Machine-Learning-Labs

Machine Learning is concerned with computer programs that automatically improve their performance through experience. This course covers the practical algorithms for machine learning from a variety of perspectives.

Description of labs :

1. Numpy and Pandas: To understand Numpy and Pandas libraries in depth and implement the Basic functions using these libraries.

2. Search Algorithms: Write two functions A* Traversal and DFS Traversal which implements the respective algorithm.

3. Decision Tree Classifier: Decision Tree is to create a training model that can be used to predict the class or value of the target variable by learning simple decision rules inferred from prior data.

4. K-Nearest Neighbours(KNN): Prepare a Python class KNN which can be used for classification.

5. Backpropogation [ANN]: Implement "chain rule" using computation graphs. Compute the gradient of a Tensor variable with respect to the leaf nodes of the computation graph that created the Tensor.

6. Support Vector Machines: Implement a Support Vector Machine classifier using the scikit-learn machine learning framework. Create a pipeline using the pre-processing steps and the SVM classifier to automate the entire process of training and evaluating the model you build.

7. Adaboost: An ensemble method is a technique that combines the predictions from multiple machine learning algorithms together. To make more accurate predictions than any individual model.

8. Hidden Markov Model(HMM): Implement the Viterbi algorithm for decoding a sequence of observations to find the most probable sequence of internal states that generated the observations.

9. K-Means Clustering: Code for the class K-Means Clustering which will implement K-Means Algorithm.

File structure documentation :

There are total 9 MI Weeks and Coding Assignments

Each week folder has 3 comman file :

• Week Manual.pdf - This document includes a detail explanation of each task and function block.
• File_Name.py - The implementation of the actual code block and function is contained in this document.
• SampleTest.py - This document offers test cases to help you validate your code.

NOTE : These sample test cases are just for your reference only.

Additional files in some week directories include report and dataset in .csv format

How to run :

For Windows Systems

  python SampleTest.py --SRN File_Name

• Example : python SampleTest.py --SRN Nump_Pandas

For Linux Systems

  python3 SampleTest.py --SRN File_Name

• Incase of any import error use the below command

  python3.7 SampleTest.py --SRN File_Name

Library Installation

In case of missing library errors install packages via pip package manager or any other package manager of your choice.

  pip install <library_name>

Authors

• @AdarshKumar275

License

• The source code for the site is licensed under the MIT license, which you can find in LICENSE page.