unimelb-projects/comp20008-project01
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

created basic dataframes

Browse source
This commit is contained in:
Rory Healy 2021-04-09 22:46:35 +10:00
parent 4af42c9144
commit 6a41b385e7
3 changed files with 148008 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

73994
data/owid-covid-data.csv Normal file
View file

File diff suppressed because it is too large Load diff

73994
output.csv Normal file
View file

File diff suppressed because it is too large Load diff

20
parta1.py
View file

@ -1,2 +1,22 @@
import pandas as pd
import argparse
all_covid_data = pd.read_csv('data/owid-covid-data.csv', encoding = 'ISO-8859-1')
reduced_data = all_covid_data.loc[:,['location', 'date', 'total_cases', 'new_cases', 'total_deaths', 'new_deaths']]
# reduced_data_grouped = reduced_data.groupby(['location', 'date'], as_index = False)
new_cases = all_covid_data.loc[:, ['location', 'date', 'new_cases']]
new_cases.date = pd.to_datetime(new_cases.date)
new_cases_grouped = new_cases.groupby([new_cases.date.dt.month, new_cases.location]).new_cases.sum()
new_deaths = all_covid_data.loc[:, ['location', 'date', 'new_deaths']]
new_deaths.date = pd.to_datetime(new_deaths.date)
new_deaths_grouped = new_deaths.groupby([new_deaths.date.dt.month, new_deaths.location]).new_deaths.sum()
print(new_cases_grouped)
print("\n\n")
print(new_deaths_grouped)