Wednesday, September 22, 2021

Unemployment analysis in India based on CMIE data

 

#unemployment

#india

#analytics

#jobs

#hobby


Please find below my analysis of the unemployment data from CMIE website.

I have created metrics for mean unemployment by states and standard deviation of the unemployment rate by states. 

Furthermore, I have also calculated the rate of change of unemployment across states of India for the duration of 2016-2021.

If you need the data for analysis, please visit: https://unemploymentinindia.cmie.com 






Thursday, December 19, 2019

When flights get delayed: Rebooking flights, refreshments, Hotel Accommodation and more!



Airlines ✈️ can reduce the hardships of delayed passengers 😣 by providing quick rebooking, and refreshments. Here is a look at how Air Asia is creating a differentiated experience for Indian air travellers. Note how Indigo airlines has the least number of passengers affected by cancellations and denied boarding. 🤷‍♂️ Air India is the only carrier to provide Hotel Accommodation in case of cancellation.
Vistara, Indigo, SpiceJet, Air India and Air Asia compared using the DGCA dataset. For more information, do leave your comment or send an email. Thanks.

#IRROPS

Friday, August 9, 2019

Departure delays and arrival delays at the airports? Check some stats

Hi there, I have created some charts on arrival and departure delays using the Bureau of Transportation Statistics data.
All the contents are public information and the charts are also under Creative Commons with Attribution- Non Commercial. Drop a comment under this post if you have further questions regarding use of the blog materials.

Chart 1

 Chart 2
 Chart 3
 Chart 4

Thanks.


Wednesday, July 31, 2019

Top 50 companies of the world by number of patents filed















I have prepared a database of Top 50 companies of the world by 
number of patents filed. The database contains the R&D expenditures 
for year 2017 and 2018, and their number of patents filed in the year 
2017 and 2018. If you are interested to get a copy of the same, please 
drop in your email ID and I will give you access. 

Link to file: https://docs.google.com/spreadsheets/d/1mMcX7oX2_l0SuaQF3TmQTp9ExEbAcj_IvYQLP6HVhr0/

Sunday, December 9, 2018

Immunisation stats for India: UNICEF Data (1980- 2018)

                  Direct link to the Tableau visualization is here:
https://public.tableau.com/profile/n.singh#!/vizhome/Indianvaccinationstats/Indiavaccinationgrowth?publish=yes

        I set about exploring the immunization rates in India for the vaccines suggested by UNICEF.

Child health immunization data has been sourced from the following location: https://data.unicef.org/topic/child-health/immunization/

There are the following new vaccines introduced post 2000 and I believe that the millennial need to get their shots done:


  1. HepB3: Hepatitis
  2. MCV2: Measles
  3. HepBB: Hepatitis
  4. Hib3: Haemophilus influenza
  5. IPV1: Polio
  6. RotaC: RotaVirus, acute gastroenteritis
  7. RCV1: Rubella, Polio


Sunday, May 20, 2018

Rashtriya Swasthya Bima Yojana (RSBY) or National Health Insurance Programme: A case study of Odisha

The health insurance program for the people below poverty line was launched in 2008. More details here: https://en.wikipedia.org/wiki/Rashtriya_Swasthya_Bima_Yojana 
Data sources:
  1. District wise data about the health insurance premium and hospitalization expenses is available here: http://www.rsby.gov.in/Statewise.aspx?state=24 
  2. District wise census data is available here: https://odisha.data.gov.in/catalog/primary-census-abstract-odisha#web_catalog_tabs_block_10 
Data analysis:
  1. The two datasets were merged by district name and simple charts were created using scatter plots and maps.
  2. Female literacy percentage was calculated as number of female literates over total number of females.
  3. Enrollment percentage was calculated as enrolled families over total target families.
  4. Private percentage was calculated as number of private hospitals empaneled to provide RSBY benefits over total number of public and private hospitals empaneled.
  5. Data was grouped by District.
  6. Tableau was used as charting software tool.
Charts:
I started by displaying parameters by state map to give an overall understanding of the geographic distribution of parameters.
3 districts had 100% RSBY enrollment among the target families; Sonepur, Nayagarh and Kalahandi.


The average hospitalization expense was a mixed bag across districts ranging from 889 rupees in Kandhamal to 7062 rupees in Jagatsinghpur.


 Districts near capital city of Bhubaneshwar were equipped with both public and private empaneled hospitals as compared to public hospital majority regions. Khordha had 71% private hospitals empaneled to serve patients under RSBY scheme.


 The geographical spread of female literacy showed distinct areas of low, medium and high literacy.

After the geographical charts were plotted, I created some scatter plots to understand the interdependence of factors.
The private hospital had 14 times higher average hospitalization expense as compared to a public hospital. (Slope of private graph trend line is 85 while slope of public graph trend line is 6)



Overall hospitalization expense increased with the increase of private public mix of hospitals.


Hospitalization expense increased with the number of hospitalization. Private hospital dominated districts can be seen as falling way above the trend line.
Hospitalization expense = 2105 * Number of Hospitalization or 1 hospitalization resulted in 2105 rupees worth of expense on average.



Number of hospitalizations generally increased with the increase in the number of enrolled families. Female literacy didn't appear as an impact factor here.
Number of hospitalization = 0.05*Enrolled families or only 1 out of 20 enrolled families used the hospitalization facility.




Count of enrolled families under the RSBY scheme decreased with increase in female literacy, which was a surprise.





Average hospitalization expense increased with female literacy; which shows that hospitalizations were lesser in number but more expensive suggesting surgeries or accidental illnesses.




Conclusion
Few important observations come up after the analysis:
  1. Average hospitalization expense per family was 105 rupees whereas premium was 370 rupees as mentioned on the webpage, i.e. claim ratio of 28%.
  2. The enrollment of target families is yet to be completed. Emphasis needs to be put on finishing enrollment soon.
  3. Use of private is meaningful only if they provide a medical treatment that government hospitals can't or if they are located at a place where there are no government hospitals.
  4. The data was available till September 2017. So there is a need to update the data on RSBY portal.

Sunday, August 6, 2017

NYC Taxi Duration challenge





Your Release Just Wrote Its Own Docs

  Every release ships with a shadow task nobody wants: writing the docs. The README needs updating. The changelog needs to actually reflect...