Final Exam: Prompt Engineering Use Cases

WHAT YOU WILL LEARN

• 

  Use prompt engineering to learn machine learning and statistics
  

  configure and explore generative ai chatbots
  

  use prompt engineering to learn statistics and machine learning
  

  compute median and mean in python using prompt engineering
  

  compute mean and median in python using prompt engineering
  

  describe the benefits of calculating range and inter-quartile range
  

  calculate range and inter-quartile range
  

  calculate variance and standard deviation
  

  interpret skewness and kurtosis using ai chatbots
  

  analyze images with generative ai
  

  interpret images with generative ai
  

  set up and explore generative ai chatbots
  

  recall how p-values work
  

  understand hypothesis testing
  

  analyze p-values using alpha levels
  

  introduce t-tests
  

  identify assumptions of t-tests
  

  use prompt engineering help to test data for normality with
  

  perform the one-sample t-test
  

  use the one-sample t-test end-to-end
  

  perform the one-sample t-test end-to-end
  

  test data for normality with prompt engineering help
  

  identify the two-sided and one-sided t-tests
  

  explore the two-sided and one-sided t-tests
  

  explore assumptions of t-tests
  

  interpret p-values using alpha levels
  

  introduce the paired-samples t-test
  

  use the welch's t-test
  

  use prompt engineering to interpret results of the two sample t-test
  

  run the welch's t-test
• 

  identify the appropriate test to test data for equal variances
  

  describe how to test data for normality
  

  test data for equal variances
  

  test data for normality
  

  describe the two-sample t-tests
  

  introduce the two-sample t-tests
  

  run the paired-samples t-test
  

  test the assumptions of the paired samples t-test
  

  describe anova
  

  use anova and tukey hsd tests
  

  test assumptions of anova
  

  run anova and tukey hsd tests
  

  introduce anova
  

  train a clustering model
  

  balance imbalanced data
  

  balance out imbalanced data
  

  train a model on an imbalanced dataset
  

  train a classification model on an imbalanced dataset
  

  split data and then train a classification model
  

  split data and train a classification model
  

  analyze the performance of clustering
  

  evaluate the performance of clustering
  

  evaluate the performance of classification models
  

  review data for classification
  

  describe machine learning models
  

  understand regression models
  

  analyze data for classification
  

  analyze relationships in data
  

  interpret relationships in data
  

  introduce machine learning models