Updating tibble join notes

UBC-STAT · Sep 13, 2023 · 6dd6442 · 6dd6442
1 parent e255aaa
commit 6dd6442
Show file tree

Hide file tree

Showing 19 changed files with 23 additions and 260 deletions.
diff --git a/content/notes/notes-a11/images/README.md b/content/notes/notes-a11/images/README.md
@@ -0,0 +1 @@
+A folder for images used in the tutorial.
diff --git a/content/notes/notes-a11/images/anti_join.png b/content/notes/notes-a11/images/anti_join.png
diff --git a/content/notes/notes-a11/images/bind_cols.png b/content/notes/notes-a11/images/bind_cols.png
diff --git a/content/notes/notes-a11/images/bind_rows.png b/content/notes/notes-a11/images/bind_rows.png
diff --git a/content/notes/notes-a11/images/df.png b/content/notes/notes-a11/images/df.png
diff --git a/content/notes/notes-a11/images/full_join.png b/content/notes/notes-a11/images/full_join.png
diff --git a/content/notes/notes-a11/images/inner_join.png b/content/notes/notes-a11/images/inner_join.png
diff --git a/content/notes/notes-a11/images/intersect.png b/content/notes/notes-a11/images/intersect.png
diff --git a/content/notes/notes-a11/images/left_join.png b/content/notes/notes-a11/images/left_join.png
diff --git a/content/notes/notes-a11/images/multiple_conditions.png b/content/notes/notes-a11/images/multiple_conditions.png
diff --git a/content/notes/notes-a11/images/new_df.png b/content/notes/notes-a11/images/new_df.png
diff --git a/content/notes/notes-a11/images/new_df2.png b/content/notes/notes-a11/images/new_df2.png
diff --git a/content/notes/notes-a11/images/right_join.png b/content/notes/notes-a11/images/right_join.png
diff --git a/content/notes/notes-a11/images/semi_join.png b/content/notes/notes-a11/images/semi_join.png
diff --git a/content/notes/notes-a11/images/setdiff.png b/content/notes/notes-a11/images/setdiff.png
diff --git a/content/notes/notes-a11/images/three_tibbles.png b/content/notes/notes-a11/images/three_tibbles.png
diff --git a/content/notes/notes-a11/images/union.png b/content/notes/notes-a11/images/union.png
diff --git a/content/notes/notes-a11.Rmd → content/notes/notes-a11/index.Rmd b/content/notes/notes-a11.Rmd → content/notes/notes-a11/index.Rmd
@@ -27,9 +27,9 @@ Video lecture:
 
 - [Tibble Joins with dplyr](https://youtu.be/YAdX9MVRY1c)
 
-Demonstration .Rmd file:
+<!-- Demonstration .Rmd file: -->
 
-- [Tibble join demonstration with gapminder](https://raw.githubusercontent.com/UBC-STAT/stat545.stat.ubc.ca/master/content/notes/notes-a11/gapminder_demonstration.Rmd)
+<!-- - [Tibble join demonstration with gapminder](https://raw.githubusercontent.com/UBC-STAT/stat545.stat.ubc.ca/master/content/notes/notes-a11/gapminder_demonstration.Rmd) -->
 
 Other resources, in addition to the notes below:
 
@@ -179,15 +179,15 @@ full_join(df4, df5, by = c("FirstName" = "First_name", "LastName" = "Last_name")
 ```
 
 
-What if you did not realize that multiple people shared the same Last Name?
-```{r}
-full_join(df4, df5, by = c("LastName" = "Last_name"))
-```
+<!-- What if you did not realize that multiple people shared the same Last Name? -->
+<!-- ```{r} -->
+<!-- full_join(df4, df5, by = c("LastName" = "Last_name")) -->
+<!-- ``` -->
 
-What if you did not realize that multiple people shared the same First Name?
-```{r}
-full_join(df4, df5, by = c("FirstName" = "First_name"))
-```
+<!-- What if you did not realize that multiple people shared the same First Name? -->
+<!-- ```{r} -->
+<!-- full_join(df4, df5, by = c("FirstName" = "First_name")) -->
+<!-- ``` -->
 
 
 ## Set operations
@@ -255,134 +255,7 @@ We think the best way to learn the basics of tibble joins from here is to work t
 
 There will be some class time to go over solutions if you got stuck on any questions. 
 
-If we have time left, then we'll do a case study with the `gapminder` data. 
-
-
-<!-- ## Demonstration with `gapminder` -->
-
-<!-- Get an overview of `gapminder` data -->
-<!-- ```{r} -->
-<!-- glimpse(gapminder) -->
-<!-- ``` -->
-
-<!-- ### Part 1 -->
-
-<!-- Obtain additional information on countries from other open data sources -->
-<!-- ```{r} -->
-<!-- country_data <- read.csv(file = "https://raw.githubusercontent.com/open-numbers/ddf--gapminder--geo_entity_domain/master/ddf--entities--geo--country.csv") -->
-
-<!-- glimpse(country_data) -->
-<!-- ``` -->
-
-
-<!-- Narrow down information to income groups, OECD status, and religion -->
-<!-- ```{r} -->
-<!-- country_data <- country_data %>%  -->
-<!--   select(name, income_groups, g77_and_oecd_countries, main_religion_2008) -->
-
-<!-- # Check data structure -->
-<!-- glimpse(country_data) -->
-<!-- ``` -->
-
-<!-- Count how many unique country names are in `gapminder` and `country_data` -->
-<!-- ```{r} -->
-<!-- nlevels(gapminder$country) -->
-<!-- nlevels(as.factor(country_data$name)) -->
-<!-- ``` -->
-
-<!-- Merge `gapminder` and `country_data` using `left_join()` -->
-<!-- ```{r} -->
-<!-- gapminder_extended <- left_join(gapminder, country_data, by=c("country"="name")) -->
-
-<!-- head(gapminder_extended) -->
-<!-- ``` -->
-
-<!-- **Note:**: `left_join()` is probably the most useful and the most used join. It is often used when you want to expand your existing dataset with new variables from other sources. -->
-
-
-<!-- Compare lifeExp for OECD, G77, and other countries -->
-<!-- ```{r} -->
-<!-- gapminder_extended %>%  -->
-<!--   ggplot(aes(x=g77_and_oecd_countries,y=lifeExp))+ -->
-<!--     geom_boxplot()+ -->
-<!--     geom_jitter(aes(color=continent), alpha=0.3)+ -->
-<!--     labs(x="Country group") -->
-<!-- ``` -->
-
-<!-- Compare lifeExp for OECD, G77, and other countries by most common religion -->
-<!-- ```{r} -->
-<!-- gapminder_extended %>%  -->
-<!--   filter(main_religion_2008 %in% c("christian","eastern_religions","muslim")) %>%  -->
-<!--   ggplot(aes(x=g77_and_oecd_countries,y=lifeExp))+ -->
-<!--     geom_boxplot()+ -->
-<!--     geom_jitter(aes(color=continent), alpha=0.3)+ -->
-<!--     labs(x="Country group")+ -->
-<!--     facet_wrap(~main_religion_2008) -->
-<!-- ``` -->
-
-
-<!-- ### Part 2 -->
-
-
-<!-- Gapminder data is only available from 1952 to 2007. What if we wanted to examine data after 2007 as well as population projections? -->
-
-<!-- Download population size estimates by country from 1800 to 2100 -->
-<!-- ```{r} -->
-<!-- population <- gsheet2tbl("https://docs.google.com/spreadsheets/d/14_suWY8fCPEXV0MH7ZQMZ-KndzMVsSsA5HdR-7WqAC0/edit#gid=176703676") -->
-<!-- ``` -->
-
-
-<!-- See what population data looks like -->
-<!-- ```{r} -->
-<!-- glimpse(population) -->
-<!-- ``` -->
-
-
-<!-- Only retain population estimates after 2007, rename variables to match gapminder variable names -->
-<!-- ```{r} -->
-<!-- population <- population %>%  -->
-<!--   filter(time>2007) %>%  -->
-<!--   rename(year=time, country=name, pop=Population) %>%  -->
-<!--   select(-geo) -->
-<!-- ``` -->
-
-
-<!-- Add continent data to `population` from `gapminder` -->
-<!-- ```{r} -->
-<!-- # create a data frame listing continent for every country -->
-<!-- continent <- gapminder %>% -->
-<!--   select(country, continent) %>%  -->
-<!--   distinct() -->
-
-<!-- # add continent data to population data frame -->
-<!-- population <- left_join(population, continent, by = "country") -->
-
-<!-- # see how many countries are missing continent data by continent -->
-<!-- population %>%  -->
-<!--   group_by(year) %>%  -->
-<!--   summarise(missing_continent = sum(is.na(continent))) -->
-<!-- ``` -->
-
-
-<!-- Use `bind_rows()` to stack `population` below `gapminder` -->
-<!-- ```{r} -->
-<!-- gapminder_pop <- bind_rows(gapminder, population) %>%  -->
-<!--   arrange(country,year) -->
-<!-- ``` -->
-
-
-<!-- Visualize trends in population growth by continent -->
-<!-- ```{r} -->
-<!-- gapminder_pop %>%  -->
-<!--   filter(!is.na(continent)) %>%  -->
-<!--   group_by(continent, year) %>% -->
-<!--   summarise(pop=sum(pop)/1000000) %>% -->
-<!--   ggplot(aes(x=year, y=pop, fill=continent))+ -->
-<!--   geom_area()+ -->
-<!--   labs(title="Population projections by continent",  -->
-<!--                y="Population (in mil)") -->
-<!-- ``` -->
-
+<!-- If we have time, then we will do a case study with the `gapminder` data. [Link to case study here](https://raw.githubusercontent.com/UBC-STAT/stat545.stat.ubc.ca/master/content/notes/supp-a11.Rmd).  -->
 
 ### Attributions
 

diff --git a/content/notes/notes-a11.html → content/notes/notes-a11/index.html b/content/notes/notes-a11.html → content/notes/notes-a11/index.html
@@ -24,10 +24,8 @@ <h2>Resources</h2>
 <ul>
 <li><a href="https://youtu.be/YAdX9MVRY1c">Tibble Joins with dplyr</a></li>
 </ul>
-<p>Demonstration .Rmd file:</p>
-<ul>
-<li><a href="https://raw.githubusercontent.com/UBC-STAT/stat545.stat.ubc.ca/master/content/notes/notes-a11/gapminder_demonstration.Rmd">Tibble join demonstration with gapminder</a></li>
-</ul>
+<!-- Demonstration .Rmd file: -->
+<!-- - [Tibble join demonstration with gapminder](https://raw.githubusercontent.com/UBC-STAT/stat545.stat.ubc.ca/master/content/notes/notes-a11/gapminder_demonstration.Rmd) -->
 <p>Other resources, in addition to the notes below:</p>
 <ul>
 <li>A comprehensive overview can be found in the <a href="https://r4ds.had.co.nz/relational-data.html">“Relational Data” chapter</a> in “R for Data Science”.</li>
@@ -190,30 +188,14 @@ <h2>Joining tibbles on multiple conditions</h2>
 ## 2 Josh      Smith       20    167
 ## 3 Alex      Smith       50    190
 ## 4 Sophie    Jones       NA    155</code></pre>
-<p>What if you did not realize that multiple people shared the same Last Name?</p>
-<pre class="r"><code>full_join(df4, df5, by = c(&quot;LastName&quot; = &quot;Last_name&quot;))</code></pre>
-<pre><code>## Warning in full_join(df4, df5, by = c(LastName = &quot;Last_name&quot;)): Detected an unexpected many-to-many relationship between `x` and `y`.
-## ℹ Row 2 of `x` matches multiple rows in `y`.
-## ℹ Row 1 of `y` matches multiple rows in `x`.
-## ℹ If a many-to-many relationship is expected, set `relationship =
-##   &quot;many-to-many&quot;` to silence this warning.</code></pre>
-<pre><code>## # A tibble: 6 × 5
-##   FirstName LastName   Age First_name Height
-##   &lt;chr&gt;     &lt;chr&gt;    &lt;dbl&gt; &lt;chr&gt;       &lt;dbl&gt;
-## 1 Sophie    Wang        42 &lt;NA&gt;           NA
-## 2 Josh      Smith       20 Josh          167
-## 3 Josh      Smith       20 Alex          190
-## 4 Alex      Smith       50 Josh          167
-## 5 Alex      Smith       50 Alex          190
-## 6 &lt;NA&gt;      Jones       NA Sophie        155</code></pre>
-<p>What if you did not realize that multiple people shared the same First Name?</p>
-<pre class="r"><code>full_join(df4, df5, by = c(&quot;FirstName&quot; = &quot;First_name&quot;))</code></pre>
-<pre><code>## # A tibble: 3 × 5
-##   FirstName LastName   Age Last_name Height
-##   &lt;chr&gt;     &lt;chr&gt;    &lt;dbl&gt; &lt;chr&gt;      &lt;dbl&gt;
-## 1 Sophie    Wang        42 Jones        155
-## 2 Josh      Smith       20 Smith        167
-## 3 Alex      Smith       50 Smith        190</code></pre>
+<!-- What if you did not realize that multiple people shared the same Last Name? -->
+<!-- ```{r} -->
+<!-- full_join(df4, df5, by = c("LastName" = "Last_name")) -->
+<!-- ``` -->
+<!-- What if you did not realize that multiple people shared the same First Name? -->
+<!-- ```{r} -->
+<!-- full_join(df4, df5, by = c("FirstName" = "First_name")) -->
+<!-- ``` -->
 </div>
 <div id="set-operations" class="section level2">
 <h2>Set operations</h2>
@@ -286,100 +268,7 @@ <h2>Joining tibbles with different types of variables</h2>
 <h2>Your turn: learning tibble joins</h2>
 <p>We think the best way to learn the basics of tibble joins from here is to work through the corresponding part of Worksheet A5.</p>
 <p>There will be some class time to go over solutions if you got stuck on any questions.</p>
-<p>If we have time left, then we’ll do a case study with the <code>gapminder</code> data.</p>
-<!-- ## Demonstration with `gapminder` -->
-<!-- Get an overview of `gapminder` data -->
-<!-- ```{r} -->
-<!-- glimpse(gapminder) -->
-<!-- ``` -->
-<!-- ### Part 1 -->
-<!-- Obtain additional information on countries from other open data sources -->
-<!-- ```{r} -->
-<!-- country_data <- read.csv(file = "https://raw.githubusercontent.com/open-numbers/ddf--gapminder--geo_entity_domain/master/ddf--entities--geo--country.csv") -->
-<!-- glimpse(country_data) -->
-<!-- ``` -->
-<!-- Narrow down information to income groups, OECD status, and religion -->
-<!-- ```{r} -->
-<!-- country_data <- country_data %>%  -->
-<!--   select(name, income_groups, g77_and_oecd_countries, main_religion_2008) -->
-<!-- # Check data structure -->
-<!-- glimpse(country_data) -->
-<!-- ``` -->
-<!-- Count how many unique country names are in `gapminder` and `country_data` -->
-<!-- ```{r} -->
-<!-- nlevels(gapminder$country) -->
-<!-- nlevels(as.factor(country_data$name)) -->
-<!-- ``` -->
-<!-- Merge `gapminder` and `country_data` using `left_join()` -->
-<!-- ```{r} -->
-<!-- gapminder_extended <- left_join(gapminder, country_data, by=c("country"="name")) -->
-<!-- head(gapminder_extended) -->
-<!-- ``` -->
-<!-- **Note:**: `left_join()` is probably the most useful and the most used join. It is often used when you want to expand your existing dataset with new variables from other sources. -->
-<!-- Compare lifeExp for OECD, G77, and other countries -->
-<!-- ```{r} -->
-<!-- gapminder_extended %>%  -->
-<!--   ggplot(aes(x=g77_and_oecd_countries,y=lifeExp))+ -->
-<!--     geom_boxplot()+ -->
-<!--     geom_jitter(aes(color=continent), alpha=0.3)+ -->
-<!--     labs(x="Country group") -->
-<!-- ``` -->
-<!-- Compare lifeExp for OECD, G77, and other countries by most common religion -->
-<!-- ```{r} -->
-<!-- gapminder_extended %>%  -->
-<!--   filter(main_religion_2008 %in% c("christian","eastern_religions","muslim")) %>%  -->
-<!--   ggplot(aes(x=g77_and_oecd_countries,y=lifeExp))+ -->
-<!--     geom_boxplot()+ -->
-<!--     geom_jitter(aes(color=continent), alpha=0.3)+ -->
-<!--     labs(x="Country group")+ -->
-<!--     facet_wrap(~main_religion_2008) -->
-<!-- ``` -->
-<!-- ### Part 2 -->
-<!-- Gapminder data is only available from 1952 to 2007. What if we wanted to examine data after 2007 as well as population projections? -->
-<!-- Download population size estimates by country from 1800 to 2100 -->
-<!-- ```{r} -->
-<!-- population <- gsheet2tbl("https://docs.google.com/spreadsheets/d/14_suWY8fCPEXV0MH7ZQMZ-KndzMVsSsA5HdR-7WqAC0/edit#gid=176703676") -->
-<!-- ``` -->
-<!-- See what population data looks like -->
-<!-- ```{r} -->
-<!-- glimpse(population) -->
-<!-- ``` -->
-<!-- Only retain population estimates after 2007, rename variables to match gapminder variable names -->
-<!-- ```{r} -->
-<!-- population <- population %>%  -->
-<!--   filter(time>2007) %>%  -->
-<!--   rename(year=time, country=name, pop=Population) %>%  -->
-<!--   select(-geo) -->
-<!-- ``` -->
-<!-- Add continent data to `population` from `gapminder` -->
-<!-- ```{r} -->
-<!-- # create a data frame listing continent for every country -->
-<!-- continent <- gapminder %>% -->
-<!--   select(country, continent) %>%  -->
-<!--   distinct() -->
-<!-- # add continent data to population data frame -->
-<!-- population <- left_join(population, continent, by = "country") -->
-<!-- # see how many countries are missing continent data by continent -->
-<!-- population %>%  -->
-<!--   group_by(year) %>%  -->
-<!--   summarise(missing_continent = sum(is.na(continent))) -->
-<!-- ``` -->
-<!-- Use `bind_rows()` to stack `population` below `gapminder` -->
-<!-- ```{r} -->
-<!-- gapminder_pop <- bind_rows(gapminder, population) %>%  -->
-<!--   arrange(country,year) -->
-<!-- ``` -->
-<!-- Visualize trends in population growth by continent -->
-<!-- ```{r} -->
-<!-- gapminder_pop %>%  -->
-<!--   filter(!is.na(continent)) %>%  -->
-<!--   group_by(continent, year) %>% -->
-<!--   summarise(pop=sum(pop)/1000000) %>% -->
-<!--   ggplot(aes(x=year, y=pop, fill=continent))+ -->
-<!--   geom_area()+ -->
-<!--   labs(title="Population projections by continent",  -->
-<!--                y="Population (in mil)") -->
-<!-- ``` -->
+<!-- If we have time, then we will do a case study with the `gapminder` data. [Link to case study here](https://raw.githubusercontent.com/UBC-STAT/stat545.stat.ubc.ca/master/content/notes/supp-a11.Rmd).  -->
 <div id="attributions" class="section level3">
 <h3>Attributions</h3>
 <p>Written by Albina Gibadullina, reviewed by Vincenzo Coia.</p>