Plotly express
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
Zambia0.9%
Italy0.9%
106 others98.1%
2699
108
Zambia
1199
48
Italy
1324
53
Kyrgyz Republic
1299
52
Kenya
1274
51
Kazakhstan
2649
106
Vietnam
1249
50
Japan
1224
49
Jamaica
1174
47
Israel
1374
55
Lithuania
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
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
df2 = df1[['country', 'year', 'log_GDPpc', 'log_h', 'log_ky', 'log_tfp']]
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_chn = df1[['country', 'year', 'log_GDPpc', 'log_h', 'log_ky', 'log_tfp']].query("country == 'China'")
df_chn
countryobject
China100%
yearint64
1990 - 2014
450
China
1990
451
China
1991
452
China
1992
453
China
1993
454
China
1994
455
China
1995
456
China
1996
457
China
1997
458
China
1998
459
China
1999
df1[['country', 'year','log_GDPpc', 'log_h', 'log_ky', 'log_tfp']].query("country==['China', 'India', 'Indonesia'] and year == 2008")
countryobject
yearint64
468
China
2008
1068
India
2008
1093
Indonesia
2008
df1[['country', 'year','log_GDPpc', 'log_h', 'log_ky', 'log_tfp']].query("country==['China', 'India', 'Indonesia'] and year == 2014")
countryobject
yearint64
474
China
2014
1074
India
2014
1099
Indonesia
2014
# Define the logical condictions
is_Asia = df1['region'] == 'Asia'
is_HighIncome = df1['hi1990'] == 'yes'
is_1990 = df1['year'] == 1990
# Apply the logical conditions
df1[is_Asia & is_HighIncome & is_1990]
idint64
countryobject
1000
41
Hong Kong
1150
47
Israel
1225
50
Japan
1975
80
Saudi Arabia
2050
83
Singapore
2300
93
Taiwan
groupby
df_2014.groupby('region').mean().round(2)
yearfloat64
log_GDPpcfloat64
Africa
2014
7.85
Americas
2014
9.37
Asia
2014
9.37
Europe
2014
10.34
Oceania
2014
10.58
df_2014.groupby('region').std().round(2)
yearfloat64
log_GDPpcfloat64
Africa
0
0.9
Americas
0
0.77
Asia
0
0.99
Europe
0
0.46
Oceania
0
0.23
#df_2014.groupby('region')['log_GDPpc'].agg(['mean', 'std', 'min', 'max']).round(2)
df_2014.groupby('region').log_GDPpc.agg(['mean', 'std', 'min', 'max']).round(2)
meanfloat64
stdfloat64
Africa
7.85
0.9
Americas
9.37
0.77
Asia
9.37
0.99
Europe
10.34
0.46
Oceania
10.58
0.23
df1.groupby('year').s.agg(['mean', 'std', 'min', 'max']).round(2)
meanfloat64
6.5 - 8.81
stdfloat64
2.9 - 3.01
1990
6.5
2.9
1991
6.6
2.91
1992
6.71
2.92
1993
6.81
2.93
1994
6.92
2.95
1995
7.02
2.96
1996
7.11
2.96
1997
7.2
2.96
1998
7.29
2.96
1999
7.38
2.96
pivot_table
df1_gdppc_wide = df1.pivot_table(
index = ['country','region','hi1990'],
columns = 'year',
values = 'log_GDPpc').reset_index(drop=False)
# Make sure the column names are strings
df1_gdppc_wide.columns = df1_gdppc_wide.columns.astype(str)
df1_gdppc_wide
countryobject
Albania0.9%
Algeria0.9%
106 others98.1%
regionobject
Europe27.8%
Asia25.9%
3 others46.3%
0
Albania
Europe
1
Algeria
Africa
2
Argentina
Americas
3
Armenia
Asia
4
Australia
Oceania
5
Austria
Europe
6
Bangladesh
Asia
7
Belgium
Europe
8
Benin
Africa
9
Bolivia
Americas
df1_gdppc_wide.describe().round(2)
1990float64
1991float64
count
108
108
mean
8.54
8.56
std
1.19
1.19
min
6.16
6.2
25%
7.57
7.59
50%
8.68
8.71
75%
9.6
9.63
max
10.49
10.51
df1_gdppc_wide.std().round(2).plot();
<ipython-input-39-e24b465a3f55>:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction.
df1_gdppc_wide.std().round(2).plot();
loc
df1_gdppc_wide.loc[:,'1990':'2014']
1990float64
6.1637506 - 10.49228
1991float64
6.195724 - 10.514265
0
8.1303272
8.1708374
1
8.8438606
8.8517218
2
8.964241
9.0307903
3
8.1737623
8.1513538
4
10.187983
10.216832
5
10.117168
10.14943
6
7.249866
7.2520657
7
10.079113
10.107697
8
7.0329933
7.0541086
9
7.6487226
7.686933
df1_gdppc_wide.loc[:,'1990':'2014'].std().round(2).plot();
isin
df1[df1.country.isin(['China', 'Indonesia','India'])]
idint64
19 - 44
countryobject
China33.3%
India33.3%
Indonesia33.3%
450
19
China
451
19
China
452
19
China
453
19
China
454
19
China
455
19
China
456
19
China
457
19
China
458
19
China
459
19
China
Visualize data
Strip plot
#fig1 = px.strip(df_2014, x = 'GDPpc', hover_name= 'country')
#save2cs.plot(fig1, filename = 'figureName', auto_open=True)
px.strip(df1,
x = 'log_GDPpc',
y = 'region',
hover_name= 'country',
hover_data= ['log_h', 'log_ky'],
color= 'region',
animation_frame= 'year',
range_x = [6,12]
)
Line plots
px.line(df1, x='year', y='log_GDPpc', color='country')
px.line(df1, x='year', y='log_GDPpc', color='country', facet_col= 'region', facet_col_wrap= 2, height= 800)
px.line(df1.query("country=='China'"), x="year", y="log_GDPpc")
px.line(df1.query("country=='China'"), x="year", y="log_ky")
px.line(df1.query("country=='China'"), x="year", y="log_tfp")
px.line(df1.query("country=='China'"), x="year", y="log_h")
fig1 = px.line(df1.query("country=='China'"), x="year", y="log_GDPpc")
fig1.write_html("fig1.html")
px.line(
df1.query("country==['Indonesia', 'China','India']"),
x="year",
y="log_GDPpc",
color="country"
)
px.line(
df1.query("region=='Asia'"),
x="year",
y="log_GDPpc",
color="country"
)
Box plot
px.box(
df1,
x="log_GDPpc",
color="hi1990",
hover_name= 'country',
animation_frame = 'year'
)
ECDF
px.ecdf(
df1.query('region== "Asia"'),
x="log_GDPpc",
range_x= [6, 12],
color="hi1990",
hover_name= 'country',
animation_frame = 'year',
)
Sunburst plot
px.sunburst(df1.query("year == 2008"), color = "log_GDPpc", values = "pop", path = ["region", "country"], hover_name = "country")
px.sunburst(df1.query("year == 2014"), color = "log_GDPpc", values = "pop", path = ["region", "country"], hover_name = "country")
Scatter plots
Regression by groups
px.scatter(
df1,
x="log_tfp",
y="log_GDPpc",
color="hi1990",
hover_name="country",
animation_frame = 'year',
trendline="ols",
range_x = [4,9],
range_y = [6,11.5])
px.scatter(
df1,
x="log_ky",
y="log_GDPpc",
color="hi1990",
hover_name="country",
animation_frame = 'year',
trendline="ols",
range_x = [-2,2.5],
range_y = [6,11.5])
px.scatter(
df1,
x="log_h",
y="log_GDPpc",
color="hi1990",
hover_name="country",
animation_frame = 'year',
trendline="ols")
Margins
px.scatter(
df1,
x="log_tfp",
y="log_GDPpc",
hover_name="country",
color="hi1990",
trendline="ols",
marginal_x="box",
marginal_y="box",
animation_frame = 'year',
range_x = [4,9],
range_y = [6,11.5])
Lowess regression
px.scatter(
df1,
x="log_tfp",
y="log_GDPpc",
color="hi1990",
hover_name="country",
animation_frame = 'year',
trendline="lowess",
range_x = [4,9],
range_y = [6,11.5])
Multivariate
px.scatter(
df1.query("year == 2008"),
x="log_tfp",
y="log_GDPpc",
color="region",
size="pop", size_max=60,
hover_name="country",
labels=dict(log_tfp="Total factor productivity in 2008 (in logs)",
log_GDPpc="GDP per capita in 2008 (in logs)",
region="Continent",
pop= "Population")
)
Customized
fig = px.scatter(df1.query("year == 2008"),
y="log_GDPpc",
x="log_tfp",
log_x = False,
color = "region",
size ="pop", 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(region = "Continent",
pop = "Population",
log_GDPpc = "GDP per capita (in logs)",
log_tfp = "Total factor productivity (in logs)")
)
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 == 2008")['log_GDPpc'].mean(), line_width=1, line_dash="dot")
fig.add_vline(df1.query("year == 2008")['log_tfp'].mean(), line_width=1, line_dash="dot")
fig.show()
px.scatter(df1,
animation_frame="year",
x="log_tfp",
y="log_GDPpc",
range_x = [4,9],
range_y = [6,11.5],
color="region",
size="pop", size_max=60,
hover_name="country",
hover_data = ['log_ky', 'log_h'],
labels=dict(log_tfp="Total factor productivity (in logs)",
log_GDPpc="GDP per capita (in logs)",
region="Continent",
pop= "Population")
)
px.scatter(
df1,
x="log_tfp",
y="log_GDPpc",
color="region",
size="pop", size_max=60,
trendline="ols",
hover_name="country",
facet_col="hi1990",
animation_frame="year"
)
px.choropleth(
df1.query("year == 2008"),
locations="isocode",
color="log_GDPpc",
hover_name="country",
color_continuous_scale=px.colors.sequential.Plasma,
projection="natural earth")
px.choropleth(
df1,
locations="isocode",
color="log_GDPpc",
hover_name="country",
animation_frame="year",
color_continuous_scale=px.colors.sequential.Plasma,
projection="natural earth")