8000 version correction and added state/county names in dataframe · NulledExceptions/plotly.py@a007525 · GitHub
[go: up one dir, main page]
Skip to content

Commit a007525

Browse files
KullyKully
committed
version correction and added state/county names in dataframe
1 parent be825a2 commit a007525

File tree

2 files changed

+67
-52
lines changed

2 files changed

+67
-52
lines changed

‎plotly/figure_factory/_county_choropleth.py

Lines changed: 66 additions & 51 deletions
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,8 @@ def _create_us_counties_df(st_to_state_name_dict, state_to_st_dict):
2222
shape_pre2010 = 'gz_2010_us_050_00_500k/gz_2010_us_050_00_500k.shp'
2323
shape_pre2010 = data_url + shape_pre2010
2424
df_shape_pre2010 = gp.read_file(shape_pre2010)
25-
df_shape_pre2010['FIPS'] = df_shape_pre2010['STATE'] + df_shape_pre2010['COUNTY']
25+
df_shape_pre2010['FIPS'] = (df_shape_pre2010['STATE'] +
26+
df_shape_pre2010['COUNTY'])
2627
df_shape_pre2010['FIPS'] = pd.to_numeric(df_shape_pre2010['FIPS'])
2728

2829
states_path = 'cb_2016_us_state_500k/cb_2016_us_state_500k.shp'
@@ -31,6 +32,7 @@ def _create_us_counties_df(st_to_state_name_dict, state_to_st_dict):
3132
# state df
3233
df_state = gp.read_file(states_path)
3334
df_state = df_state[['STATEFP', 'NAME', 'geometry']]
35+
df_state = df_state.rename(columns={'NAME': 'STATE_NAME'})
3436

3537
county_url = 'plotly/package_data/data/cb_2016_us_county_500k/'
3638
filenames = ['cb_2016_us_county_500k.dbf',
@@ -65,9 +67,9 @@ def _create_us_counties_df(st_to_state_name_dict, state_to_st_dict):
6567
[st_to_state_name_dict['SD'], 'SD',
6668
df_shape_pre2010[df_shape_pre2010['FIPS'] == f]['geometry'].iloc[0],
6769
df_shape_pre2010[df_shape_pre2010['FIPS'] == f]['FIPS'].iloc[0],
68-
'46']
70+
'46', 'Shannon']
6971
],
70-
columns=['State', 'ST', 'geometry', 'FIPS', 'STATEFP'],
72+
columns=['State', 'ST', 'geometry', 'FIPS', 'STATEFP', 'NAME'],
7173
index=[max(gdf.index) + 1]
7274
)
7375
gdf = gdf.append(singlerow)
@@ -78,9 +80,9 @@ def _create_us_counties_df(st_to_state_name_dict, state_to_st_dict):
7880
[st_to_state_name_dict['VA'], 'VA',
7981
df_shape_pre2010[df_shape_pre2010['FIPS'] == f]['geometry'].iloc[0],
8082
df_shape_pre2010[df_shape_pre2010['FIPS'] == f]['FIPS'].iloc[0],
81-
'51']
83+
'51', 'Bedford City']
8284
],
83-
columns=['State', 'ST', 'geometry', 'FIPS', 'STATEFP'],
85+
columns=['State', 'ST', 'geometry', 'FIPS', 'STATEFP', 'NAME'],
8486
index=[max(gdf.index) + 1]
8587
)
8688
gdf = gdf.append(singlerow)
@@ -91,9 +93,9 @@ def _create_us_counties_df(st_to_state_name_dict, state_to_st_dict):
9193
[st_to_state_name_dict['AK'], 'AK',
9294
df_shape_pre2010[df_shape_pre2010['FIPS'] == f]['geometry'].iloc[0],
9395
df_shape_pre2010[df_shape_pre2010['FIPS'] == f]['FIPS'].iloc[0],
94-
'02']
96+
'02', 'Wade Hampton']
9597
],
96-
columns=['State', 'ST', 'geometry', 'FIPS', 'STATEFP'],
98+
columns=['State', 'ST', 'geometry', 'FIPS', 'STATEFP', 'NAME'],
9799
index=[max(gdf.index) + 1]
98100
)
99101
gdf = gdf.append(singlerow)
@@ -109,12 +111,14 @@ def _create_us_counties_df(st_to_state_name_dict, state_to_st_dict):
109111
row_2105.loc[row_2105.index[0], 'FIPS'] = 2232
110112
row_2105.loc[row_2105.index[0], 'STATEFP'] = '02'
111113
gdf = gdf.append(row_2105)
114+
gdf = gdf.rename(columns={'NAME': 'COUNTY_NAME'})
112115

113-
gdf_reduced = gdf[['FIPS', 'STATEFP', 'geometry']]
114-
gdf_statefp = gdf_reduced.merge(df_state[['STATEFP', 'NAME']], on='STATEFP')
116+
gdf_reduced = gdf[['FIPS', 'STATEFP', 'COUNTY_NAME', 'geometry']]
117+
gdf_statefp = gdf_reduced.merge(df_state[['STATEFP', 'STATE_NAME']],
118+
on='STATEFP')
115119

116120
ST = []
117-
for n in gdf_statefp['NAME']:
121+
for n in gdf_statefp['STATE_NAME']:
118122
ST.append(state_to_st_dict[n])
119123

120124
gdf_statefp['ST'] = ST
@@ -254,7 +258,7 @@ def _human_format(number):
254258
return '%.2f%s' % (number / k**magnitude, units[magnitude])
255259

256260

257-
def _intervals_as_labels(array_of_intervals, round_leg, exponent_format):
261+
def _intervals_as_labels(array_of_intervals, round_legend_values, exponent_format):
258262
"""
259263
Transform an number interval to a clean string for legend
260264
@@ -264,7 +268,7 @@ def _intervals_as_labels(array_of_intervals, round_leg, exponent_format):
264268
string_intervals = []
265269
for interval in array_of_intervals:
266270
# round to 2nd decimal place
267-
if round_leg:
271+
if round_legend_values:
268272
rnd_interval = [
269273
(int(interval[i]) if interval[i] not in infs else
270274
interval[i])
@@ -309,9 +313,12 @@ def _calculations(df, fips, values, index, f, simplify_county, level,
309313
).exterior.xy[1].tolist()
310314

311315
x_c, y_c = fips_polygon_map[f].centroid.xy
316+
county_name_str = str(df[df['FIPS'] == f]['COUNTY_NAME'].iloc[0])
317+
state_name_str = str(df[df['FIPS'] == f]['STATE_NAME'].iloc[0])
312318
t_c = (
313-
'County: ' + df[df['FIPS'] == f]['NAME'].iloc[0] + '<br>' +
314-
'FIPS: ' + str(f) + '<br> Value: ' + str(values[index])
319+
'County: ' + county_name_str + '<br>' +
320+
'State: ' + state_name_str + '<br>' +
321+
'FIPS: ' + str(f) + '<br>Value: ' + str(values[index])
315322
)
316323

317324
x_centroids.append(x_c[0])
@@ -330,8 +337,9 @@ def _calculations(df, fips, values, index, f, simplify_county, level,
330337
y_c = [poly.centroid.xy[1].tolist() for poly in fips_polygon_map[f]]
331338

332339
text = (
333-
'County: ' + df[df['FIPS'] == f]['NAME'].iloc[0] + '<br>' +
334-
'FIPS: ' + str(f) + '<br> Value: ' + str(values[index])
340+
'County: ' + df[df['FIPS'] == f]['COUNTY_NAME'].iloc[0] + '<br>' +
341+
'State: ' + df[df['FIPS'] == f]['STATE_NAME'].iloc[0] + '<br>' +
342+
'FIPS: ' + str(f) + '<br>Value: ' + str(values[index])
335343
)
336344
t_c = [text for poly in fips_polygon_map[f]]
337345
x_centroids = x_c + x_centroids
@@ -344,12 +352,12 @@ def _calculations(df, fips, values, index, f, simplify_county, level,
344352
return x_traces, y_traces, x_centroids, y_centroids, centroid_text
345353

346354

347-
def create_choropleth(fips, values, scope=['usa'], endpts=None,
355+
def create_choropleth(fips, values, scope=['usa'], binning_endpoints=None,
348356
colorscale=None, order=None, simplify_county=0.02,
349357
simplify_state=0.02, asp=None, offline_mode=False,
350-
show_hover=True, show_statedata=True,
358+
show_hover=True, show_state_data=True,
351359
state_outline=None, county_outline=None,
352-
centroid_marker=None, round_leg=False,
360+
centroid_marker=None, round_legend_values=False,
353361
exponent_format=False, legend_title='', df=df,
354362
df_state=df_state, **layout_options):
355363
"""
@@ -368,15 +376,15 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
368376
'United States Virgin Islands'. These must be added manually to the
369377
list.
370378
Default = ['usa']
371-
:param (list) endpts: ascending numbers which implicitly define real
372-
number intervals which are used as bins. The colorscale used must have
373-
the same number of colors as the number of bins and this will result
374-
in a categorical colormap.
379+
:param (list) binning_endpoints: ascending numbers which implicitly define
380+
real number intervals which are used as bins. The colorscale used must
381+
have the same number of colors as the number of bins and this will
382+
result in a categorical colormap.
375383
:param (list) colorscale: a list of colors with length equal to the
376384
number of categories of colors. The length must match either all
377385
unique numbers in the 'values' list or if endpoints is being used, the
378386
number of categories created by the endpoints.\n
379-
For example, if endpts = [4, 6, 8], then there are 4 bins:
387+
For example, if binning_endpoints = [4, 6, 8], then there are 4 bins:
380388
[-inf, 4), [4, 6), [6, 8), [8, inf)
381389
:param (list) order: a list of the unique categories (numbers/bins) in any
382390
desired order. This is helpful if you want to order string values to
@@ -400,7 +408,7 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
400408
yet part of the plotly.py python library. Stay tuned for updates.
401409
Default = False
402410
:param (bool) show_hover: show county hover and centroid info
403-
:param (bool) show_statedata: reveals state boundary lines
411+
:param (bool) show_state_data: reveals state boundary lines
404412
:param (dict) state_outline: dict of attributes of the state outline
405413
including width and color. See
406414
https://plot.ly/python/reference/#scatter-marker-line for all valid
@@ -412,8 +420,8 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
412420
:param (dict) centroid_marker: dict of attributes of the centroid marker.
413421
See https://plot.ly/python/reference/#scatter-marker for all valid
414422
params
415-
:param (bool) round_leg: automatically round the numbers that appear in
416-
the legend to the nearest integer.
423+
:param (bool) round_legend_values: automatically round the numbers that
424+
appear in the legend to the nearest integer.
417425
Default = False
418426
:param (bool) exponent_format: if set to True, puts numbers in the K, M,
419427
B number format. For example 4000.0 becomes 4.0K
@@ -438,15 +446,16 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
438446
values = df_sample_r['TOT_POP'].tolist()
439447
fips = df_sample_r['FIPS'].tolist()
440448
441-
endpts = list(np.mgrid[min(values):max(values):4j])
449+
binning_endpoints = list(np.mgrid[min(values):max(values):4j])
442450
colorscale = ["#030512","#1d1d3b","#323268","#3d4b94","#3e6ab0",
443451
"#4989bc","#60a7c7","#85c5d3","#b7e0e4","#eafcfd"]
444452
fig = ff.create_choropleth(
445-
fips=fips, values=values, scope=['Florida'], show_statedata=True,
446-
colorscale=colorscale, endpts=endpts, round_leg=True,
447-
plot_bgcolor='rgb(229,229,229)', paper_bgcolor='rgb(229,229,229)',
448-
legend_title='Florida Population', exponent_format=True,
453+
fips=fips, values=values, scope=['Florida'], show_state_data=True,
454+
colorscale=colorscale, binning_endpoints=binning_endpoints,
455+
round_legend_values=True, plot_bgcolor='rgb(229,229,229)',
456+
paper_bgcolor='rgb(229,229,229)', legend_title='Florida Population',
449457
county_outline={'color': 'rgb(255,255,255)', 'width': 0.5},
458+
exponent_format=True,
450459
)
451460
py.iplot(fig, filename='choropleth_florida')
452461
```
@@ -473,7 +482,7 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
473482
values = df_sample_r['TOT_POP'].tolist()
474483
fips = df_sample_r['FIPS'].tolist()
475484
fig = ff.create_choropleth(
476-
fips=fips, values=values, scope=NE_states, show_statedata=True
485+
fips=fips, values=values, scope=NE_states, show_state_data=True
477486
)
478487
py.iplot(fig, filename='choropleth_new_england')
479488
```
@@ -505,7 +514,7 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
505514
fig = ff.create_choropleth(
506515
fips=fips, values=values, colorscale=colorscale,
507516
scope=['CA', 'AZ', 'Nevada', 'Oregon', ' Idaho'],
508-
endpts=[14348, 63983, 134827, 426762, 2081313],
517+
binning_endpoints=[14348, 63983, 134827, 426762, 2081313],
509518
county_outline={'color': 'rgb(255,255,255)', 'width': 0.5},
510519
legend_title='California Counties',
511520
title='California and Nearby States'
@@ -534,15 +543,16 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
534543
df_sample['State FIPS Code'] + df_sample['County FIPS Code']
535544
)
536545
537-
endpts = list(np.linspace(1, 12, len(colorscale) - 1))
538-
colorscale = ["#f7fbff","#ebf3fb","#deebf7","#d2e3f3","#c6dbef","#b3d2e9",
539-
"#9ecae1", "#85bcdb","#6baed6","#57a0ce","#4292c6","#3082be",
540-
"#2171b5","#1361a9", "#08519c","#0b4083","#08306b"]
546+
binning_endpoints = list(np.linspace(1, 12, len(colorscale) - 1))
547+
colorscale = ["#f7fbff", "#ebf3fb", "#deebf7", "#d2e3f3", "#c6dbef",
548+
"#b3d2e9", "#9ecae1", "#85bcdb", "#6baed6", "#57a0ce",
549+
"#4292c6", "#3082be", "#2171b5", "#1361a9", "#08519c",
550+
"#0b4083","#08306b"]
541551
fips = df_sample['FIPS']
542552
values = df_sample['Unemployment Rate (%)']
543553
fig = ff.create_choropleth(
544554
fips=fips, values=values, scope=['usa'],
545-
endpts=endpts, colorscale=colorscale,
555+
binning_endpoints=binning_endpoints, colorscale=colorscale,
546556
show_hover=True, centroid_marker={'opacity': 0},
547557
asp=2.9, title='USA by Unemployment %',
548558
legend_title='Unemployment %'
@@ -581,9 +591,10 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
581591
# make fips numeric
582592
fips = map(lambda x: int(x), fips)
583593

584-
if endpts:
585-
intervals = utils.endpts_to_intervals(endpts)
586-
LEVELS = _intervals_as_labels(intervals, round_leg, exponent_format)
594+
if binning_endpoints:
595+
intervals = utils.endpts_to_intervals(b 10000 inning_endpoints)
596+
LEVELS = _intervals_as_labels(intervals, round_legend_values,
597+
exponent_format)
587598
else:
588599
if not order:
589600
LEVELS = sorted(list(set(values)))
@@ -646,8 +657,8 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
646657
raise exceptions.PlotlyError(
647658
"You have {} LEVELS. Your number of colors in 'colorscale' must "
648659
"be at least the number of LEVELS: {}. If you are "
649-
"using 'endpts' then 'colorscale' must have at "
650-
"least len(endpts) + 2 colors".format(
660+
"using 'binning_endpoints' then 'colorscale' must have at "
661+
"least len(binning_endpoints) + 2 colors".format(
651662
len(LEVELS), min(LEVELS, LEVELS[:20])
652663
)
653664
)
@@ -668,7 +679,7 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
668679
'American Samoa']
669680
for state in scope:
670681
if state.lower() == 'usa':
671-
scope_names = df['NAME'].unique()
682+
scope_names = df['STATE_NAME'].unique()
672683
scope_names = list(scope_names)
673684
for ex_st in extra_states:
674685
try:
@@ -679,14 +690,14 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
679690
if state in st_to_state_name_dict.keys():
680691
state = st_to_state_name_dict[state]
681692
scope_names.append(state)
682-
df_state = df_state[df_state['NAME'].isin(scope_names)]
693+
df_state = df_state[df_state['STATE_NAME'].isin(scope_names)]
683694

684695
plot_data = []
685696
x_centroids = []
686697
y_centroids = []
687698
centroid_text = []
688699
fips_not_in_shapefile = []
689-
if not endpts:
700+
if not binning_endpoints:
690701
for index, f in enumerate(fips):
691702
level = values[index]
692703
try:
@@ -695,7 +706,8 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
695706
(x_traces, y_traces, x_centroids,
696707
y_centroids, centroid_text) = _calculations(
 57AE
697708
df, fips, values, index, f, simplify_county, level,
698-
x_centroids, y_centroids, centroid_text, x_traces, y_traces
709+
x_centroids, y_centroids, centroid_text, x_traces,
710+
y_traces
699711
)
700712
except KeyError:
701713
fips_not_in_shapefile.append(f)
@@ -713,7 +725,8 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
713725
(x_traces, y_traces, x_centroids,
714726
y_centroids, centroid_text) = _calculations(
715727
df, fips, values, index, f, simplify_county, level,
716-
x_centroids, y_centroids, centroid_text, x_traces, y_traces
728+
x_centroids, y_centroids, centroid_text, x_traces,
729+
y_traces
717730
)
718731
except KeyError:
719732
fips_not_in_shapefile.append(f)
@@ -790,7 +803,7 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
790803
hover_points.update(centroids_on_select)
791804
plot_data.append(hover_points)
792805

793-
if show_statedata:
806+
if show_state_data:
794807
state_data = dict(
795808
type='scatter',
796809
legendgroup='States',
@@ -880,7 +893,9 @@ def create_choropleth(fips, values, scope=['usa'], endpts=None,
880893

881894
# aspect ratio
882895
if asp is None:
883-
asp = (USA_XRANGE[1] - USA_XRANGE[0]) / (USA_YRANGE[1] - USA_YRANGE[0])
896+
usa_x_range = USA_XRANGE[1] - USA_XRANGE[0]
897+
usa_y_range = USA_YRANGE[1] - USA_YRANGE[0]
898+
asp = usa_x_range / usa_y_range
884899

885900
# based on your figure
886901
width = float(fig['layout']['xaxis']['range'][1] -

‎plotly/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
__version__ = '2.3.1'
1+
__version__ = '2.4.0'

0 commit comments

Comments
 (0)
0