Setup

# Install libraries !pip install --upgrade pip --quiet !pip install statsmodels --quiet

import numpy as np import pandas as pd import matplotlib.pyplot as plt from matplotlib.ticker import FormatStrFormatter import seaborn as sns sns.set_style("darkgrid") sns.set_context(context="paper", font_scale=1.5, rc=None) sns.set(font="serif") import plotly.express as px import plotly.graph_objects as go import statsmodels.api as sm import statsmodels.formula.api as smf import warnings #warnings.filterwarnings('ignore')

Import data

df1 = pd.read_csv("https://raw.githubusercontent.com/quarcs-lab/mendez2020-convergence-clubs-code-data/master/assets/dat.csv") #df1 = pd.read_csv("https://raw.githubusercontent.com/quarcs-lab/mendez2020-convergence-clubs-code-data/master/assets/dat.csv", parse_dates =['year'])

df1

idint64

1 - 108

countryobject

Albania0.9%

Algeria0.9%

106 others98.1%

0

1

Albania

1

Albania

2

1

Albania

3

1

Albania

4

1

Albania

5

1

Albania

6

1

Albania

7

1

Albania

8

1

Albania

9

1

Albania

#df1.head()

df1.columns

df1.dtypes

df1['country'].unique()

Dataset definitions

# Import definitions of dataset df1_def = pd.read_csv("https://raw.githubusercontent.com/quarcs-lab/mendez2020-convergence-clubs-code-data/master//assets/dat-definitions.csv") df1_def

var_nameobject

country3.6%

year3.6%

26 others92.9%

var_defobject

Standardized country name (from PWT)3.6%

Year3.6%

26 others92.9%

0

country

Standardized country name (from PWT)

1

year

Year

2

Y

GDP

3

K

Physical Capital

4

pop

Population

5

L

Labor Force

6

s

Years of Schooling

7

alpha_it

Variable Capital Share

8

GDPpc

GDP per capita

9

lp

Labor Productivity

Descriptive statistics

df1.describe().round(2)

idfloat64

yearfloat64

count

2700

mean

54.5

2002

std

31.18

7.21

min

1

1990

25%

27.75

1996

50%

54.5

2002

75%

81.25

2008

max

108

2014

Transform data

select

df1.log_GDPpc

df2 = df1[['country', 'year', 'log_GDPpc', 'log_h']] df2

countryobject

Albania0.9%

Algeria0.9%

106 others98.1%

yearint64

1990 - 2014

0

Albania

1990

1

Albania

1991

2

Albania

1992

3

Albania

1993

4

Albania

1994

5

Albania

1995

6

Albania

1996

7

Albania

1997

8

Albania

1998

9

Albania

1999

query

df_2014 = df1[['country', 'region', 'hi1990', 'year', 'log_GDPpc', 'log_h']].query("year == 2014") df_2014

countryobject

Albania0.9%

Algeria0.9%

106 others98.1%

regionobject

Europe27.8%

Asia25.9%

3 others46.3%

24

Albania

Europe

49

Algeria

Africa

74

Argentina

Americas

99

Armenia

Asia

124

Australia

Oceania

149

Austria

Europe

174

Bangladesh

Asia

199

Belgium

Europe

224

Benin

Africa

249

Bolivia

Americas

df_indonesia = df1[['country', 'year', 'log_GDPpc', 'log_h']].query("country == 'Indonesia'") df_indonesia

countryobject

Indonesia100%

yearint64

1990 - 2014

1075

Indonesia

1990

1076

Indonesia

1991

1077

Indonesia

1992

1078

Indonesia

1993

1079

Indonesia

1994

1080

Indonesia

1995

1081

Indonesia

1996

1082

Indonesia

1997

1083

Indonesia

1998

1084

Indonesia

1999

Visualize data

Strip plot

px.strip(df_2014, x = 'log_GDPpc', hover_name= 'country', color= 'region')

Line plots

px.line(df1.query("country == 'Indonesia'"), x='year', y='log_GDPpc', color='country')

fig1 = px.line(df1.query("country=='Indonesia'"), x="year", y="log_GDPpc") fig1.write_html("fig1.html")

px.line(df1, x='year', y='log_GDPpc', color='country', facet_col= 'region')

Box plot

px.box( df1.query("year == 2014"), x="log_GDPpc", color="hi1990", hover_name= 'country' )

px.box( df1, x="log_h", color="hi1990", hover_name= 'country', animation_frame = 'year' )

Scatter plots

Simple

px.scatter( df1.query("year == 1990"), x="log_GDPpc", y="log_h", color="region", hover_name="country" )

Regression

px.scatter( df1.query("year == 1990"), x="log_GDPpc", y="log_h", color="hi1990", hover_name="country", trendline="ols")

px.scatter( df1.query("year == 1990"), x="log_GDPpc", y="log_h", color="region", size="pop", size_max=60, hover_name="country", labels=dict(log_GDPpc="GDP per capita in 1990 (in logs)", log_H="Human capita index in 1990 (in logs)", region="Continent", pop= "Population") )

px.scatter( df1.query("year == 1990"), x="log_GDPpc", y="log_h", color="region", size="pop", size_max=60, trendline="ols", hover_name="country", facet_col="hi1990")

px.choropleth( df1, locations="isocode", color="log_h", hover_name="country", animation_frame="year", color_continuous_scale=px.colors.sequential.Plasma, projection="natural earth")

Exploring the relationship between GDPpc and Human Capital

Setup

Import data

Dataset definitions

Descriptive statistics

Transform data

select

query

Visualize data

Strip plot

Line plots

Box plot

Scatter plots

Simple

Regression

References

.css-ytumd6{-webkit-text-decoration:none;text-decoration:none;}Setup

Import data

Dataset definitions

Descriptive statistics

Transform data

select

query

Visualize data

Strip plot

Line plots

Box plot

Scatter plots

Simple

Regression

References

Setup