DMG HW0

import numpy as np import urllib.request import pandas as pd from urllib.request import urlopen import json state_code_temp = {'andaman and nicobar islands':'an', #ut 'andhra pradesh':'ap', 'arunachal pradesh':'ar', 'assam':'as', 'bihar':'br', 'chandigarh':'ch', #ut 'chhattisgarh':'ct', 'delhi':'dl', #ut 'dadra & nagar haveli & daman & diu':'dn', #ut 'goa':'ga', 'gujarat':'gj', 'himachal pradesh':'hp', 'haryana':'hr', 'jharkhand':'jh', 'jammu and kashmir':'jk', 'karnataka':'ka', 'kerala':'kl', 'ladakh':'la', #ut 'lakshadweep':'ld', #ut 'maharashtra':'mh', 'manipur':'mn', 'madhya pradesh':'mp', 'mizoram':'mz', 'nagaland':'nl', 'odisha':'or', 'punjab':'pb', 'puducherry':'py', #ut 'rajasthan':'rj', 'sikkim':'sk', 'telangana':'tg', 'tamil nadu':'tn', 'tripura':'tr', 'uttar pradesh':'up', 'uttarakhand':'ut', 'west bengal':'wb', 'states unassigned':'un' } statesonly = ['andhra pradesh', 'arunachal pradesh', 'assam', 'bihar', 'chhattisgarh', 'goa', 'gujarat', 'himachal pradesh','haryana', 'jharkhand','jammu and kashmir', 'karnataka', 'kerala', 'maharashtra','manipur','madhya pradesh','mizoram', 'nagaland', 'odisha','punjab','rajasthan','sikkim','telangana','tamil nadu','tripura','uttar pradesh','uttarakhand','west bengal'] state_code = {} for i in state_code_temp: code = state_code_temp[i] state_code[code]=i state_code[i]=code url = "https://data.covid19india.org/states_daily.json" urlfile = urlopen(url) data = json.loads(urlfile.read()) df = pd.json_normalize(data, record_path =['states_daily']) # print((df.columns))

#code for Q1 A def get_total_sum(status): currentdata = df.loc[df['status']==status] return currentdata['tt'].astype(int).sum() print("Q1 A") print("Total Number of Confirmed Cases:",get_total_sum('Confirmed')) print("Total Number of Recovered Cases:",get_total_sum('Recovered')) print("Total Number of Deceased Cases:",get_total_sum('Deceased'))

#Code for Q1 B def get_statewise_total(stateid,status): currentdata = df.loc[df['status']==status] return currentdata[stateid].astype(int).sum() states = ['delhi','maharashtra','west bengal','tamil nadu'] print("Q1 B") for i in states: code = state_code[i] i = i.upper() status = ['Confirmed','Recovered','Deceased'] for s in status: total = get_statewise_total(code,s) print("Total Number of %s Cases in %s: %d"%(s,i,total)) print()

#code for Q1 C states = list(state_code_temp.keys()) recovery_rates = {} print("Q1 C") for i in statesonly: code = state_code[i] i = i.upper() total_recovered = get_statewise_total(code,'Recovered') total_confirmed = get_statewise_total(code,'Confirmed') if total_recovered>0 and total_confirmed>0: # print(i,total_recovered,total_confirmed) recovery_rates[i] = total_recovered/total_confirmed * 100 sort_states = sorted(recovery_rates.items(), key = lambda x:x[1]) # print(sort_states) print("Top 10 States with highest recovery rates\n") for i in sort_states[:-11:-1]: print(i[0],"%.2f%%" % i[1]) print("\nTop 10 States with lowest recovery rates\n") for i in sort_states[:10]: print(i[0],"%.2f%%" % i[1])

#code for Q1 D,E confirmed_count = {} recovered_count = {} deceased_count = {} for i in statesonly: code = state_code[i] i = i.upper() total_recovered = get_statewise_total(code,'Recovered') total_confirmed = get_statewise_total(code,'Confirmed') total_deceased = get_statewise_total(code,'Deceased') if total_recovered>0: recovered_count[i] = total_recovered if total_confirmed>0: confirmed_count[i] = total_confirmed if total_deceased>0: deceased_count[i] = total_deceased sort_states_r = sorted(recovered_count.items(), key = lambda x:x[1]) sort_states_c = sorted(confirmed_count.items(), key = lambda x:x[1]) sort_states_d = sorted(deceased_count.items(), key = lambda x:x[1]) print("Q1 D") print("\nTop 3 highest affected states in terms of confirmed cases") for i in sort_states_c[:-4:-1]: print(i[0],i[1]) print("\nTop 3 highest affected states in terms of recovered cases") for i in sort_states_r[:-4:-1]: print(i[0],i[1]) print("\nTop 3 highest affected states in terms of deceased cases") for i in sort_states_d[:-4:-1]: print(i[0],i[1]) print("\n\nQ1 E") print("\nTop 3 lowest affected states in terms of confirmed cases") for i in sort_states_c[:3]: print(i[0],i[1]) print("\nTop 3 lowest affected states in terms of recovered cases") for i in sort_states_r[:3]: print(i[0],i[1]) print("\nTop 3 lowest affected states in terms of deceased cases") for i in sort_states_d[:3]: print(i[0],i[1])

#code for Q1 F dates = df.loc[df['status']=="Confirmed"]['date'].tolist() status = ['Confirmed','Recovered','Deceased'] for i in states: code = state_code[i] i = i.upper() print(i) for s in status: cases = df.loc[df['status']==s][code].astype(int) cases.index = dates dailydiff = cases.diff() # print(cases) # print(dailydiff) d = cases.idxmax() amount = cases[d] print("Highest spike in %s cases on %s by %d"%(s,d,amount)) print()

#code for Q1 G print("Active cases on 15 Aug 2021") for i in state_code_temp: code = state_code[i] i = i.upper() confirmed_cases = df.loc[df['status']=='Confirmed'][code].astype(int) recovered_cases = df.loc[df['status']=='Recovered'][code].astype(int) deceased_cases = df.loc[df['status']=='Deceased'][code].astype(int) df_cc = pd.DataFrame({'tt':confirmed_cases.values}) df_rc = pd.DataFrame({'tt':recovered_cases.values}) df_dc = pd.DataFrame({'tt':deceased_cases.values}) df_cc['ctt']=df_cc['tt'].cumsum() df_rc['ctt']=df_rc['tt'].cumsum() df_dc['ctt']=df_dc['tt'].cumsum() sum1 = df_rc['ctt']+df_dc['ctt'] df_cc['sctt']=sum1 diff = df_cc['ctt']-df_cc['sctt'] df_cc['att']=diff active_cases = df_cc.iloc[:,3] active_cases = active_cases.tolist() print("%s : %d"%(i,active_cases[-2]))

#Code for Q2 A import matplotlib.pyplot as plt import datetime as datetime import matplotlib.dates as mdates from matplotlib.pyplot import figure dateob = datetime.datetime dates=[] cases = df[['date','status','tt']] dates_temp = cases.loc[cases['status']=='Confirmed']['date'] dates_temp = dates_temp.tolist() for i in range(0,len(dates_temp)): strdate = dates_temp[i] dates.append(dateob.strptime(strdate,'%d-%b-%y')) confirmed_cases = cases.loc[cases['status']=='Confirmed']['tt'].astype(int) recovered_cases = cases.loc[cases['status']=='Recovered']['tt'].astype(int) deceased_cases = cases.loc[cases['status']=='Deceased']['tt'].astype(int) start = dates[0] end = dates[-1] figure(figsize=(14, 4), dpi=150) plt.subplot(1,2,1) plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b%y')) plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=60)) plt.gca().set_xbound(start, end) plt.plot(dates,confirmed_cases,label='Confirmed Cases') plt.plot(dates,recovered_cases,label='Recovered Cases') plt.legend(loc="upper left") plt.subplot(1,2,2) plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b%y')) plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=60)) plt.plot(dates,deceased_cases,label='Deceased Cases',color='green') plt.legend(loc="upper left") plt.show()

#Code for Q2 B dateob = datetime.datetime dates=[] cases = df[['date','status','dl']] dates_temp = cases.loc[cases['status']=='Confirmed']['date'] dates_temp = dates_temp.tolist() print("DELHI") for i in range(0,len(dates_temp)): strdate = dates_temp[i] dates.append(dateob.strptime(strdate,'%d-%b-%y')) confirmed_cases = cases.loc[cases['status']=='Confirmed']['dl'].astype(int) recovered_cases = cases.loc[cases['status']=='Recovered']['dl'].astype(int) deceased_cases = cases.loc[cases['status']=='Deceased']['dl'].astype(int) start = dates[0] end = dates[-1] figure(figsize=(14, 4), dpi=150) plt.subplot(1,2,1) plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b%y')) plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=60)) plt.gca().set_xbound(start, end) plt.plot(dates,confirmed_cases,label='Confirmed Cases') plt.plot(dates,recovered_cases,label='Recovered Cases') plt.legend(loc="upper left") plt.subplot(1,2,2) plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b%y')) plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=60)) plt.plot(dates,deceased_cases,label='Deceased Cases',color='green') plt.legend(loc="upper left") plt.show()

import matplotlib.ticker as ticker dateob = datetime.datetime dates=[] cases = df[['date','status','tt']] dates_temp = cases.loc[cases['status']=='Confirmed']['date'] dates_temp = dates_temp.tolist() for i in range(0,len(dates_temp)): strdate = dates_temp[i] dates.append(dateob.strptime(strdate,'%d-%b-%y')) confirmed_cases = cases.loc[cases['status']=='Confirmed']['tt'].astype(int) recovered_cases = cases.loc[cases['status']=='Recovered']['tt'].astype(int) deceased_cases = cases.loc[cases['status']=='Deceased']['tt'].astype(int) df_cc = pd.DataFrame({'tt':confirmed_cases.values}) df_rc = pd.DataFrame({'tt':recovered_cases.values}) df_dc = pd.DataFrame({'tt':deceased_cases.values}) df_cc['ctt']=df_cc['tt'].cumsum() df_rc['ctt']=df_rc['tt'].cumsum() df_dc['ctt']=df_dc['tt'].cumsum() sum1 = df_rc['ctt']+df_dc['ctt'] df_cc['sctt']=sum1 diff = df_cc['ctt']-df_cc['sctt'] df_cc['att']=diff active_cases = df_cc.iloc[:,3] # print(active_cases) start = dates[0] end = dates[-1] figure(figsize=(8, 4), dpi=100) plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b%y')) plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=60)) plt.gca().set_xbound(start, end) plt.gca().yaxis.set_major_formatter(ticker.EngFormatter()) plt.plot(dates,df_cc['att'],label='Active Cases') plt.legend(loc="upper left") plt.show()

#Code for Q2 D df_new = df.iloc[50:200] states = ['delhi','tamil nadu','gujarat'] dateob = datetime.datetime dates=[] dates_temp = df_new.loc[df_new['status']=='Confirmed']['date'] dates_temp = dates_temp.tolist() for i in range(0,len(dates_temp)): strdate = dates_temp[i] dates.append(dateob.strptime(strdate,'%d-%b-%y')) print("Start Date:",dates[0]) print("End Date:",dates[-1]) for i in states: code = state_code[i] i = i.upper() confirmed_cases = df_new.loc[df_new['status']=='Confirmed'][code].astype(int) recovered_cases = df_new.loc[df_new['status']=='Recovered'][code].astype(int) deceased_cases = df_new.loc[df_new['status']=='Deceased'][code].astype(int) df_cc = pd.DataFrame({'tt':confirmed_cases.values}) df_rc = pd.DataFrame({'tt':recovered_cases.values}) df_dc = pd.DataFrame({'tt':deceased_cases.values}) df_cc['ctt']=df_cc['tt'].cumsum() df_rc['ctt']=df_rc['tt'].cumsum() df_dc['ctt']=df_dc['tt'].cumsum() sum1 = df_rc['ctt']+df_dc['ctt'] df_cc['sctt']=sum1 diff = df_cc['ctt']-df_cc['sctt'] df_cc['att']=diff active_cases = df_cc.iloc[:,3] active_cases = active_cases.tolist() # print("%s : %d"%(i,active_cases[-2])) # print(dates[-1])#noice start = dates[0] end = dates[-1] figure(figsize=(8, 4), dpi=100) plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%d %b %y')) plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=10)) plt.gca().set_xbound(start, end) plt.gca().yaxis.set_major_formatter(ticker.EngFormatter()) plt.xticks(rotation=-30) plt.bar(dates,active_cases,label='Active Cases : %s'%(i)) plt.legend(loc="upper left") plt.show()