msb-public
/
ML-For-Beginners
mirror of https://github.com/microsoft/ML-For-Beginners.git
1
0
Code Issues Projects Releases Wiki Activity

Update lesson_10-R.ipynb

Browse Source
pull/313/head
R-icntay 4 years ago
parent 74bf75f37f
commit 6dded01820
1 changed files with 130 additions and 130 deletions
Show Stats Download Patch File Download Diff File

260
4-Classification/1-Introduction/solution/R/lesson_10-R.ipynb
Unescape View File

@ -103,8 +103,8 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"suppressWarnings(if (!require(\"pacman\"))install.packages(\"pacman\"))\n", "suppressWarnings(if (!require(\"pacman\"))install.packages(\"pacman\"))\r\n",
"\n", "\r\n",
"pacman::p_load(tidyverse, tidymodels, DataExplorer, themis, here)" "pacman::p_load(tidyverse, tidymodels, DataExplorer, themis, here)"
], ],
"outputs": [], "outputs": [],
@ -138,12 +138,12 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Import data\n", "# Import data\r\n",
"df <- read_csv(file = \"https://raw.githubusercontent.com/microsoft/ML-For-Beginners/main/4-Classification/data/cuisines.csv\")\n", "df <- read_csv(file = \"https://raw.githubusercontent.com/microsoft/ML-For-Beginners/main/4-Classification/data/cuisines.csv\")\r\n",
"\n", "\r\n",
"# View the first 5 rows\n", "# View the first 5 rows\r\n",
"df %>% \n", "df %>% \r\n",
" slice_head(n = 5)\n" " slice_head(n = 5)\r\n"
], ],
"outputs": [], "outputs": [],
"metadata": { "metadata": {
@ -218,7 +218,7 @@
"\r\n", "\r\n",
"Next, let's assign each cuisine into its individual tibble and find out how much data is available (rows, columns) per cuisine.\r\n", "Next, let's assign each cuisine into its individual tibble and find out how much data is available (rows, columns) per cuisine.\r\n",
"\r\n", "\r\n",
"> A tibble is a modern reimagining of the data frame, keeping what time has proven to be effective, and throwing out what is not.\r\n", "> A [tibble](https://tibble.tidyverse.org/) is a modern data frame.\r\n",
"\r\n", "\r\n",
"<p >\r\n", "<p >\r\n",
" <img src=\"../../images/dplyr_filter.jpg\"\r\n", " <img src=\"../../images/dplyr_filter.jpg\"\r\n",
@ -305,24 +305,24 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Creates a functions that returns the top ingredients by class\n", "# Creates a functions that returns the top ingredients by class\r\n",
"\n", "\r\n",
"create_ingredient <- function(df){\n", "create_ingredient <- function(df){\r\n",
" \n", " \r\n",
" # Drop the id column which is the first colum\n", " # Drop the id column which is the first colum\r\n",
" ingredient_df = df %>% select(-1) %>% \n", " ingredient_df = df %>% select(-1) %>% \r\n",
" # Transpose data to a long format\n", " # Transpose data to a long format\r\n",
" pivot_longer(!cuisine, names_to = \"ingredients\", values_to = \"count\") %>% \n", " pivot_longer(!cuisine, names_to = \"ingredients\", values_to = \"count\") %>% \r\n",
" # Find the top most ingredients for a particular cuisine\n", " # Find the top most ingredients for a particular cuisine\r\n",
" group_by(ingredients) %>% \n", " group_by(ingredients) %>% \r\n",
" summarise(n_instances = sum(count)) %>% \n", " summarise(n_instances = sum(count)) %>% \r\n",
" filter(n_instances != 0) %>% \n", " filter(n_instances != 0) %>% \r\n",
" # Arrange by descending order\n", " # Arrange by descending order\r\n",
" arrange(desc(n_instances)) %>% \n", " arrange(desc(n_instances)) %>% \r\n",
" mutate(ingredients = factor(ingredients) %>% fct_inorder())\n", " mutate(ingredients = factor(ingredients) %>% fct_inorder())\r\n",
" \n", " \r\n",
" \n", " \r\n",
" return(ingredient_df)\n", " return(ingredient_df)\r\n",
"} # End of function" "} # End of function"
], ],
"outputs": [], "outputs": [],
@ -343,10 +343,10 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Call create_ingredient and display popular ingredients\n", "# Call create_ingredient and display popular ingredients\r\n",
"thai_ingredient_df <- create_ingredient(df = thai_df)\n", "thai_ingredient_df <- create_ingredient(df = thai_df)\r\n",
"\n", "\r\n",
"thai_ingredient_df %>% \n", "thai_ingredient_df %>% \r\n",
" slice_head(n = 10)" " slice_head(n = 10)"
], ],
"outputs": [], "outputs": [],
@ -367,11 +367,11 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Make a bar chart for popular thai cuisines\n", "# Make a bar chart for popular thai cuisines\r\n",
"thai_ingredient_df %>% \n", "thai_ingredient_df %>% \r\n",
" slice_head(n = 10) %>% \n", " slice_head(n = 10) %>% \r\n",
" ggplot(aes(x = n_instances, y = ingredients)) +\n", " ggplot(aes(x = n_instances, y = ingredients)) +\r\n",
" geom_bar(stat = \"identity\", width = 0.5, fill = \"steelblue\") +\n", " geom_bar(stat = \"identity\", width = 0.5, fill = \"steelblue\") +\r\n",
" xlab(\"\") + ylab(\"\")" " xlab(\"\") + ylab(\"\")"
], ],
"outputs": [], "outputs": [],
@ -392,12 +392,12 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Get popular ingredients for Japanese cuisines and make bar chart\n", "# Get popular ingredients for Japanese cuisines and make bar chart\r\n",
"create_ingredient(df = japanese_df) %>% \n", "create_ingredient(df = japanese_df) %>% \r\n",
" slice_head(n = 10) %>%\n", " slice_head(n = 10) %>%\r\n",
" ggplot(aes(x = n_instances, y = ingredients)) +\n", " ggplot(aes(x = n_instances, y = ingredients)) +\r\n",
" geom_bar(stat = \"identity\", width = 0.5, fill = \"darkorange\", alpha = 0.8) +\n", " geom_bar(stat = \"identity\", width = 0.5, fill = \"darkorange\", alpha = 0.8) +\r\n",
" xlab(\"\") + ylab(\"\")\n" " xlab(\"\") + ylab(\"\")\r\n"
], ],
"outputs": [], "outputs": [],
"metadata": { "metadata": {
@ -417,11 +417,11 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Get popular ingredients for Chinese cuisines and make bar chart\n", "# Get popular ingredients for Chinese cuisines and make bar chart\r\n",
"create_ingredient(df = chinese_df) %>% \n", "create_ingredient(df = chinese_df) %>% \r\n",
" slice_head(n = 10) %>%\n", " slice_head(n = 10) %>%\r\n",
" ggplot(aes(x = n_instances, y = ingredients)) +\n", " ggplot(aes(x = n_instances, y = ingredients)) +\r\n",
" geom_bar(stat = \"identity\", width = 0.5, fill = \"cyan4\", alpha = 0.8) +\n", " geom_bar(stat = \"identity\", width = 0.5, fill = \"cyan4\", alpha = 0.8) +\r\n",
" xlab(\"\") + ylab(\"\")" " xlab(\"\") + ylab(\"\")"
], ],
"outputs": [], "outputs": [],
@ -442,11 +442,11 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Get popular ingredients for Indian cuisines and make bar chart\n", "# Get popular ingredients for Indian cuisines and make bar chart\r\n",
"create_ingredient(df = indian_df) %>% \n", "create_ingredient(df = indian_df) %>% \r\n",
" slice_head(n = 10) %>%\n", " slice_head(n = 10) %>%\r\n",
" ggplot(aes(x = n_instances, y = ingredients)) +\n", " ggplot(aes(x = n_instances, y = ingredients)) +\r\n",
" geom_bar(stat = \"identity\", width = 0.5, fill = \"#041E42FF\", alpha = 0.8) +\n", " geom_bar(stat = \"identity\", width = 0.5, fill = \"#041E42FF\", alpha = 0.8) +\r\n",
" xlab(\"\") + ylab(\"\")" " xlab(\"\") + ylab(\"\")"
], ],
"outputs": [], "outputs": [],
@ -467,11 +467,11 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Get popular ingredients for Korean cuisines and make bar chart\n", "# Get popular ingredients for Korean cuisines and make bar chart\r\n",
"create_ingredient(df = korean_df) %>% \n", "create_ingredient(df = korean_df) %>% \r\n",
" slice_head(n = 10) %>%\n", " slice_head(n = 10) %>%\r\n",
" ggplot(aes(x = n_instances, y = ingredients)) +\n", " ggplot(aes(x = n_instances, y = ingredients)) +\r\n",
" geom_bar(stat = \"identity\", width = 0.5, fill = \"#852419FF\", alpha = 0.8) +\n", " geom_bar(stat = \"identity\", width = 0.5, fill = \"#852419FF\", alpha = 0.8) +\r\n",
" xlab(\"\") + ylab(\"\")" " xlab(\"\") + ylab(\"\")"
], ],
"outputs": [], "outputs": [],
@ -494,12 +494,12 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Drop id column, rice, garlic and ginger from our original data set\n", "# Drop id column, rice, garlic and ginger from our original data set\r\n",
"df_select <- df %>% \n", "df_select <- df %>% \r\n",
" select(-c(1, rice, garlic, ginger))\n", " select(-c(1, rice, garlic, ginger))\r\n",
"\n", "\r\n",
"# Display new data set\n", "# Display new data set\r\n",
"df_select %>% \n", "df_select %>% \r\n",
" slice_head(n = 5)" " slice_head(n = 5)"
], ],
"outputs": [], "outputs": [],
@ -510,16 +510,16 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [ "source": [
"## Preprocessing data using recipes 👩‍🍳👨‍🍳 - Dealing with imbalanced data ⚖️\n", "## Preprocessing data using recipes 👩‍🍳👨‍🍳 - Dealing with imbalanced data ⚖️\r\n",
"\n", "\r\n",
"<p >\n", "<p >\r\n",
" <img src=\"../../images/recipes.png\"\n", " <img src=\"../../images/recipes.png\"\r\n",
" width=\"600\"/>\n", " width=\"600\"/>\r\n",
" <figcaption>Artwork by @allison_horst</figcaption>\n", " <figcaption>Artwork by @allison_horst</figcaption>\r\n",
"\n", "\r\n",
"Given that this lesson is about cuisines, we have to put `recipes` into context .\n", "Given that this lesson is about cuisines, we have to put `recipes` into context .\r\n",
"\n", "\r\n",
"Tidymodels provides yet another neat package: `recipes`- a package for preprocessing data.\n" "Tidymodels provides yet another neat package: `recipes`- a package for preprocessing data.\r\n"
], ],
"metadata": { "metadata": {
"id": "kkFd-JxdIaL6" "id": "kkFd-JxdIaL6"
@ -538,11 +538,11 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Distribution of cuisines\n", "# Distribution of cuisines\r\n",
"old_label_count <- df_select %>% \n", "old_label_count <- df_select %>% \r\n",
" count(cuisine) %>% \n", " count(cuisine) %>% \r\n",
" arrange(desc(n))\n", " arrange(desc(n))\r\n",
"\n", "\r\n",
"old_label_count" "old_label_count"
], ],
"outputs": [], "outputs": [],
@ -572,13 +572,13 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Load themis package for dealing with imbalanced data\n", "# Load themis package for dealing with imbalanced data\r\n",
"library(themis)\n", "library(themis)\r\n",
"\n", "\r\n",
"# Create a recipe for preprocessing data\n", "# Create a recipe for preprocessing data\r\n",
"cuisines_recipe <- recipe(cuisine ~ ., data = df_select) %>% \n", "cuisines_recipe <- recipe(cuisine ~ ., data = df_select) %>% \r\n",
" step_smote(cuisine)\n", " step_smote(cuisine)\r\n",
"\n", "\r\n",
"cuisines_recipe" "cuisines_recipe"
], ],
"outputs": [], "outputs": [],
@ -609,18 +609,18 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Prep and bake the recipe\n", "# Prep and bake the recipe\r\n",
"preprocessed_df <- cuisines_recipe %>% \n", "preprocessed_df <- cuisines_recipe %>% \r\n",
" prep() %>% \n", " prep() %>% \r\n",
" bake(new_data = NULL) %>% \n", " bake(new_data = NULL) %>% \r\n",
" relocate(cuisine)\n", " relocate(cuisine)\r\n",
"\n", "\r\n",
"# Display data\n", "# Display data\r\n",
"preprocessed_df %>% \n", "preprocessed_df %>% \r\n",
" slice_head(n = 5)\n", " slice_head(n = 5)\r\n",
"\n", "\r\n",
"# Quick summary stats\n", "# Quick summary stats\r\n",
"preprocessed_df %>% \n", "preprocessed_df %>% \r\n",
" introduce()" " introduce()"
], ],
"outputs": [], "outputs": [],
@ -641,12 +641,12 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Distribution of cuisines\n", "# Distribution of cuisines\r\n",
"new_label_count <- preprocessed_df %>% \n", "new_label_count <- preprocessed_df %>% \r\n",
" count(cuisine) %>% \n", " count(cuisine) %>% \r\n",
" arrange(desc(n))\n", " arrange(desc(n))\r\n",
"\n", "\r\n",
"list(new_label_count = new_label_count,\n", "list(new_label_count = new_label_count,\r\n",
" old_label_count = old_label_count)" " old_label_count = old_label_count)"
], ],
"outputs": [], "outputs": [],
@ -675,7 +675,7 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"source": [ "source": [
"# Save preprocessed data\n", "# Save preprocessed data\r\n",
"write_csv(preprocessed_df, \"../../../data/cleaned_cuisines_R.csv\")" "write_csv(preprocessed_df, \"../../../data/cleaned_cuisines_R.csv\")"
], ],
"outputs": [], "outputs": [],
@ -686,32 +686,32 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [ "source": [
"This fresh CSV can now be found in the root data folder.\n", "This fresh CSV can now be found in the root data folder.\r\n",
"\n", "\r\n",
"**🚀Challenge**\n", "**🚀Challenge**\r\n",
"\n", "\r\n",
"This curriculum contains several interesting datasets. Dig through the `data` folders and see if any contain datasets that would be appropriate for binary or multi-class classification? What questions would you ask of this dataset?\n", "This curriculum contains several interesting datasets. Dig through the `data` folders and see if any contain datasets that would be appropriate for binary or multi-class classification? What questions would you ask of this dataset?\r\n",
"\n", "\r\n",
"## [**Post-lecture quiz**](https://white-water-09ec41f0f.azurestaticapps.net/quiz/20/)\n", "## [**Post-lecture quiz**](https://white-water-09ec41f0f.azurestaticapps.net/quiz/20/)\r\n",
"\n", "\r\n",
"## **Review & Self Study**\n", "## **Review & Self Study**\r\n",
"\n", "\r\n",
"- Check out [package themis](https://github.com/tidymodels/themis). What other techniques could we use to deal with imbalanced data?\n", "- Check out [package themis](https://github.com/tidymodels/themis). What other techniques could we use to deal with imbalanced data?\r\n",
"\n", "\r\n",
"- Tidy models [reference website](https://www.tidymodels.org/start/).\n", "- Tidy models [reference website](https://www.tidymodels.org/start/).\r\n",
"\n", "\r\n",
"- H. Wickham and G. Grolemund, [*R for Data Science: Visualize, Model, Transform, Tidy, and Import Data*](https://r4ds.had.co.nz/).\n", "- H. Wickham and G. Grolemund, [*R for Data Science: Visualize, Model, Transform, Tidy, and Import Data*](https://r4ds.had.co.nz/).\r\n",
"\n", "\r\n",
"#### THANK YOU TO:\n", "#### THANK YOU TO:\r\n",
"\n", "\r\n",
"[`Allison Horst`](https://twitter.com/allison_horst/) for creating the amazing illustrations that make R more welcoming and engaging. Find more illustrations at her [gallery](https://www.google.com/url?q=https://github.com/allisonhorst/stats-illustrations&sa=D&source=editors&ust=1626380772530000&usg=AOvVaw3zcfyCizFQZpkSLzxiiQEM).\n", "[`Allison Horst`](https://twitter.com/allison_horst/) for creating the amazing illustrations that make R more welcoming and engaging. Find more illustrations at her [gallery](https://www.google.com/url?q=https://github.com/allisonhorst/stats-illustrations&sa=D&source=editors&ust=1626380772530000&usg=AOvVaw3zcfyCizFQZpkSLzxiiQEM).\r\n",
"\n", "\r\n",
"[Cassie Breviu](https://www.twitter.com/cassieview) and [Jen Looper](https://www.twitter.com/jenlooper) for creating the original Python version of this module ♥️\n", "[Cassie Breviu](https://www.twitter.com/cassieview) and [Jen Looper](https://www.twitter.com/jenlooper) for creating the original Python version of this module ♥️\r\n",
"\n", "\r\n",
"<p >\n", "<p >\r\n",
" <img src=\"../../images/r_learners_sm.jpeg\"\n", " <img src=\"../../images/r_learners_sm.jpeg\"\r\n",
" width=\"600\"/>\n", " width=\"600\"/>\r\n",
" <figcaption>Artwork by @allison_horst</figcaption>\n" " <figcaption>Artwork by @allison_horst</figcaption>\r\n"
], ],
"metadata": { "metadata": {
"id": "WQs5621pMGwf" "id": "WQs5621pMGwf"

Write Preview
Loading…
Cancel
Save