Earning Criteria

• The earner completed two miniprojects associated with the data wrangling module, scoring at least a 90%. They used Python libraries and SQL to gather, clean, organize, and analyze messy real-world data. They built a social graph of social connections of the population, and used that to determine influential people within the group. For the SQL miniproject, they wrote complex SQL queries to extract information from a NYC database of restaurant inspections, revealing common types of violations.
• The earner completed the machine learning module and successfully completed the ml miniproject, scoring at least a 90%. They used Python and Scikit Learn to develop a machine learning model. They combine existing estimators and transformers via pipelines and feature unions, and they are able to develop custom estimators and transformers to predict venue popularity from these features. Finally, they have built an ensemble model combining several smaller models to achieve better performance.
• The earner completed two miniprojects associated with the advanced machine learning module, scoring at least a 90%. They have shown the ability to use Python and Scikit Learn to develop time series machine learning models to address natural language processing and time series problems. The functioning of, and trade-offs in, more advanced models, like support vector machines, random forests, and gradient boosting trees, and had chosen, trained, and tuned their models appropriately for the domain.
• The earner has completed the spark miniproject, scoring at least a 90%. They have parsed, cleaned, and processed a 10 GB set of XML files of user actions on a Q&A website. Using this behavior, they have answered questions about user behavior to predict the long-term behavior of new users. They have trained a word2vec model and a classification model on tags associated with questions. They have worked with RDDs and DataFrames, and they have implemented a machine learning pipeline using Spark ML.
• The earner has completed the tensorflow miniproject, scoring at least a 90%. Their final model performs image classification with an accuracy of at least 75%. They have built and trained a series of neural networks to perform image classification, including a multi-layer perceptron, a convolutional neural network, and a network using transfer learning from a pre-trained model. They understand the many hyperparameters of a neural network and how to adjust them to avoid issues of overfitting.
• The earner has completed a capstone project to the satisfaction of TDI's instructors. The capstone project requires use of real-world data to help solve a practical issue. They used modern data analysis techniques to produce a product usable by the layperson to address this issue. They have used statistical tests and machine learning algorithms to derive actionable insights from that data and assembled this work into a form suitable for non-experts, allowing users to solve real-world problems.
• Earner attended courses from The Data Incubator, 21001 N Tatum Blvd Ste 1630 #642, Phoenix, AZ 85050, (480) 515-1411, thedataincubator.com, admissions@thedataincubator.com