Difference between revisions of "ANLY482 AY2017-18T2 Group19 Data"

From Analytics Practicum
Jump to navigation Jump to search
(Created page with "<!--Logo--> center|748x116px<br> <!--Navbar Start--> {|style="background-color:#FFFFFF; color:#F5F5F5; padding: 10 0 10 0;" width="100%" cellspacing="0...")
 
Line 51: Line 51:
 
|}
 
|}
 
<!--Sub Navbar End-->
 
<!--Sub Navbar End-->
 +
 +
 +
<div style="background: #FFFFFF; padding: 15px; font-weight: bold; line-height: 0.3em; text-indent: 15px;letter-spacing:-0.03em;font-size:16px;id:UT1"><font face='Century Gothic' color=#000000 ><u>DATA DESCRIPTION</u></font></div>
 +
 +
The data required for us comes in 3 parts.
 +
#The demand side where the patients live which is derived from the percentage distribution of elderly in the respective subzones. This data will be created at random to simulate the daily nodes for each patient.
 +
#The supply side where the foundation/organisation dispatches nurses to their scheduled patients
 +
#The details of services with details such as the mean and standard deviation to provide a more realistic constraint for the algorithm to take into account when routing the nurses to their patients.
 +
 +
The dataset for the demand side will need to be generated by ourselves which includes:
 +
*Address: Address of patient
 +
*Latitude: Latitude of patient’s address
 +
*Longitude: Longitude of patient’s address
 +
*Type:
 +
*Appointment_Times: Prefered appointment time
 +
 +
The dataset for the supply side will need to be generated by ourselves which includes:
 +
*Id: Identification for nurse
 +
*Address: Address of origin
 +
*Latitude: Latitude of address
 +
*Longitude: Longitude of address
 +
*Type:
 +
 +
The dataset for the details of services includes:
 +
*Discipline:
 +
*Type (i.e. revisits, etc):
 +
*Request count:
 +
*Average: average time required for the treatment type
 +
*SD: standard deviation of time required for the treatment type
 +
 +
 +
<div style="background: #FFFFFF; padding: 15px; font-weight: bold; line-height: 0.3em; text-indent: 15px;letter-spacing:-0.03em;font-size:16px;id:UT1"><font face='Century Gothic' color=#000000 ><u>DATA COLLECTION</u></font></div>
 +
 +
We need to conduct research to better understand the demand side and supply side to generate sufficient amount of data to work with.
 +
 +
 +
<div style="background: #FFFFFF; padding: 15px; font-weight: bold; line-height: 0.3em; text-indent: 15px;letter-spacing:-0.03em;font-size:16px;id:UT1"><font face='Century Gothic' color=#000000 ><u>DATA CLEANING AND TRANSFORMATION</u></font></div>
 +
 +
The data will need to be transformed into the required formats in order for us to perform the necessary processing later.
 +
 +
 +
<div style="background: #FFFFFF; padding: 15px; font-weight: bold; line-height: 0.3em; text-indent: 15px;letter-spacing:-0.03em;font-size:16px;id:UT1"><font face='Century Gothic' color=#000000 ><u>EXPLORATION OF DATA</u></font></div>
 +
 +
At this phase, the data will be explored in order for us to choose a suitable model to be built.

Revision as of 01:03, 12 January 2018

748x116px


G19 Home.png   HOME

 

G19 Overview Icon.png   PROJECT OVERVIEW

 

G19 Findings Icon.png   PROJECT FINDINGS

 

G19 Management Icon.png   PROJECT MANAGEMENT

 

G19 Documentation Icon.png   DOCUMENTATION

 

G19 To Main Page icon.png   BACK TO MAIN PAGE


 


DATA DESCRIPTION

The data required for us comes in 3 parts.

  1. The demand side where the patients live which is derived from the percentage distribution of elderly in the respective subzones. This data will be created at random to simulate the daily nodes for each patient.
  2. The supply side where the foundation/organisation dispatches nurses to their scheduled patients
  3. The details of services with details such as the mean and standard deviation to provide a more realistic constraint for the algorithm to take into account when routing the nurses to their patients.

The dataset for the demand side will need to be generated by ourselves which includes:

  • Address: Address of patient
  • Latitude: Latitude of patient’s address
  • Longitude: Longitude of patient’s address
  • Type:
  • Appointment_Times: Prefered appointment time

The dataset for the supply side will need to be generated by ourselves which includes:

  • Id: Identification for nurse
  • Address: Address of origin
  • Latitude: Latitude of address
  • Longitude: Longitude of address
  • Type:

The dataset for the details of services includes:

  • Discipline:
  • Type (i.e. revisits, etc):
  • Request count:
  • Average: average time required for the treatment type
  • SD: standard deviation of time required for the treatment type


DATA COLLECTION

We need to conduct research to better understand the demand side and supply side to generate sufficient amount of data to work with.


DATA CLEANING AND TRANSFORMATION

The data will need to be transformed into the required formats in order for us to perform the necessary processing later.


EXPLORATION OF DATA

At this phase, the data will be explored in order for us to choose a suitable model to be built.

Retrieved from ‘https://wiki.smu.edu.sg/ANLY482/index.php?title=ANLY482_AY2017-18T2_Group19_Data&oldid=17986’