Doing Data Science

Index

A

• A/B testing for evaluation, Evaluation, A/B Tests-A/B Tests
• absolute timestamps, Thought Experiment
• abuse of notation, A Real-World Recommendation Engine
• access to medical records thought experiment, Thought Experiment
• accuracy, Pick an evaluation metric, How About k-nearest Neighbors?, Evaluation
• accuracy of models, Accuracy: Meh
• actors, Terminology from Social Networks
• actual errors, Adding in modeling assumptions about the errors
• actual preferences, Principal Component Analysis (PCA)
• adding predictors, Adding other predictors
• additive estimates, Exponential Downweighting
• adjacency matrix, Representations of Networks and Eigenvalue Centrality
• adversarial behavior, Challenges in features and learning
• aggregate users, Exploratory Data Analysis (EDA)
• aggregating bootstraps, Random Forests
• Akaike Information Criterion (AIC), Selection criterion
• Aldhous, Peter, Thought Experiment: What Are the Ethical Implications of a Robo-Grader?
• algorithms, Algorithms
  • association, Being an Ethical Data Scientist
  • at scale, Sample R code: K-NN on the housing dataset
  • Basic Machine Learning Algorithm Exercise, Exercise: Basic Machine Learning Algorithms-Sample R code: K-NN on the housing dataset
  • black box, Machine Learning Algorithms
  • clustering, Thought Experiment: Meta-Definition, k-means
  • constraints on, Classifiers-Scalability
  • converged, Alternating Least Squares
  • evaluating models and, Choosing an Algorithm
  • for wrapper feature selection, Selecting an algorithm
  • Fruchterman-Reingold, Morningside Analytics
  • k-means, k-means ...