Covid-Survival-Analysis

Loading libraries

import json
from datetime import timedelta
from urllib.request import urlopen
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import plotly.graph_objs as go
from plotly.subplots import make_subplots

from plotly.offline import plot, iplot, init_notebook_mode
init_notebook_mode(connected=True)

from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score,silhouette_samples
from sklearn.linear_model import LinearRegression,Ridge,Lasso
from sklearn.svm import SVR
from sklearn.metrics import mean_squared_error,r2_score
import statsmodels.api as sm
from statsmodels.tsa.api import Holt,SimpleExpSmoothing,ExponentialSmoothing
# ! pip install fbprophet
# from fbprophet import Prophet
from sklearn.preprocessing import PolynomialFeatures
from statsmodels.tsa.stattools import adfuller
#from pyramid.arima import auto_arima
std=StandardScaler()

import warnings
warnings.filterwarnings('ignore')

Loading Dataset

# Full data
covid_19_data = pd.read_csv('covid/covid_19_data.csv')
print(covid_19_data.size)
covid_19_data.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	SNo	ObservationDate	Province/State	Country/Region	Last Update	Confirmed
0	1	01/22/2020	Anhui	Mainland China	1/22/2020 17:00	1.0
1	2	01/22/2020	Beijing	Mainland China	1/22/2020 17:00	14.0
2	3	01/22/2020	Chongqing	Mainland China	1/22/2020 17:00	6.0
3	4	01/22/2020	Fujian	Mainland China	1/22/2020 17:00	1.0
4	5	01/22/2020	Gansu	Mainland China	1/22/2020 17:00	0.0

full_grouped = pd.read_csv('covid/full_grouped.csv')
full_grouped['Date'] = pd.to_datetime(full_grouped['Date'])
print(full_grouped.size)
full_grouped.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Date	Country/Region	WHO Region
0	2020-01-22	Afghanistan	Eastern Mediterranean
1	2020-01-22	Albania	Europe
2	2020-01-22	Algeria	Africa
3	2020-01-22	Andorra	Europe
4	2020-01-22	Angola	Africa

day_wise = pd.read_csv('covid/day_wise.csv')
day_wise['Date'] = pd.to_datetime(day_wise['Date'])
print(day_wise.size)
day_wise.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Date	Confirmed	Deaths	Recovered	Active	New cases	New deaths	New recovered	Deaths / 100 Cases	Recovered / 100 Cases	Deaths / 100 Recovered	No. of countries
0	2020-01-22	555	17	28	510	0	0	0	3.06	5.05	60.71	6
1	2020-01-23	654	18	30	606	99	1	2	2.75	4.59	60.00	8
2	2020-01-24	941	26	36	879	287	8	6	2.76	3.83	72.22	9
3	2020-01-25	1434	42	39	1353	493	16	3	2.93	2.72	107.69	11
4	2020-01-26	2118	56	52	2010	684	14	13	2.64	2.46	107.69	13

country_wise = pd.read_csv('covid/country_wise_latest.csv')
country_wise = country_wise.replace('', np.nan).fillna(0)
print(country_wise.size)
country_wise.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Country/Region	Confirmed	Deaths	Recovered	Active	New cases	New deaths	New recovered	Deaths / 100 Cases	Recovered / 100 Cases	Deaths / 100 Recovered	Confirmed last week	1 week change	1 week % increase	WHO Region
0	Afghanistan	36263	1269	25198	9796	106	10	18	3.50	69.49	5.04	35526	737	2.07	Eastern Mediterranean
1	Albania	4880	144	2745	1991	117	6	63	2.95	56.25	5.25	4171	709	17.00	Europe
2	Algeria	27973	1163	18837	7973	616	8	749	4.16	67.34	6.17	23691	4282	18.07	Africa
3	Andorra	907	52	803	52	10	0	0	5.73	88.53	6.48	884	23	2.60	Europe
4	Angola	950	41	242	667	18	1	0	4.32	25.47	16.94	749	201	26.84	Africa

worldometer_data = pd.read_csv('covid/worldometer_data.csv')
worldometer_data = worldometer_data.replace('', np.nan).fillna(0)
print(worldometer_data.size)
worldometer_data.head()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	Country/Region	Continent	Population	TotalCases	TotalDeaths	TotalRecovered	ActiveCases	Serious,Critical	Tot Cases/1M pop	Deaths/1M pop	TotalTests	Tests/1M pop	WHO Region
0	USA	North America	3.311981e+08	5032179	162804.0	2576668.0	2292707.0	18296.0	15194.0	492.0	63139605.0	190640.0	Americas
1	Brazil	South America	2.127107e+08	2917562	98644.0	2047660.0	771258.0	8318.0	13716.0	464.0	13206188.0	62085.0	Americas
2	India	Asia	1.381345e+09	2025409	41638.0	1377384.0	606387.0	8944.0	1466.0	30.0	22149351.0	16035.0	South-EastAsia
3	Russia	Europe	1.459409e+08	871894	14606.0	676357.0	180931.0	2300.0	5974.0	100.0	29716907.0	203623.0	Europe
4	South Africa	Africa	5.938157e+07	538184	9604.0	387316.0	141264.0	539.0	9063.0	162.0	3149807.0	53044.0	Africa

Exploratory Data Analysis

covid_19_data.describe()

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>

	SNo	Confirmed	Deaths	Recovered
count	306429.000000	3.064290e+05	306429.000000	3.064290e+05
mean	153215.000000	8.567091e+04	2036.403268	5.042029e+04
std	88458.577156	2.775516e+05	6410.938048	2.015124e+05
min	1.000000	-3.028440e+05	-178.000000	-8.544050e+05
25%	76608.000000	1.042000e+03	13.000000	1.100000e+01
50%	153215.000000	1.037500e+04	192.000000	1.751000e+03
75%	229822.000000	5.075200e+04	1322.000000	2.027000e+04
max	306429.000000	5.863138e+06	112385.000000	6.399531e+06

# Get the shape of the data (rows, columns)
print("Shape of the DataFrame:", covid_19_data.shape)

Shape of the DataFrame: (306429, 8)

# Get the column names
print("Column names:", covid_19_data.columns)

Column names: Index(['SNo', 'ObservationDate', 'Province/State', 'Country/Region',
       'Last Update', 'Confirmed', 'Deaths', 'Recovered'],
      dtype='object')

# Get the data types of the columns
print("Data types:", covid_19_data.dtypes)

Data types: SNo                  int64
ObservationDate     object
Province/State      object
Country/Region      object
Last Update         object
Confirmed          float64
Deaths             float64
Recovered          float64
dtype: object

# Get the number of missing values in each column
print("Number of missing values in each column:\n", covid_19_data.isnull().sum())

Number of missing values in each column:
 SNo                    0
ObservationDate        0
Province/State     78100
Country/Region         0
Last Update            0
Confirmed              0
Deaths                 0
Recovered              0
dtype: int64

# Visualize the distribution of numerical columns using histograms
covid_19_data[["Confirmed","Deaths","Recovered"]].hist(bins=20, figsize=(20,15))
plt.show()

observations

most number of confirmed cases are 0 - 200,000
most number of deaths are in range 0 - 5,000
most number of recovered are in range 0 - 300,000

Creating a Tree map using day wise, country_wise data set showing number of active, recovered, and deaths.

fig = px.treemap(day_wise[['Date','Deaths', 'Recovered', 'Active']].melt(id_vars="Date", 
                 value_vars=['Active', 'Deaths', 'Recovered']), 
                 path=["variable"], values="value", height=700, width=700)
fig.data[0].textinfo = 'label+value'
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

The number of Active and Recovered are nearly equal and completely overweigh Deaths

tree map showing confirmed cases over different countries

fig = px.treemap(country_wise, path=["Country/Region"], values="Confirmed", height=700,
             title="Confirmed", color_discrete_sequence = px.colors.qualitative.G10)
fig.data[0].textinfo = 'label+text+value'
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

US and Brazil have the highest confirmed cases

tree map showing confirmed cases over different countries

fig = px.treemap(country_wise, path=["Country/Region"], values="Active", height=700,
             title="Active", color_discrete_sequence = px.colors.qualitative.Dark2)
fig.data[0].textinfo = 'label+text+value'
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

US, Brazil and India have the highest number of active cases overall

cases over the time

fig = px.bar(day_wise, x="Date", y="Active", width=800, color_discrete_sequence=["red"])
fig2 = px.bar(day_wise, x="Date", y="Confirmed", width=800, color_discrete_sequence=["black"])
fig2.update_layout(title="confirmed cases")

fig.update_layout(title="active cases")
fig.show()
fig2.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

Both the active and Confirmed cases are increasing rapidly and July 27th 2020 has the highest recorded cases according to the data

Line plots showing trend of Deaths per 100 cases and Recovered per 100 cases

fig = px.line(day_wise, x="Date", y="Deaths / 100 Cases", width=900, color_discrete_sequence=["orange"])
fig.update_layout(title="Deaths / 100 Cases")
fig.show()
fig = px.line(day_wise, x="Date", y="Recovered / 100 Cases", width=900, color_discrete_sequence=["green"])
fig.update_layout(title="Recovered / 100 Cases")
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

april 24 and 30 2020 had the highest deaths /100 cases and the number is gradually decreasing over time
March 8th 2020 had the highest recovered/ 100 cases and the number is gradually increasing over time and again reached a peak value on July 26th 2020

Stacked line plot showing totoal number of recovered, deaths and active cases over time.

fig = px.area(full_grouped[['Recovered', 'Deaths', 'Active','Date']].groupby(by = 'Date').sum().reset_index().melt(id_vars="Date", value_vars=['Recovered', 'Deaths', 'Active'],
                 var_name='Case', value_name='Count'), x="Date", y="Count", color='Case', height=700, width=800,
             title='Cases over time')
fig.update_layout(xaxis_rangeslider_visible=True)
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

Number of total Active is > total number of deaths > total number of recovered over the entire time period of the data

trend of recovered and active cases over a time period

px.line(day_wise[['Date', 'Recovered', 'Active']].melt(id_vars='Date', value_vars=['Recovered', 'Active'], 
                 var_name='Variable', value_name='Count'), x='Date', y='Count', color='Variable')

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

observation

till june 15th 2020 active cases are more than recovered cases but after that recovered cases is more than active cases

Bar plot of top 15 countries with highest confirmed cases

fig = px.bar(country_wise.sort_values("Confirmed").tail(15), 
             x="Confirmed", y="Country/Region", color='WHO Region',  
             text="Confirmed", orientation='h', width=700,
             color_discrete_sequence = px.colors.qualitative.G10)
fig.update_layout(title="Confirmed", 
                  yaxis_categoryorder = 'total ascending',
                  uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

observation

America region has the highest number of confirmed cases
US Country had the highest number confirmed cases

Bar plot of top 15 countries with highest confirmed cases

fig = px.bar(country_wise.sort_values("Active").tail(15), 
             x="Active", y="Country/Region", color='WHO Region',  
             text="Active", orientation='h', width=700,
             color_discrete_sequence = px.colors.qualitative.G10)
fig.update_layout(title="Active", 
                  yaxis_categoryorder = 'total ascending',
                  uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

observation

America WHO region has the highest number of active cases
US Country had the highest number active cases

Bar plot of top 10 countries with highest confirmed cases per 1 million population

fig = px.bar(worldometer_data[worldometer_data['Population']>1000000].sort_values('Tot Cases/1M pop', ascending=True).tail(10),
             x='Tot Cases/1M pop', y="Country/Region", color='WHO Region',  
             text='Tot Cases/1M pop', orientation='h', width=700, 
             color_discrete_sequence = px.colors.qualitative.Dark2)
fig.update_layout(title='Tot Cases/1M pop'+' (Only countries with > 1M Pop)', 
                  xaxis_title="", yaxis_title="", 
                  yaxis_categoryorder = 'total ascending',
                  uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

Observation

Eastern Maditerranean countries has the highest cases/ 1 million population
Qatar country has the highest number of cases/ 1 million population

Bar plot of top 10 countries with highest Total tests

fig = px.bar(worldometer_data[worldometer_data['Population']>1000000].sort_values('TotalTests', ascending=True).tail(10),
             x='TotalTests', y="Country/Region", color='WHO Region',  
             text='TotalTests', orientation='h', width=700, 
             color_discrete_sequence = px.colors.qualitative.Dark2)
fig.update_layout(title='TotalTests'+' (Only countries with > 1M Pop)', 
                  xaxis_title="", yaxis_title="", 
                  yaxis_categoryorder = 'total ascending',
                  uniformtext_minsize=8, uniformtext_mode='hide')
fig.show()

// Listen for the removal of the full notebook cells var notebookContainer = gd.closest('#notebook-container'); if (notebookContainer) {{ x.observe(notebookContainer, {childList: true}); }}

// Listen for the clearing of the current output cell var outputEl = gd.closest('.output'); if (outputEl) {{ x.observe(outputEl, {childList: true}); }}

                    })                };                });            </script>        </div>

observation

USA has highest number of total tests

Stacked bar plot showing confirmed cases per day for different countries and regions

fig = px.bar(full_grouped, x="Date", y='Confirmed', color='Country/Region', 
             height=600, title='Confirmed', 
             color_discrete_sequence = px.colors.cyclical.mygbm)
fig.update_layout(showlegend=True)
fig.show()

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
README.md		README.md
covid data survival analysis.html		covid data survival analysis.html
covid data survival analysis.ipynb		covid data survival analysis.ipynb
covid.zip		covid.zip

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

Covid-Survival-Analysis

Loading libraries

Loading Dataset

Exploratory Data Analysis

observations

Creating a Tree map using day wise, country_wise data set showing number of active, recovered, and deaths.

Observation

tree map showing confirmed cases over different countries

Observation

tree map showing confirmed cases over different countries

Observation

cases over the time

Observation

Line plots showing trend of Deaths per 100 cases and Recovered per 100 cases

Observation

Stacked line plot showing totoal number of recovered, deaths and active cases over time.

Observation

trend of recovered and active cases over a time period

observation

Bar plot of top 15 countries with highest confirmed cases

observation

Bar plot of top 15 countries with highest confirmed cases

observation

Bar plot of top 10 countries with highest confirmed cases per 1 million population

Observation

Bar plot of top 10 countries with highest Total tests

observation

Stacked bar plot showing confirmed cases per day for different countries and regions

About

Uh oh!

Releases

Packages

Uh oh!

Contributors

Uh oh!

Languages

Folders and files

Latest commit

History

Repository files navigation

Covid-Survival-Analysis

Loading libraries

Loading Dataset

Exploratory Data Analysis

observations

Creating a Tree map using day wise, country_wise data set showing number of active, recovered, and deaths.

Observation

tree map showing confirmed cases over different countries

Observation

tree map showing confirmed cases over different countries

Observation

cases over the time

Observation

Line plots showing trend of Deaths per 100 cases and Recovered per 100 cases

Observation

Stacked line plot showing totoal number of recovered, deaths and active cases over time.

Observation

trend of recovered and active cases over a time period

observation

Bar plot of top 15 countries with highest confirmed cases

observation

Bar plot of top 15 countries with highest confirmed cases

observation

Bar plot of top 10 countries with highest confirmed cases per 1 million population

Observation

Bar plot of top 10 countries with highest Total tests

observation

Stacked bar plot showing confirmed cases per day for different countries and regions

About

Resources

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages