Data Montgomery Experience Final Report Presentation
The Data Montgomery Experience Final Report Presentation by Brian Perez showcased the project plan which included creating services for users to interact with geographical data through a web-based interactive map and analyzing 911 calls received by MCFRS. The report covered data clean-up, descriptive statistics, final product outcomes, data stories, and recommendations. Various tools and datasets were utilized to achieve the project goals effectively.
Download Presentation
![](/assets/img/so-down.gif)
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
DATA MONTGOMERY EXPERIENCE FINAL REPORT PRESENTATION BRIAN PEREZ | DATA 205 CAPSTONE IN DATA SCIENCE | WEDNESDAY, MAY 1ST2019
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
OVERVIEW OF THE PROJECT PLAN Shelters Interactive Map Goal 1 Create services that allow users to interact with geographical data via a web-based interactive map Dataset Emergency Shelter Activation Status Tools HTML, JavaScript, Leaflet JS, Bing, AWS S3 (hosting), Route 53 (Domain Name Registration) Pet Shelter Name Address Status Location Friendly 250 Richard Montgomery Drive Rockville, MD 20852 (39.078636, -77.145631) Richard Montgomery High School 250 Richard Montgomery Drive, Rockville, MD 20852 CLOSED No Montgomery Country Fire & Rescue Service (MCFRS) Incident Analysis Goal 2 Provide an analysis of 911 calls received by MCFRS to better understand the nature, frequency and locations of the calls Dataset MCFRS_Incidents_by_Station, Population MD, Zip Code Shape File Tools Python, Geopy, Nominatim, pandas, numpy, matplotlib, seaborn, statsmodels.api, datetime, Tableau Fire Station Number Monthly Total Month Num Fire Station Nature of 911 call Year Month Station address Kensington Volunteer Fire Department (Station 18) 12251 Georgia Ave Wheaton, MD 20902 18 PREGNANCY 2 2017 MAY 5
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
SHELTERS INTERACTIVE MAP DATA CLEAN UP Extracted shelter data (GeoJSON) via Socrata s API function Active Shelters Link All shelters are listed as CLOSED Created mock data with a few shelters listed as OPEN Included Hospital and Police stations in the area Source:dataMontgomery (hospitals), and GIS Open Data (police stations) API Links changes when new data gets uploaded to dataMontgomery Old Link (Mar-19): https://data.montgomerycountymd.gov/resource/4yqk-nikt.geojson New Link (Apr -19): https://data.montgomerycountymd.gov/resource/mhua-idee.geojson
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. 3. Descriptive Statistics Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
SHELTERS INTERACTIVE MAP FINAL PRODUCT THE PRODUCT THE PROCESS http://itforaid.org/map/mcshelters.html - Test http://itforaid.org/map/mcshelterslive.html - Live
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. 5. Data Story Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
SHELTERS INTERACTIVE MAP RECOMMENDATIONS Provide additional details for shelters Maximum capacity permitted Description of services offered Point of Contact: email and number Shelter type (e.g. school, rec. center, community center) Set static API links when updating data in Socrata Increase number of pet friendly shelters Enhancements to the application: Find nearest open shelter based on a user s location Integrate app. with mapping apps Add layers such as road closures and traffic conditions Provide additional details for Police Stations dataset on Data Montgomery
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
MCFRS INCIDENT ANALYSIS DATA CLEAN UP 1. Geocoding Incident Data Merge Lat/Long to Incidents Isolate Addresses Drop Duplicates Get Lat/Long 2. Reclassifying Call Types: From 99 to 5 Types ('Health', 'Structural/Environment', 'Threat/Legal', 'Service', 'UNK ) Merge New Types with Incidents N/As = Not Reported Drop Duplicates New Types List 3. Time Series Analysis Date Format: Add expected date formats for Time Series and Seasonal Decomposition Analysis Adding Decimal Date 4/1/2014 = 2014.25 Index data based on Dates Format Dates: yyyy-mm-dd 4. Tableau Analysis & Dashboard Maryland Political Boundaries Shape File Population Data 2010 Census Merge All based on Zip Codes
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. 2. Data Clean Up Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
MCFRS INCIDENT ANALYSIS DESCRIPTIVE STATS Barplot - Calls Received - Agg. 3/2014 - 2/2019 Barplot - Calls Received by Year - Agg. 2014 - 2019
MCFRS INCIDENT ANALYSIS DESCRIPTIVE STATS 2019 does not have a full year of data
MCFRS INCIDENT ANALYSIS DESCRIPTIVE STATS Drop due to missing data on 3/2014
MCFRS INCIDENT ANALYSIS DESCRIPTIVE STATS Removed March 2014
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. 3. Descriptive Statistics Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
MCFRS INC. ANALYSIS SEASONAL DECOMPOSITION Observed = Trend + Seasonal + Residual Calls increase over time, perhaps due to increase in population Spikes at the start of each year, perhaps due to the flu common during the winter Observed = Trend + Seasonal + Residual Trend = Overall change over time Seasonal = Change within a given period Residual = Random variation in the series
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. 4. Final Product: The Analysis Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
MCFRS INCIDENT ANALYSIS DATA STORY CALLS BY CITY 2014 - 2019 73% of calls are Health related Specifically Sickness The majority of the calls occur in Silver Spring (162,500) Gaithersburg-Washington Grove Volunteer Fire Department (Station 8) has received the most calls: 49,135 TREND OF HEALTH CALLS RECEIVED Most Health calls occur during the winter months - Staff Centers Accordingly - Increase Flu Shot Availability NOTE: INFO BASED ON DATA APR 2014 MAR 2019
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. 5. Data Story Recommendations IV. dataMontgomery Experience V. Acknowledgements
MCFRS INCIDENT ANALYSIS RECOMMENDATIONS Add lat/long coordinates for the Fire Stations Add Time Stamp of Call Validate Zip Codes and Addresses Fire Station Original Address Fixed Address Kensington Volunteer Fire Department (Station 5) Damascus Volunteer Fire Department (Station 13) 10620 Connecticut Ave Kensington, MD 20985 10620 Connecticut Ave Kensington, MD 20895 26334 Ridge Rd Damascus, MD 20750 26334 Ridge Rd Damascus, MD 20872
AGENDA I. Overview Of Project Plan 1. Shelters Interactive Map 2. MCFRS Incident Analysis II. Shelters Interactive Map 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The map 4. Data Story 5. Recommendations III. MCFRS Incident Analysis 1. Data Clean Up 2. Descriptive Statistics 3. Final Product: The Analysis 4. Data Story 5. Recommendations IV. dataMontgomery Experience V. Acknowledgements
EXPERIENCES & ACKNOWLEDGEMENTS Pros of dataMontgomery Open Government: Montgomery County s commitment to increasing transparency and citizen involvement in general aspects of e-Government services Support: Quick Response from Data Owners/Staff Accessible: As a first time Socrata user, the tool meets its goal of making data accessible to the average non- technical user. Cons of dataMontgomery Navigation: Navigation can be cumbersome with a large amount of unvalidated data sets and views Maps: Mapping functionality was limited APIs: API links should be static if possible Acknowledgements Kathryn L -- Dennis L -- Kathy L -- Mayro N Peter P Carlos C stackOverflow -- machinelearningmastery.com -- http://sopac-old.ucsd.edu/convertDate.shtml -- data.imap.maryland.gov