import pandas as pd import datetime as datetime from datetime import timedelta from dateutil.relativedelta import relativedelta import numpy as np import matplotlib.pyplot as plt import seaborn as sns %matplotlib inline sns.set() print('Setup completed ^_____^')

df = pd.read_csv('/content/country_vaccinations_by_manufacturer.csv') df.head()

df.tail()

df.nunique() # Get the number of unique value on each column:

df.dtypes # take a look of the data types that we dealing with; precisely the date column

df['date'] = pd.to_datetime(df['date'], format="%Y-%m-%d") # to_datetime is a pandas method which helps to convert datetime string into pandas datetime object to make it easy when works with TimseSeries data

df.dtypes # check our new data types after converting date(column) into datetime64[ns] by using pd.to_datetime()

# Check the missing values: missing_values = df.isnull().sum() missing_values[:]

df.columns

df.dtypes

variables = ['date', 'vaccine', 'total_vaccinations'] group_variables = variables[:2] outcome_variable = variables[2] data = df.groupby(group_variables)[outcome_variable].sum().reset_index()

data.head()

data.tail()

sns.barplot(x=data['total_vaccinations'], y=data['vaccine'])

data.set_index('date', inplace=True)

data.head()

print(data.index)

# Get the observations of 2020:- print(data['2020'].head()) print(data['2020'].tail())

print('Day:', data.index.day, '\n') print('Week:', data.index.week, '\n') data['dayofweek'] = data.index.dayofweek # Day of Week: Monday=0, Sunday=6 print(data.head()) print(data.tail()) del(data['dayofweek'])

data.head()

data.reset_index(inplace=True) data_pivot= data.pivot(index='date', columns='vaccine', values='total_vaccinations') data_pivot.head()

data_pivot.tail()

# Convert NaN values with 0: data_pivot.fillna(0, axis=0, inplace=True)

data_pivot.head()

vaccination_amount = data.set_index(['date', 'vaccine']).unstack('vaccine').fillna(0) vaccination_amount.columns = vaccination_amount.columns.levels[1].rename(None) vaccination_amount.head()

print(vaccination_amount.index) print('\nUnique dates in our data: ', len(vaccination_amount.index.unique()), 'Days')

print('\nUnique dates in our data: ', len(vaccination_amount.index.unique()), 'Days') date_ranges = vaccination_amount.index.max() - vaccination_amount.index.min() # Calculate number of days in date range: print('Total days in our date range: ', date_ranges.days, 'Days')

new_index = pd.date_range(vaccination_amount.index.min(), vaccination_amount.index.max()) print(new_index)

new_vaccinations_amount = vaccination_amount.reindex(new_index, fill_value=0)

new_vaccinations_amount.index

weekly_vaccinations = new_vaccinations_amount.resample('W').sum() print('Weekly vaccinations') print(weekly_vaccinations.head(), '\n') monthly_vacinations = new_vaccinations_amount.resample('M').sum() print('Monthly Vaccinations') print(monthly_vacinations.head(), '\n') quaterly_vaccinations = new_vaccinations_amount.resample('Q').sum() print('Quarterly Vaccinations') print(quaterly_vaccinations.head(), '\n') annual_vaccinations = new_vaccinations_amount.resample('Y').sum() print('Annual Vaccinations') print(annual_vaccinations.head(), '\n')

# Variable First Difference print('Monthly Vaccination, First Difference \n', monthly_vacinations.diff().head()) # Variable Percentage Change: print('Monthly Vaccinations % Change \n', monthly_vacinations.pct_change().head()) # Add % change to original data: monthly_vacinations.join(monthly_vacinations.pct_change().add_suffix('_%_Change')).head()

plotsize = (13, 5) quaterly_vaccinations.plot(figsize=plotsize, title='Quarterly Vaccinations') monthly_vacinations.plot(figsize=plotsize, title='Monthly Vaccinations') weekly_vaccinations.plot(figsize=plotsize, title='Weekly Vaccinations')