import requests # math operations from numpy import inf import datetime as dt import yfinance as yf # time operations from datetime import timedelta # for numerical analyiss import numpy as np # to store and process data in dataframe import pandas as pd # basic visualization package import matplotlib.pyplot as plt import io # advanced ploting import seaborn as sns # interactive visualization import plotly.express as px import plotly.graph_objs as go # import plotly.figure_factory as ff # from plotly.subplots import make_subplots # for offline ploting from plotly.offline import plot, iplot, init_notebook_mode init_notebook_mode(connected=True) # hide warnings import warnings warnings.filterwarnings("ignore") import scipy.stats as st

# color pallette cnf, dth, rec, act = "#393e46", "#ff2e63", "#21bf73", "#fe9801"

url = 'https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv' download = requests.get(url).content covid = pd.read_csv(io.StringIO(download.decode('utf-8')), parse_dates=['date']) covid.info() covid.tail(5)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 117670 entries, 0 to 117669
Data columns (total 62 columns):
 #   Column                                 Non-Null Count   Dtype         
---  ------                                 --------------   -----         
 0   iso_code                               117670 non-null  object        
 1   continent                              112290 non-null  object        
 2   location                               117670 non-null  object        
 3   date                                   117670 non-null  datetime64[ns]
 4   total_cases                            111883 non-null  float64       
 5   new_cases                              111880 non-null  float64       
 6   new_cases_smoothed                     110865 non-null  float64       
 7   total_deaths                           101201 non-null  float64       
 8   new_deaths                             101356 non-null  float64       
 9   new_deaths_smoothed                    110865 non-null  float64       
 10  total_cases_per_million                111293 non-null  float64       
 11  new_cases_per_million                  111290 non-null  float64       
 12  new_cases_smoothed_per_million         110280 non-null  float64       
 13  total_deaths_per_million               100624 non-null  float64       
 14  new_deaths_per_million                 100779 non-null  float64       
 15  new_deaths_smoothed_per_million        110280 non-null  float64       
 16  reproduction_rate                      94434 non-null   float64       
 17  icu_patients                           13337 non-null   float64       
 18  icu_patients_per_million               13337 non-null   float64       
 19  hosp_patients                          15309 non-null   float64       
 20  hosp_patients_per_million              15309 non-null   float64       
 21  weekly_icu_admissions                  1177 non-null    float64       
 22  weekly_icu_admissions_per_million      1177 non-null    float64       
 23  weekly_hosp_admissions                 2144 non-null    float64       
 24  weekly_hosp_admissions_per_million     2144 non-null    float64       
 25  new_tests                              51051 non-null   float64       
 26  total_tests                            50905 non-null   float64       
 27  total_tests_per_thousand               50905 non-null   float64       
 28  new_tests_per_thousand                 51051 non-null   float64       
 29  new_tests_smoothed                     60501 non-null   float64       
 30  new_tests_smoothed_per_thousand        60501 non-null   float64       
 31  positive_rate                          57240 non-null   float64       
 32  tests_per_case                         56614 non-null   float64       
 33  tests_units                            62379 non-null   object        
 34  total_vaccinations                     25855 non-null   float64       
 35  people_vaccinated                      24726 non-null   float64       
 36  people_fully_vaccinated                21723 non-null   float64       
 37  total_boosters                         2290 non-null    float64       
 38  new_vaccinations                       21401 non-null   float64       
 39  new_vaccinations_smoothed              46078 non-null   float64       
 40  total_vaccinations_per_hundred         25855 non-null   float64       
 41  people_vaccinated_per_hundred          24726 non-null   float64       
 42  people_fully_vaccinated_per_hundred    21723 non-null   float64       
 43  total_boosters_per_hundred             2290 non-null    float64       
 44  new_vaccinations_smoothed_per_million  46078 non-null   float64       
 45  stringency_index                       97416 non-null   float64       
 46  population                             116866 non-null  float64       
 47  population_density                     108804 non-null  float64       
 48  median_age                             104015 non-null  float64       
 49  aged_65_older                          102857 non-null  float64       
 50  aged_70_older                          103444 non-null  float64       
 51  gdp_per_capita                         104601 non-null  float64       
 52  extreme_poverty                        70245 non-null   float64       
 53  cardiovasc_death_rate                  104316 non-null  float64       
 54  diabetes_prevalence                    107469 non-null  float64       
 55  female_smokers                         81469 non-null   float64       
 56  male_smokers                           80285 non-null   float64       
 57  handwashing_facilities                 52401 non-null   float64       
 58  hospital_beds_per_thousand             94870 non-null   float64       
 59  life_expectancy                        111623 non-null  float64       
 60  human_development_index                104407 non-null  float64       
 61  excess_mortality                       4007 non-null    float64       
dtypes: datetime64[ns](1), float64(57), object(4)
memory usage: 55.7+ MB

#Analysing Covid cases in Taiwan taiwan = covid[covid['location'] == 'Taiwan'] taiwan.index = (pd.to_datetime(taiwan['date'],format='%m/%d/%y %I:%M%p')) taiwan.groupby(by=[taiwan.index.month, taiwan.index.year]) taiwan.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 612 entries, 2020-01-16 to 2021-09-18
Data columns (total 62 columns):
 #   Column                                 Non-Null Count  Dtype         
---  ------                                 --------------  -----         
 0   iso_code                               612 non-null    object        
 1   continent                              612 non-null    object        
 2   location                               612 non-null    object        
 3   date                                   612 non-null    datetime64[ns]
 4   total_cases                            606 non-null    float64       
 5   new_cases                              605 non-null    float64       
 6   new_cases_smoothed                     600 non-null    float64       
 7   total_deaths                           581 non-null    float64       
 8   new_deaths                             581 non-null    float64       
 9   new_deaths_smoothed                    600 non-null    float64       
 10  total_cases_per_million                606 non-null    float64       
 11  new_cases_per_million                  605 non-null    float64       
 12  new_cases_smoothed_per_million         600 non-null    float64       
 13  total_deaths_per_million               581 non-null    float64       
 14  new_deaths_per_million                 581 non-null    float64       
 15  new_deaths_smoothed_per_million        600 non-null    float64       
 16  reproduction_rate                      545 non-null    float64       
 17  icu_patients                           0 non-null      float64       
 18  icu_patients_per_million               0 non-null      float64       
 19  hosp_patients                          0 non-null      float64       
 20  hosp_patients_per_million              0 non-null      float64       
 21  weekly_icu_admissions                  0 non-null      float64       
 22  weekly_icu_admissions_per_million      0 non-null      float64       
 23  weekly_hosp_admissions                 0 non-null      float64       
 24  weekly_hosp_admissions_per_million     0 non-null      float64       
 25  new_tests                              608 non-null    float64       
 26  total_tests                            608 non-null    float64       
 27  total_tests_per_thousand               608 non-null    float64       
 28  new_tests_per_thousand                 608 non-null    float64       
 29  new_tests_smoothed                     602 non-null    float64       
 30  new_tests_smoothed_per_thousand        602 non-null    float64       
 31  positive_rate                          597 non-null    float64       
 32  tests_per_case                         576 non-null    float64       
 33  tests_units                            609 non-null    object        
 34  total_vaccinations                     150 non-null    float64       
 35  people_vaccinated                      146 non-null    float64       
 36  people_fully_vaccinated                78 non-null     float64       
 37  total_boosters                         0 non-null      float64       
 38  new_vaccinations                       126 non-null    float64       
 39  new_vaccinations_smoothed              180 non-null    float64       
 40  total_vaccinations_per_hundred         150 non-null    float64       
 41  people_vaccinated_per_hundred          146 non-null    float64       
 42  people_fully_vaccinated_per_hundred    78 non-null     float64       
 43  total_boosters_per_hundred             0 non-null      float64       
 44  new_vaccinations_smoothed_per_million  180 non-null    float64       
 45  stringency_index                       591 non-null    float64       
 46  population                             612 non-null    float64       
 47  population_density                     0 non-null      float64       
 48  median_age                             612 non-null    float64       
 49  aged_65_older                          0 non-null      float64       
 50  aged_70_older                          612 non-null    float64       
 51  gdp_per_capita                         0 non-null      float64       
 52  extreme_poverty                        0 non-null      float64       
 53  cardiovasc_death_rate                  612 non-null    float64       
 54  diabetes_prevalence                    0 non-null      float64       
 55  female_smokers                         0 non-null      float64       
 56  male_smokers                           0 non-null      float64       
 57  handwashing_facilities                 0 non-null      float64       
 58  hospital_beds_per_thousand             0 non-null      float64       
 59  life_expectancy                        612 non-null    float64       
 60  human_development_index                0 non-null      float64       
 61  excess_mortality                       50 non-null     float64       
dtypes: datetime64[ns](1), float64(57), object(4)
memory usage: 301.2+ KB

new_cases = taiwan['new_cases_smoothed_per_million'] new_deaths = taiwan['new_deaths_smoothed_per_million'] icu_patients = taiwan['icu_patients_per_million'] hosp_patients = taiwan['hosp_patients_per_million'] new_tests = taiwan['new_tests'] new_vaccinations_smoothed = taiwan['new_vaccinations_smoothed'] date = taiwan['date'] stringency_index = taiwan['stringency_index']

QUESTION 1

1. Pick a country and evaluate the Covid19 situation in the country.

#EVALUATING COVID IN TAIWAN fig,ax=plt.subplots() sns.lineplot(date, new_cases, color='orange', label='New Cases') sns.lineplot(date, new_deaths,color='red', label='New Deaths') plt.xlabel('Date') plt.ylabel('New Cases & New Deaths') plt.xticks(rotation=90) ax2= plt.twinx() sns.lineplot(date, new_vaccinations_smoothed,color='blue', alpha=0.5, label='New vaccinations') ax2.set_ylabel('New Vaccination') ax2.legend(frameon=False, loc='center left') plt.title('COVID IN TAIWAN') plt.show()

Answer to Question 1:

In this question, we are evaluating Taiwan's Covid19 situation. As we can see from the graph, the spike of Covid19 happens in late May 2021 and lasts till July 2021. It all started with a case outbreak caused by a tested positive pilot. We can assume that a positive outbreak is a direct result from the accidental release of the virus from a confined person. We believe had this not happened then the country's outbreak wouldn't have happened, and therefore the spike in cases, and subsequent deaths would have been avoided.

Overall, there are not many death cases, and the death cases only have its spike as the new cases increased in May. Moreover, by plotting the new vaccination in Taiwan, we can see more and more people are taking vaccination after the rise in Covid19 cases. Also, from the plot, we can imply that the vaccination actually help cease the new cases. we must still be on alert as studies have shown that people with the vaccine are in some instances more likely to get the disease in a variant, however, it shouldn't be as bad and their effects will be 'supposedly' in a lesser manner.

# EVALUATING COVID IN THE WORLD world_new_cases = covid['new_cases_smoothed_per_million'] world_new_deaths = covid['new_deaths_smoothed_per_million'] world_new_vaccinations_smoothed = covid['new_vaccinations_smoothed'] world_date = covid['date']

fig,ax=plt.subplots() sns.lineplot(world_date, world_new_cases, color='green', label='World_New Cases') sns.lineplot(world_date, world_new_deaths,color='yellow', label='World_New Deaths') plt.xlabel('Date') plt.ylabel('World_New Cases & World_New Deaths') plt.xticks(rotation=90) ax2= plt.twinx() sns.lineplot(world_date, world_new_vaccinations_smoothed,color='gray', alpha=0.5, label='New vaccinations') ax2.set_ylabel('World_New Vaccination') ax2.legend(frameon=False, loc='upper left') plt.title('WORLD COVID CASES & DEATHS') plt.show()

Here we plot the new cases, new deaths, and new vaccination of the world. We can see that compared to the world's new cases, Taiwan's new cases are relatively low and seem controllable. However, the vaccination level of Taiwan is also low compared to the world. This is caused by a vaccine shortage in Taiwan.

QUESTION 2

2. Evaluate the potential hidden cases (e.g., case positivity rate) and deaths (e.g., estimated infection fatality rate, excess death).

covid['world_positivity'] = (covid['total_cases']/covid['total_tests'])*100 covid[covid['world_positivity'] == inf] = 0 avg_world_positivity= np.mean(covid['world_positivity']) taiwan['case_positivity'] = (taiwan['total_cases']/taiwan['total_tests'])*100 avg_taiwan_case_positivity = np.mean(taiwan['case_positivity'])

#IDENTIFYING BENCHMARK COUNTRIES benchmark_countries = covid[covid['world_positivity']<=0.5] benchmark_countries.tail() #NO OF BENCHMARK COUNTRIES print(len(benchmark_countries['iso_code'].unique())) #THESE ARE THE COUNTRIES THAT GO FOR RIGOROUS TESTING REGIMES benchmark_countries['benchmark_case_positivity'] = (benchmark_countries['total_cases']/benchmark_countries['total_tests'])*100 benchmark_case_positivity_rate = np.mean(benchmark_countries['benchmark_case_positivity'])

#COMPARING CASE POSITIVITY OF THE WORLD, THE BENCHMARK, AND TAIWAN print("Average World Positivity: " + str(avg_world_positivity)) print("Average Taiwan Case Positivity: " + str(avg_taiwan_case_positivity)) print("Benchmark Case Positivity Rate: " + str(benchmark_case_positivity_rate))

Average World Positivity: 9.666241669295307
Average Taiwan Case Positivity: 0.6732414990403995
Benchmark Case Positivity Rate: 0.2669669703303415

Here we compare the average world positivity, benchmark positivity, and the case positivity in Taiwan. Taiwan appears to be well below the average world positivity rate of 9.66% with only 0.67%. However, above the benchmark positivity rate 0.26%. So, we conclude that there aren't much hidden cases in Taiwan, given the enough number of tested people country can reflect a more accurate positivity rate.

#COMPARING CASE FATILITY OF THE WORLD, THE BENCHMARK, AND TAIWAN covid['world_fatality']=(covid['total_deaths']/covid['total_cases'])*100 avg_world_fatality = np.mean(covid['world_fatality']) print("Average World Fatality: " + str(avg_world_fatality) ) taiwan['case_fatality'] = (taiwan['total_deaths']/taiwan['total_cases'])*100 avg_taiwan_fatality = np.mean(taiwan['case_fatality']) print("Average Taiwan Fatality: " + str(avg_taiwan_fatality)) benchmark_countries['case_fatality'] = (benchmark_countries['total_deaths']/benchmark_countries['total_cases'])*100 benchmark_fatality_rate = np.mean(benchmark_countries['case_fatality']) print("Benchmark Fatality Rate: " + str(benchmark_fatality_rate))

Average World Fatality: 2.7610901620719646
Average Taiwan Fatality: 1.9360694249456274
Benchmark Fatality Rate: 2.1652237114269783

Here we compare the average world fatality, benchmark infection fatality, and the case fatality in Taiwan. Taiwan appears to be below the average world fatality rate of 2.76% and benchmark fatality of 2.17% with only 1.92%. There could be potential hidden death due to the disparity in the fatality rate. Yet, shouldn't be much since 1.92% isn't far from 2.17%.

#COMPARING THE FATALITY RATE BEFORE AND AFTER COVID OF TAIWAN #Taiwan's fatality rate per 1000 people before covid is 7.631 #Source:https://www.macrotrends.net/countries/TWN/taiwan/death-rate taiwan_after_covid = taiwan[taiwan['date'] > '2020-01-20'] avg_taiwan_fatality_after_covid= np.mean(taiwan_after_covid['new_deaths_per_million']*1000) print(avg_taiwan_fatality_after_covid)

60.55249569707401

There is a big gap between the fatality before 7.63 and after 60.76 Covid19 in Taiwan. So, we can infer that there is not much hidden death in Taiwan.

#COMPARING THE CASE POSITIVITY AND FATALITY IN TAIWAN sns.lineplot(date,taiwan['case_positivity'], label='Case Positivity') sns.lineplot(date, taiwan['case_fatality'], label='Case Fatality') plt.legend() plt.xticks(rotation=90) #COMPARING THE CASE POSITIVITY AND FATALITY IN TAIWAN sns.jointplot(x='case_positivity', y='case_fatality', data=taiwan, kind='reg', color='b')

fig,ax=plt.subplots() sns.lineplot(date, taiwan['new_vaccinations_smoothed_per_million'],label='Taiwan Vaccinations') sns.lineplot(world_date, covid['new_vaccinations_smoothed_per_million'],label='World Vaccinations') plt.xticks(rotation=90) plt.legend() ax2= plt.twinx() sns.lineplot(date, new_deaths,color='red', alpha=0.5, label='New Deaths') ax2.set_ylabel('Taiwan Death') ax2.legend(frameon=False, loc='center left') plt.title('Vaccinations and Taiwan Death') plt.show()

There seems to be positive correlation between the case fatality and the spread of the infection as seen in the regression above. The line plot below also suggests the same, where increases in the case positivity have been followed by increases in case fatality. We can infer from the graph that the community spread has a relationship with fatality. Taiwan has also started vaccinating its residents long after the world began rolling out vaccines. This is because there are not enough capacity in health care and medical centers in Taiwan when it comes to community spread with many people ending up in severe cases and need a lot of medical resources. Since the vaccination rate is low, so the likelihood for patients to be in severe case is higher and need more medical capacity.

We also can see from the graph that, once the vaccination rate in creases, the death rate lowers.

#COMPARING THE TOTAL TESTS DONE TO THE TOTAL POSITIVE CASES sns.jointplot(x='total_tests', y='total_cases', data=taiwan, kind='reg', color='b')

Here, we see a positive correlation between the total tests taken and the total cases. The more total_tests, the more likely we are going to capture more Covid19 cases. However, there is a diminishing return effect. When total_test reaches 3 million, it seems that the more tests taken wouldn't help much in capturing more cases since most cases are already identified. As a result, when we set the benchmark country, we use a positivity rate that's below 0.5% (15000 cases/ 3000000 tests).

QUESTION 3

3.  Explore the relationship between the country's Covid19 cases and deaths and government health intervention policies (e.g., vaccination rate, closure), as well as Google community mobility reports.

#STRINGENCY INDEX fig,ax=plt.subplots() sns.lineplot(date, new_cases, color='orange', label='New Cases') sns.lineplot(date, new_deaths,color='red', label='New Deaths') plt.xlabel('Date') plt.ylabel('New Cases & New Deaths') plt.xticks(rotation=90) ax2= plt.twinx() sns.lineplot(date, stringency_index,color='blue', alpha=0.5, label='Stringency Index') ax2.set_ylabel('Stringency Index') ax2.legend(frameon=False, loc='center left') plt.show()

The Stringency Index measures the strictness go government intervention policies but doesn't imply the effectiveness or appropriateness of the country's response. The graph for the index remains flat in many areas indicating that the index has remained the same and new cases, new deaths have remained low. We can infer that the government intervention is taking effect. However, recently there has been a huge spike and outbreak in the number of Covid19 cases in Taiwan in May 2021. The Stringency Index had increased right away to reflect this spike from an average of about 30 to 70. Given that the number of cases have fallen, it can be understood that the Government's quick Intervention reflected by the Index has played a part in this decrease.

#TAIWAN MOBILITY INDEX Taiwan_mobility_2020 = pd.read_csv('/work/TW mobility.csv') Taiwan_mobility_2021 = pd.read_csv('/work/2021_TW_Region_Mobility_Report.csv') Taiwan_mobility_data = Taiwan_mobility_2020.append(Taiwan_mobility_2021) Taiwan_mobility_data.index = (pd.to_datetime(Taiwan_mobility_data['date'])) Taiwan_mobility_data.groupby(by=[Taiwan_mobility_data.index.month, Taiwan_mobility_data.index.year])

taiwan_mobility = pd.merge(Taiwan_mobility_data, taiwan, left_index=True, right_index=True) taiwan_mobility.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 575 entries, 2020-02-15 to 2021-09-11
Data columns (total 79 columns):
 #   Column                                              Non-Null Count  Dtype         
---  ------                                              --------------  -----         
 0   country_region_code                                 575 non-null    object        
 1   country_region                                      575 non-null    object        
 2   sub_region_1                                        0 non-null      float64       
 3   sub_region_2                                        0 non-null      float64       
 4   metro_area                                          0 non-null      float64       
 5   iso_3166_2_code                                     0 non-null      float64       
 6   census_fips_code                                    0 non-null      float64       
 7   place_id                                            575 non-null    object        
 8   date_x                                              575 non-null    object        
 9   retail_and_recreation_percent_change_from_baseline  575 non-null    int64         
 10  grocery_and_pharmacy_percent_change_from_baseline   575 non-null    int64         
 11  parks_percent_change_from_baseline                  575 non-null    int64         
 12  transit_stations_percent_change_from_baseline       575 non-null    int64         
 13  workplaces_percent_change_from_baseline             575 non-null    int64         
 14  residential_percent_change_from_baseline            575 non-null    int64         
 15  iso_code                                            575 non-null    object        
 16  continent                                           575 non-null    object        
 17  location                                            575 non-null    object        
 18  date_y                                              575 non-null    datetime64[ns]
 19  total_cases                                         575 non-null    float64       
 20  new_cases                                           575 non-null    float64       
 21  new_cases_smoothed                                  575 non-null    float64       
 22  total_deaths                                        574 non-null    float64       
 23  new_deaths                                          574 non-null    float64       
 24  new_deaths_smoothed                                 575 non-null    float64       
 25  total_cases_per_million                             575 non-null    float64       
 26  new_cases_per_million                               575 non-null    float64       
 27  new_cases_smoothed_per_million                      575 non-null    float64       
 28  total_deaths_per_million                            574 non-null    float64       
 29  new_deaths_per_million                              574 non-null    float64       
 30  new_deaths_smoothed_per_million                     575 non-null    float64       
 31  reproduction_rate                                   542 non-null    float64       
 32  icu_patients                                        0 non-null      float64       
 33  icu_patients_per_million                            0 non-null      float64       
 34  hosp_patients                                       0 non-null      float64       
 35  hosp_patients_per_million                           0 non-null      float64       
 36  weekly_icu_admissions                               0 non-null      float64       
 37  weekly_icu_admissions_per_million                   0 non-null      float64       
 38  weekly_hosp_admissions                              0 non-null      float64       
 39  weekly_hosp_admissions_per_million                  0 non-null      float64       
 40  new_tests                                           575 non-null    float64       
 41  total_tests                                         575 non-null    float64       
 42  total_tests_per_thousand                            575 non-null    float64       
 43  new_tests_per_thousand                              575 non-null    float64       
 44  new_tests_smoothed                                  575 non-null    float64       
 45  new_tests_smoothed_per_thousand                     575 non-null    float64       
 46  positive_rate                                       575 non-null    float64       
 47  tests_per_case                                      554 non-null    float64       
 48  tests_units                                         575 non-null    object        
 49  total_vaccinations                                  144 non-null    float64       
 50  people_vaccinated                                   140 non-null    float64       
 51  people_fully_vaccinated                             72 non-null     float64       
 52  total_boosters                                      0 non-null      float64       
 53  new_vaccinations                                    121 non-null    float64       
 54  new_vaccinations_smoothed                           174 non-null    float64       
 55  total_vaccinations_per_hundred                      144 non-null    float64       
 56  people_vaccinated_per_hundred                       140 non-null    float64       
 57  people_fully_vaccinated_per_hundred                 72 non-null     float64       
 58  total_boosters_per_hundred                          0 non-null      float64       
 59  new_vaccinations_smoothed_per_million               174 non-null    float64       
 60  stringency_index                                    561 non-null    float64       
 61  population                                          575 non-null    float64       
 62  population_density                                  0 non-null      float64       
 63  median_age                                          575 non-null    float64       
 64  aged_65_older                                       0 non-null      float64       
 65  aged_70_older                                       575 non-null    float64       
 66  gdp_per_capita                                      0 non-null      float64       
 67  extreme_poverty                                     0 non-null      float64       
 68  cardiovasc_death_rate                               575 non-null    float64       
 69  diabetes_prevalence                                 0 non-null      float64       
 70  female_smokers                                      0 non-null      float64       
 71  male_smokers                                        0 non-null      float64       
 72  handwashing_facilities                              0 non-null      float64       
 73  hospital_beds_per_thousand                          0 non-null      float64       
 74  life_expectancy                                     575 non-null    float64       
 75  human_development_index                             0 non-null      float64       
 76  excess_mortality                                    46 non-null     float64       
 77  case_positivity                                     575 non-null    float64       
 78  case_fatality                                       574 non-null    float64       
dtypes: datetime64[ns](1), float64(64), int64(6), object(8)
memory usage: 359.4+ KB

#EXAMINING THE MOBILITY INDICES fig,ax=plt.subplots() sns.lineplot(date, taiwan_mobility['parks_percent_change_from_baseline'],color='lightpink', label='Parks') sns.lineplot(date, taiwan_mobility['grocery_and_pharmacy_percent_change_from_baseline'], color='yellow', label='Grocery and Pharmacy') sns.lineplot(date, taiwan_mobility['retail_and_recreation_percent_change_from_baseline'],color='lightblue', label='Retail and Recreation') plt.xlabel('Date') plt.ylabel('Grocery, Retail and Parks') plt.xticks(rotation=90) ax2= plt.twinx() sns.lineplot(date,taiwan['case_positivity'] ,color='gray', alpha=0.5, label='Case Positivity') ax2.set_ylabel('Case Positivity') ax2.legend(frameon=False, loc='upper left') plt.title('MOBILITY INDICES') plt.show()

Upon comparing the changes in retail, parks and grocery with the case positivity, the recent sudden spike in cases have been met by a fall in grocery and pharmaceutical runs, parks and retail and recreation. This may be due to voluntary avoidance by the residents of Taiwan. But a portion of it can also be attributed to restrictions imposed by the government as indicated by the stringency levels which increased during this period. Taiwan immediately went into level 3 soft lock down right after the outbreak of cases in May 2021.

#EXAMINING THE MOBILITY INDICES fig,ax=plt.subplots() sns.lineplot(date, taiwan_mobility['residential_percent_change_from_baseline'],color='lightpink', label='Residential') sns.lineplot(date, taiwan_mobility['workplaces_percent_change_from_baseline'], color='violet', label='Workplace') sns.lineplot(date, taiwan_mobility['transit_stations_percent_change_from_baseline'],color='lightblue', label='Transit Stations') plt.xlabel('Date') plt.ylabel('Residential, Workplaces and Transit') plt.xticks(rotation=90) ax2= plt.twinx() sns.lineplot(date,taiwan['case_positivity'] ,color='gray', alpha=0.5, label='Case Positivity') ax2.set_ylabel('Case Positivity') ax2.legend(frameon=False, loc='upper left') plt.title('MOBILITY INDICES') plt.show()

Upon comparing the changes in residential, workplace and transit stations with the case positivity, the recent sudden spike in cases have been met by a surprising rise in the residential percentage. There has however been a fall in the workspaces and the transit stations. As see above this could be due to higher stringency levels and imposition of lockdowns.

Overall we can say the government reacted pretty fast in leveling up the restriction after the Covid19 outbreak, and Taiwanese also tighten their mobility according to the policy. We observe the decrease of cases right after that.

LAB 5

Industries:

#NEED TO FIND STOCKS WE WANT TO OBSERVE AND A MARKET INDEX symbols_list = ['TSM','TLC', 'BNTX', 'CHT', 'ASX','UMC', 'EWT'] start = dt.datetime(2016,7,15) end = dt.datetime(2021,9,15) data = yf.download(symbols_list, start=start, end=end) # filter column adjusted close df = data['Adj Close'] df = df.ffill()

[*********************100%***********************]  7 of 7 completed

!pip install PyPortfolioOpt==1.2.1

Collecting PyPortfolioOpt==1.2.1
  Downloading PyPortfolioOpt-1.2.1-py3-none-any.whl (49 kB)
     |████████████████████████████████| 49 kB 11.6 MB/s 
Requirement already satisfied: numpy in /shared-libs/python3.7/py/lib/python3.7/site-packages (from PyPortfolioOpt==1.2.1) (1.19.5)
Requirement already satisfied: scipy in /shared-libs/python3.7/py/lib/python3.7/site-packages (from PyPortfolioOpt==1.2.1) (1.7.1)
Collecting cvxpy<2.0.0,>=1.0.28
  Downloading cvxpy-1.1.15-cp37-cp37m-manylinux_2_24_x86_64.whl (2.7 MB)
     |████████████████████████████████| 2.7 MB 53.5 MB/s 
Collecting pandas<0.26.0,>=0.25.3
  Downloading pandas-0.25.3-cp37-cp37m-manylinux1_x86_64.whl (10.4 MB)
     |████████████████████████████████| 10.4 MB 49.5 MB/s 
Collecting scs>=1.1.6
  Downloading scs-2.1.4.tar.gz (6.6 MB)
     |████████████████████████████████| 6.6 MB 64.2 MB/s 
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
    Preparing wheel metadata ... done
Collecting ecos>=2
  Downloading ecos-2.0.7.post1-cp37-cp37m-manylinux1_x86_64.whl (147 kB)
     |████████████████████████████████| 147 kB 77.2 MB/s 
Collecting osqp>=0.4.1
  Downloading osqp-0.6.2.post0-cp37-cp37m-manylinux2014_x86_64.whl (212 kB)
     |████████████████████████████████| 212 kB 79.3 MB/s 
Collecting qdldl
  Downloading qdldl-0.1.5.post0-cp37-cp37m-manylinux2014_x86_64.whl (941 kB)
     |████████████████████████████████| 941 kB 60.7 MB/s 
Requirement already satisfied: python-dateutil>=2.6.1 in /shared-libs/python3.7/py-core/lib/python3.7/site-packages (from pandas<0.26.0,>=0.25.3->PyPortfolioOpt==1.2.1) (2.8.2)
Requirement already satisfied: pytz>=2017.2 in /shared-libs/python3.7/py/lib/python3.7/site-packages (from pandas<0.26.0,>=0.25.3->PyPortfolioOpt==1.2.1) (2021.1)
Requirement already satisfied: six>=1.5 in /shared-libs/python3.7/py-core/lib/python3.7/site-packages (from python-dateutil>=2.6.1->pandas<0.26.0,>=0.25.3->PyPortfolioOpt==1.2.1) (1.16.0)
Building wheels for collected packages: scs
  Building wheel for scs (PEP 517) ... done
  Created wheel for scs: filename=scs-2.1.4-cp37-cp37m-linux_x86_64.whl size=113462 sha256=cfe45cf2093f5528be232905b1e9f3b45e1ad107e7b50857347a1b6ee60e32f8
  Stored in directory: /root/.cache/pip/wheels/d6/58/0b/a55ff6d4e2da4c9776e363a778ea13e4068037a7be82eb85e0
Successfully built scs
Installing collected packages: qdldl, scs, osqp, ecos, pandas, cvxpy, PyPortfolioOpt
  Attempting uninstall: pandas
    Found existing installation: pandas 1.2.5
    Not uninstalling pandas at /shared-libs/python3.7/py/lib/python3.7/site-packages, outside environment /root/venv
    Can't uninstall 'pandas'. No files were found to uninstall.
Successfully installed PyPortfolioOpt-1.2.1 cvxpy-1.1.15 ecos-2.0.7.post1 osqp-0.6.2.post0 pandas-0.25.3 qdldl-0.1.5.post0 scs-2.1.4
WARNING: You are using pip version 21.2.3; however, version 21.2.4 is available.
You should consider upgrading via the '/root/venv/bin/python -m pip install --upgrade pip' command.

from pypfopt.efficient_frontier import EfficientFrontier from pypfopt import risk_models from pypfopt import expected_returns from pypfopt import cla from pypfopt.plotting import Plotting from pypfopt.discrete_allocation import DiscreteAllocation, get_latest_prices from matplotlib.ticker import FuncFormatter import seaborn as sns

# Check NaN values in the data nullin_df = pd.DataFrame(df,columns=symbols_list) print(nullin_df.isnull().sum()) # Calculate portfolio mean return mu = expected_returns.mean_historical_return(df) print(mu) # Calculate portfolio return variance sigma = risk_models.sample_cov(df) print(sigma)

TSM       0
TLC     594
BNTX    815
CHT       0
ASX       0
UMC       0
EWT       0
dtype: int64
ASX     0.195913
BNTX    2.256440
CHT     0.064080
EWT     0.199110
TLC     0.370357
TSM     0.369458
UMC     0.462993
dtype: float64
           ASX      BNTX       CHT       EWT       TLC       TSM       UMC
ASX   0.135827  0.046578  0.015103  0.049189  0.035185  0.065884  0.063968
BNTX  0.046578  1.300404  0.017043  0.025382  0.031571  0.058421  0.052941
CHT   0.015103  0.017043  0.012803  0.012473  0.007097  0.012878  0.009698
EWT   0.049189  0.025382  0.012473  0.040825  0.029105  0.047660  0.038566
TLC   0.035185  0.031571  0.007097  0.029105  0.632766  0.039781  0.021155
TSM   0.065884  0.058421  0.012878  0.047660  0.039781  0.093203  0.058008
UMC   0.063968  0.052941  0.009698  0.038566  0.021155  0.058008  0.157886

QUESTION 1

1. Based on your investment strategy (i.e., chosen stocks, industries, asset classes), identify the maximum Sharpe ratio and minimum volatility portfolios.

# Note max sharpe ratio is the tangency portfolio # weight bounds in negative allows shorting of stocks ef = EfficientFrontier(mu, sigma, weight_bounds=(-1,1)) # optional constraints possible, read pypfopt documentation. sharpe_portfolio=ef.max_sharpe(risk_free_rate=0.008) sharpe_portfolio_wt=ef.clean_weights() print(sharpe_portfolio_wt) Plotting.plot_weights(sharpe_portfolio_wt)

{'ASX': -0.32434, 'BNTX': 0.33452, 'CHT': -0.21005, 'EWT': 0.30105, 'TLC': 0.06969, 'TSM': 0.43368, 'UMC': 0.39544}

Maximum Shape Ratio Portfolio {'ASX': -0.32434, 'BNTX': 0.33452, 'CHT': -0.21005, 'EWT': 0.30105, 'TLC': 0.06969, 'TSM': 0.43368, 'UMC': 0.39544}.

QUESTION 2

2. If you have USD 1 million now, how much should you invest in each?

latest_prices = get_latest_prices(df) # Allocate Portfolio Value in $ as required to show number of shares/stocks to buy, # also bounds for shorting will affect allocation # Maximum Sharpe Portfolio Allocation $1000000 da = DiscreteAllocation(sharpe_portfolio_wt, latest_prices, total_portfolio_value=1000000) allocation, leftover = da.greedy_portfolio() #change allocation in line above print(allocation) print("Leftover Fund value for the maximum Sharpe portfolio is ${:.2f}".format(leftover))

{'TSM': 2305, 'UMC': 21548, 'BNTX': 651, 'EWT': 3010, 'TLC': 6343, 'ASX': -20119, 'CHT': -2952}
Leftover Fund value for the maximum Sharpe portfolio is $129.66

Out of the $1000000 available for allocation, the amounts have been invested in the stocks as shown above. The leftover fund in the maximum Sharpe portfolio is $69.73. The portfolio indicates that we short the stocks of ASX a tech company and CHT a telecom company.

max_sharpe_cla = cla.CLA(mu, sigma) max_sharpe_cla.max_sharpe() Plotting.plot_efficient_frontier(max_sharpe_cla, show_assets="True")

sharpe_portfolio_wt_list = list(sharpe_portfolio_wt.values()) ret_data = df.pct_change()[1:] weighted_returns = (sharpe_portfolio_wt_list * ret_data) portfolio_ret = pd.DataFrame(weighted_returns.sum(axis=1)) ret_data = ret_data.merge(portfolio_ret, on="Date", how="left") ret_data = ret_data.rename(columns={0: "portfolio_ret"}) ret_data.tail()

ret_data['cumulative_portfolio_ret'] = (ret_data['portfolio_ret'] + 1).cumprod() ret_data['cumulative_EWT_ret'] = (ret_data['EWT'] + 1).cumprod() ret_data.tail()

QUESTION 3

3. Plot a graph showing how your portfolios (maximum Sharpe and minimum volatility portfolios) perform relative to the market (i.e., SPY)

sns.scatterplot('Date', 'cumulative_portfolio_ret', data=ret_data) sns.scatterplot('Date', 'cumulative_EWT_ret', data=ret_data)

plt.hist(ret_data['portfolio_ret'], bins=10)

st.norm.interval(alpha=0.95, loc=np.mean(ret_data['portfolio_ret']), scale=st.sem(ret_data['portfolio_ret']))

QUESTION 1

1. Calculate the Minimum Volatility Portfolio

#Minimum Volatility Portfolio ef = EfficientFrontier(mu, sigma, weight_bounds=(-1,1)) min_vol_portfolio=ef.min_volatility() min_vol_portfolio_wt=ef.clean_weights() print(min_vol_portfolio_wt) Plotting.plot_weights(min_vol_portfolio_wt)

{'ASX': -0.03946, 'BNTX': -0.0034, 'CHT': 0.97866, 'EWT': 0.03672, 'TLC': 0.00927, 'TSM': -0.01263, 'UMC': 0.03084}

For our MVP we calculated that we need a majority of CHT for our portfolio, along with smaller amounts EWT, UMC, TLC. We had to short stocks for TSM, BNTX, and ASX for the portfolio as well.

da = DiscreteAllocation(min_vol_portfolio_wt, latest_prices, total_portfolio_value=1000000) allocation, leftover = da.greedy_portfolio() print(allocation) print("Leftover Fund value for the maximum Sharpe portfolio is ${:.2f}".format(leftover))

{'CHT': 23215, 'EWT': 533, 'UMC': 2443, 'TLC': 1227, 'ASX': -23573, 'TSM': -557, 'BNTX': -54}
Leftover Fund value for the maximum Sharpe portfolio is $348.54

As per MVP, the funds are allocated as shown above. We short the stocks of ASX a tech company, TSM a semi-conductor manufacturing company and BNTX a pharma company. The leftover fund for the maximum Sharpe portfolio is now $102.48.

min_vol_cla = cla.CLA(mu, sigma) min_vol_cla.min_volatility() Plotting.plot_efficient_frontier(min_vol_cla, show_assets="True")

min_vol_portfolio_wt_list = list(min_vol_portfolio_wt.values()) ret_data2 = df.pct_change()[1:] weighted_returns2 = (min_vol_portfolio_wt_list * ret_data2) portfolio_ret2 = pd.DataFrame(weighted_returns2.sum(axis=1)) ret_data2 = ret_data2.merge(portfolio_ret2, on="Date", how="left") ret_data2 = ret_data2.rename(columns={0: "portfolio_ret"}) ret_data2.head()

df = df.stack() df.head()

df = df.reset_index() df = df.rename(columns={"level_1": "ticker", 0: "price"}) df.head()

df = df.dropna() df.head()

sns.scatterplot('Date', 'price', data=df, hue='ticker')

QUESTION 4

4. Comment on your strategy note and highlight the potential future issues/risks.

We chose to diversify our portfolio by choosing Taiwanese stocks or companies critical to Taiwan traded in USD. The portfolio comprises stocks of TSM, an electricity manufacturing company; TLC and BNTX pharma companies; CHT in the telecom industry; and ASX a tech & hardware manufacturing company; and UMC a tech company. The market index we chose is EWT which comprises of the top 85% of Taiwanese companies.

The sharpe portfolio helps provide the weights of each stock. TSM appears to be the largest by weight with us shorting ASX. Based on our observation of the covid situation in Taiwan, we believe that technology sector represents the strongest growth in the Taiwan economy. As a result we take portfolio is consisting to take the advantage of technology sector. As our portfolio is tech sector weighted heavy, We choose to put CHT(Taiwan Telecom Company) in our portfolio to reduce the risk variance of our portfolio. As CHT is in defense industry(Telecom), it will add diversification in our portfolio. As a result we take advantage of the technology sector. Although shorting could be inherently volatile, it could help the portfolio in long-term risk exposure.

The potential qualitative risk will be global competition on semiconductor, the rising shortage on semiconductor and competition in manufacture in future.

.css-ytumd6{-webkit-text-decoration:none;text-decoration:none;}QUESTION 1

Answer to Question 1:

QUESTION 2

QUESTION 3

LAB 5

QUESTION 1

QUESTION 2

QUESTION 3

QUESTION 1

QUESTION 4

QUESTION 1