Time at home and total cases during the pandemic

Introduction
The North American Free Trade Agreement (NAFTA) is an economic bloc made up of the United States, Canada, and Mexico. Effectively created on January 1, 1994, it aims to strengthen trade relations between these countries. One of its objectives is to compete for head-on against the European and Chinese markets, which have evolved vigorously in recent years.
The NAFTA block is essentially economic, there is no institution or government to manage the block compared to other economic blocks. As the bloc is known for its social and economic disparity, it is interesting to analyze its graphs of social isolation and the total cases of Covid19 during the pandemic to get a better idea of each country and their differences in this new scenario.
Database
All data was taken from the google mobility report website, There you will be able to see community mobility reports about what has changed due to the policies created to face Covid-19. They show graphs with trends of displacement over time by region and in different categories. Finally, data on the total number of cases were removed from the site Our World in Data.
Pre-processing and cleaning
Important libraries for the program
import Pandas as pd
import matplotlib.pyplot as plt
Reading the data
link='https://www.gstatic.com/covid19/mobility/Global_Mobility_Report.csv'
data = pd.read_csv(link)
data.head()

Separating the main columns
data_country = data.iloc[:,[1,7,8,9,10,11,12,13]].copy()
data_country.columns = ['country','date', 'retail', 'grocery', 'parks', 'transit', 'workplaces', 'residential']
data_country.date = pd.to_datetime(data_country.date)
data_country.index = data_country.date
data_country.drop(labels = 'date', axis=1, inplace=True)
data_country.head()

Grouping the countries of the economic bloc about the "residential" column, using the method "groupby".
data_country.groupby(by[data_country.index,"country"])
.mean().unstack()["residential"][['United States','Canada','Mexico']]

Data visualization
fig, ax = plt.subplots(nrows=1,ncols=3,figsize=(20,4))
item = "residential" #grocery, parks, transit, workplaces, retailcountrys = ['United States','Canada','Mexico']
for i,country in enumerate(countrys):
data_country.groupby(by=[data_country.index,"country"]).mean().unstack()[item].rolling(window=7).mean().plot(legend=False,color="grey",linewidth=1, alpha=0.4, ax=ax[i])
data_country.groupby(by=[data_country.index,"country"]).mean().unstack()[item][country].rolling(window=7).mean().plot(legend=False,color="blue",linewidth=7, alpha=0.6, ax=ax[i])
ax[i].set_title(country,fontsize=12,ha='right')
ax[i].xaxis.grid(False)
ax[i].set_xlabel("")
ax[i].set_xticklabels(["","Mar","Apr","May","Jun","Jul","Aug","Sep"])
ax[i].xaxis.set_tick_params(labelsize=12)
ax[i].yaxis.set_tick_params(labelsize=12)
if (i==0) or (i==2):
ax[i].yaxis.tick_right()
else:
ax[i].set_yticklabels([])
#plt.savefig("nafta.png",dpi=300)
plt.show()

In this graph, we have the value of the country highlighted by the color blue and gray we have the values of other countries in the world.

In this second graph we can see that even though the United States had an index and tended to have similar case numbers to Canada, Covid’s number of cases is numerous times greater than that of Canada and Mexico, revealing to us that the virus has not yet been controlled compared to Canada which has a similar graph for isolation.
Conclusion
It is important to note that the two graphs are different, Canada, for example, had a high level of social isolation like Mexico, and today it already has a much lower number, this may say that there was greater control by the government and the disease population. So, even though the USA and Canada have a similar graph of social isolation, the graph for the number of cases shows us a very large disparity for the USA, having very high-value participation in all countries of the bloc.
For a better understanding of the code and data observed here is the link to the repository on GitHub and for more in-depth NAFTA content.