Thank GOD for Sklearn
Every subject has some fundamentals and without these fundamentals, the subject becomes tough to understand. Sklearn is one such fundamental library of python which played a key role in making technologies like Machine learning and Data Science catapult many years into the future and making it a reality today. Sklearn is also known as scikit-learn.
This project was started by David Cournapeau as a Google Summer of Code project which later became a part of Matthieu Brucher’s thesis. Further many authors contributed and made sklearn what it is today. sklearn specializes in classification, regression, clustering and dimensionality reduction.
As mentioned above there are 4 primary ways to use sklearn:-
- Classification: — In general classification means “The action or process of classifying something”
- In terms of machine learning, it means identifying the categories present in the data set.
sklearn contains 3 classification models: -
1)Support vector machines (SVMs)
2)Nearest neighbours
3)Random forest
2. Regression: — It means finding a relationship between the input and output of the given data. An example would be linear regression.
- Regression contains these 3 algorithms: -
1-SVMs
2-Ridge regression
3-Lasso
3.Clustering- When we are provided with a data set there is some data which are alike and clustering helps us bring all the alike data set together. There are mainly 3 clustering methods: -
1-K-means
2-Spectral clustering
3-Mean-shift
4.Dimensionality reduction: -In an analysis of a data set there can be n number of variables and these variables can decrease the efficiency and increase the time for analysis. So sklearn has features to reduce the non-required variables: -
1-Principal component analysis (PCA)
2-Feature selection
3-Non-negative matrix factorization
These were the main or top 4 uses of sklearn but it has many more features like model selection and pre-processing.
In my last blog, I went into detail about Data Pre-processing sklearn plays a major role in Data pre-processing
For further information, you can refer to the scikit-learn website or get in contact with me through mail-aishwar99govil@gmail.com or you can contact me on instagram-aishwargovil
