Edits to Chapter 1. Closes #1.

.gitignore

@@ -69,3 +69,4 @@ yarn-error.log
 .pnp.js
 # Yarn Integrity file
 .yarn-integrity
+.Rproj.user

exercises/exc_01_06.R

@@ -1,14 +1,16 @@
-library(tidyverse)
-cars_vars <- readRDS("/usr/local/share/datasets/c1_cars_vars_full.rds")
-
-# Load caret
-___
-
-# Split the data into training and test sets
-set.seed(1234)
-in_train <- createDataPartition(cars_vars$___, p = ___, list = FALSE)
-training <- cars_vars[___, ]
-testing <- cars_vars[___, ]
-
-
-
+library(tidyverse)
+cars_vars <- readRDS("/usr/local/share/datasets/c1_cars_vars_full.rds")
+
+# Load rsample
+___
+
+# Split the data into training and test sets
+set.seed(1234)
+in_train <- car_vars %>%
+    initial_split(prop = ___, strata = "___")
+
+car_train <- training()
+car_test <- testing()
+
+
+

exercises/exc_01_07_1.R

@@ -1,16 +1,18 @@
-library(caret)
-library(tidyverse)
-
-training <- readRDS("/usr/local/share/datasets/c1_training_full.rds")
-testing <- readRDS("/usr/local/share/datasets/c1_testing_full.rds")
-
-# Load caret
-___
-
-# Train a linear regression model
-fit_lm <- train(log(MPG) ~ ., method = ___, data = ___,
-                trControl = trainControl(method = "none"))
-
-# Print the model object
-fit_lm
-
+library(caret)
+library(tidyverse)
+
+car_train <- readRDS("/usr/local/share/datasets/c1_training_full.rds")
+car_test <- readRDS("/usr/local/share/datasets/c1_testing_full.rds")
+
+# Load caret
+___
+
+# Train a linear regression model
+fit_lm <- train(log(MPG) ~ ., 
+                method = ___, 
+                data = ___,
+                trControl = trainControl(method = "none"))
+
+# Print the model object
+fit_lm
+

exercises/exc_01_07_2.R

@@ -1,8 +1,10 @@
-# Train a random forest model
-fit_rf <- ___(log(MPG) ~ ., method = ___, data = ___,
-                trControl = trainControl(method = "none"))
-
-# Print the model object
-fit_rf
-
-
+# Train a random forest model
+fit_rf <- ___(log(MPG) ~ ., 
+                method = ___, 
+                data = ___,
+                trControl = trainControl(method = "none"))
+
+# Print the model object
+fit_rf
+
+

exercises/exc_01_08.R

@@ -1,19 +1,19 @@
-library(caret)
-library(tidyverse)
-
-training <- readRDS("/usr/local/share/datasets/c1_training_full.rds")
-fit_lm <- readRDS("/usr/local/share/datasets/c1_fit_lm.rds")
-fit_rf <- readRDS("/usr/local/share/datasets/c1_fit_rf.rds")
-
-# Load yardstick
-library(___)
-
-# Create the new columns
-results <- training %>%
-    mutate(`Linear regression` = predict(___, training),
-           `Random forest` = predict(___, training))
-
-# Evaluate the performance
-metrics(results, truth = ___, estimate = `Linear regression`)
-metrics(results, truth = ___, estimate = `Random forest`)
-
+library(caret)
+library(tidyverse)
+
+car_train <- readRDS("/usr/local/share/datasets/c1_training_full.rds")
+fit_lm <- readRDS("/usr/local/share/datasets/c1_fit_lm.rds")
+fit_rf <- readRDS("/usr/local/share/datasets/c1_fit_rf.rds")
+
+# Load yardstick
+library(___)
+
+# Create the new columns
+results <- car_train %>%
+    mutate(`Linear regression` = predict(___, training),
+           `Random forest` = predict(___, training))
+
+# Evaluate the performance
+metrics(results, truth = ___, estimate = `Linear regression`)
+metrics(results, truth = ___, estimate = `Random forest`)
+

exercises/exc_01_09.R

@@ -1,17 +1,17 @@
-library(caret)
-library(tidyverse)
-library(yardstick)
-
-testing <- readRDS("/usr/local/share/datasets/c1_testing_full.rds")
-fit_lm <- readRDS("/usr/local/share/datasets/c1_fit_lm.rds")
-fit_rf <- readRDS("/usr/local/share/datasets/c1_fit_rf.rds")
-
-# Create the new columns
-results <- ___ %>%
-    mutate(`Linear regression` = predict(fit_lm, ___),
-           `Random forest` = predict(fit_rf, ___))
-
-# Evaluate the performance
-metrics(results, truth = MPG, estimate = `Linear regression`)
-metrics(results, truth = MPG, estimate = `Random forest`)
-
+library(caret)
+library(tidyverse)
+library(yardstick)
+
+car_test <- readRDS("/usr/local/share/datasets/c1_testing_full.rds")
+fit_lm <- readRDS("/usr/local/share/datasets/c1_fit_lm.rds")
+fit_rf <- readRDS("/usr/local/share/datasets/c1_fit_rf.rds")
+
+# Create the new columns
+results <- ___ %>%
+    mutate(`Linear regression` = predict(fit_lm, ___),
+           `Random forest` = predict(fit_rf, ___))
+
+# Evaluate the performance
+metrics(results, truth = MPG, estimate = `Linear regression`)
+metrics(results, truth = MPG, estimate = `Random forest`)
+

exercises/exc_01_11.R

@@ -1,14 +1,19 @@
-library(caret)
-library(tidyverse)
-
-training <- readRDS("/usr/local/share/datasets/c1_training_one_percent.rds")
-
-# Fit the models with bootstrap resampling
-cars_lm_bt <- train(log(MPG) ~ ., method = "lm", data = ___,
-                   trControl = trainControl(method = ___))
-cars_rf_bt <- train(log(MPG) ~ ., method = "rf", data = ___,
-                   trControl = ___(method = ___))
-
-# Quick look at the models
-cars_lm_bt
-cars_rf_bt
+library(caret)
+library(tidyverse)
+
+car_train <- readRDS("/usr/local/share/datasets/c1_training_one_percent.rds")
+
+# Fit the models with bootstrap resampling
+cars_lm_bt <- train(log(MPG) ~ ., 
+                    method = "lm", 
+                    data = ___,
+                    trControl = trainControl(method = ___))
+
+cars_rf_bt <- train(log(MPG) ~ ., 
+                    method = "rf", 
+                    data = ___,
+                    trControl = ___(method = ___))
+
+# Quick look at the models
+cars_lm_bt
+cars_rf_bt

exercises/exc_01_12_1.R

@@ -1,14 +1,14 @@
-library(caret)
-library(tidyverse)
-library(yardstick)
-
-testing <- readRDS("/usr/local/share/datasets/c1_testing_full.rds")
-cars_lm_bt <- readRDS("/usr/local/share/datasets/cars_lm_bt.rds")
-cars_rf_bt <- readRDS("/usr/local/share/datasets/cars_rf_bt.rds")
-
-results <- testing %>%
-    ___(`Linear regression` = predict(cars_lm_bt, testing),
-           `Random forest` = predict(cars_rf_bt, testing))
-
-metrics(results, ___ = MPG, ___ = `Linear regression`)
-metrics(results, ___ = MPG, ___ = `Random forest`)
+library(caret)
+library(tidyverse)
+library(yardstick)
+
+car_test <- readRDS("/usr/local/share/datasets/c1_testing_full.rds")
+cars_lm_bt <- readRDS("/usr/local/share/datasets/cars_lm_bt.rds")
+cars_rf_bt <- readRDS("/usr/local/share/datasets/cars_rf_bt.rds")
+
+results <- car_test %>%
+    ___(`Linear regression` = predict(cars_lm_bt, testing),
+           `Random forest` = predict(cars_rf_bt, testing))
+
+metrics(results, ___ = MPG, ___ = `Linear regression`)
+metrics(results, ___ = MPG, ___ = `Random forest`)

meta.json

@@ -1,25 +1,26 @@
 {
-    "courseId": "course-starter-r",
-    "title": "My cool online course",
-    "slogan": "A free online course",
-    "description": "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nullam tristique libero at est congue, sed vestibulum tortor laoreet. Aenean egestas massa non commodo consequat. Curabitur faucibus, sapien vitae euismod imperdiet, arcu erat semper urna, in accumsan sapien dui ac mi. Pellentesque felis lorem, semper nec velit nec, consectetur placerat enim.",
-    "bio": "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nullam tristique libero at est congue, sed vestibulum tortor laoreet. Aenean egestas massa non commodo consequat. Curabitur faucibus, sapien vitae euismod imperdiet, arcu erat semper urna.",
+    "courseId": "supervised-ML-case-studies-course",
+    "title": "Supervised machine learning case studies in R!",
+    "slogan": "A free interactive course",
+    "description": "This is a free, open source course on supervised machine learning in R. In this course, you'll work through four case studies and practice skills from exploratory data analysis through model evaluation. <a href='https://ines.io/'>Ines Montani</a> designed the web framework that runs this course, and <a href='https://florencia.netlify.com/'>Florencia D'Andrea</a> helped build the site.</p><p>Contributions and comments on how to improve this course are welcome! Please <a href='https://github.com/juliasilge/supervised-ML-case-studies-course/issues'>file an issue</a> or submit a pull request if you find something that could be fixed or improved.</p>",
+    "bio": "Hello! My name is Julia Silge and I'm a data scientist at <a href='https://stackoverflow.com/'>Stack Overflow</a> where I use tidyverse tools and statistical analysis to understand developers and the software industry. I am both an international keynote speaker and a real-world practitioner focused on data analysis and machine learning practice. I love making beautiful charts and communicating about technical topics with diverse audiences. </p><p><a rel='license' href='http://creativecommons.org/licenses/by/4.0'><img alt='Creative Commons License' src='https://i.creativecommons.org/l/by/4.0/88x31.png'/></a></p>",
     "siteUrl": "https://course-starter-r.netlify.com",
-    "twitter": "spacy_io",
+    "twitter": "juliasilge",
     "fonts": "IBM+Plex+Mono:500|IBM+Plex+Sans:700|Lato:400,400i,700,700i",
     "testTemplate": "success <- function(text) {\n    cat(paste(\"\\033[32m\", text, \"\\033[0m\", sep = \"\"))\n}\n\n.solution <- \"${solutionEscaped}\"\n\n${solution}\n\n${test}\ntryCatch({\n    test()\n}, error = function(e) {\n    cat(paste(\"\\033[31m\", e[1], \"\\033[0m\", sep = \"\"))\n})",
     "juniper": {
-        "repo": "ines/course-starter-r",
+        "repo": "juliasilge/supervised-ML-case-studies-course",
         "branch": "binder",
         "lang": "r",
         "kernelType": "ir",
         "debug": false
     },
     "showProfileImage": true,
     "footerLinks": [
-        { "text": "Website", "url": "https://spacy.io" },
-        { "text": "Source", "url": "https://github.com/ines/course-starter-r" },
-        { "text": "Built with ♥", "url": "https://github.com/ines/course-starter-r" }
+        { "text": "Follow Me on Twitter", "url": "https://twitter.com/juliasilge" },
+        { "text": "My Website", "url": "https://juliasilge.com/" },
+        { "text": "Source Code on GitHub", "url": "https://github.com/juliasilge/supervised-ML-case-studies-course" },
+        { "text": "Built with ♥ and Open Source", "url": "https://github.com/ines/course-starter-r" }
     ],
     "theme": "#de7878"
 }

package.json

@@ -1,9 +1,9 @@
 {
-    "name": "course-starter-r",
+    "name": "supervised-ML-case-studies-course",
     "private": true,
-    "description": "Starter package to build interactive R courses",
+    "description": "Supervised machine learning case studies in R! A free interactive course ",
     "version": "0.0.1",
-    "author": "Ines Montani <[email protected]>",
+    "author": "Julia Silge <[email protected]>",
     "dependencies": {
         "@illinois/react-use-local-storage": "^1.1.0",
         "@jupyterlab/outputarea": "^0.19.1",
@@ -52,6 +52,6 @@
     },
     "repository": {
         "type": "git",
-        "url": "https://github.com/ines/course-starter-python"
+        "url": "https://github.com/juliasilge/supervised-ML-case-studies-course"
     }
 }