See [this document](../Practicum.md) for general information about the practicums.
Learning objectives:
- Familiarizing with numpy and matplotlib
- Using various classifiers implemented in scikit-learn
Task 1: Plotting Gaussian distributions for the Iris dataset
- Create a plot for each of the four attributes in the Iris dataset and display the Gaussian distribution for each of the three classes (i.e., three lines).
Task 2. Comparing different classifiers on the Iris dataset
- Using the training/test splits from Practicum 2, train different classifiers and compare their performance by filling out the following table:
| Method | Accuracy | Error rate |
| -------------------- | -------- | ---------- |
| Decision tree | | |
| Nearest Neighbors | | |
| Naive Bayes | | |
| SVM (linear kernel) | | |
| SVM (polyn. kernel) | | |
| SVM (RBF kernel) | | |
| Random Forest | | |
- Documentation for the classifiers can be found here:
* [Decision trees](http://scikit-learn.org/stable/modules/tree.html)
* [Nearest Neighbors](http://scikit-learn.org/stable/modules/neighbors.html)
* [Naive Bayes](http://scikit-learn.org/stable/modules/naive_bayes.html)
* [SVM](http://scikit-learn.org/stable/modules/svm.html) with different [kernels](http://scikit-learn.org/stable/auto_examples/svm/plot_svm_kernels.html)
* [Random Forest](http://scikit-learn.org/stable/modules/ensemble.html forests-of-randomized-trees)
References
- Scikit-learn
* [Tutorial](http://scikit-learn.org/stable/tutorial/index.html)
* [Supervised learning](http://scikit-learn.org/stable/supervised_learning.html)
* [Class and function reference](http://scikit-learn.org/stable/modules/classes.html)
* [Dataset loading utilities](http://scikit-learn.org/stable/datasets/index.html)
- [Scikit-learn tutorial video](https://vimeo.com/53062607) and [online material](http://www.astroml.org/sklearn_tutorial/)
