Motivation

Setup

#!pip install --quiet wbgapi

import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import plotly.express as px import plotly.graph_objects as go import chart_studio chart_studio.tools.set_credentials_file(username='econdata777', api_key='HERE') import chart_studio.plotly as save2cs import statsmodels.api as sm import statsmodels.formula.api as smf from scipy import stats import inequality import wbgapi as wb

WBGAPI library

Sources

wb.source.info()

wb.series.info(db = 12) # Series in the Education Statistics Database

Economies

wb.economy.info()

wb.economy.DataFrame()

nameobject

Aruba0.4%

Africa Eastern and Southern0.4%

264 others99.2%

aggregateobject

False81.6%

True18.4%

BGD

Bangladesh

False

BGR

Bulgaria

False

BHR

Bahrain

False

BHS

Bahamas, The

False

BIH

Bosnia and Herzegovina

False

BLR

Belarus

False

BLZ

Belize

False

BMU

Bermuda

False

BOL

Bolivia

False

BRA

Brazil

False

wb.economy.info(wb.income.members('HIC')) # high-income economies

Regions

wb.region.info()

# population for African countries, every other year wb.data.DataFrame('SP.POP.TOTL', wb.region.members('AFR'), range(2010, 2020, 2))

YR2010float64

89770.0 - 158503203.0

YR2012float64

88303.0 - 167228803.0

AGO

23356247

25107925

BDI

8675606

9245992

BEN

9199254

9729254

BFA

15605211

16571252

BWA

1987106

2039551

CAF

4386765

4436411

CIV

20532944

21547188

CMR

20341236

21485267

COD

64563853

69020749

COG

4273738

4510197

COM

689696

723865

CPV

492644

505241

DJI

840194

868136

DZA

35977451

37383899

EGY

82761244

86422240

ERI

3170437

nan

ETH

87639962

92726982

GAB

1624146

1749677

GHA

24779614

25996454

GIN

10192168

10652032

GMB

1793199

1905020

GNB

1522603

1604981

GNQ

943640

1031191

KEN

42030684

44343469

LBR

3891357

4135662

LBY

6197667

6285751

LSO

1995575

2014988

MAR

32343384

33241898

MDG

21151640

22346641

MLI

15049352

15979492

MOZ

23531567

24862673

MRT

3494200

3706555

MUS

1250400

1255882

MWI

14539609

15396010

NAM

2118877

2194777

NER

16464025

17795209

NGA

158503203

167228803

RWA

10039338

10549668

SDN

34545014

36193781

SEN

12678143

13401990

SLE

6415636

6712586

SOM

12043886

12715487

SSD

9508372

10113648

STP

180372

188394

SWZ

1064841

1079285

SYC

89770

88303

TCD

11952134

12784748

TGO

6421674

6773807

TUN

10635245

10846993

TZA

44346532

47053033

UGA

32428164

34558700

ZAF

51216967

52832659

ZMB

13605986

14465148

ZWE

12697728

13115149

Income groups

wb.income.info()

Topics

wb.topic.info()

Series

wb.series.info() # WDI by default

wb.series.info(db = 6) # Series in the Debt Statistics database

wb.series.info(topic = 3) # Series in the topic Economy & Growth

Search series

#Not working #wb.series.info(q='gdp')

Metadata of series

wb.series.metadata.get('NY.GNS.ICTR.GN.ZS')

wb.series.metadata.get('NY.GDP.PCAP.PP.KD')

Import data

Function DataFrame

help(wb.data.DataFrame)

Help on function DataFrame in module wbgapi.data:

DataFrame(series, economy='all', time='all', index=None, columns=None, mrv=None, mrnev=None, skipBlanks=False, labels=False, skipAggs=False, numericTimeKeys=False, timeColumns=False, params={}, db=None, **dimensions)
    Retrieve a 2-dimensional pandas dataframe. 
    
    Arguments:
        series:             a series identifier or list-like, e.g., SP.POP.TOTL
    
        economy:            an economy identifier or list-like, e.g., 'BRA' or ['USA', 'CAN', 'MEX']
    
        time:               a time identifier or list-like, e.g., 'YR2015' or range(2010,2020).
                            Both element keys and values are acceptable
    
        index:              name or list of dimensions for the DataFrame's index, e.g., 'economy'. If None then the function
                            will define the index based on your request. Note: to get a dataframe with no index
                            (i.e., 0-based integers) call `reset_index()` with on the return value of this function.
    
        columns:            name of the dimension for the DataFrame's columns, e.g., 'series'. If None then the function
                            will define columns based on your request.
    
        mrv:                return only the specified number of most recent values (same time period for all economies)
    
        mrnev:              return only the specified number of non-empty most recent values (time period varies)
    
        skipBlanks:         skip empty observations
    
        labels:             include the dimension name for rows
    
        skipAggs:           skip aggregates
    
        numericTimeKeys:    store the time object by value (e.g., 2014) instead of key ('YR2014') if value is numeric
    
        timeColumns:        add extra columns to show the time dimension for each series/economy
                            If 'auto' then the function will guess based on other parameters
    
        params:             extra query parameters to pass to the API
    
        dimensions:         extra dimensions, database specific (e.g., version)
        
    Returns:
        a pandas DataFrame
    
    Examples:
        # 5 years of population data (with economy names)
        wbgapi.data.DataFrame('SP.POP.TOTL, time=range(2010,2020),labels=True)
    
        # Most recent poverty and income data for LAC
        wbgapi.data.DataFrame(['SI.POV.NAHC', 'NY.GDP.PCAP.CD'], economy=wb.region.members('LAC'),mrnev=1,timeColumns=True)
    
        # Fetch most recent CO2 emissions for each country and merge its income group
        wbgapi.data.DataFrame('EN.ATM.CO2E.PC',mrnev=1).join(wbgapi.economy.DataFrame()['incomeLevel'])
    
        # Top 10 emitters per capita
        wbgapi.data.DataFrame('EN.ATM.CO2E.PC',mrnev=1,labels=True).sort_values('EN.ATM.CO2E.PC',ascending=False).head(10)
    
    Notes:
        timeColumns currently defaults to False so that the default column composition is consistent. This may change to 'auto'
        at some point, so that mrv behavior is more intuitive for data discovery

# 5 years of population data (with economy names) from 2010 to 2014 wb.data.DataFrame('SP.POP.TOTL', time=range(2010,2015), labels=True)

Countryobject

Zimbabwe0.4%

Zambia0.4%

264 others99.2%

YR2010float64

10009.0 - 6921854591.0

ZWE

Zimbabwe

12697728

ZMB

Zambia

13605986

YEM

Yemen, Rep.

23154854

PSE

West Bank and Gaza

3786161

VIR

Virgin Islands (U.S.)

108357

VNM

Vietnam

87967655

VEN

Venezuela, RB

28439942

VUT

Vanuatu

236216

UZB

Uzbekistan

28562400

URY

Uruguay

3359273

# Most recent poverty and income data for Latin American countries (LAC) wb.data.DataFrame(['SI.POV.NAHC', 'NY.GDP.PCAP.CD'], economy = wb.region.members('LAC'), mrnev = 1, # Most recent non-empty most values (time period varies) timeColumns = True, # Show the time dimension for each series/economy labels = True )

Countryobject

Colombia4%

Bolivia4%

23 others92%

NY.GDP.PCAP.CDfloat64

1272.36799204205 - 12509.8352901414

COL

Colombia

5334.556042

BOL

Bolivia

3133.099803

NIC

Nicaragua

1905.261152

PAN

Panama

12509.83529

SLV

El Salvador

3798.636521

ARG

Argentina

8579.017773

ECU

Ecuador

5600.389615

PER

Peru

6126.87454

MEX

Mexico

8329.271313

JAM

Jamaica

4664.530242

wb.series.metadata.get('SI.POV.NAHC') # Note: National poverty rates lines are not necessarily comparable across contries

wb.series.metadata.get('EN.ATM.CO2E.PC')

# Most recent CO2 emissions per capita for each country and merge its income group wb.data.DataFrame('EN.ATM.CO2E.PC', mrnev=1, labels = True).join(wb.economy.DataFrame()['incomeLevel'])

Countryobject

Africa Eastern and Southern0.4%

Africa Western and Central0.4%

237 others99.2%

EN.ATM.CO2E.PCfloat64

0.0261692628875174 - 32.4156391708326

AFE

Africa Eastern and Southern

0.9335412011

AFW

Africa Western and Central

0.515544239

ARB

Arab World

4.438715965

CSS

Caribbean small states

5.017034408

CEB

Central Europe and the Baltics

6.597232486

EAR

Early-demographic dividend

2.27814572

EAS

East Asia & Pacific

6.333951297

EAP

East Asia & Pacific (excluding high income)

5.692966704

TEA

East Asia & Pacific (IDA & IBRD countries)

5.754705895

EMU

Euro area

6.454837567

# Top 10 emitters per capita wb.data.DataFrame('EN.ATM.CO2E.PC',mrnev=1,labels=True).sort_values('EN.ATM.CO2E.PC',ascending=False).head(10)

Countryobject

Qatar10%

Kuwait10%

8 others80%

EN.ATM.CO2E.PCfloat64

15.2708795551588 - 32.4156391708326

QAT

Qatar

32.41563917

KWT

Kuwait

21.62272431

ARE

United Arab Emirates

20.7974984

BHR

Bahrain

19.59297584

BRN

Brunei Darussalam

16.64490862

PLW

Palau

16.19116744

CAN

Canada

15.49706457

AUS

Australia

15.47551649

LUX

Luxembourg

15.33020808

NAC

North America

15.27087956

Long and wide panel data

# Import GDP per capita (PPP Constant international $) GDPpc_long = wb.data.DataFrame(['NY.GDP.PCAP.PP.CD'], time=range(2000, 2021), labels=True, skipAggs=True, skipBlanks=True, columns='series').reset_index() GDPpc_long

economyobject

AGO0.5%

ALB0.5%

196 others99%

timeobject

YR20114.8%

YR20134.8%

19 others90.3%

10

ABW

YR2010

11

ABW

YR2011

12

ABW

YR2012

13

ABW

YR2013

14

ABW

YR2014

15

ABW

YR2015

16

ABW

YR2016

17

ABW

YR2017

18

AFG

YR2002

19

AFG

YR2003

# Rearrange data in wide form and drop countries for which data for all years are not available GDPpc_wide = pd.pivot_table(GDPpc_long, values='NY.GDP.PCAP.PP.CD', index = 'economy', columns='time').dropna() GDPpc_wide

YR2000float64

447.082160419758 - 98365.1573861082

YR2001float64

435.076432921769 - 99035.2578440416

AGO

3289.409549

3389.196967

ALB

3860.804627

4299.546493

ARE

98365.15739

96724.06511

ARG

11618.79323

11226.87975

ARM

2658.344322

2995.908846

ATG

16843.12161

16173.32622

AUS

26343.0767

27439.82779

AUT

29376.01974

29702.79753

AZE

3385.512727

3772.943783

BDI

527.0808747

537.3594612

wb.data.DataFrame('NY.GDP.PCAP.CD', wb.region.members('EMU'), time=range(1960, 2020))

YR1960float64

360.499298506858 - 2242.0158166161

YR1961float64

382.729946994368 - 2222.36636636277

AUT

935.4604269

1031.815004

BEL

1273.691659

1350.197673

CYP

nan

DEU

nan

ESP

396.3922533

450.0532892

EST

nan

FIN

1179.353011

1327.427224

FRA

1334.689512

1428.046001

GRC

520.3227443

590.7800548

IRL

685.6147124

739.2764064

wb.data.DataFrame('NY.GDP.PCAP.CD', wb.region.members('EMU'), time=range(1960, 2020)).dropna()

YR1960float64

360.499298506858 - 2242.0158166161

YR1961float64

382.729946994368 - 2222.36636636277

AUT

935.4604269

1031.815004

BEL

1273.691659

1350.197673

ESP

396.3922533

450.0532892

FIN

1179.353011

1327.427224

FRA

1334.689512

1428.046001

GRC

520.3227443

590.7800548

IRL

685.6147124

739.2764064

ITA

804.4926233

887.3367446

LUX

2242.015817

2222.366366

NLD

1068.784587

1159.392357

ren = wb.data.DataFrame('EG.ELC.RNEW.ZS', ['DEU','FRA','ESP','GBR','USA'], time=range(2000,2016,5)) ren

YR2000float64

YR2005float64

DEU

6.198531223

10.15021111

ESP

15.61372617

14.60139232

FRA

12.96787647

9.860646697

GBR

2.663105175

4.283481612

USA

8.205996942

8.578465534

Countries and regions

regionalIndentifiers = wb.economy.DataFrame(skipAggs=True).reset_index() regionalIndentifiers

indexobject

ABW0.5%

AFG0.5%

215 others99.1%

nameobject

Aruba0.5%

Afghanistan0.5%

215 others99.1%

0

ABW

Aruba

1

AFG

Afghanistan

2

AGO

Angola

3

ALB

Albania

4

AND

Andorra

5

ARE

United Arab Emirates

6

ARG

Argentina

7

ARM

Armenia

8

ASM

American Samoa

9

ATG

Antigua and Barbuda

Merge datasets

# Merge regional intifiers with long-form panel data (merge one to many) GDPpc_longWITHri = pd.merge(GDPpc_long, regionalIndentifiers, how="left", left_on= "economy", right_on= "index") GDPpc_longWITHri

economyobject

AGO0.5%

ALB0.5%

196 others99%

timeobject

YR20114.8%

YR20134.8%

19 others90.3%

0

ABW

YR2000

1

ABW

YR2001

2

ABW

YR2002

3

ABW

YR2003

4

ABW

YR2004

5

ABW

YR2005

6

ABW

YR2006

7

ABW

YR2007

8

ABW

YR2008

9

ABW

YR2009

px.line(GDPpc_longWITHri, x= 'Time', y= 'NY.GDP.PCAP.PP.CD', #log_y= True, color='Country', #facet_col = 'incomeLevel', #facet_col_wrap= 2, labels={'NY.GDP.PCAP.PP.CD': 'GDP per capita'} )

px.line(GDPpc_longWITHri, x= 'Time', y= 'NY.GDP.PCAP.PP.CD', log_y= True, color='Country', facet_col = 'incomeLevel', facet_col_wrap= 2, labels={'NY.GDP.PCAP.PP.CD': 'GDP per capita'} )

# Save to Chart Studio figPlotly20220520 = px.line(GDPpc_longWITHri, x= 'Time', y= 'NY.GDP.PCAP.PP.CD', log_y= True, color='Country', facet_col = 'incomeLevel', facet_col_wrap= 2, labels={'NY.GDP.PCAP.PP.CD': 'GDP per capita'} ) #save2cs.plot(figPlotly20220520, filename = 'figPlotly20220520', auto_open=True)

Visualize data

wb.series.metadata.get('EG.ELC.RNEW.ZS')

Bar plots

wb.data.DataFrame('EG.ELC.RNEW.ZS', ['DEU','FRA','ESP','GBR','USA'], time=range(2000,2016,5)).plot.bar();

Line plots

wb.data.DataFrame('EG.ELC.RNEW.ZS', ['DEU','FRA','ESP','GBR','USA'], time=range(2000,2016,5)).T.plot();

df8 = wb.data.DataFrame('EG.ELC.RNEW.ZS', ['DEU','FRA','ESP','GBR','USA'], time=range(2000, 2016, 5), numericTimeKeys = True).T.reset_index() df8

indexint64

DEUfloat64

0

2000

6.198531223

1

2005

10.15021111

2

2010

16.72707367

3

2015

29.23177012

px.line(df8, x= 'index', y= ['DEU','FRA','ESP','GBR','USA'], labels=dict(index = '', value = 'Renewable electricity share', variable = 'Country') )

wb.series.metadata.get('NY.GDP.PCAP.CD')

# What about this other indicator? wb.series.metadata.get('NY.GDP.PCAP.PP.KD')

#Basic chart of income growth for countries in the South Asia region wb.data.DataFrame('NY.GDP.PCAP.PP.KD', economy = wb.region.members('SAS'), time = range(2000, 2021), numericTimeKeys = True, labels = True).set_index('Country').transpose().plot(title='GDP per capita in South Asia');

wb.data.DataFrame('NY.GDP.PCAP.PP.KD', economy = wb.region.members('SAS'), time = range(2000, 2016), numericTimeKeys = True, labels = True)

Countryobject

2000float64

IND

India

2578.59153

BTN

Bhutan

4061.499026

AFG

Afghanistan

nan

PAK

Pakistan

3245.378342

MDV

Maldives

13358.06556

NPL

Nepal

2077.652056

LKA

Sri Lanka

5949.970029

BGD

Bangladesh

1937.729192

# Import GDP per capita (PPP Constant international $) GDPpc_long_SAS = wb.data.DataFrame(['NY.GDP.PCAP.PP.KD'], economy = wb.region.members('SAS'), time=range(2000, 2021), labels=True, skipAggs=True, #skipBlanks=True, columns='series').reset_index().sort_values(['economy', 'Time']) GDPpc_long_SAS

economyobject

AFG12.5%

BGD12.5%

6 others75%

timeobject

YR20004.8%

YR20014.8%

19 others90.5%

0

AFG

YR2000

1

AFG

YR2001

2

AFG

YR2002

3

AFG

YR2003

4

AFG

YR2004

5

AFG

YR2005

6

AFG

YR2006

7

AFG

YR2007

8

AFG

YR2008

9

AFG

YR2009

px.line(GDPpc_long_SAS, x= 'Time', y= 'NY.GDP.PCAP.PP.KD', color='Country', labels={"NY.GDP.PCAP.PP.KD": "GDP per capita"} )

Scatter plots

# Import GDP per capita and secondary school enrollment df2017_2019 = wb.data.DataFrame(['NY.GDP.PCAP.PP.KD', 'SE.SEC.NENR'], time=range(2017, 2019), labels=True, skipAggs=True, skipBlanks=True, columns='series').reset_index() df2017_2019

economyobject

AFG0.5%

AGO0.5%

198 others99%

timeobject

YR201750.6%

YR201849.4%

0

ABW

YR2017

1

AFG

YR2017

2

AFG

YR2018

3

AGO

YR2017

4

AGO

YR2018

5

ALB

YR2017

6

ALB

YR2018

7

ARE

YR2017

8

ARE

YR2018

9

ARG

YR2017

px.scatter(df2017_2019.query("Time == '2017'"), x="SE.SEC.NENR", y="NY.GDP.PCAP.PP.KD", log_y = True, # log scale for the y axis trendline="ols", trendline_options=dict(log_y=True), #color="region", #size="pop", size_max=60, hover_name="Country", labels={"SE.SEC.NENR": "School enrollment, secondary (% net)", "NY.GDP.PCAP.PP.KD": "GDP per capita" } )

Maps

px.choropleth( df2017_2019.query("Time == '2017'"), locations = "economy", color = "NY.GDP.PCAP.PP.KD", hover_name = "Country", color_continuous_scale = px.colors.sequential.Plasma, projection = "natural earth", labels = {"NY.GDP.PCAP.PP.KD": "GDP per capita"} )

Cross-country inequality

GDPpc_wide = wb.data.DataFrame('NY.GDP.PCAP.KD', wb.region.members('WLD'), skipAggs=True, time=range(1970, 2021)).dropna() GDPpc_wide

YR1970float64

154.536978708365 - 75168.6790435862

YR1971float64

157.828325139823 - 78318.2611389014

AND

35391.0736

35159.46658

ARG

9243.256579

9613.676881

AUS

26894.50648

27040.51029

AUT

18101.99195

18943.18115

BDI

352.6487174

357.107685

BEL

17849.49471

18527.14874

BEN

758.3926365

730.9189297

BFA

276.4799815

275.5480694

BGD

512.1211627

474.4632052

BHS

28557.29298

28267.75498

cv = GDPpc_wide.apply(stats.variation, axis = 0)

def gini_by_col(column): return inequality.gini.Gini(column.values).g

gini = GDPpc_wide.apply(gini_by_col, axis=0)

def theil_by_col(column): return inequality.theil.Theil(column.values).T

theil = GDPpc_wide.apply(theil_by_col, axis=0)

df = pd.DataFrame({'cv': cv, 'gini': gini, 'theil': theil}) df.round(2)

cvfloat64

1.52 - 1.62

ginifloat64

0.66 - 0.69

YR1970

1.61

0.67

YR1971

1.61

0.67

YR1972

1.6

0.67

YR1973

1.6

0.67

YR1974

1.6

0.67

YR1975

1.59

0.66

YR1976

1.59

0.66

YR1977

1.6

0.66

YR1978

1.6

0.66

YR1979

1.59

0.66

px.line(df, x=df.index, y="gini")

px.line(df, x=df.index, y="cv")

px.line(df, x=df.index, y= 'theil')

px.line(df, x=df.index, y= ['theil','gini'])

World evolution

df = GDPpc_wide.apply(np.mean, axis = 0)

px.line(df, x=df.index, y= df.values, )

Motivation

Setup

WBGAPI library

Sources

Economies

Regions

Income groups

Topics

Series

Search series

Metadata of series

Import data

Function DataFrame

Long and wide panel data

Countries and regions

Merge datasets

Visualize data

Bar plots

Line plots

Scatter plots

Maps

Cross-country inequality

World evolution

References