TripleTen provides an eight-month long, project-based online course that provides rigorous course work and education in machine learning, data exploration, statistical data analysis, python programming, time series forecasting, A/B testing, natural language processing, computer vision, and more. The eight month long program is split into sprints – two- or- three-week-long periods that cover separate technical topics. Each sprint includes theory, coding exercises, and projects where students can apply their skills and create functional applications, services, and features.
This repository will host all of my projects that I completed at the end of each sprint. Below, you will find a table of contents that contains a link to each project along with a brief description of the project and skills used to complete the project. Each project demonstrates my ability to apply various methods of exploratory data analysis, data visualization, and machine learning to different complex problems across the various sprints.
| Sprint Number | Project Name | Project Description | Libraries Used |
|---|---|---|---|
| 17 | Final Project | Develop a classification model to help a telecom company predict customer churn | pandas numpy matplotlib sklearn lightgbm catboost xgboost |
| 15 | Computer Vision | Use computer vision methods to determine the age of a person from a photo to help a liquor store adhere to alcohol laws by making sure they do not sell alcohol to people underage | pandas numpy matplotlib tensorflow keras |
| 14 | ML for Texts | Generate a model for classifying positive and negative movie reviews | pandas numpy matplotlib seaborn, sklearn nltk spacy |
| 13 | Time Series Forecasting | Build a regression model to predict the amount of taxi orders at an airport over the next hour | pandas numpy matplotlib sklearn statsmodel.tsa lightgbm catboost xgboost |
| 12 | Numerical Methods | Use GridSearchCV to automate hyperparameter tuning for a handful of gradient boosting models in order to choose the best model for predicting the value of a car given various vehicle attributes | pandas numpy sklearn lightgbm catboost xgboost |
| 11 | Linear Algebra | Help an insurance company find customers who are similar to a given customer by testing a kNN algorithm on combination of different distances and scaling of features to help the company's agents with marketing. Additionally, in this project I created a model to predict whether a new customer is likely to receive an insurance benefit using matrix math for data obfuscation. | pandas numpy seaborn sklearn math |
| 10 | Integrated Project 2 | Prepare a prototype of a machine learning model that predicts and maximizes the amount of gold concentration output throughout the gold extraction process | pandas numpy matplotlib sklearn |
| 9 | Machine Learning in Business | Using bootstrapping techniques, build a regression model that predicts the volume of oil in a region to help an oil mining company chose where develop its business to maximize its profits | pandas numpy matplotlib sklearn |
| 8 | Supervised Learning | Predict whether a customer will leave the bank soon using using new model evaluation metrics and adjusting for class imbalance | pandas numpy matplotlib sklearn |
| 7 | Introduction to ML | Develop a classification model that will predict the right plan for subscribers on legacy mobile plans | pandas numpy matplotlib sklearn |
| 6 | Data Collection and Storage (SQL) | Test a hypothesis about the impact of weather on ride frequency using ride-sharing data | pandas numpy matplotlib scipy |
| 5 | Integrated Project 1 | Generate insights and run hypothesis tests to determine which video games consoles should be featured in an upcoming advertising campaign | pandas, numpy, matplotlib, scipy, seaborn |
| 4 | Software Development Tools (Streamlit) | Streamlit application hosted on Render that allows users in interact with the car advertisement dataset to uncover insights about what car attributes can increase its value on the secondary market | pandas numpy plotly.express altair |
| 3 | Statistical Data Analysis | Perform hypothesis testing to determine if there is a statistically significant difference in revenue for pre-paid mobile plans | pandas numpy matplotlib scipy |
| 2 | Exploratory Data Analysis | Uncover insights about the shopping habits of Instacart customers | pandas numpy matplotlib |
| 1 | Working With Data in Python | Investigate how the number of votes a movie title receives impacts its ratings | pandas |