Análise da Felicidade com Pandas

pip install pandas matplotlib

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import figure

df = pd.read_csv("./datasets_894_813759_2019.csv")
df.head()

df = df.rename(columns={"Overall rank": "Rank", "Country or region": "Region",
                   "GDP per capita": "GDP", "Social support": "Social",
                   "Healthy life expectancy": "Healthy",
                   "Freedom to make life choices": "Freedom", "Perceptions of corruption": "Corruption"})

values_columns = ["Score", "GDP", "Social", "Healthy", "Freedom", "Generosity", "Corruption"]
corr = df[values_columns].corr()
corr

pd.plotting.scatter_matrix(df[values_columns], figsize=(18, 18))
plt.savefig("radar_scatter_matrix_correlation.svg", formatstr="svg")
plt.show()

pip install beautifulsoup4 requests lxml

# Importação das bibliotecas para Web Scraping e requisições HTTP
from bs4 import BeautifulSoup
from requests import get

# Colher o conteúdo do geonames
html = get("https://www.geonames.org/countries/").text
# Converter o texto para elementos de tags do Beautiful Soup
soup = BeautifulSoup(html)
# Para visualizar de forma estruturada: print(soup.prettify())

# Procurar a tag <table> com o id "countries"
table = soup.find("table", attrs={"id": "countries"})
# Para visualizar de forma estruturada: print(table.prettify())

# Converter o conteúdo DataFrame do pandas
# Alterando valor NA para NT, para evitar a conversão para valores nulos
table_countries = pd.read_html(str(table).replace("<td>NA</td>", "<td>NT</td>"))[0]

# Selecionar os campos que serão usados
countries = table_countries[["Country", "Area in km²", "Population", "Continent"]]
countries.head()

set(df["Region"]) - set(countries["Country"])

data = pd.merge(df, countries, left_on="Region", right_on="Country").drop("Country", axis=1)
data = data.rename(columns={"Area in km²": "Area"})
data.head()

# Definição do tamanho do gráfico
plt.figure(figsize=(18, 18))

# Colher os continentes diferentes da base
continents = data["Continent"].unique()

# Geração dos ciclos
for continent in continents:
    dc = data[data["Continent"] == continent]
    plt.scatter(dc["Score"], dc["GDP"], s=dc["Healthy"] * 500, alpha=0.4, label=continent)

# Adicionar título
plt.title("Scatter Happiness Radar")
# Adicionar rótulos nos eixos
plt.xlabel("Score")
plt.ylabel("GDP per capita")
# Adicionar legenda para os continentes
plt.legend(scatterpoints=1, frameon=False, labelspacing=1, title="Continents")
# Salvar gráfico em arquivo
plt.savefig("radar_scatter_happiness_radar.svg", formatstr="svg")
# Apresentar o gráfico em tela
plt.show()

coods = pd.read_csv("./datasets_2312_3908_countries.csv")
coods.head()

set(data["Region"]) - set(coods["name"])

cc = pd.merge(data, coods, left_on="Region", right_on="name").drop(["name", "country"], axis=1)
cc.head()

plt.figure(figsize=(18, 9))

continents = cc["Continent"].unique()
for continent in continents:
    dc = cc[cc["Continent"] == continent]
    plt.scatter(dc["longitude"], dc["latitude"], s=dc["Score"] * 50, alpha=0.4)

plt.savefig("radar_coods.svg", formatstr="svg")
plt.show()

import matplotlib.image as mpimg
world_img = mpimg.imread("./world-map.png") # 2000 x 1202

plt.figure(figsize=(18, 9))

continents = cc["Continent"].unique()
for continent in continents:
    dc = cc[cc["Continent"] == continent]
    plt.scatter(dc["longitude"], dc["latitude"], s=dc["Score"].pow(3), alpha=0.6) #

plt.imshow(world_img, extent=[-149, 190, -75, 105], alpha=0.25) # left, right, bottom, top
plt.savefig("radar_world_map.svg", formatstr="svg")
plt.show()

cc.to_csv("./countries.csv", index = False, header=True)