Setup
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
#chart_studio.tools.set_credentials_file(username='econdata777', api_key='ADDhere')
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
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%
20
log_GDPpc
Trend (HP400) of log of GDP per capita
21
log_lp
Trend (HP400) of log of labor productivity
22
log_ky
Trend (HP400) of log of Capital-Output Ratio
23
log_h
Trend (HP400) of log of Human Capital
24
log_tfp
Trend (HP400) of log of Aggregate Efficiency
25
region
Regional group (Classification of the UN)
26
hi1990
High income country (as of 1990, World Bank classification)
27
isocode
ISO code from the PWT9.0
Descriptive statistics
df1.describe().round(2)
idfloat64
yearfloat64
count
2700
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
Prepare data
select
df1.country
df2 = df1[['country', 'year', 'GDPpc', 'h', 'lp', 's', 'log_GDPpc']]
df2
countryobject
Norway0.9%
Singapore0.9%
106 others98.1%
yearint64
1990 - 2014
1718
Norway
2008
1722
Norway
2012
1721
Norway
2011
1723
Norway
2013
1724
Norway
2014
1717
Norway
2007
1716
Norway
2006
1720
Norway
2010
1715
Norway
2005
1719
Norway
2009
query
dfcj = df1[['country', 'region', 'hi1990', 'year', 'GDPpc', 'h', 's', 'lp', 'log_GDPpc']].query("country == ['China','Japan']")
dfcj
countryobject
Japan50%
China50%
regionobject
Asia100%
1249
Japan
Asia
1248
Japan
Asia
1247
Japan
Asia
1246
Japan
Asia
1245
Japan
Asia
1244
Japan
Asia
1243
Japan
Asia
1242
Japan
Asia
1241
Japan
Asia
1240
Japan
Asia
dfcj.groupby('country').s.agg(['mean', 'std', 'min', 'max']).round(2)
meanfloat64
stdfloat64
China
7.34
0.63
Japan
11
0.59
Visualize data
Strip plot
px.strip(dfcj, x = 's', hover_name= 'country', color = 'country')
#fig1 = px.strip(df_2014, x = 'GDPpc', hover_name= 'country')
#save2cs.plot(fig1, filename = 'figureName', auto_open=True)
px.strip(dfcj,
x = 'GDPpc',
y = 'country',
color= 'country')
Line plots
px.line(dfcj, x='year', y='GDPpc', color='country')
px.line(dfcj, x='year', y='s', color='country')
fig1 = px.line(df1.query("country=='Japan'"), x="year", y="log_lp")
fig1.write_html("fig1.html")
Histogram
px.histogram(dfcj, x= 's', hover_name= 'country', color = 'country')
px.histogram(
dfcj,
x="GDPpc",
color="country",
hover_name= 'country'
)
Box plot
px.box(
dfcj,
x="GDPpc",
color="country",
hover_name= 'country'
)
Violin plot
px.violin(
dfcj,
y="country",
x="s",
range_x= [6, 12],
color="country",
box=True,
hover_name= 'country',
points="all")
ECDF
px.ecdf(
dfcj,
x="s",
range_x= [6, 12],
color="country",
hover_name= 'country'
)
Scatter plots
Simple
px.scatter(
dfcj,
x="s",
y="GDPpc",
color="country",
hover_name="country"
)
Regression
px.scatter(
dfcj,
x="s",
y="GDPpc",
color="country",
hover_name="country",
hover_data= ['country'],
trendline="ols"
)
px.scatter(
dfcj,
x="s",
y="GDPpc",
hover_name="country",
color="country",
trendline="ols",
marginal_x="box",
marginal_y="box")
Customized
fig = px.scatter(df1.query("country == ['China','Japan']"),
y="GDPpc",
x="s",
log_x = False,
color = "country",
size ="GDPpc", size_max=60,
hover_name = "country",
height =500, width=800,
template = "simple_white",
color_discrete_sequence=px.colors.qualitative.G10,
#title = "Year 1990",
labels=dict(
s = "Years of Schooling",
GDPpc = "GDP Per Capita")
)
fig.update_layout(font_family = "Rockwell",
legend=dict(orientation = "h", title="", y=1.1, x=1, xanchor="right", yanchor="bottom"))
fig.add_hline(df1.query("year == 1990")['log_lp'].mean(), line_width=1, line_dash="dot")
fig.add_vline(df1.query("year == 1990")['log_h'].mean(), line_width=1, line_dash="dot")
fig.show()
px.scatter(dfcj,
animation_frame="year",
x="s",
y="log_GDPpc",
range_x= [2, 18],
range_y= [7, 14],
color="country",
size="GDPpc", size_max=30,
hover_name="country",
hover_data = ['s', 'GDPpc'],
labels=dict(s = "Years of Schooling",
GDPpc = "GDP Per Capita",
)
)
px.density_contour(
dfcj,
x="s",
y="log_GDPpc",
marginal_x="rug",
marginal_y="rug",
animation_frame="year",
color= "country"
)
3D
px.scatter_3d(
dfcj,
x="s",
y="GDPpc",
z= "log_GDPpc",
color="country",
hover_name="country"
)