Introduction:

The workshop series is designed with a focus on the practical aspects of machine learning. We will be working in Python and using real-world datasets from Kaggle, the machine learning platform most suited for the “learn-by-doing” philosophy. This hands-on series is targeted towards complete beginners familiar with Python and will cover the minimal but most useful tools and concepts to get you started to work on a data science project. In the first session, we will explore a couple datasets from Kaggle and practise feature engineering using pandas. In the second session, we will learn the classification and regression algorithms along with other important concepts of practical use in machine learning and train models using scikit-learn for the datasets from the previous session.

This series is a condensed version of the previous four-session Machine Learning workshop series at Harvey Mudd College by the same instructor.

Topics to be covered in the first session:

• Pandas dataframes as the data structure for datasets
• Converting csv files to dataframes
• Slicing and indexing dataframes using conditionals as well as iloc and loc methods.
• Statistical summary and exploration of dataframes
• Detecting and filling missing values in the dataframes
• Regular expressions for data extraction
• Feature engineering such as creating new features
• Basic plots
• Basic operations such as dropping rows/columns, setting index, replacing values of a column using a dictionary, etc.
• Split-apply-combine operations by grouping rows of a dataframe
• Encoding categorical variables
• Correlation among features (optional)
• Merging dataframes (optional)

Topics to be covered in the second session:

• Linear Regression
• Logistic Classifier
• Overfitting and underfitting
• k-fold Cross-validation
• Dimensionality reduction (Optional)
  • Principal Component Analysis (PCA)
• Evaluation metrics for classification
  • Classification accuracy
  • Confusion matrix
  • Decision Threshold
  • Precision and Recall
  • F1 score
  • Area Under ROC curve

Instructor:

Aashita Kesarwani (Scientific Computing Specialist, Harvey Mudd College)
Jeho Park (QCL Director, Claremont McKenna College)

Teaching Assistants:

Lan Phan (CMC ‘19), Bruno Youn (CMC ‘19)

Registration

• Part 1: Friday, April 26th from 1:30 PM to 3:30 PM
• Part 2: Friday, May 3rd from 1:30 PM to 3:30 PM

We recommend you to register for both workshops as they are designed to cover different topics.

Part 1 workshop will be more hands-on and cover the data exploration, data manipulation, and feature engineering using pandas. It is a precursor to Part 2 that will cover machine learning concepts along with model building using scikit-learn.

Workshop Topics

See Machine Learning workshop series at Harvey Mudd College for more information. This 2-day workshop will be a condensed version of the original HMC workshop.

FAQ

Q: Should I register for both part 1 and part 2 workshops?

We recommend you to attend both workshops. Part 1 workshop will be more hands-on and cover the data exploration, data manipulation, and feature engineering using pandas. It is a precursor to Part 2 that will cover machine learning concepts along with model building using scikit-learn.

Q: Should I bring my own laptop?

For CMC folk: No, you don’t have to. But we encourage you to bring your laptop to download all the workshop materials on it. You can also use lab computers. RN12 has over 50 Windows computers and you can log in the computers using your CMC credential. For non-CMC folks, yes, you should bring your laptop. We can also provide a loaner laptop if you need one.

Q: How can I cancel my ticket?

Your confirmation ticket email has a link, “View and manage your order online.” Follow that link and cancel your ticket.

Q: Should I be affiliated with CMC?

No, the workshops are open to all Claremont Colleges.

Q: What is Kaggle?

Kaggle is a cloud platform for data science and machine learning community. Competitions, data sets, and computing resources are available for free. Check it out – Kaggle website.

Q: Where can I get the topics, data, and Python files for the workshops?

The workshop topics, data and files will be available on A hands on introduction to Machine Learning using Python on Kaggle before the workshop.