Homework2

Set up

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 statsmodels.api as sm import statsmodels.formula.api as smf

Import data

df = pd.read_csv("https://raw.githubusercontent.com/quarcs-lab/mendez2020-convergence-clubs-code-data/master/assets/dat.csv") df

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

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

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

Transform and subset data

df2014 = df.query("year == 2014") df2014

idint64

1 - 108

countryobject

Albania0.9%

Algeria0.9%

106 others98.1%

24

1

Albania

49

2

Algeria

74

3

Argentina

99

4

Armenia

124

5

Australia

149

6

Austria

174

7

Bangladesh

199

8

Belgium

224

9

Benin

249

10

Bolivia

Describe data

df2014.describe()

idfloat64

yearfloat64

count

108

mean

54.5

2014

std

31.32091953

0

min

1

2014

25%

27.75

2014

50%

54.5

2014

75%

81.25

2014

max

108

2014

Analyze one numerical variable

df2014['log_lp'].describe()

df2014['log_lp'].describe().round(2)

px.strip(df2014, x = 'log_lp', hover_name= 'country')

px.histogram(df2014, x = 'log_lp', hover_name= 'country')

px.box(df2014, x = 'log_lp', hover_name= 'country')

Analyze two numerical variables

px.scatter(df2014, x = 'log_lp', y = 'log_GDPpc', hover_name= 'country')

px.scatter(df2014, x = 'log_lp', y = 'log_GDPpc', hover_name= 'country', trendline= 'ols')

Analyze one categorical variable

px.bar(df2014, x = 'hi1990')

Analyze two categorical variables

px.bar(df2014, x = 'hi1990', color= 'region')

Analyze one categorical variable and one numeric variable

px.box(df2014, x = 'log_lp', y = 'hi1990') #px.box(df2014, x = 'log_lp', y = 'hi1990', labels=dict(lp = 'Labor Productivity', hi1990 = 'Is it a developed country?'))

fig = px.histogram(df2014, #dataframe x = 's', #x-values column color = 'hi1990', #column shown by color marginal = 'rug', #plot type (eg box,rug) hover_data = df2014.columns #extra info in hover ) fig.show()

px.box(df2014, x = 'log_lp', y = 'region')

Analyze two numerical variables and one categorical variable

px.scatter(df2014, x = 'log_lp', y = 'log_GDPpc', hover_name= 'country', trendline= 'ols', color = 'hi1990')

Gapminder dataset

gapminder = px.data.gapminder() gapminder

countryobject

Afghanistan0.7%

Albania0.7%

140 others98.6%

continentobject

Africa36.6%

Asia23.2%

3 others40.1%

0

Afghanistan

Asia

1

Afghanistan

Asia

2

Afghanistan

Asia

3

Afghanistan

Asia

4

Afghanistan

Asia

5

Afghanistan

Asia

6

Afghanistan

Asia

7

Afghanistan

Asia

8

Afghanistan

Asia

9

Afghanistan

Asia

gapminder.describe()

yearfloat64

lifeExpfloat64

count

1704

mean

1979.5

59.47443937

std

17.26532951

12.91710742

min

1952

23.599

25%

1965.75

48.198

50%

1979.5

60.7125

75%

1993.25

70.8455

max

2007

82.603

gapminder_china = gapminder.query("country=='China'") gapminder_china

countryobject

China100%

continentobject

Asia100%

288

China

Asia

289

China

Asia

290

China

Asia

291

China

Asia

292

China

Asia

293

China

Asia

294

China

Asia

295

China

Asia

296

China

Asia

297

China

Asia

fig = px.line(gapminder_china, #dataframe x = 'year', #x-values column y = 'lifeExp', #y-values column ) fig.show()

fig = px.bar(gapminder_china, #dataframe x = 'year', #x-values column y = 'pop', #y-values column hover_data = ['lifeExp', 'gdpPercap'],#extra hover info color = 'lifeExp', #column by color labels = {'pop':'population of China'}#label change ) fig.show()

fig = px.scatter_geo(gapminder, #dataframe locations = 'iso_alpha', #location code color = 'continent', #column shown by color hover_name = 'country', #hover info title size = 'gdpPercap', #column shown by size animation_frame = 'year',#column animated projection = 'orthographic'#type of map ) fig.show()

fig = px.choropleth(gapminder, #dataframe locations = 'iso_alpha', #location code color = 'pop', #column shown by color hover_name = 'country', #hover info title animation_frame = 'year', #column animated range_color = [60000,1300000000]#color range ) fig.show()

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

Import data

Transform and subset data

Describe data

Analyze one numerical variable

Analyze two numerical variables

Analyze one categorical variable

Analyze two categorical variables

Analyze one categorical variable and one numeric variable

Analyze two numerical variables and one categorical variable

Gapminder dataset

Set up