US_CORONA_Analysis.py

# -*- coding: utf-8 -*-
"""US_CORONA_Analysis.ipynb
"""

import numpy as np
import pandas as pd
import io
import requests
import matplotlib.pyplot as plt

"""In case of failure of URL,The dataset is taken from ::::

https://covidtracking.com/api
"""

url="http://covidtracking.com/api/states/daily.csv"
s=requests.get(url).content

df = pd.read_csv(io.StringIO(s.decode('utf-8')))

df['date'] =  pd.to_datetime(df['date'], format='%Y%m%d')

df.drop(['dateChecked'],axis=1,inplace=True)

df['state']=df['state'].apply(str)

df.info()

df.head(10)

df.fillna(value=-1, inplace=True)
df.head(50)

"""Function to plot a bar chart -->>"""

def plot_var(var='positiveIncrease',
             state='NY'):
    """
    Plots a bar chart of the given variable over the date range
    """
    assert type(var)==str, "Expected string as the variable name"
    assert type(state)==str, "Expected string as the state name"
 
    y = df[df['state']==state][var]
    x = df[df['state']==state]['date']
    plt.figure(figsize=(12,4))
    plt.title("Plot of \"{}\" for {}".format(var,state),fontsize=18)
    plt.bar(x=x,height=y,edgecolor='k',color='orange')
    plt.grid(True)
    plt.xticks(fontsize=14,rotation=45)
    plt.yticks(fontsize=14)
    plt.show()

plot_var()

plot_var('hospitalizedIncrease','GA')

plot_var('deathIncrease','MI')

plot_var('totalTestResultsIncrease','MA')

"""Function to plot scatter plot -->>"""

def plot_xy(varx='totalTestResultsIncrease',
            vary='positiveIncrease',
            state='NY'):
    """
    Plots a bar chart of the given variable over the date range
    """
    assert type(varx)==str, "Expected string as the variable x name"
    assert type(vary)==str, "Expected string as the variable y name"
 
    y = df[df['state']==state][vary]
    x = df[df['state']==state][varx]
    if (x.nunique()!=1) and (y.nunique()!=1):
        plt.figure(figsize=(12,4))
        plt.title("Plot of \"{}\" vs. \"{}\" for {}".format(varx,vary,state),fontsize=18)
        plt.scatter(x=x,y=y,edgecolor='k',color='lightgreen',s=100)
        plt.grid(True)
        plt.xticks(fontsize=14,rotation=45)
        plt.yticks(fontsize=14)
        plt.show()
    else:
        print("Some of the data unavailable for a scatter plot. Sorry!")

plot_xy(state='NY')

plot_xy('hospitalized','death','GA')

"""Testing tracker function -->>"""

def plotTesting(lst_states=['NY','CA','MA','TX','PA','AL','CO']):
    """
    Plots the cumulative testing done by the given list of states
    """
    legends = []
    plt.figure(figsize=(10,5))
    plt.title("Total test results",fontsize=18)
    for s in lst_states:
        data = np.array(df[df['state']==s]['totalTestResults'])[-1::-1]
        slope = int((data[-1]-data[0])/len(data))
        plt.plot(data,linewidth=2)
        plt.text(x=len(data)-2,y=data[-1]*1.05,s=s,fontsize=14)
        legends.append(str(slope)+" tests/day in " + s)
    plt.legend(legends,fontsize=14)
    plt.grid(True)
    plt.xlim(0,len(data)+2)
    plt.xticks(fontsize=16)
    plt.yticks(fontsize=16)
    plt.xlabel("Days",fontsize=16)
    plt.ylabel("Total test results",fontsize=16)
    plt.show()

plotTesting()

"""Function to compute fatality ratio -->>"""

def fatality_ratio(state='CA'):
    """
    Computes the fatality ratio for the given state
    Fatality ratio is the ratio of total dead to total positive case
    """
    
    date = df.iloc[0]['date']
    try:
        d = float(df[(df['state']==state) & (df['date']==date)]['death'])
        p = float(df[(df['state']==state) & (df['date']==date)]['positive'])
    except:
        print("Could not retrieve the necessary information")
    
    if (d!=-1.0) and (p!=-1.0) and (p!=0):
        return round(d/p,3)
    else:
        return -1

"""Function to compute hospitalization ratio -->>"""

def hospitalization_ratio(state='NY'):
    """
    Computes the hospitalization ratio for the given state
    Hospitalization ratio is the ratio of total hospitalized to total positive case
    """
    
    date = df.iloc[0]['date']
    try:
        h = float(df[(df['state']==state) & (df['date']==date)]['hospitalized'])
        p = float(df[(df['state']==state) & (df['date']==date)]['positive'])
    except:
        print("Could not retrieve the necessary information")
    
    if (h!=-1.0) and (p!=-1.0) and (p!=0):
        return round(h/p,3)
    else:
        return -1

"""Function to compute positive case/total test ratio -->>"""

def positiveTest_ratio(state='NY'):
    """
    Computes the test-positive ratio for the given state
    Test-positive ratio is the ratio of total positive cases to total number of tests
    """
    
    date = df.iloc[0]['date']
    try:
        p = float(df[(df['state']==state) & (df['date']==date)]['positive'])
        t = float(df[(df['state']==state) & (df['date']==date)]['totalTestResults'])
    except:
        print("Could not retrieve the necessary information")
        return -1
    
    if (p!=-1.0) and (t!=-1.0) and (t!=0):
        return round(p/t,3)
    else:
        return -1

"""Function to compute recovery ratio -->>"""

def recovery_ratio(state='NY'):
    """
    Computes the recovery ratio for the given state
    Recovery ratio is the ratio of total recovered cases to total positive cases
    """
    
    date = df.iloc[0]['date']
    try:
        r = float(df[(df['state']==state) & (df['date']==date)]['recovered'])
        p = float(df[(df['state']==state) & (df['date']==date)]['positive'])
    except:
        print("Could not retrieve the necessary information")
        return -1
    
    if (r!=-1.0) and (p!=-1.0) and (p!=0):
        return round(r/p,3)
    else:
        return -1

"""Fatality ratio chart -->>"""

states = ['CA','NY','MI','MA','PA','IL','AL','CO','PR']
fr,x = [],[]
for s in states:
    data = fatality_ratio(s)
    if data!=-1:
        fr.append(data)
        x.append(s)

plt.figure(figsize=(8,4))
plt.title("Fatality ratio chart",fontsize=18)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
plt.bar(x=x,height=fr,color='red',
        edgecolor='k',linewidth=2)
plt.show()

"""Hospitalization ratio chart -->>"""

states = ['CA','NY','MI','MA','PA','IL']
hos,x = [],[]
for s in states:
    data = hospitalization_ratio(s)
    if data!=-1:
        hos.append(data)
        x.append(s)
plt.figure(figsize=(8,4))
plt.title("Hospitalization ratio chart",fontsize=18)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
plt.bar(x=x,height=hos,color='brown',
        edgecolor='k',linewidth=2)
plt.show()

"""Test-positive ratio chart -->>"""

states = ['CA','NY','MI','MA','PA','IL','CO','AL']
tp,x = [],[]
for s in states:
    data = positiveTest_ratio(s)
    if data!=-1:
        tp.append(data)
        x.append(s)
plt.figure(figsize=(8,4))
plt.title("Test-positive ratio chart",fontsize=18)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
plt.bar(x=x,height=tp,color='blue',
        edgecolor='k',linewidth=2)
plt.show()

"""Bubble charts -->>"""

states = list(df['state'].unique())
for s in ['AS','GU','MP','PU','VI']:
    try:
        states.remove(s)
    except:
        pass

fr,x = [],[]
for s in states:
    data = fatality_ratio(s)
    if data!=-1:
        fr.append(data)
        x.append(s)
fr = np.array(fr)
plt.figure(figsize=(15,7))
plt.tick_params(
    axis='x',          # changes apply to the x-axis
    which='both',      # both major and minor ticks are affected
    bottom=False,      # ticks along the bottom edge are off
    top=False,         # ticks along the top edge are off
    labelbottom=False)
plt.title("Fatality ratio across the states",fontsize=18)
plt.scatter(x=x,y=fr,
            s=4e5*fr**2,
            color='orange',edgecolor='red',alpha=0.75,linewidth=2.5)
#plt.xticks(rotation=45,fontsize=12)
for i,s in enumerate(x):
    plt.annotate(s=s,xy=(x[i],fr[i]))
plt.ylim(0,0.12)
plt.yticks(fontsize=16)
plt.grid(True,axis='y')
plt.show()

states = list(df['state'].unique())
for s in ['AS','GU','MP','PU','VI']:
    try:
        states.remove(s)
    except:
        pass

tp,x = [],[]
for s in states:
    data = positiveTest_ratio(s)
    if data!=-1:
        tp.append(data)
        x.append(s)
tp = np.array(tp)
plt.figure(figsize=(15,7))
plt.tick_params(
    axis='x',          # changes apply to the x-axis
    which='both',      # both major and minor ticks are affected
    bottom=False,      # ticks along the bottom edge are off
    top=False,         # ticks along the top edge are off
    labelbottom=False)
plt.title("Test-positive ratio across the states",fontsize=18)
plt.scatter(x=x,y=tp,
            s=2e4*tp**2,
            color='blue',edgecolor='red',alpha=0.5,linewidth=2)
plt.xticks(rotation=90,fontsize=12)
for i,s in enumerate(x):
    plt.annotate(s=s,xy=(x[i],tp[i]))
plt.ylim(0,0.6)
plt.yticks(fontsize=16)
plt.grid(True,axis='y')
plt.show()

"""Function for states having 14 days of decreasing case counts -->>"""

def caseCountsdecrease(days=14,state='NY'):
    """
    Determines whether the given state has a decreasing case counts for given number of days
    Arguments:
            days: Number of days to go back
            state: Name of the state (a string)
    Returns:
            A tuple containing the successive difference vector (of new cases) and
            the number of negative quantities in that vector. When all the quantities are negative,
            the state has shown consistent decrease in new cases for the given number of days.
    """
    positiveIncrease = np.array(df[df['state']==state]['positiveIncrease'][:days+1])[-1::-1]
    diff = np.diff(positiveIncrease)
    countofNeg = np.sum(diff <= 0, axis=0)
    return (countofNeg, diff)

states = ['CA','MI','GA','LA']
cd = []
x = np.arange(1,15,1)
plt.figure(figsize=(10,6))
plt.title("Last 14 days successive difference in new positive cases \n(more negative numbers is better)",
          fontsize=18)
for s in states:
    _,data = caseCountsdecrease(days=14,state=s)
    plt.plot(x,data,linewidth=2)
plt.legend(states,fontsize=16,ncol=2)
plt.grid(True)
plt.xticks(fontsize=16)
plt.yticks(fontsize=16)
plt.xlabel("Last 14 days",fontsize=16)
plt.ylabel("Successive difference in new cases",fontsize=16)
plt.hlines(y=0,xmin=0,xmax=15,linestyles='--',lw=3)
plt.show()

states = ['CA']
cd = []
x = np.arange(1,15,1)
plt.figure(figsize=(10,6))
plt.title("Last 14 days successive difference in new positive cases \n(more negative numbers is better)",
          fontsize=18)
for s in states:
    _,data = caseCountsdecrease(days=14,state=s)
    plt.plot(x,data,linewidth=2)
plt.legend(states,fontsize=16,ncol=2)
plt.grid(True)
plt.xticks(fontsize=16)
plt.yticks(fontsize=16)
plt.xlabel("Last 14 days",fontsize=16)
plt.ylabel("Successive difference in new cases",fontsize=16)
plt.hlines(y=0,xmin=0,xmax=15,linestyles='--',lw=3)
plt.show()

states = ['LA']
cd = []
x = np.arange(1,15,1)
plt.figure(figsize=(10,6))
plt.title("Last 14 days successive difference in new positive cases \n(more negative numbers is better)",
          fontsize=18)
for s in states:
    _,data = caseCountsdecrease(days=14,state=s)
    plt.plot(x,data,linewidth=2)
plt.legend(states,fontsize=16,ncol=2)
plt.grid(True)
plt.xticks(fontsize=16)
plt.yticks(fontsize=16)
plt.xlabel("Last 14 days",fontsize=16)
plt.ylabel("Successive difference in new cases",fontsize=16)
plt.hlines(y=0,xmin=0,xmax=15,linestyles='--',lw=3)
plt.show()