Simple Implementations of some Machine Learning Algorithms.
Along with implementation, it contains simple notebook that compares results of these implemenations
with standard sklearn library implementations.
Note that these implementations are very simple and do not consider aspects like space complexity, time complexity,
scalability, correct error messaging etc.
Most of the implementations use NumPy ( scarcely use Scipy ) and mostly do not have any other requirement.

1. NumPy ( pip install numpy)
2. SciPy ( pip install scipy)
3. Sklearn ( used for comparison and metrics like accuracy_score etc) ( pip install -U scikit-learn)
4. seaborn ( for plotting, similar plotting can be done using matplotlib too)
5. cvxopt ( for quadratic optimization for SVM )

1. Decision Tree
2. k-Nearest Neighbors
3. Random Forest
4. Gradient Boosting
5. Linear Regression
6. Logistic Regression (with Gradient Descent)
7. K-means
8. DBSCAN
9. SVM
10. Naive_Bayes
11. PCA
12. tSNE

Feel free to email or contact me on LinkedIn