search

hackforla / data-science

The Hack For LA Data Science team is a Community of Practice within the LA brigade seeking to make analytical and machine learning services available to local communities and organizations.
28 stars 17 forks source link

COVID 19 impact project #110

Open ryanmswan opened 4 years ago

ryanmswan commented 4 years ago

Dependency

Access to clean 311 data from 311-data-org team Project one sheet (can continue issue w/o completion of one sheet template)

Overview

Investigate methods for mapping COVID-19 data for LA County to the 311-data tool and assess additional data that can be mapped using the 311-data tool

Action Items

Resources

http://publichealth.lacounty.gov/media/Coronavirus/locations.htm https://occovid19.ochealthinfo.com/coronavirus-in-oc https://csungis.maps.arcgis.com/apps/webappviewer/index.html https://github.com/CSSEGISandData/COVID-19/tree/master/csse_covid_19_data/csse_covid_19_time_series https://covidtracking.com/data https://data.lacity.org/browse?q=covid&sortBy=relevance https://geohub.lacity.org/search?q=covid%2019 https://huggingface.co/311-data

Data needed from 311 project

all data from three years before covid shutdown and all data during will not need an ongoing pipeline but probably we be revised to update it the shutdowns ever end. We have got Data during Covid lockdowns from March 2020 till June 2021 but we don't have the data from prior to lockdown.

ExperimentsInHonesty commented 3 years ago

Identify

akhaleghi commented 2 months ago

@jskfang @VamsiB11 @PretheeshS @SaiPranaswi23 @jefryk18 There have been no updates on this issue in over a month so if you would like to work on this issue please reassign yourself and provide weekly updates on your progress.

@darth-franky Are there any updates on your work on this issue since you assigned yourself two weeks ago?

darth-franky commented 2 months ago

Hi @akhaleghi,

Could we possibly meet on this? I recently joined the group and would like to know where to help. I'm not sure who's working on what.

jefryk18 commented 2 months ago

Attaching my work for this week

On Mon, 23 Sept, 2024, 7:34 pm Abe, @.***> wrote:

@jskfang https://github.com/jskfang @VamsiB11 https://github.com/VamsiB11 @PretheeshS https://github.com/PretheeshS @SaiPranaswi23 https://github.com/SaiPranaswi23 @jefryk18 https://github.com/jefryk18 There have been no updates on this issue in over a month so if you would like to work on this issue please reassign yourself and provide weekly updates on your progress.

@darth-franky https://github.com/darth-franky Are there any updates on your work on this issue since you assigned yourself two weeks ago?

— Reply to this email directly, view it on GitHub https://github.com/hackforla/data-science/issues/110#issuecomment-2369777153, or unsubscribe https://github.com/notifications/unsubscribe-auth/BKK5YPJTIZGKKPQMPOHERMDZYCQP7AVCNFSM6AAAAABOXCX3Z6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGNRZG43TOMJVGM . You are receiving this because you were mentioned.Message ID: @.***>

PretheeshS commented 2 months ago

Hi @akhaleghi

We have been working on collecting and cleaning both 311 data and LA County Covid data. Me specifically have been working on cleaning and understanding Neighborhood-level Covid data and Covid-19 Spending data from the links below. I have also collected the specific 311 data needed for the project which is during the lockdown from March 2020 - June 2021. The next steps are to do EDA and define the stakeholders of the project.

https://data.lacity.org/COVID-19/Neighborhood-level-COVID-data/fvye-93wd/about_data https://controllerdata.lacity.org/Finance/COVID-19-Spending/3sn9-wkuu/about_data

VamsiB11 commented 2 months ago

Hi @akhaleghi

Added a couple datasets to the resources that showed promise and I have also started working on one of the datasets from the and the initial steps are done, the data cleaning, finding the missing values and all but the the only issue is with the outliers, which I'll probably get it done in a couple days. Also if we take a look at the current epidemic growth status, the covid-19 infections are still prevalent in a couple states in the US so i believe this is an ongoing project rather than a One-time project and how do i change the label as mentioned in the Action items.

PretheeshS commented 1 month ago

Doing EDA on the datasets that I have been working on for the past week. The Neighborhood data has 35 million rows and hence I have been exploring various options on how to handle such large datasets.

VamsiB11 commented 1 month ago

Hey @akhaleghi, how do we prep the One-sheet? Do i Just post it in these comments?

VamsiB11 commented 1 month ago

@akhaleghi

The One-sheet is done, we just need need feedback to see if there are any necessary changes/improvements since we're all new to this. Our team will present the sheet at the meet tonight if I am unable to join.

PretheeshS commented 1 month ago

Researched necessary technologies required to achieve the goals that are outlined in our roadmap especially for dashboard and how to visualize location specific data.

VamsiB11 commented 2 weeks ago

The one sheet and the preliminary research questions were presented and approved.

SaiPranaswi23 commented 2 weeks ago

I am performing different statistical analysis on 20 Neighborhoods. Different methods of analysis include Descriptive Analysis - Overall spread of the data. Trend based analysis - to identify the trends in the overall data - no.of cases increased per day accross diff counties, how are the cases and deaths varying. Comparative analysis - compares the cases and deaths between 2020, 2021, 2022. Correlation Analysis- measures the relation between cases and deaths and population density. Outlier Analysis - Identifies the outliers. Forecast Analysis