------------------Feature Engineering----------------------
The success of all Machine Learning algorithms depends on how you present the data. Every model gets input data and gives us an output. When your goal is to get the best possible output from input,
1/
The success of all Machine Learning algorithms depends on how you present the data. Every model gets input data and gives us an output. When your goal is to get the best possible output from input,
1/
You need to present the best data to the model. This is a problem that Feature Engineering solves. Feature Engineering refers to the process of using the domain of Knowledge to extract features from raw data.
2/
2/
In other words, Feature Engineering selects the most useful features from our raw data and presents them to our model, whereby we improve the performance of our model.
(hopefully, you get the point 😀).
3/
(hopefully, you get the point 😀).
3/
Feature Engineering consists of these approaches:
1 - Feature Creation
2- Transformations
3- Feature Extraction
4- Feature Selection
4/
1 - Feature Creation
2- Transformations
3- Feature Extraction
4- Feature Selection
4/
1- Feature Creation:
It means creating a new feature from existing features. For instance, your training data contain the length of the house and the width of the house. You multiply these two features and make a new feature called the area of the house.
5/
It means creating a new feature from existing features. For instance, your training data contain the length of the house and the width of the house. You multiply these two features and make a new feature called the area of the house.
5/
2- Transformations:
I leave this part blank and will write a thread in the future.
6/
I leave this part blank and will write a thread in the future.
6/
3- Feature Extraction:
Sometimes we have a huge volume of data, for instance, images, audio and etc. In this case, our model cant directly uses our data, so we use Feature Extraction. Feature Extraction is a process of automatically reducing the dimensionality of these data.
7/
Sometimes we have a huge volume of data, for instance, images, audio and etc. In this case, our model cant directly uses our data, so we use Feature Extraction. Feature Extraction is a process of automatically reducing the dimensionality of these data.
7/
Feature extraction methods include cluster analysis, text analytics, edge detection algorithms, and principal components analysis (PCA).
4- Feature Selection:
In every dataset, there are only a few features that are useful to build a model and other features are
8/
4- Feature Selection:
In every dataset, there are only a few features that are useful to build a model and other features are
8/
redundant or irrelevant. If we apply a dataset with all those features to our model, it will reduce the accuracy of our model. In this case, we should determine these important features and delete other features. We do this with the help of Feature Selection.
9/
9/
#ArtificialIntelligence #AI #ML #DataScience #DataScientists #CodeNewbies #Tech #deeplearning #CyberSecurity #Python #Coding #javascript #rstats #100DaysOfCode #programming #Linux #IoT #IIoT #BigData
10/
10/
• • •
Missing some Tweet in this thread? You can try to
force a refresh
