Machine Learning: 2 Books in 1: Python Machine Learning and Data Science. A Comprehensive Guide for Beginners to Master Deep Learning, Artificial Intelligence and Data Science with Python. by Andrew Park

Author:Andrew Park [Park, Andrew]
Language: eng
Format: epub
Published: 2020-01-19T17:00:00+00:00

Getting the data prepared

After we spend some time going through all of the different sources to find the information that we need, it is time to look at how we can use these data, and data preparation will help out with this. There are a few steps that happen in this phase, basically we are going to do things like converting the information from all of those different sources into one common format so that they work together, and an algorithm that we pick out later will be able to handle the data without errors or mistakes.

This process is going to be more involved, but it is where the data scientist will start collecting clean subsets of data and then will insert the defaults and the parameters that are needed for you. In some cases, the methods that you use will be more complex, like identifying some of the values that are missing out of that data, and more.

Another step that needs to happen while you are here is to clean off the data. This is so important when you collect the data from more than one source because it ensures that it’s the same and that the algorithm you pick will be able to read it all later. You also want to make sure that there isn’t any information missing, that the duplicate values are gone, and there is nothing else found within the set of data you want to work with that will decrease the accuracy of the model that you are trying to make.

After you go through and clean off the data you would like to use, the next step is to do the integration and then create our conclusion based on the set of data for the analysis. This analysis is going to involve taking the data and then merging two or more tables that have the same objects, but different information. It can also include the process of aggregation, which is when we summarize the different fields found in the table as we go through the process.

During this whole process, the goal is for us to explore and then come up with an understanding of the patterns, as well as the values, that are going to show up in the data set that we are working with. This can take some time and some patience, but it is going to ensure that any mathematical models we work with later make sense and work the way that we want.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.