NYC Coronavirus Data Analysis

Big Data Final Project

Team Member: Jessie Jin, Zhi Zhang, Xuexuan Wang, Jenny Zhou

About this Project

As we are living in unprecedented times of pandemic, our team would like to put our efforts and contribute to battling COVID-19 health crisis. This project aims to help track and analyze the current COVID pandemic spread in NYC across the five boroughs: Manhattan, Queens, Brooklyn, and Staten Island. In addition, we included studies of relations between pandemic and its influential factors: age, income and traffic. Moreover, we analyzed impacted areas due to the burst of the virus: job market, business license application, certificate of occupancy issued for new buildings, public transportation, emergency notification for public health, hospital icu beds and permitted events. Based on current data, we forecasted the number of positive cases using machine learning algorithms.

  • Positive tests tracking map
  • Infections and fatalities analysis
  • Influential factors: Who is getting sick
  • Impacted areas: job market, business license application, certificate of occupancy issued for new buildings, traffic collision, emergency notification for public health, hospital icu beds and permitted events
Big Data Technology:
  • Spark and Pandas: data processing and analysis
  • SparkML: k-means algorithm for anomaly detection
  • Cases Prediction: logistic increase model with least squares approximation
  • matplotlib, D3.js: big data visualization

NYC COVID-19 Summary

Notice the below summary number might be slightly different to another tables and maps due to different update/analysis time.

update:

0

NYC Cases

0

NYC Deaths

0

NYC Hosplitalized


NYC COVID-19 cases, deaths and hosplitalized data for each borough

Update: 2020-05-14 (from 2020-03-12)


Cases, Deaths and Hosplitalized Data


The Cases Growth Rate is getting lower than 5%.

Cases distribution

This is case number distribution Map for each zipcode

Update: 2020-05-15 12:30PM (from 2020-03-12)

  • Data from Map and population data from NYC OpenData
  • Income data from the IRS.
  • COVID-19 testing data from NYC Department of Health.
  • Impacted areas: job market, business license application, certificate of occupancy issued for new buildings, traffic collison, emergency notification for public health, hospital icu beds and permitted events
Zipcode
Name
-
Test: -
Positives : -
Positives Rate : -
Population : -
Annual Income: (2017)
under $25k income: -
$25k - 50k income: -
$50k - 75k income: -
$75k - 100k income: -
$100k - 200k income: -
above $200k income: -

Information for Each Borough

Cases, Deaths and Hosplitalized Data for Each Borough

Update: 2020-05-14 (from 2020-03-12)

Click below buttons to check each borough data in Area chart.

NYC COVID-19 Cases & Tests

The number of tests is getting higher and the number of positive cases is flattening, which is good.

Update: 2020-05-14 (from 2020-03-12)

NYC COVID-19 Cases Prediction

NYC COVID-19 cases prediction by logistic increase model with least squares approximation

Update: 2020-05-14 (from 2020-03-12)


NYC COVID-19 Cases Prediction in A Week

Social Factors Affecting COVID-19

We analyzed three factors that would affect the COVID-19 case:

  • Age: adult and middle-aged group has the highest positive case number. The number of deaths and death rate are highest in senior citizens.
  • Income: the low-income group has the largest number of COVID-19 cases.
  • Traffic: boroughs with more traffics have the higher number of COVID-19 cases.


—— How Age Affects The COVID-19 Case ——


The chart below shows the relationship between COVID-19 case and age. Adult and middle-aged group has the highest case number. But the number of deaths and death rate are highest in senior citizens.

Update: 2020-05-13 (from 2020-03-12)



—— How Income Affects The COVID-19 Case ——


The chart below shows the relationship between COVID-19 case and income. The number of low-income units (blue part) gradually increases on the x-axis. The right part of the chart shows that COVID-19 cases (orange part) is also increasing with the increase of number of low-income units.

Update: 2020-05-13 (from 2020-03-12)




According to the income, we divide the data into three groups. The result shows that the COVID-19 cases from the low-income group is much more than the middle-income group and moderate-income group.



—— How Traffic Affects The COVID-19 Case ——



The bar graphs below show the number of car crashes and number of COVID-19 cases acrossing the five boroughs. Queens and Brooklyn have the highest number of infections also have the highest number of car crashes. Since data on nyc traffics are limited, number of car crashes is used to reflect the traffic. This shows that the areas where have more traffics tend to have more COVID-19 cases.

Update: 2020-05-13 (from 2020-03-12)

COVID-19 Impacts on NYC

We analyzed COVID-19 Impacts on the job market, business license application, certificate of occupancy issued for new buildings, public transportation, emergency notification for public health, and permitted events.

Comparing with the 6-month average prior to pandemic, the results show that the following areas are declining:

  • Job application down by: 39.19%
  • Business license application down by: 86.71%
  • Certificate of occupancy issued for new buildings down by: 33.43%
  • Traffic collision down by: 74.77%
  • 2020 NYC permitted events down by: 98.73% per month


Categories That Are Falling:

Update: 2020-05-14 (from 2019-09-01)



Update: 2020-05-14 (from 2019-01-01)


On the other hand, the followings are increasing:

  • Emergency notification for public health up by: 1362.50%
  • Hospital ICU bed numbers up by: 77.23%


Categories That Are Rising:

Update: 2020-05-13 (from 2019-06-01)                       Update: 2020-05-13 (from 2020-03-26)

Data Source

  • NYC Department of Health and Mental Hygiene (DOHMH)
  • New York State Department of Health
  • THE CITY
  • NYC Open Data



—Stay well and take care —