefficient discussed and assessed. Linear regression (ordinary least squares), and geographically weighted regression are presented as methods for analysing geographic processes. These methods warrant a full text in their own right and there is a list of further reading available at the end of the chapter.

Overall Verdict: I feel that I will be referring back to this text a lot. Having recently completed a MSc in Geocomputation I wish that this had crossed my path during the course of my studies and I would highly recommend this book to anyone venturing into spatial analysis where statistics can aid and back up the analysis. Although they are littered throughout the chapters, you really do not need to get bogged down with the formulas behind the statistical analysis techniques, the most important points is that you understand what the methods are performing, their limitations, and how to assess the results and this book really is a fantastic reference for doing just that. Knowing the theory is a huge step to being able to apply the analysis techniques confidently and derive accurate reporting of your data.

# Book Review: The ESRI Guide to GIS Analysis Vol. 1: Geographic Patterns & Relationships

Title: The ESRI Guide to GIS Analysis Vol. 1: Geographic Patterns & Relationships
Author: Andy Mitchell
Publisher: ESRI Press
Year: 1999
Aimed at: GIS/Analysts/Map Designers – beginner
Purchased from: www.wordery.com

This textbook is a companion text for GIS Tutorial 2: Spatial Analysis Workbook (for ArcGIS 10.3.x) where you can match up the chapters in each book. Although not a necessity, I would recommend using both texts in tandem to apply the theory and methods discussed with practical tutorials and walkthroughs using ArcGIS.

The title of this book might lead you to believe that ArcGIS will feature heavily throughout the text but Michael F. Goodchild sets this straight in the Preface by stating that he applauds ESRI for backing this book even though it isn’t Arc eccentric. The author, Andy Mitchell, presents the material as generic GIS such that most GIS software packages should be able to utilise the techniques discussed.

Chapter 1 is a short introduction to what GIS analysis is, understanding the representation of geographic features in a GIS, and the common attributes associated with geographic features that allow for analysis. The wording is simplistic in nature and easy to follow, and acts as a good entrance to the rest of the book.

The second chapter begins to delve into the realm of visual analysis, using your brain to to discern patterns for a better understanding of the data and the area that you are mapping. Several real-life mapped examples are displayed to show how ‘mapping where things are’ aids in more focused decision making. The chapter steps through; deciding what to map, preparing your data, and making your map, with comparison figures to show you why you might perform such tasks.

Why map the most and least? Because mapping features based on quantities adds an additional level of information beyond simply mapping the locations of the features and this notion is made clear from providing some real-life examples in Chapter 3. The author then takes us down a path to understanding quantities and the importance of knowing the type of quantities that you are mapping, and this naturally leads onto the next topic of classification, why use classes? and choosing an appropriate classification method/scheme for the purpose of your data. It is important to understand how classification methods such as Natural Breaks (Jenk’s), Quantile, Equal Interval, and Standard Deviation classify your data and having a general guideline on choosing the appropriate method.

A great recurring aspect in this book is that every chapter begins with a question and Chapter 4’s is ‘Why Map Density?’ and then proceeds to answer the question and the methods available for mapping in a GIS. This chapter discusses density for defined areas, dot density mapping, and density surfaces, what the GIS does to create them and the results of the output.

The fifth chapter takes a look at mapping what’s inside an area, discusses why you would want to map inside an area?, and some analysis and results that can be derived from such. Do you need to map a single area to find what’s happening inside or multiple areas to analyse what’s happening inside each for comparison purposes? Methods are explained along with how the GIS performs these for analysis. You might want to find out if a certain feature is within an area, a list of all features inside an area and a count of each, or the sum of a designated land type area within a boundary for examples. Summaries and statistics can also be generated from what is found inside an area boundary.

Having assessed some simple techniques for mapping what’s inside an area, the next chapter casts it’s attention towards finding what’s nearby. People often think of nearness in straight lines or along transport networks, but GIS is also useful for travel cost analysis giving weight to different land use or soil types for example when considering the path for a pipeline. Nearness by straight-line distance, distance/cost over a network, and cost over a geographic surface are discussed in detail. At this point we are venturing into understanding some of the concepts behind Network Analysis.

The last chapter looks at mapping change with regards to change over time for time pattern analysis. Three ways of mapping change are presented; creating a time series, creating a tracking map, and measuring change, along with the considerations required when creating each type for change in discrete features, events, summarized areas, and continuous categories and values.

Following the last chapter there are some recommendations for some further reading.

Overall Verdict: The perfect companion for a GIS student embarking on their geospatial educational quest. The theory behind GIS is essential for accurate analysis and troubleshooting. This book is an easy read with a plethora of figures and maps utilised in real-life situations found in each chapter to aid in the experience. Although getting closer to being two decades old this text stands the test of time and acts as a solid base for a foundation in simple analysis using a GIS to find patterns and relationships.

The only shortcoming of a text of this nature is that you cannot see how methods and techniques discussed are performed in a GIS. This is where the companion text GIS Tutorial 2: Spatial Analysis Workbook (for ArcGIS 10.3.x) comes in and aids in providing walkthroughs to further enhance your understanding of the underlying theory.