Machine_learning

This repo contains the implementation of the labs and practical work of the module Machine learning

Content :

---

1. Data preprocessing :

• Data wrangling
• Exploratory data analysis on covid dataset
• Visualization

2. Linear regression :

• Gradient descent implementation to optimize the loss function from scratch.
• The normal equation implementation to find the best parameters that minimize the loss function.

3. Support vector machine :

• Performing classification with svm model

4. K-Nearest neighbors :

• Implementation of k-NN from scratch.
• Implementation of K-NN with scikit-learn.
• Performing binary classification using K-NN.

5. Decision trees :

• Implementing and visuailzing decison trees scikit-learn.
• Analyzing the effect of the maximum tree depth and criterion on the train and test accuracy.
• Plot decision tree graphs of a given dataset.

6. Naive Bayes :

• Implementing a gaussian naive bayes classifier
• Getting familiar with other types of naive bayes classifiers such as multinomial naive bayes ...

7. Random forests :

• Implementing a random forest classifier and performing hyperparameters tuning with grid search.

8. K-means :

• Implementing K-means from scratch
• Implementing k-means using scikit-learn and plotting clustering results.

9. Neural Networks :

• Implementing a perceptron from scratch