import pandas as pd
import cufflinks as cf
from IPython.display import display,HTML
cf.set_config_file(sharing='public',theme='white',offline=True) # write cf.getThemes() to find all themes availableGraficas con Plotly en Python
print(pd.read_csv('population_total.csv')) country year population
0 China 2020.0 1.439324e+09
1 China 2019.0 1.433784e+09
2 China 2018.0 1.427648e+09
3 China 2017.0 1.421022e+09
4 China 2016.0 1.414049e+09
... ... ... ...
4180 United States 1965.0 1.997337e+08
4181 United States 1960.0 1.867206e+08
4182 United States 1955.0 1.716853e+08
4183 India 1960.0 4.505477e+08
4184 India 1955.0 4.098806e+08
[4185 rows x 3 columns]df_population = pd.read_csv('population_total.csv')
df_population = df_population.dropna()
df_population = df_population.pivot(index='year', columns='country',
values='population')
df_population = df_population[['United States', 'India', 'China',
'Indonesia', 'Brazil']]
print(df_population)country United States India China Indonesia Brazil
year
1955.0 171685336.0 4.098806e+08 6.122416e+08 77273425.0 62533919.0
1960.0 186720571.0 4.505477e+08 6.604081e+08 87751068.0 72179226.0
1965.0 199733676.0 4.991233e+08 7.242190e+08 100267062.0 83373530.0
1970.0 209513341.0 5.551898e+08 8.276014e+08 114793178.0 95113265.0
1975.0 219081251.0 6.231029e+08 9.262409e+08 130680727.0 107216205.0
1980.0 229476354.0 6.989528e+08 1.000089e+09 147447836.0 120694009.0
1985.0 240499825.0 7.843600e+08 1.075589e+09 164982451.0 135274080.0
1990.0 252120309.0 8.732778e+08 1.176884e+09 181413402.0 149003223.0
1995.0 265163745.0 9.639226e+08 1.240921e+09 196934260.0 162019896.0
2000.0 281710909.0 1.056576e+09 1.290551e+09 211513823.0 174790340.0
2005.0 294993511.0 1.147610e+09 1.330776e+09 226289470.0 186127103.0
2010.0 309011475.0 1.234281e+09 1.368811e+09 241834215.0 195713635.0
2015.0 320878310.0 1.310152e+09 1.406848e+09 258383256.0 204471769.0
2016.0 323015995.0 1.324517e+09 1.414049e+09 261556381.0 206163053.0
2017.0 325084756.0 1.338677e+09 1.421022e+09 264650963.0 207833823.0
2018.0 327096265.0 1.352642e+09 1.427648e+09 267670543.0 209469323.0
2019.0 329064917.0 1.366418e+09 1.433784e+09 270625568.0 211049527.0
2020.0 331002651.0 1.380004e+09 1.439324e+09 273523615.0 212559417.0df_population.iplot(kind='line', xTitle='Years', yTitle='Population',
title='Population (1955-2020)')df_population_2020 = df_population[df_population.index.isin([2020])]
df_population_2020 = df_population_2020.T
df_population_2020.iplot(kind='bar', color='lightgreen',
xTitle='Years', yTitle='Population',
title='Population in 2020')# filter years out
df_population_sample = df_population[df_population.index.isin([1980, 1990, 2000, 2010, 2020])]
# plotting
df_population_sample.iplot(kind='bar', xTitle='Years',
yTitle='Population')df_population['United States'].iplot(kind='box', color='green',
yTitle='Population')df_population.iplot(kind='box', xTitle='Countries',
yTitle='Population')df_population[['United States', 'Indonesia']].iplot(kind='hist',
xTitle='Population')# transforming data
df_population_2020 = df_population_2020.reset_index()
df_population_2020 = df_population_2020.rename(columns={2020:'2020'})
# plotting
df_population_2020.iplot(kind='pie', labels='country',
values='2020',
title='Population in 2020 (%)')# transforming data
df_population_2020 = df_population_2020.reset_index()
df_population_2020 = df_population_2020.rename(columns={2020:'2020'})
# plotting
df_population_2020.iplot(kind='pie', labels='country',
values='2020',
title='Population in 2020 (%)')df_population.iplot(kind='scatter', mode='markers')