-2

How many types of different pre-processing techniques are exists in machine learning for data-sets. I want to define the general template that help me in pre-processing on the different problem.

I done some operation on image classification like resize, rgb2grayscale, find out dummy images, process on two images and that result added in the data-set.

My goal to optimise the data-set with the different techniques.

desertnaut
  • 57,590
  • 26
  • 140
  • 166
Rahul Savariya
  • 1
  • 5

2 Answers2

1

There are lots of pre-processing techniques, which to use depends upon your dataset. Some of the techniques are:

  • Data Cleaning: Data is cleansed through processes such as filling in missing values, smoothing the noisy data, or resolving the inconsistencies in the data.
  • Data Integration: Data with different representations are put together and conflicts within the data are resolved.
  • Data Transformation: Data is normalized, aggregated and generalized.
  • Data Reduction: This step aims to present a reduced representation of the data in a data warehouse.
  • Data Discretization: Involves the reduction of a number of values of a continuous attribute by dividing the range of attribute intervals.
Waleed Naveed
  • 2,293
  • 2
  • 29
  • 57
0

Pre-processing is a very broad term and more importantly what one might consider as pre-processing depends heavily on what you want to do with the data -for example cropping out the faces for a face recognition task- and the data itself since you might have a dataset that would need a very specific kind of pre-processing - e.g. deleting watermarks from a corner of image.

That being said, here is a useful guide I found. I think you have already done most of what would be considered as general pre-processing.

Bahman Rouhani
  • 1,139
  • 2
  • 14
  • 33