coid_19_status_tracker_with_interactive_visualuzations.py

# -*- coding: utf-8 -*-
"""Coid 19 Status Tracker with Interactive Visualuzations.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1IbBJKOrCTJR2m2WyQUJCbYlSKz-cNYmh

# **Coid 19 Status Tracker with Interactive Visualuzations**
"""

#mount google drive to read uploaded shapefile
from google.colab import drive
drive.mount('/content/drive')

#install geopandas
!pip install git+git://github.com/geopandas/geopandas.git

"""#### **Import Dependencies**"""

# Commented out IPython magic to ensure Python compatibility.
from datetime import date
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# %matplotlib inline
import seaborn as sns
import geopandas as gpd
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
from IPython.display import Markdown as md
import plotly.io as pio
import warnings
warnings.filterwarnings("ignore")

import os

if not os.path.exists("images"):
    os.mkdir("images")

"""#### **Import Theme Templates & Colours palets**"""

#plotly available templates
pio.templates

"""#### **Plotly Colours** :
###### *aliceblue, antiquewhite, aqua, aquamarine, azure, beige, bisque, black, blanchedalmond, blue, blueviolet, brown, burlywood, cadetblue, chartreuse chocolate, coral, cornflowerblue, cornsilk, crimson, cyan, darkblue, darkcyan, darkgoldenrod, darkgray, darkgrey, darkgreen, darkkhaki, darkmagenta, darkolivegreen, darkorange, darkorchid, darkred, darksalmon, darkseagreen, darkslateblue, darkslategray, darkslategrey, darkturquoise, darkviolet, deeppink, deepskyblue, dimgray, dimgrey, dodgerblue, firebrick, floralwhite, forestgreen, fuchsia, gainsboro, ghostwhite, gold, goldenrod, gray, grey, green, greenyellow, honeydew, hotpink, indianred, indigo, ivory, khaki, lavender, lavenderblush, lawngreen, lemonchiffon, lightblue, lightcoral, lightcyan, lightgoldenrodyellow, lightgray, lightgrey, lightgreen, lightpink, lightsalmon, lightseagreen, lightskyblue, lightslategray, lightslategrey, lightsteelblue, lightyellow, lime, limegreen, linen, magenta, maroon, mediumaquamarine, mediumblue, mediumorchid, mediumpurple, mediumseagreen, mediumslateblue, mediumspringgreen, mediumturquoise, mediumvioletred, midnightblue, mintcream, mistyrose, moccasin, navajowhite, navy, oldlace, olive, olivedrab, orange, orangered, orchid, palegoldenrod, palegreen, paleturquoise, palevioletred, papayawhip, peachpuff, peru, pink, plum, powderblue, purple, red, rosybrown, royalblue, rebeccapurple, saddlebrown, salmon, sandybrown, seagreen, seashell, sienna, silver, skyblue, slateblue, slategray, slategrey, snow, springgreen, steelblue, tan, teal, thistle, tomato, turquoise, violet, wheat, white, whitesmoke, yellow, yellowgreen*

### **Geopandas Colous**
##### *'Grays' is not a valid value for name; supported values are 'Accent', 'Accent_r', 'Blues', 'Blues_r', 'BrBG', 'BrBG_r', 'BuGn', 'BuGn_r', 'BuPu', 'BuPu_r', 'CMRmap', 'CMRmap_r', 'Dark2', 'Dark2_r', 'GnBu', 'GnBu_r', 'Greens', 'Greens_r', 'Greys', 'Greys_r', 'OrRd', 'OrRd_r', 'Oranges', 'Oranges_r', 'PRGn', 'PRGn_r', 'Paired', 'Paired_r', 'Pastel1', 'Pastel1_r', 'Pastel2', 'Pastel2_r', 'PiYG', 'PiYG_r', 'PuBu', 'PuBuGn', 'PuBuGn_r', 'PuBu_r', 'PuOr', 'PuOr_r', 'PuRd', 'PuRd_r', 'Purples', 'Purples_r', 'RdBu', 'RdBu_r', 'RdGy', 'RdGy_r', 'RdPu', 'RdPu_r', 'RdYlBu', 'RdYlBu_r', 'RdYlGn', 'RdYlGn_r', 'Reds', 'Reds_r', 'Set1', 'Set1_r', 'Set2', 'Set2_r', 'Set3', 'Set3_r', 'Spectral', 'Spectral_r', 'Wistia', 'Wistia_r', 'YlGn', 'YlGnBu', 'YlGnBu_r', 'YlGn_r', 'YlOrBr', 'YlOrBr_r', 'YlOrRd', 'YlOrRd_r', 'afmhot', 'afmhot_r', 'autumn', 'autumn_r', 'binary', 'binary_r', 'bone', 'bone_r', 'brg', 'brg_r', 'bwr', 'bwr_r', 'cividis', 'cividis_r', 'cool', 'cool_r', 'coolwarm', 'coolwarm_r', 'copper', 'copper_r', 'crest', 'crest_r', 'cubehelix', 'cubehelix_r', 'flag', 'flag_r', 'flare', 'flare_r', 'gist_earth', 'gist_earth_r', 'gist_gray', 'gist_gray_r', 'gist_heat', 'gist_heat_r', 'gist_ncar', 'gist_ncar_r', 'gist_rainbow', 'gist_rainbow_r', 'gist_stern', 'gist_stern_r', 'gist_yarg', 'gist_yarg_r', 'gnuplot', 'gnuplot2', 'gnuplot2_r', 'gnuplot_r', 'gray', 'gray_r', 'hot', 'hot_r', 'hsv', 'hsv_r', 'icefire', 'icefire_r', 'inferno', 'inferno_r', 'jet', 'jet_r'*

## **Getting Know About the Dataset**

#### Import Datasets
"""

#live covid 19 datset
df_raw = pd.read_csv('https://covid.ourworldindata.org/data/owid-covid-data.csv')

#world geopatial boundaries for plot maps
regions = gpd.read_file("/content/drive/MyDrive/Colab Materials/Geospatial World Boundaries/WB_countries_Admin0_10m.shp")

df_raw.head()

df_raw.shape

#last 5 rows
df_raw.tail()

df_raw.sample(5)

"""### **Derive World Data From The Dataset**"""

#derive world data from the dataframe

#filter data
world_all = df_raw[(df_raw['location']=='World')]
world_all = world_all[['date', 'total_cases', 'new_cases', 'total_deaths', 'new_deaths', 'people_vaccinated',	'people_fully_vaccinated','population']]


#calculate percentage
world_all['wo_cas_per'] = round((world_all['total_cases'] / world_all['population']) * 100 , 2)
world_all['wo_vc_per'] = round((world_all['people_vaccinated'] / world_all['population']) * 100 , 2)
world_all['wo_fl_vc_per'] = round((world_all['people_fully_vaccinated'] / world_all['population']) * 100 , 2)
world_all['wo_de_per'] = round((world_all['total_deaths'] / world_all['population']) * 100 , 2)

#get the last date data points
world_all = world_all.iloc[:-1,:]
world = world_all.tail(1)


#define neccesery values into the variables
vaccine_percentage_world = np.array(world['wo_vc_per'])[0]
fully_vaccine_percentage_world = np.array(world['wo_fl_vc_per'])[0]
cases_percentage_world = np.array(world['wo_cas_per'])[0]
deaths_percentage_world = np.array(world['wo_de_per'])[0]


#convert neccesery values into the variables
ca = round(np.array(world['total_cases'])[0] / 1000000,1)
de = round(np.array(world['total_deaths'])[0] / 1000000,1)
vc = round(np.array(world['people_vaccinated'])[0] / 1000000,1)
fvc = round(np.array(world['people_fully_vaccinated'])[0] / 1000000,1)

#world dreived data
world_all

#Summary of on the recent date
world

#remove world data from the main dataset 
df_raw = pd.DataFrame(df_raw[~(df_raw['continent'].isnull())])

#remove data regarding to recent date

#this recent date we cant use directy for the analysis, becasue this dataset only contain the complete updated data that 2 days before the recent date. therefore we have to change the date)
print("Last Date Data Recorded",df_raw['date'].max())
print(' ')

rec_fully_up_date = df_raw['date'].iloc[-1] #derive fully update date into a variable

#filter data which under the fully complated date
df = pd.DataFrame(df_raw[~(df_raw['date'] == rec_fully_up_date )])

#derive neccessery columns for the further calculatins
df = df[['date','continent',	'location','total_tests','new_tests'	,'total_cases'	,'new_cases'	,'total_deaths'	,'new_deaths', 'total_vaccinations'	,'people_vaccinated'	,'people_fully_vaccinated'	,'population']]

#check after data cleaned
df.tail()

df.shape

for columns in df.columns:
        print(columns)

df.info()

df.isnull().sum()

"""## **Pre Processing**

### **Define Dataframes for the further analysis**

### *Country Wise Dataframe*
"""

#list of countries in the dataset
country_count = len(df['location'].unique())

md(f'## *Number of Countries in The Dataset : {country_count}*')

#filter & group data by location
Ctr_wise = pd.DataFrame(df.groupby(['location']).agg({ 
                                                    'total_cases':'max', 
                                                    'total_deaths':'max', 
                                                    'people_vaccinated':'max',
                                                    'people_fully_vaccinated':'max',
                                                    'population':'max'}).reset_index())

Ctr_wise.head()

"""### *Continent Wise Dataframe*"""

Cont_wise = pd.DataFrame(df.groupby(['continent','location']).agg({ 
                                                    'total_cases':'max', 
                                                    'total_deaths':'max', 
                                                    'people_vaccinated':'max',
                                                    'people_fully_vaccinated':'max',
                                                    'population':'max'}).reset_index())



Cont_wise = pd.DataFrame(Cont_wise.groupby('continent').agg({ 
                                                    'total_cases':'sum', 
                                                    'total_deaths':'sum', 
                                                    'people_vaccinated':'sum',
                                                    'people_fully_vaccinated':'sum',
                                                    'population':'sum'}).reset_index())

Cont_wise

"""#### *Calculate Percentage Columns*"""

# vaccination percentage countries

Ctr_wise['vacc_percentage'] = round(Ctr_wise['people_vaccinated'] / Ctr_wise['population'],2)*100
Ctr_wise['Fully_vacc_percentage'] = round(Ctr_wise['people_fully_vaccinated'] / Ctr_wise['population'],2)*100

Ctr_wise['deaths_percentage'] = round(Ctr_wise['total_deaths'] / Ctr_wise['population'],4)*100
Ctr_wise['cases_percentage'] = round(Ctr_wise['total_cases'] / Ctr_wise['population'],2)*100


Ctr_wise.head(5)

# vaccination percentage of continents

Cont_wise['vacc_percentage'] = round(Cont_wise['people_vaccinated'] / Cont_wise['population'],2)*100
Cont_wise['Fully_vacc_percentage'] = round(Cont_wise['people_fully_vaccinated'] / Cont_wise['population'],2)*100

Cont_wise['deaths_percentage'] = round(Cont_wise['total_deaths'] / Cont_wise['population'],4)*100
Cont_wise['cases_percentage'] = round(Cont_wise['total_cases'] / Cont_wise['population'],2)*100


Cont_wise

"""# **Exploratory Data Analysis & Visualizations - Global**

## **Summary of Global Covid 19 Status**
"""

#pre-process the current date
Analysis_Date = df_raw['date'].iloc[-2]

title_name = "Summary of Global Covid 19 status as at " + str(Analysis_Date)

values = [['Total Cases','Total Death Cases','Vaccinated People','Fully Vaccinated People'],
          [str(ca)+str('M'), str(de)+str('M') , str(vc)+str('M') ,str(fvc)+str('M') ],
          [str(cases_percentage_world)+str('%'), str(deaths_percentage_world)+str('%'), str(vaccine_percentage_world) +str('%'), str(fully_vaccine_percentage_world)+str('%')]]

fig = go.Figure(data=[go.Table(
                                columnorder = [1,2,3],
                                columnwidth = [40,20,20],
                                header = dict(
                                  values = [['<b>Details</b>'] , ['<b>No of People</b>'],['<b>Percentage Value</b>']],
                                  line_color='darkslategray',
                                  fill_color='royalblue',
                                  align=['center','center','center'],
                                  font=dict(color='white', size=22),
                                  height=70
                                ),
                                cells=dict(
                                  values=values,
                                  line_color='darkslategray',
                                  fill=dict(color=['white', 'white', 'white']),
                                  align=['center', 'center', 'center'],
                                  font_size=20,
                                  height=70)
                                  )
                              ])

fig.update_layout(
     title = title_name,
     title_font_size = 25,
     width = 1400, height = 600)


fig.show()

"""### **World Vaccination Progress Percentage**"""

fig = go.Figure(go.Indicator(
                              domain = {'x': [0, 1], 'y': [0, 1]},
                              value = vaccine_percentage_world,
                              mode = "gauge+number+delta",
                              title = {'text': "World Vaccination Progress (At least 1 Dose)"},
                              delta = {'reference':100},
                              gauge = {'axis': {'range': [None, 100]},
                                      'bar': {'color': "darkblue"},
                                      'threshold' : {'line': {'color': "red", 'width': 4}, 'thickness': 0.75, 'value': 99}}))

fig.show()

"""### **World Fully Vaccination Progress Percentage**"""

fig = go.Figure(go.Indicator(
                              domain = {'x': [0, 1], 'y': [0, 1]},
                              value = fully_vaccine_percentage_world,
                              mode = "gauge+number+delta",
                              title = {'text': "World Fully Vaccination Progress"},
                              delta = {'reference':100},
                              gauge = {'axis': {'range': [None, 100]},
                                      'bar': {'color': "orange"},
                                      'threshold' : {'line': {'color': "red", 'width': 4}, 'thickness': 0.75, 'value': 99}}))

fig.show()

"""## **Time Line of World Data**"""

world_all.head(5)

"""### **Time Series Of Covid 19 Positive Cases**"""

fig = go.Figure()

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['total_cases'],
     mode = 'lines',
     line=dict(width=0.5, color='yellowgreen'),stackgroup = 'one'))

fig.update_layout(
     title = "Time Series Of Covid 19 Cases",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.update_yaxes(
     title_text = "Cases",
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.show()

"""### **Time Series Of Covid 19 Deaths**"""

fig = go.Figure()

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['total_deaths'],
     mode = 'lines',
     line=dict(width=0.5, color='orangered'),stackgroup = 'one'))

fig.update_layout(
     title = "Time Series Of Covid 19 Death Cases",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.update_yaxes(
     title_text = "Death Cases",
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.show()

"""### **Time Series Of Covid 19 Vaccination**"""

fig = go.Figure()

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['people_vaccinated'],
     mode = 'lines',
     line=dict(width=0.5, color='royalblue'),stackgroup = 'one'))

fig.update_layout(
     title = "Time Series Of Covid 19 Vaccination Progress",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.update_yaxes(
     title_text = "Vaccination Count",
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.show()

"""### **Time Series Of Covid 19 Fully Vaccinations**"""

fig = go.Figure()

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['people_fully_vaccinated'],
     mode = 'lines',
     line=dict(width=0.5, color='purple'),stackgroup = 'one'))

fig.update_layout(
     title = "Time Series Of Covid 19 Fully Vaccination Progress",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.update_yaxes(
     title_text = "Vaccination Count",
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.show()

"""### **Deaths vs Positive Cases Time Series**"""

fig = make_subplots(specs=[[{"secondary_y": True}]])

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['total_cases'],
     mode = 'lines',
     name='Positive Cases',
     line=dict(width=2, color='yellowgreen')),secondary_y=False)

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['total_deaths'],
     mode = 'lines',
     name='Death Cases',
     line=dict(width=2, color='orangered')),secondary_y=True)

fig.update_layout(
     title = "Deaths Cases vs Positive Cases Time Series",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))


fig.update_yaxes(title_text="Total Cases", secondary_y=False)
fig.update_yaxes(title_text="Death Cases", secondary_y=True)

fig.show()

"""### **Vaccinations Vs Positive Cases Time Series**"""

fig = make_subplots(specs=[[{"secondary_y": True}]])

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['total_cases'],
     mode = 'lines',
     name='Positive Cases',
     line=dict(width=2, color='yellowgreen')),secondary_y=False)

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['people_vaccinated'],
     mode = 'lines',
     name='Vaccination',
     line=dict(width=2, color='royalblue')),secondary_y=True)

fig.update_layout(
     title = "Vaccination vs Positive Cases Time Series",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))



fig.update_yaxes(title_text="Positive Cases", secondary_y=False)
fig.update_yaxes(title_text="Vaccination", secondary_y=True)

fig.show()

"""### **Vaccinations Vs Deaths Cases Time Series**"""

fig = make_subplots(specs=[[{"secondary_y": True}]])

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['people_vaccinated'],
     mode = 'lines',
     name='Vaccination',
     line=dict(width=2, color='royalblue')),secondary_y=False)

fig.add_trace(go.Scatter(
     x= world_all['date'], y = world_all['total_deaths'],
     mode = 'lines',
     name='Death Cases',
     line=dict(width=2, color='orangered')),secondary_y=True)

fig.update_layout(
     title = "Vaccination vs Death Cases Time Series",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620)

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='black'),
     tickfont=dict(family='Calibri', color='black', size=15))

fig.update_yaxes(title_text="Vaccination", secondary_y=False)
fig.update_yaxes(title_text="Death Cases", secondary_y=True)

fig.show()

"""## **Country Wise Data Analysis & Visualization**

#### **Pre-processing**
"""

#replaced regions country names with corrected one's according to covid 19 datasets country names
regions.replace(to_replace ={"People's Republic of China":'China',
                             'United States of America':'United States',
                             'The Bahamas':'Bahamas',
                             'The Gambia':'Gambia',
                             'Ivory Coast':"Cote d'Ivoire",
                             'Czech Republic':'Czechia',
                             'Democratic Republic of the Congo':'Democratic Republic of Congo',
                             'São Tomé and Príncipe':'Sao Tome and Principe',
                             'Vatican City':'Vatican',
                             'eSwatini':'Eswatini',
                             'Sint Maarten':'Sint Maarten (Dutch part)',
                             'Republic of the Congo':'Congo',
                             'East Timor':'Timor',
                             'Macau':'Macao',
                             'Curaçao':'Curacao',
                             'Pitcairn Islands':'Pitcairn',
                             'Faroe Islands':'Faeroe Islands',
                             'Republic of Macedonia':'North Macedonia',
                             'Federated States of Micronesia':'Micronesia (country)'}, 
                              value =None,inplace=True)

#rename regions column name for merge
regions.rename({'NAME_EN':'location'}, axis=1,inplace=True)

#merege two dataframes ( ctr_wise & regions)
mg_cont = regions.merge(Ctr_wise, on='location', how='left')

#select neccessery columns from the entire dataframe
mg_cont = mg_cont[['location','geometry','total_cases','total_deaths','people_vaccinated','people_fully_vaccinated','vacc_percentage','Fully_vacc_percentage','deaths_percentage','cases_percentage']]

#convert to millions for better visualization 7 understand
mg_cont['total_cases'] = round(mg_cont['total_cases'] / 1000000,2)
mg_cont['people_vaccinated'] = round(mg_cont['people_vaccinated'] / 1000000,2)
mg_cont['people_fully_vaccinated'] = round(mg_cont['people_fully_vaccinated'] / 1000000,2)

#display first 5 rows of pre processed data
mg_cont.head()

"""## **Countries Total Vaccination Geospatial Visualization (At least 1 Dose)**"""

#plot total cases
mg_cont.plot(column='people_vaccinated',
            figsize=(22,16),
            legend=True,
            legend_kwds={'label': "Total People Vaccinated (Millions)",'orientation': "horizontal"},
             cmap='Blues')

"""## **Countries Fully Vaccination Geospatial Visualization**"""

#plot total cases
mg_cont.plot(column='people_fully_vaccinated',
            figsize=(22,16),
            legend=True,
            legend_kwds={'label': "Fully Vaccinated (Millions)",'orientation': "horizontal"},
             cmap='Greens')

"""### **Top 10 Countries With Highest Vaccination Percentage (At least 1 Dose)**"""

Vaccination = Ctr_wise.sort_values('vacc_percentage',ascending=False)

Vaccination_filter = Vaccination[['location','people_vaccinated','vacc_percentage',	'Fully_vacc_percentage']]

Vaccination_filter.head(10)

# visualize source reported times
Vaccination_filter_top_10 = Vaccination_filter.iloc[2:10,:]

fig = px.bar(Vaccination_filter_top_10, x=Vaccination_filter_top_10['location'], 
                                        y=Vaccination_filter_top_10['vacc_percentage'],
                                        title = "Top 10 Countries with Highest Vaccination Percentage")
fig.show()

"""#### *This dataset is from github respository under oxford unviversity project. it contain first two countries gibralter has vaccinated people more than it's population. so i didnt able to figure out the reason. therefore removed those two countries from the visualization*

### **Countries Total Cases Geospatial Visualization**
"""

#plot total cases
mg_cont.plot(column='total_cases',
            figsize=(22,16),
            legend=True,
            legend_kwds={'label': "Total Cases (Millions)",'orientation': "horizontal"},
             cmap="Oranges")

"""### **Top 10 Countries With Highest Covid 19 Cases**"""

cases = Ctr_wise.sort_values('total_cases',ascending=False)

test_filter_highest = cases[['location','total_cases','cases_percentage']]

test_filter_highest.head(10)

"""### **Top 10 Countries With Highest Covid 19 Cases Percentage**"""

cases_pr = Ctr_wise.sort_values('cases_percentage',ascending=False)

test_filter_highest_pr = cases_pr[['location','total_cases','cases_percentage']]

test_filter_highest_pr.head(10)

"""### **Countries Total Deaths Geospatial Visualization**"""

#plot total cases
mg_cont.plot(column='total_deaths',
            figsize=(22,16),
            legend=True,
            legend_kwds={'label': "Total Deaths",'orientation': "horizontal"},
             cmap='Reds')

"""### **Top 10 Countries With Highest Death Cases**"""

deaths = Ctr_wise.sort_values('total_deaths',ascending=False)

deaths_highest = deaths[['location','total_deaths','deaths_percentage']]

deaths_highest.head(10)

"""### **Top 10 Countries With Highest Death Cases Percentage**"""

deaths_pr = Ctr_wise.sort_values('deaths_percentage',ascending=False)

deaths_highest_pr = deaths_pr[['location','total_deaths','deaths_percentage']]

deaths_highest_pr.head(10)

"""## **Continents Wise Data Analysis & Visualization**

#### **Preprocessing a Fucntion to Plot Customized Bar Graphs**
"""

#define function to ploting the graphs.

def customized_barchart(Data_frame, Attribute_name_Discrete, Attribute_name_Continious ,max_Colour_name, Rest_colour_name ,Title_name, Yaxis_name, Xaxis_name, Template_name):

  #set axis colours according to theme colour
  if Template_name == 'plotly_dark':

       COL_TICKS = 'white'

  else:
       COL_TICKS = 'black'

  #set max colour effect to maximum value
  list_series = [i for i in Data_frame[Attribute_name_Continious]]
  length = len(list_series)

  colors = [Rest_colour_name,] * length
  colors[list_series.index(max(list_series))] = max_Colour_name

  #setting ploting figure & main propertise 
  fig = go.Figure(data=[go.Bar( x =Data_frame[Attribute_name_Discrete], y= Data_frame[Attribute_name_Continious], marker_color=colors )])

  #add layout styles
  fig.update_layout(title_text=Title_name,
                    title_font_size = 25, legend_font_size = 10,
                    width=1400, height=620,
                    template=Template_name)
  
  #add xaxxes styles
  fig.update_xaxes(title_text = Xaxis_name,
                    title_font=dict(size=15, family='Verdana', color=COL_TICKS),
                    tickfont=dict(family='Calibri', color=COL_TICKS, size=15))
                    
  #add yaxes styles
  fig.update_yaxes(title_text = Yaxis_name,
                    title_font=dict(size=15, family='Verdana', color=COL_TICKS),
                    tickfont=dict(family='Calibri', color=COL_TICKS, size=15))

                    
  fig.show()

"""### **Contitnents With Total Vaccination Percentage (At least 1 Dose)**"""

#deaths_percentage	cases_percentage

dfr = Cont_wise
attnd = 'continent'
attnc = 'vacc_percentage'

mcn = 'deepskyblue'
rcn = 'lightslategray'

tn = 'Continents Vs Total Vaccination Percentage (At least 1 Dose)'
yxn = 'Vaccinations Percentage'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Contitnents vs Total Vaccination**"""

#deaths_percentage	cases_percentage

dfr = Cont_wise
attnd = 'continent'
attnc = 'people_vaccinated'

mcn = 'deepskyblue'
rcn = 'lightslategray'

tn = 'Continents vs Vaccination (At least 1 Dose)'
yxn = 'Vaccinations'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Continents vs Fully Vaccination Percentage**"""

#deaths_percentage	cases_percentage

dfr = Cont_wise
attnd = 'continent'
attnc = 'Fully_vacc_percentage'

mcn = 'gold'
rcn = 'limegreen'

tn = 'Continents vs Total Fully Vaccination Percentage'
yxn = 'Fully Vaccinations Percentage'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Continents vs Total Fully Vaccination**"""

dfr = Cont_wise
attnd = 'continent'
attnc = 'people_fully_vaccinated'

mcn = 'gold'
rcn = 'limegreen'

tn = 'Continents vs Total Fully Vaccination'
yxn = 'Fully Vaccinations'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Continents vs Death Cases Percentage**"""

deaths_con = Cont_wise.sort_values('deaths_percentage',ascending=False)
deaths_con = deaths_con[['continent','total_deaths','deaths_percentage']]
deaths_con

"""### **Continents vs Death Cases Percentage**"""

dfr = Cont_wise
attnd = 'continent'
attnc = 'deaths_percentage'

mcn = 'orange'
rcn = 'mediumaquamarine'

tn = 'Continents vs Death Cases Percentage'
yxn = 'Death Cases Percentage'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Continents vs Total Death Cases**"""

dfr = Cont_wise
attnd = 'continent'
attnc = 'total_deaths'

mcn = 'orange'
rcn = 'mediumaquamarine'

tn = 'Continents vs Total Death Cases'
yxn = 'Total Death Cases'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Continents vs Covid 19 Cases Percentage**"""

dfr = Cont_wise
attnd = 'continent'
attnc = 'cases_percentage'

mcn = 'crimson'
rcn = 'lightslategray'

tn = 'Continents vs Total Covid 19 Cases Percentage'
yxn = 'Cases Percentage'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""### **Continents vs Total Covid 19 Cases**"""

dfr = Cont_wise
attnd = 'continent'
attnc = 'total_cases'
mcn = 'crimson'
rcn = 'lightslategray'
tn = 'Continents vs Total Covid 19 Cases'
yxn = 'Cases'
xxn =  'Continents'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""## **Sri Lanka's Status During Covid 19 Pandemic**"""

#derive srilanka's data from the main daatset
sl_df = df[df['location']=='Sri Lanka']

sl_df['people_vaccinated'].fillna(method='ffill',inplace=True)
sl_df['people_fully_vaccinated'].fillna(method='ffill',inplace=True)


sl_df

sl_df.shape

sl_df.isnull().sum()

"""### **Pre Proccessing**"""

#get last date data
sl_summary = sl_df.tail(1)

#claculate percentages
sl_summary['ca_pr_sl'] = round(sl_summary['total_cases'] / sl_summary['population'] * 100,3)
sl_summary['de_pr_sl'] = round(sl_summary['total_deaths'] / sl_summary['population'] * 100,3)
sl_summary['vc_pr_sl'] = round(sl_summary['people_vaccinated'] / sl_summary['population'] * 100,3)
sl_summary['fvc_pr_sl'] = round(sl_summary['people_fully_vaccinated'] / sl_summary['population'] * 100,3)

#drop unwanted columns
sl_summary.drop(['continent','total_vaccinations'],axis=1,inplace=True)

#display proccesed summary data
sl_summary

# define function to plot customized line charts

def line_chart(data_li ,x_vr, y_vr, colour_li, titl, x_n, y_n ):
  #defune figure
  fig = go.Figure()

  #define line chart
  fig.add_trace(go.Scatter(
      x= data_li[x_vr], y = data_li[y_vr],
      mode = 'lines',
      line=dict(width=3, color=colour_li)))
  
  #add title details
  fig.update_layout(
      title = titl,
      title_font_size = 25, legend_font_size = 10,
      width = 1400, height = 620,template='plotly_dark')
  
  #add X axis details
  fig.update_xaxes(
      title_text = x_n ,
      title_font=dict(size=15, family='Verdana', color='white'),
      tickfont=dict(family='Calibri', color='white', size=15))
  
  #add Y axis details
  fig.update_yaxes(
      title_text = y_n,
      title_font=dict(size=15, family='Verdana', color='white'),
      tickfont=dict(family='Calibri', color='white', size=15))

  #plot the line chart
  fig.show()

#define neccesery values into the variables
population_sl = np.array(sl_summary['population'])[0]

vaccine_sl = np.array(sl_summary['people_vaccinated'])[0]

fully_vaccine_sl = np.array(sl_summary['people_fully_vaccinated'])[0]

cases_sl = np.array(sl_summary['total_cases'])[0]

deaths_sl = np.array(sl_summary['total_deaths'])[0]

#calculate Covid 19 Total Vaccination Daily Count 

#define list for store proccessed values
c_list = []
p_list = []
diff_list = []
per_list = []

# calculate chanage presentage & value
for l , t in zip(range(0, (len(sl_df['people_vaccinated']) + 1)) , range(1, len(sl_df['people_vaccinated']))):

  cu_value = sl_df['people_vaccinated'].iloc[t]

  pr_value = sl_df['people_vaccinated'].iloc[l]

  diff_val = cu_value - pr_value

  per_val  = round(( diff_val / pr_value) * 100,2)

  c_list.append(cu_value)
  p_list.append(pr_value)
  diff_list.append(diff_val)
  per_list.append(per_val)


# clean data for further calculations
date_dr = list(sl_df['date'].values)
per_list.insert(0,0)
diff_list.insert(0,0)
c_list.insert(0,0)
p_list.insert(0,0)

#create new dataframe
new_df = {'Date':date_dr ,'Current Faccination':c_list ,'Previous Faccination':p_list,'New Faccination' : diff_list, 'Change Rate' : per_list }
new_faccinations = pd.DataFrame(new_df,columns=['Date','Current Faccination','Previous Faccination','New Faccination','Change Rate'])

new_faccinations.tail()

"""# **Exploratory Data Analysis & Visualization - Sri Lanka**

## **Sri Lanka Covid 19 Vaccination Progress**
"""

#convert integer values to Millions format & round
def round_values(value_raw):
  return round((value_raw/1000000),2)

#convert variable for do-nut chart 
val_1 = [round_values(vaccine_sl), round_values(population_sl - vaccine_sl)]
val_2 = [round_values(fully_vaccine_sl), round_values(population_sl - fully_vaccine_sl)]

annoatation_text_1 = str(vaccine_sl)
annoatation_text_2 = str(fully_vaccine_sl)

labels_1 = ['Vaccinated(Millions)','Not Vaccinated(Millions)']
labels_2 = ['Fully Vaccinated(Millions)','Not Fully Vaccinated(Millions)']

title_name = "Sri Lanka Covid 19 Vaccination Progress " + str(Analysis_Date)

# Create subplots: use 'domain' type for Pie subplot
fig = make_subplots(rows=1, cols=2, specs=[[{'type':'domain'}, {'type':'domain'}]], subplot_titles =( "Vaccine", "Fully Vaccine" ))

#add first pie-chart
fig.add_trace(go.Pie(labels=labels_1, 
                     values= val_1, 
                     name="Vaccination (at least 1 dose)",
                     marker=dict(colors=['#2d8cff','#727274'])),
                     1, 1)

#add first pie-chart
fig.add_trace(go.Pie(labels=labels_2,
                     values= val_2,
                     name="Fully Vaccination",
                     marker=dict(colors=['#ff00eb','#727274'])),
                     1, 2)


# use `hole` to create a donut-like pie chart
fig.update_traces(hole=.6, 
                  hoverinfo="label+value",
                  hoverlabel=dict(font_size=20),
                  textfont_size=20,
                  showlegend=False)

# update other propertise
fig.update_layout(
    title_text=title_name,
    title_font_size = 25,
    template='plotly_dark',
    width = 1400, 
    height = 620,
    # Add annotations in the center of the donut pies.
    annotations=[dict(text='At Least 1 Dose <br>'+ annoatation_text_1, x=0.23, y=0.435, font_size=24, font_color='white' ,showarrow=False,),
                 dict(text='Fully Vaccination <br>'+annoatation_text_2, x=0.78, y=0.435, font_size=24, font_color='white',showarrow=False)])


fig.show()

"""## **Sri Lanka Covid 19 Tests Time Series**"""

dataset_line_chart = sl_df
x_line_chart = 'date'
y_line_chart = 'total_tests'
colour_line_chart = 'limegreen'
title_line_chart = 'Sri Lanka Covid 19 Tests Time Series'
xname_line_chart = 'Date'
yname_line_chart = 'Total Tests'

line_chart(dataset_line_chart, x_line_chart, y_line_chart, colour_line_chart, title_line_chart, xname_line_chart, yname_line_chart  )

"""## **Covid 19 Daily Tests Count In Sri Lanka**"""

#covid 19 test daily count

dfr = sl_df
attnd = 'date'
attnc = 'new_tests'

mcn = 'red'
rcn = 'limegreen'

tn = 'Covid 19 Daily Tests In Sri Lanka'
yxn = 'Tests'
xxn =  'Date'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""## **Sri Lanka Covid 19 Positive Cases Time Series**"""

dataset_line_chart = sl_df
x_line_chart = 'date'
y_line_chart = 'total_cases'
colour_line_chart = 'gold'
title_line_chart = 'Sri Lanka Covid 19 Positive Cases Time Series'
xname_line_chart = 'Date'
yname_line_chart = 'Total Positive Cases'

line_chart(dataset_line_chart, x_line_chart, y_line_chart, colour_line_chart, title_line_chart, xname_line_chart, yname_line_chart  )

"""## **Covid 19 Positive cases Daily count In Sri Lanka**"""

#Covid 19 Positive cases day by day count

dfr = sl_df
attnd = 'date'
attnc = 'new_cases'

mcn = 'gold'
rcn = 'gold'

tn = 'Covid 19 Positive cases Daily count In Sri Lanka'
yxn = 'Tests'
xxn =  'Date'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""## **Sri Lanka Covid 19 Death Cases Time Series**"""

dataset_line_chart = sl_df
x_line_chart = 'date'
y_line_chart = 'total_deaths'
colour_line_chart = 'red'
title_line_chart = 'Sri Lanka Covid 19 Death Cases Time Series'
xname_line_chart = 'Date'
yname_line_chart = 'Total Death Cases'

line_chart(dataset_line_chart, x_line_chart, y_line_chart, colour_line_chart, title_line_chart, xname_line_chart, yname_line_chart  )

"""## **Covid 19 Death Cases Daily Count In Sri Lanka**"""

dfr = sl_df
attnd = 'date'
attnc = 'new_deaths'

mcn = '#ff0000'
rcn = '#ff0000'

tn = 'Covid 19 Death Cases Daily Count In Sri Lanka'
yxn = 'Deaths'
xxn =  'Date'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""## **Sri Lanka Covid 19 Vaccination (at least 1 Dose) Time Series**"""

dataset_line_chart = sl_df
x_line_chart = 'date'
y_line_chart = 'people_vaccinated'
colour_line_chart = 'deepskyblue'
title_line_chart = 'Sri Lanka Covid 19 Vaccination (at least 1 Dose) Time Series'
xname_line_chart = 'Date'
yname_line_chart = 'Total Vaccinations'

line_chart(dataset_line_chart, x_line_chart, y_line_chart, colour_line_chart, title_line_chart, xname_line_chart, yname_line_chart)

"""## **Covid 19 Total Vaccination Daily Count In Sri Lanka**"""

dfr = new_faccinations
attnd = 'Date'
attnc = 'New Faccination'

mcn = 'deepskyblue'
rcn = 'deepskyblue'

tn = 'Covid 19 Total Vaccination Daily Count In Sri Lanka'
yxn = 'New Faccinations'
xxn =  'Date'
tmpn = 'plotly_dark'

customized_barchart(dfr, attnd, attnc, mcn, rcn, tn, yxn, xxn, tmpn)

"""## **Sri Lanka Covid 19 Fully Vaccination Time Series**"""

dataset_line_chart = sl_df
x_line_chart = 'date'
y_line_chart = 'people_fully_vaccinated'
colour_line_chart = 'orchid'
title_line_chart = 'Sri Lanka Covid 19 Fully Vaccination Time Series'
xname_line_chart = 'Date'
yname_line_chart = 'Total Fully Vaccinations'

line_chart(dataset_line_chart, x_line_chart, y_line_chart, colour_line_chart, title_line_chart, xname_line_chart, yname_line_chart)

"""## **Vaccination vs Positive Cases Time Series - Sri Lanka**"""

fig = make_subplots(specs=[[{"secondary_y": True}]])

fig.add_trace(go.Scatter(
     x= sl_df['date'], y = sl_df['people_vaccinated'],
     mode = 'lines',
     name='Vaccination',
     line=dict(width=3, color='royalblue')),secondary_y=False)

fig.add_trace(go.Scatter(
     x= sl_df['date'], y = sl_df['total_cases'],
     mode = 'lines',
     name='Death Cases',
     line=dict(width=3, color='gold')),secondary_y=True)

fig.update_layout(
     title = "Vaccination vs Positive Cases Time Series - Sri Lanka",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620,
     template='plotly_dark')

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='white'),
     tickfont=dict(family='Calibri', color='white', size=15))

fig.update_yaxes(title_text="Vaccination", secondary_y=False)
fig.update_yaxes(title_text="Death Cases", secondary_y=True,)

fig.show()

"""## **Vaccination vs Death Cases Time Series - Sri Lanka**"""

fig = make_subplots(specs=[[{"secondary_y": True}]])

fig.add_trace(go.Scatter(
     x= sl_df['date'], y = sl_df['people_vaccinated'],
     mode = 'lines',
     name='Vaccination',
     line=dict(width=3, color='royalblue')),secondary_y=False)

fig.add_trace(go.Scatter(
     x= sl_df['date'], y = sl_df['total_deaths'],
     mode = 'lines',
     name='Death Cases',
     line=dict(width=3, color='red')),secondary_y=True)

fig.update_layout(
     title = "Vaccination vs Death Cases Time Series Sri Lanka",
     title_font_size = 25, legend_font_size = 10,
     width = 1400, height = 620,
     template='plotly_dark')

fig.update_xaxes(
     title_text = 'Year',
     title_font=dict(size=15, family='Verdana', color='white'),
     tickfont=dict(family='Calibri', color='white', size=15))

fig.update_yaxes(title_text="Vaccination", secondary_y=False)
fig.update_yaxes(title_text="Death Cases", secondary_y=True,)

fig.show()