2023 Workshops, Ceremonies, and more

2022 Workshops, Ceremonies, and more

2021 Events

2020 Events

Welcome to TAMU Datathon 2021. Watch this to learn about the event and how it works.

Opening Ceremony


Get tips & tricks on how to create a winning TAMU Datathon project from last year's winners.

- Goldman Sachs Competitor: Sola Babatunde, Victoria Catlett, Evan Meade
- Walmart 1st: Zachary Summers, Alexander Labbane,Ian Matson
- Facebook, Conocophillips 2nd: Prakhar Mohan, Sukanto Guha, Shubham Sanghavi, Dhruv Sandesara
- Goldman Sachs Learner: Marshall Allen, Brandon Merrill, Jack Grooms

---

- tags: win, advice, datathon, hackathon


How to Win TAMU Datathon

Here, we will announce winners of all challenges!


Award Ceremony

Join these to get key information about the event.

Informational Events


Are you new to programming? Or do you want a refresher to brush up on what you know? No worries!

In this class, we will learn the fundamentals of Python. From variables, to data types, to loops, we will cover the basics of the most widely used programming language in data science!

---

- tags: for loops, functions, while loops, logic, variables, data structures, syntax, types, beginner, python, languages


Intro to Python

In this talk, we will describe how we use data collected at Facebook to inform product development. Including everything from ideas, experimentations, and launches.

Learning the technical skills for analysis is key, but arguably more critical is asking the right research questions for the data you have available, and creating a story out of your findings.

Our talk will include an example of how an analysis can influence a product, as well as open up a discussion to everyone in the audience to share their own experiences. Hope to see you there!

#### Useful Links

- [Algorithmic Thinking](https://www.cs.cmu.edu/~112/notes/notes-algorithmic-thinking.html)

---

- tags: presenting, impact, business, data science

Storytelling with Data


In this talk, we will discuss some aspects of classical statistical inference that are used everyday to help guide decision making. Using a case study of running an experiment to inform website design, we discuss how to test which design is better and by how much, quantify our uncertainty about this conclusion, and decide how long we need to run the experiment in order to be confident in our results.

---

- Tags: statistics, confidence interval, testing, statistics, probability distributions, sampling bias, r


Stats for Data Science

Get started with classes that require no prior knowledge!

Beginner Classes


Howdy

So. You're interested in data science, but you don't know where to start. I want to let you know; you've come to right place.

Today, we'll dive into a process known as "data wrangling"... That word makes me think of cowboys for some reason. But seriously, finding good data and getting it into a pandas data-frame can actually be half the battle. I'll make sure you guys know how to find and load a dataset of your choice and do some quick analysis.

I'm thrilled to jump into the world of data wrangling with you. Let's get started.

---

- tags: jupyter notebook, pandas, import, packages, data science, wrangling, datasets, clean, start, introduction, mining, beginners


### Resources:
- [Seth's Jupyter Notebook](https://drive.google.com/file/d/1YmPwqDQwCLmuh1B8YxJgaGB0aLBgGD4O/view?usp=sharing)

DS Introduction Part 1/2: Wrangling


Howdy

So. You're interested in data science, but you don't know where to start. I want to let you know; you've come to right place.

Today, we'll cover data visualization and the basics of seaborne. Yeah... we gotta start with the basics. But trust me; with the basics of this tool under your belt, you'll look like a data science wizard since you'll be able to visualize most, if not all, of the data sets you encounter.

I'm thrilled to jump into the world of data visualization with you. Let's get started.

---

- tags: viz, visualization, seaborn, matplotlib, plots, charts, plotly express


DS Introduction Part 2/2: Visualization


Before you dive into some of the hot ML algorithms, it’s important for you to know the basics of whats going underneath the hood — ML is really just fancy optimization.
We will start with a refresher on linear regression and represent regression as an “optimization” problem. Next, we’ll show how machine learning is a fancy term for model fitting. A model is a function with parameters and variables. “Fitting” is the process of picking the right parameter values. I’ll show you how sklearn can be used to fit a model. Next, I’ll introduce Neural Networks and how we can represent linear regression as a NN.

---

- tags: optimization, math, theory, machine learning, linear regression, neural network, parameters, model fitting, sklearn


ML Introduction Part 1/2: Theory


In this workshop we will take you though one of the most powerful ML algorithms: Decision Trees. We will follow that up with a form of bagging called Random Forests and then a form of boosting called XGBoost.
Finally, we’ll teach how to avoid overfitting through cross validation, hyperparameter tuning and feature selection. All of this will be done in Python with sklearn. Looking forward to seeing you there!

---

- tags: applied, random forests, decision trees, xgboost, boosting, hyperparameter tuning, sklearn, evaluation, feature selection, test train split, machine learning


ML Introduction Part 2/2: Applied

Learn the fundamentals of data science to get the ball rolling!

TAMU Datathon Core Curriculum


You’ll walk away from this workshop with the basics of neural networks. You’ll be able to get your hands dirty with some of the software tools that are used to build neural networks like sklearn/keras/tensorflow. Additionally, you’ll become comfortable with many commonly heard terms of machine learning at a high level (more concept, less math) such as:
hidden layers, edges, nodes
backwards propagation (optimization)
forward propagation
activation function
loss function
learning rate
gradient decent
minibatches
epochs

---

- tags: neural networks, machine learning, introduction, deep learning, TensorFlow, Keras, numpy, Optimizer, Loss Function, Python


Intro to Neural Nets


Interested in learning what Natural Language Processing is all about?

This hour long course will teach you how to identify and separate words, extract topics, and conduct sentiment analysis. We will be using [Python](https://python.org) for this course, relying heavily on [the NLTK package](https://www.nltk.org/). By the end of the hour, you will be well-versed with the basics of NLP, the applications of which are endless.

#### Useful Links

- [Watch the trailer for this class](https://www.youtube.com/watch?v=YrnxaV5itXo)
- [Notebooks, Resources, and Datasets](https://drive.google.com/drive/folders/1gmayusAJkwke3XPVlA2RT1DOEEYYBTxv)

---

- tags: sklearn, gensim, nltk, tfidf, TfidfVectorizer, bag of words, CountVectorizer, word embeddings, Word2Vec, naive bayes, lemmatization, part of speech tags, named entity recognition, tokenization, word clouds


Intro to Natural Language Processing


Beyond supervised and unsupervised learning, did you know there is another form of ML called reinforcement learning (RL)? RL is a rapidly developing field of ML that learns to maximize its reward by choosing actions in its environment. Reinforcement learning has been successful at playing complex games such as DOTA and even beating human experts.
In this workshop, we’ll cover what you need to get started in reinforcement learning including some basic structure, theory and algorithms. We’ll finish by showing how reinforcement learning can be used for the stock prediction challenge!

---

- tags: RL, stock, trading, games, robotics, deep learning, advanced, machine learning, neural networks, policy


Reinforcement Learning


Reccommendation engines drive much of our online decision-making. From Netflix to Youtube to Tik Tok, platforms utilize reccommendation engines to provide the most relevant content possible to users.

In this workshop, we will cover the basics of reccommendation engine design and development, and the algorithms that drive them. Take a deep dive into an important,and increasingly relevant field of data science!

---

- tags: information retrieval, recommendation engine, netflix


Recommendation Engines


How do we interpret the results from our models? As we develop newer and better machine learning models, they grow more and more difficult to draw results from. In this workshop, we will go over techniques for making contemporary models easier to interpret.

---

- tags: explainability, partial dependence, LIME, conditional expectation, SHAP


Model Interpretability

Tackle advanced topics in DS/ML to get a deeper understanding!

Dive Deeper


Take a break from the hacking with MLH!


MLH Fun Events


Data or data? GIF or JIF? Should house elves be paid? In a state of late-night delirium, help Datathon answer some of our most pressing questions.


Midnight Musings

Fun Events


GM plans to bring several industry specialists to talk to you about DS/ML at GM. Next, we will
give resume/linkedin/interview tips and finally, we will take Q/A and resumes from participants.


General Motors Career Fair

### ABOUT TTI
The Texas A&M Transportation Institute (TTI) is honored to once again sponsor the Texas A&M Datathon. The amazing and energetic student organizers have risen to the challenge of a virtual Datathon and I expect that it will be even more successful than last year! We are always looking for talented data scientists who want to help solve real-world transportation problems with data.

### WEBSITE
https://tti.tamu.edu/

### VIDEO
https://vimeo.com/255088698


Texas Transportation Institute Career Fair

The Texas A&M Institute of Data Science pursues new approaches to Data Science research, education, operations and partnership. These approaches cross college boundaries to connect elements of Data Science from engineering, technology, science and the humanities, and inform wider social challenges. Join for a chance to learn more about TAMIDS.

### WEBSITE

https://tamids.tamu.edu/

### VIDEO

https://youtu.be/_fAuhcfopWk

Texas A&M Institute of Data Science Q&A

Showcase yourself to company recruiters and industry professionals

Career Fair


The agenda of the Time Series workshop is to bring students together in the analysis of time series and methods to process sequential data. This includes varied algorithms for time series analysis, feature engineering for single and multi-time series, prediction/forecasting, clustering, anomaly and change point detection. Time series data can be found in many fields of our daily life, such as sales, stocks, traffic etc. We see time series in retail in the form of sales, inventory, labor allocation etc. and to forecast them accurately is crucial for success in retail business. In this workshop, Neelabh Pant will give an introduction on time series and its applications. We will begin by understanding the domain of the data and about autocorrelation and partial autocorrelation charts and using them in conjunction with powerful ARIMA based models, including seasonal-ARIMA models and SARIMAX to include Exogenous data points. We will also talk about state-of-the-art deep learning techniques with RNNs (Recurrent Neural Networks) that use deep learning to forecast future data points. Finally, we will cover Facebook’s Prophet library, a simple to use, yet powerful Python library developed to forecast the future.


Walmart Workshop


MATLAB is a professionally developed programming environment with a variety of toolboxes for engineers and scientists. Join Connell D’Souza as he walks through how MATLAB can help you solve problems without getting bogged down by implementation issues. We will cover the basics of importing and visualizing data, rapidly testing machine learning and deep learning models as well as building apps in MATLAB.


Mathworks Workshop


Let us dive into the world of transportation with Texas A&M Transportation Institute (TTI). Attend this workshop to learn about who we are, what we do, and how you can fit in this world of transportation research with your data science skills. Transportation is a very diverse field with multiple modes – cars, trucks, bikes, buses, multiple focus areas – safety, pavement/road material, policy, air quality, and hence, comes with a multitude of real-world problems waiting to be solved. Join us to learn how we geek out on data while saving lives, time, and resources.


Texas Transporation Institute Workshop


Join us for an introduction into APIs and how to leverage them in your next data analytics project. We’ll discuss what APIs are, how and why they are useful for ML/AI projects/products, and explore some common API types you will encounter working with both public and private service/data providers. Our speakers will also walk through a live demonstration of interacting with some public APIs via Postman, JavaScript, and Python as well as illustrate how easy it is to develop your own private/public APIs.


### Resources:
- [Public APIs you can use!](https://github.com/public-apis/public-apis)


Hewlett Packard Enterprise Workshop


Tableau is a visual analytics platform transforming the way we use data to solve problems—empowering people and organizations to make the most of their data. Tableau is a an industry standard in data visualization and a vital skill for data scientists. Learn how to use Tableau to quickly create beautiful visualizations!


Tableau Workshop


The Texas A&M Institute of Data Science (TAMIDS) hosts a month-long challenge each spring open to Texas A&M students. Josiah Coad (2019 Winner) and Allyson King (2020 Winner) will be giving an overview on their TAMIDS projects from previous years.


Texas A&M Institute of Data Science Workshop

Learn from industry and see how these companies use DS/ML technologies in there day to day.

Events and Workshops

Informational Events

How to Win TAMU Datathon

Opening Ceremony

Award Ceremony

Beginner Classes

How to Win TAMU Datathon

Intro to Python

Storytelling with Data

Stats for Data Science

TAMU Datathon Core Curriculum

DS Introduction Part 1/2: Wrangling

DS Introduction Part 2/2: Visualization

ML Introduction Part 1/2: Theory

ML Introduction Part 2/2: Applied

Dive Deeper

Intro to Natural Language Processing

Recommendation Engines

Intro to Neural Nets

Reinforcement Learning

Model Interpretability

Fun Events

MLH Fun Events

Midnight Musings

Career Fair

Texas A&M Institute of Data Science Q&A

General Motors Career Fair

Texas Transportation Institute Career Fair

Company Workshops

Walmart Workshop

Mathworks Workshop

Texas Transporation Institute Workshop

Hewlett Packard Enterprise Workshop

Tableau Workshop

Texas A&M Institute of Data Science Workshop