import numpy as np
import pandas as pd

vaccine_asean = pd.read_csv('/Users/thandarmoe/Library/Mobile Documents/com~apple~CloudDocs/teaching/Cloud/me/Python/Dataset/wuenic2023rev_unicef.csv')

Data Exploration

The immunization dataset was downloaded from https://data.unicef.org/resources/dataset/immunization/ and filtered for only ASEAN countries.

print(vaccine_asean.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 124 entries, 0 to 123
Data columns (total 28 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   unicef_region  124 non-null    object 
 1   iso3           124 non-null    object 
 2   country        124 non-null    object 
 3   vaccine        124 non-null    object 
 4   2023           123 non-null    float64
 5   2022           122 non-null    float64
 6   2021           120 non-null    float64
 7   2020           117 non-null    float64
 8   2019           114 non-null    float64
 9   2018           114 non-null    float64
 10  2017           112 non-null    float64
 11  2016           105 non-null    float64
 12  2015           102 non-null    float64
 13  2014           94 non-null     float64
 14  2013           92 non-null     float64
 15  2012           88 non-null     float64
 16  2011           85 non-null     float64
 17  2010           85 non-null     float64
 18  2009           80 non-null     float64
 19  2008           78 non-null     float64
 20  2007           77 non-null     float64
 21  2006           73 non-null     float64
 22  2005           72 non-null     float64
 23  2004           71 non-null     float64
 24  2003           70 non-null     float64
 25  2002           65 non-null     float64
 26  2001           64 non-null     float64
 27  2000           64 non-null     float64
dtypes: float64(24), object(4)
memory usage: 27.3+ KB
None

print(vaccine_asean['country'].unique())
print(vaccine_asean['vaccine'].unique())

['Brunei Darussalam' 'Cambodia' 'Indonesia'
 "Lao People's Democratic Republic" 'Malaysia' 'Myanmar' 'Philippines'
 'Singapore' 'Thailand' 'Viet Nam']
['BCG' 'DTP1' 'DTP3' 'HEPB3' 'HEPBB' 'HIB3' 'IPV1' 'IPV2' 'MCV1' 'MCV2'
 'PCV3' 'POL3' 'RCV1' 'ROTAC']

The dataset includes vaccination coverage data for 14 vaccines across 10 ASEAN countries, spanning the years 2000 to 2023. It consists of 124 records and 28 variables.

Data Manipulation

# Step 1: Melt the year columns
id_vars = ['unicef_region', 'iso3', 'country', 'vaccine']
value_vars = [str(year) for year in range(2000, 2024)]

vaccine_asean_long = pd.melt(
    vaccine_asean,
    id_vars=id_vars,
    value_vars=value_vars,
    var_name='year',
    value_name='value'
)

# Step 2: Add a 'year_date' column
vaccine_asean_long['year_date'] = pd.to_datetime(vaccine_asean_long['year'], format='%Y')

# Step 3: sort by country and year
vaccine_asean_long = vaccine_asean_long.sort_values(by=['country', 'vaccine', 'year'])

print(vaccine_asean_long.head())

    unicef_region iso3            country vaccine  year  value  year_date
0            EAPR  BRN  Brunei Darussalam     BCG  2000   99.0 2000-01-01
124          EAPR  BRN  Brunei Darussalam     BCG  2001   99.0 2001-01-01
248          EAPR  BRN  Brunei Darussalam     BCG  2002   95.0 2002-01-01
372          EAPR  BRN  Brunei Darussalam     BCG  2003   95.0 2003-01-01
496          EAPR  BRN  Brunei Darussalam     BCG  2004   99.0 2004-01-01

Data Visualization

import matplotlib.pyplot as plt
import seaborn as sns

g = sns.relplot(
    data=vaccine_asean_long,
    x='year_date',
    y='value',
    kind='line',
    col='country',          # one subplot per country
    col_wrap=4,             # wrap after 4 plots per row
    hue='vaccine',          # color by vaccine
    height=3,
    aspect=1.5
)

# Remove x and y axis labels for all subplots
for ax in g.axes.flat:
    ax.set_xlabel('')
    ax.set_ylabel('')
    ax.tick_params(axis='x', rotation=0)  # rotate x-axis ticks

# Add a main title for the whole grid
g.fig.suptitle('Vaccination Trends by ASEAN Countries', fontsize=16, y=1.02)

plt.show()

• Brunei, Malayisa, and Thailand has little flacutation in the coverage of 14 vaccines compared to other countries.
• Myanmar has suffered the largest dip in vaccination in 2021, which coincides with Covid-19 and coup.