Example: Plotting U.S. Counties with Bokeh + Pyshp

I’ve been playing around with Choropleths and wanted to share this simple example (Pyshp is a package requirement in addition to some standard Anaconda packages) in case others might find it useful:

#!/usr/bin/env python

from bokeh.plotting import figure, show

from bokeh.models import HoverTool, ColumnDataSource

import itertools

import shapefile

import pandas as pd

import datetime

import requests

import zipfile

try:

from StringIO import StringIO

except ImportError:

from io import BytesIO as StringIO

import os

Get FIPS data

state_fips = pd.read_csv(‘http://www2.census.gov/geo/docs/reference/state.txt’, sep=’|’)

state_fips.drop(‘STATE’, axis=1, inplace=True)

county_fips = pd.read_csv(‘http://www2.census.gov/geo/docs/reference/codes/files/national_county.txt’, header=None)

county_fips.columns = [‘STATE’, ‘STATEFP’, ‘COUNTYFP’, ‘COUNTYNAME’, ‘CLASSFP’]

all_fips = pd.merge(county_fips, state_fips, left_on=‘STATE’, right_on=‘STUSAB’)

Get USA map data

https://www.census.gov/geo/maps-data/data/cbf/cbf_counties.html

shp = None

dbf = None

last_year = datetime.datetime.now().year - 1

url = ‘http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_20m.zip’.format(last_year, last_year) # Lowest

#url = ‘http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_5m.zip’.format(last_year, last_year)

#url = ‘http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_500k.zip’.format(last_year, last_year) #Highest

response = requests.get(url)

with zipfile.ZipFile(StringIO(response.content)) as z:

for fname in z.namelist():

    name, ext = os.path.splitext(fname)

    if ext == '.shp':

        shp = StringIO(z.read(fname)) 

        #shp = z.open(fname)

    elif ext == '.dbf':

        #dbf = z.open(fname)

        dbf = StringIO(z.read(fname))             

    else:

        pass

sf = shapefile.Reader(shp=shp, dbf=dbf)

Munge map data for bokeh

lats =

lons =

county =

state =

for shprec in sf.shapeRecords():

statefp = int(shprec.record[0])

countyfp = int(shprec.record[1])

fip = all_fips.loc[(all_fips['STATEFP'] == statefp) & (all_fips['COUNTYFP'] == countyfp)]

county.append(fip['COUNTYNAME'])

state.append(fip['STATE_NAME'])

lat, lon = map(list, zip(*shprec.shape.points))

lat = [l if l < 0 else l-360 for l in lat]

indices = shprec.shape.parts.tolist()

lat = [lat[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]

lon = [lon[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]

lat = list(itertools.chain.from_iterable(lat))

lon = list(itertools.chain.from_iterable(lon))

lats.append(lat)

lons.append(lon)

Plot with bokeh

df = pd.DataFrame({‘x’: lats, ‘y’: lons, ‘county’: county, ‘state’: state})

cds = ColumnDataSource(df)

p = figure(width=800)

county_patches = p.patches(‘x’, ‘y’, source=cds, line_color=‘white’)

hover = HoverTool(renderers=[county_patches], tooltips=[(“County, State”, “@county, @state”)])

p.add_tools(hover)

show(p)

Thank you for this. I had a hard time trying to visualize election results in Hawaii.

···

On Thu, Aug 11, 2016 at 4:31 PM [email protected] wrote:

I’ve been playing around with Choropleths and wanted to share this simple example (Pyshp is a package requirement in addition to some standard Anaconda packages) in case others might find it useful:

#!/usr/bin/env python

from bokeh.plotting import figure, show

from bokeh.models import HoverTool, ColumnDataSource

import itertools

import shapefile

import pandas as pd

import datetime

import requests

import zipfile

try:

from StringIO import StringIO

except ImportError:

from io import BytesIO as StringIO

import os

Get FIPS data

state_fips = pd.read_csv(‘http://www2.census.gov/geo/docs/reference/state.txt’, sep=‘|’)

state_fips.drop(‘STATE’, axis=1, inplace=True)

county_fips = pd.read_csv(‘http://www2.census.gov/geo/docs/reference/codes/files/national_county.txt’, header=None)

county_fips.columns = [‘STATE’, ‘STATEFP’, ‘COUNTYFP’, ‘COUNTYNAME’, ‘CLASSFP’]

all_fips = pd.merge(county_fips, state_fips, left_on=‘STATE’, right_on=‘STUSAB’)

Get USA map data

https://www.census.gov/geo/maps-data/data/cbf/cbf_counties.html

shp = None

dbf = None

last_year = datetime.datetime.now().year - 1

url = '[http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_20m.zip’.format(last_year](http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_20m.zip’.format(last_year), last_year) # Lowest

#url = '[http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_5m.zip’.format(last_year](http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_5m.zip’.format(last_year), last_year)

#url = '[http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_500k.zip’.format(last_year](http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_500k.zip’.format(last_year), last_year) #Highest

response = requests.get(url)

with zipfile.ZipFile(StringIO(response.content)) as z:

for fname in z.namelist():
    name, ext = os.path.splitext(fname)
    if ext == '.shp':
        shp = StringIO(z.read(fname)) 
        #shp = z.open(fname)
    elif ext == '.dbf':
        #dbf = z.open(fname)
        dbf = StringIO(z.read(fname))             
    else:
        pass

sf = shapefile.Reader(shp=shp, dbf=dbf)

Munge map data for bokeh

lats =

lons =

county =

state =

for shprec in sf.shapeRecords():

statefp = int(shprec.record[0])
countyfp = int(shprec.record[1])
fip = all_fips.loc[(all_fips['STATEFP'] == statefp) & (all_fips['COUNTYFP'] == countyfp)]
county.append(fip['COUNTYNAME'])
state.append(fip['STATE_NAME'])
lat, lon = map(list, zip(*shprec.shape.points))
lat = [l if l < 0 else l-360 for l in lat]
indices = shprec.shape.parts.tolist()
lat = [lat[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]
lon = [lon[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]
lat = list(itertools.chain.from_iterable(lat))
lon = list(itertools.chain.from_iterable(lon))
lats.append(lat)
lons.append(lon)

Plot with bokeh

df = pd.DataFrame({‘x’: lats, ‘y’: lons, ‘county’: county, ‘state’: state})

cds = ColumnDataSource(df)

p = figure(width=800)

county_patches = p.patches(‘x’, ‘y’, source=cds, line_color=‘white’)

hover = HoverTool(renderers=[county_patches], tooltips=[(“County, State”, “@county, @state”)])

p.add_tools(hover)

show(p)

You received this message because you are subscribed to the Google Groups “Bokeh Discussion - Public” group.

To unsubscribe from this group and stop receiving emails from it, send an email to [email protected].

To post to this group, send email to [email protected].

To view this discussion on the web visit https://groups.google.com/a/continuum.io/d/msgid/bokeh/e5a17d55-5bf1-49bb-a04c-5be5f08b9f2c%40continuum.io.

For more options, visit https://groups.google.com/a/continuum.io/d/optout.

For completeness, here are the steps for generating the World Countries Map:

#!/usr/bin/env python

from bokeh.plotting import figure, show, output_notebook

from bokeh.models import HoverTool, ColumnDataSource

import itertools

import shapefile

import pandas as pd

import datetime

import requests

import zipfile

try:

from StringIO import StringIO

except ImportError:

from io import BytesIO as StringIO

import os

Get World Country Map Data

Natural Earth » Features - Free vector and raster map data at 1:10m, 1:50m, and 1:110m scales

shp = None

dbf = None

url = ‘http://www.naturalearthdata.com/http//www.naturalearthdata.com/download/110m/cultural/ne_110m_admin_0_countries.zip

response = requests.get(url)

with zipfile.ZipFile(StringIO(response.content)) as z:

for fname in z.namelist():

    name, ext = os.path.splitext(fname)

    if ext == '.shp':

        shp = StringIO(z.read(fname)) 

        #shp = z.open(fname)

    elif ext == '.dbf':

        #dbf = z.open(fname)

        dbf = StringIO(z.read(fname))             

    else:

        pass

sf = shapefile.Reader(shp=shp, dbf=dbf)

Munge map data for bokeh

lats =

lons =

country =

for shprec in sf.shapeRecords():

name_long = unicode(shprec.record[18], 'cp1252').encode('utf8')

country.append(name_long)

lat, lon = map(list, zip(*shprec.shape.points))

indices = shprec.shape.parts.tolist()

lat = [lat[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]

lon = [lon[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]

lat = list(itertools.chain.from_iterable(lat))

lon = list(itertools.chain.from_iterable(lon))

lats.append(lat)

lons.append(lon)

df = pd.DataFrame({‘x’: lats, ‘y’: lons, ‘country’: country})

cds = ColumnDataSource(df)

p = figure(width=800)

country_patches = p.patches(‘x’, ‘y’, source=cds, line_color=‘white’)

hover = HoverTool(renderers=[country_patches], tooltips=[(‘Country’, ‘@country’)])

p.add_tools(hover)

show(p)

···

On Thursday, August 11, 2016 at 11:55:31 PM UTC-4, Ria Baldevia wrote:

Thank you for this. I had a hard time trying to visualize election results in Hawaii.

On Thu, Aug 11, 2016 at 4:31 PM [email protected] wrote:

I’ve been playing around with Choropleths and wanted to share this simple example (Pyshp is a package requirement in addition to some standard Anaconda packages) in case others might find it useful:

#!/usr/bin/env python

from bokeh.plotting import figure, show

from bokeh.models import HoverTool, ColumnDataSource

import itertools

import shapefile

import pandas as pd

import datetime

import requests

import zipfile

try:

from StringIO import StringIO

except ImportError:

from io import BytesIO as StringIO

import os

Get FIPS data

state_fips = pd.read_csv(‘http://www2.census.gov/geo/docs/reference/state.txt’, sep=‘|’)

state_fips.drop(‘STATE’, axis=1, inplace=True)

county_fips = pd.read_csv(‘http://www2.census.gov/geo/docs/reference/codes/files/national_county.txt’, header=None)

county_fips.columns = [‘STATE’, ‘STATEFP’, ‘COUNTYFP’, ‘COUNTYNAME’, ‘CLASSFP’]

all_fips = pd.merge(county_fips, state_fips, left_on=‘STATE’, right_on=‘STUSAB’)

Get USA map data

https://www.census.gov/geo/maps-data/data/cbf/cbf_counties.html

shp = None

dbf = None

last_year = datetime.datetime.now().year - 1

url = '[http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_20m.zip’.format(last_year](http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_20m.zip’.format(last_year), last_year) # Lowest

#url = '[http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_5m.zip’.format(last_year](http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_5m.zip’.format(last_year), last_year)

#url = '[http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_500k.zip’.format(last_year](http://www2.census.gov/geo/tiger/GENZ{}/shp/cb_{}_us_county_500k.zip’.format(last_year), last_year) #Highest

response = requests.get(url)

with zipfile.ZipFile(StringIO(response.content)) as z:

for fname in z.namelist():
    name, ext = os.path.splitext(fname)
    if ext == '.shp':
        shp = StringIO(z.read(fname)) 
        #shp = z.open(fname)
    elif ext == '.dbf':
        #dbf = z.open(fname)
        dbf = StringIO(z.read(fname))             
    else:
        pass

sf = shapefile.Reader(shp=shp, dbf=dbf)

Munge map data for bokeh

lats =

lons =

county =

state =

for shprec in sf.shapeRecords():

statefp = int(shprec.record[0])
countyfp = int(shprec.record[1])
fip = all_fips.loc[(all_fips['STATEFP'] == statefp) & (all_fips['COUNTYFP'] == countyfp)]
county.append(fip['COUNTYNAME'])
state.append(fip['STATE_NAME'])
lat, lon = map(list, zip(*shprec.shape.points))
lat = [l if l < 0 else l-360 for l in lat]
indices = shprec.shape.parts.tolist()
lat = [lat[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]
lon = [lon[i:j] + [float('NaN')] for i, j in zip(indices, indices[1:]+[None])]
lat = list(itertools.chain.from_iterable(lat))
lon = list(itertools.chain.from_iterable(lon))
lats.append(lat)
lons.append(lon)

Plot with bokeh

df = pd.DataFrame({‘x’: lats, ‘y’: lons, ‘county’: county, ‘state’: state})

cds = ColumnDataSource(df)

p = figure(width=800)

county_patches = p.patches(‘x’, ‘y’, source=cds, line_color=‘white’)

hover = HoverTool(renderers=[county_patches], tooltips=[(“County, State”, “@county, @state”)])

p.add_tools(hover)

show(p)

You received this message because you are subscribed to the Google Groups “Bokeh Discussion - Public” group.

To unsubscribe from this group and stop receiving emails from it, send an email to [email protected].

To post to this group, send email to [email protected].

To view this discussion on the web visit https://groups.google.com/a/continuum.io/d/msgid/bokeh/e5a17d55-5bf1-49bb-a04c-5be5f08b9f2c%40continuum.io.

For more options, visit https://groups.google.com/a/continuum.io/d/optout.