1
$\begingroup$

I am absolutely new to this area of predictive modelling in data science. I am not able to understand how and what modelling techniques do we use? Does it depend on the data type? Does it depend on size of data?

To be specific to the title, I have to predict missing values in a given temperature data set and i am unaware of anything that i can use. Could someone guide me through?

$\endgroup$
2
  • $\begingroup$ What data do you have, beyond temperature values? What features are associated with each data point? Time, location? $\endgroup$
    – jamesmf
    Dec 15, 2015 at 18:36
  • $\begingroup$ year, month, min temp, max temp. these are the only attributes that I have. $\endgroup$
    – Sagar Ghai
    Dec 17, 2015 at 9:21

1 Answer 1

2
$\begingroup$

I am not able to understand how and what modelling techniques do we use?

Every data science workflow has the follwing steps:

  1. Pre-processing (data cleaning and wrangling)
  2. Exploratory analytics
  3. Model selection
  4. Prediction and testing. (And re-iteration)
  5. (Optional) Reporting the workflow

Does it depend on the data type?

Yes, the entire workflow is dependent on the type and features of the data.

Does it depend on size of data?

Size of data makes a difference in the tools and sometimes(very rarely) the algorithms used.

I have to predict missing values in a given temperature data set and i am unaware of anything that i can use

There is a lot of material and algorithms on how to impute missing data, which you can refer to and use them accordingly depending on the type of data and the problem statement.

$\endgroup$
2
  • $\begingroup$ can you also help me with how i should go forward with learning and building a hold onto data science? $\endgroup$
    – Sagar Ghai
    Dec 12, 2015 at 11:31
  • $\begingroup$ @SagarGhai I might not be able to, due to time constraints. However, there is plenty of material over Quora and this SE for getting up to speed. Good Luck :) $\endgroup$
    – Dawny33
    Dec 12, 2015 at 15:48

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.