/Springboard-DSC

The portfolio of work that was done during my Data Science training at the Springboard Intensive Bootcamp.

Primary LanguageJupyter Notebook

Springboard Data Science Bootcamp - Business Intelligence Specialization

    The Basic Tools for Dealing w/ Data

  • London Housing - The Basics of Data Science  
    Simple workflow involving loading, cleaning, formatting, exploring, and visualizing data to answer a data analytics question.
  • API Mini Project - APIs & The Python Standard Library  
    Leveraging APIs to source data from different platforms.
  • SQL Country Club - Relational Databases & SQL
    Query data from relational databases through python packages and management tools such as pgAdmin.

    • Statistics

  • Frequentist Inference - Statistical Inference in Python  
    Understanding the basics of staistical inference
  • Statistical Modeling - Python Statistics Essential Training  
    Builing on the basics of statistical inference and adding statistical modeling.
  • App Store Integration - Hypothesis Testing in Python  
    Making software design decisions using data driven hypothesis testing.

    • Supervised Machine Learning

  • The Red Wine Dataset - Linear Regression  
    Build a series of Linear Regression models to predict alcohol levels in wine and choose one by evaluating the models' performance.
  • Logistic Regression - Introduction to Classification  
    Understand the mechanics of Logistic Regression and build a model that predicts gender from weight and height data.
  • Coffee Diner Horizontal Expansion - Decision Trees  
    Use Decision Trees to produce an analysis that can be used when considering if a horizontal expansion is beneficial to a business.
  • COVID-19 - Ensemble Methods I: Bagging - Random Forests  
    Create a Random Forest model to build a classifier to predict the "state" of a patient.
  • The Titanic Dataset - Ensemble Methods II: Boosting - Gradient Boosting  
    The simple, but iconic Titanic dataset was used to introduce Gradient Boosting algorithms.

    • Unsupervised Machine Learning

  • Manhattan & Euclidean Distances - Application of Distance Measures I  
    Preparing for Unsupervised Learning by understanding distance measures.
  • Cosine Similarity - Application of Distance Measures II  
    Alternative ways to think about similarity.
  • Wine Customer Segmentation - Clustering  
    Using the outcome of different marketing campaigns, group similar minded customers together.

    • Advanced Machine Learning Techniques

  • Featuretools - Automated Feature Engineering  
    Automate the feature engineering process using advanced tools.
  • Pima Indian Diabetes Dataset - Model Optimization I: Grid Search Optimization - KNN  
    Hyperparameter tune a KNN model using GridSearch.
  • Flight Departures Dataset - Model Optimization II: Bayesian Optimization - LightGBM  
    Hyperparameter tune a LightGBM using Bayesian Optimzation.

    • Business Intelligence

  • GBPUSD FX Profiling - Data Storytelling  
    Create a story around a dataset. Analyze it and write a report to be read by a diverse audience.
  • Growth Hacking - Data Driven Growth  
    Use a company's existing data store to create analyses that can help with growth and marketing.
  • Big Data Technologies - Introduction to Spark SQL in Python  
    Introduction to tools that can be used to work with the Big Data that will be encountered in the field.
  • Future User Adoption - Take Home Challenge I  
    Determine the most important factors realated with user adoption.
  • Ultimate Data Scientist - Take Home Challenge II  
    Complete a task from segments of the Data Science field. Analze user logins to uncover patterns of demand, design an experiment that could test the effectiveness of a business intiative, and build a predictive model to determine long-term rider retention.