Machine Learning Exploration

More tutorials can be found here

Survey a list of popular machine learning models and compute them with python.

Reference books:

• Introduction to Machine Learning with Python: A Guide for Data Scientists by Andreas C. Müller, Sarah Guido
• Applied Predictive Modeling by Max Kuhn, Kjell Johnson

Affiliation: Quantitative Methods in Social Sciences, Columbia University

Keywords: Machine Learning, Supervised Learning, Unsupervised Learning.

Software: Python, sklearn, numpy, pandas, matplotlib, keras

Supervised Learning

1. Regression on California Test Scores
2. Classification on red and white wine characteristics

Unsupervised Learning

1. K Means Cluster
2. Hierarchical Cluster Analysis
3. Principal Component Analysis

Classification on Text Data

1. Import the text data
2. Vectorize
3. Run three models and Select
4. Inspect all models by visualizing the coefficients

Neural Network

1. Run a multilayer perceptron with two hidden layers

2. selecting the number of hidden units using GridSearchCV and evaluation on a test-set.

3. Describe the differences in the predictive accuracy of models with different numbers of hidden units.

4. Describe the predictive strength of your best model.