Max is a life enhancer for tech & entrepreneurship. Which seeks to blend both to build innovative products or services for the world that solves hard problems.
Yup, i think MongoDB comes from using it for the data science field. Whereas Postgres is for a general use case point of view I guess. As from what I know, people who use MongoDB uses it for Data Science work than your typical use case like a normal web application.
Data-scientist who loves to use #datascienceforgood, especially in ecology, energy and the environment. Bonsai, gardening, bikes and music when I'm not at a keyboard.
I sort of agree. But also, having had to work with both PostGRES and Mongo in the same company, on the same product, as a Data Scientist, my experience was more: "Do I actually have to go to the Mongo DB in order to get [business report]? Can't we work around it by: [getting data from api/event bus]".
The reason is that most data science work relies on relations between data. We're not looking to find the 'one record that fits these criteria', we're trying to encapsulate the full scope of nearly all the data. I don't think I've ever done a job without needing 50-99% of all the records in a specific table in relation to 1-10 others. Doing that kind of work on Mongo is sort of a pain.
The other aspect is most data science processes focus on matrix like objects. Python tends towards Pandas/ numpy arrays for object representation, which are relatively analogous to a table in a database, and R has this kind of feature built into the base language with data.frames. Most ML will assume you pass it table like records.
There may be an argument that human written, free text based NLP might be a good fit. However, you will probably start an NLP still with tables of the frequency of the word turning up like in this project by by buddy Dom where he predicts Gross price of theatre tickets by doing NLP on the reviews of different shows
For further actions, you may consider blocking this person and/or reporting abuse
We're a place where coders share, stay up-to-date and grow their careers.
Yup, i think MongoDB comes from using it for the data science field. Whereas Postgres is for a general use case point of view I guess. As from what I know, people who use MongoDB uses it for Data Science work than your typical use case like a normal web application.
I sort of agree. But also, having had to work with both PostGRES and Mongo in the same company, on the same product, as a Data Scientist, my experience was more: "Do I actually have to go to the Mongo DB in order to get [business report]? Can't we work around it by: [getting data from api/event bus]".
The reason is that most data science work relies on relations between data. We're not looking to find the 'one record that fits these criteria', we're trying to encapsulate the full scope of nearly all the data. I don't think I've ever done a job without needing 50-99% of all the records in a specific table in relation to 1-10 others. Doing that kind of work on Mongo is sort of a pain.
The other aspect is most data science processes focus on matrix like objects. Python tends towards Pandas/ numpy arrays for object representation, which are relatively analogous to a table in a database, and R has this kind of feature built into the base language with data.frames. Most ML will assume you pass it table like records.
There may be an argument that human written, free text based NLP might be a good fit. However, you will probably start an NLP still with tables of the frequency of the word turning up like in this project by by buddy Dom where he predicts Gross price of theatre tickets by doing NLP on the reviews of different shows