differences for PR #524

04-tidyr.md

@@ -123,16 +123,16 @@ interviews %>%
 # A tibble: 10 × 4
    key_ID village  interview_date      instanceID                               
     <dbl> <chr>    <dttm>              <chr>                                    
- 1     52 Chirodzo 2016-11-16 00:00:00 uuid:6db55cb4-a853-4000-9555-757b7fae2bcf
- 2     51 Chirodzo 2016-11-16 00:00:00 uuid:18ac8e77-bdaf-47ab-85a2-e4c947c9d3ce
- 3     44 Chirodzo 2016-11-17 00:00:00 uuid:f9fadf44-d040-4fca-86c1-2835f79c4952
- 4     68 Chirodzo 2016-11-16 00:00:00 uuid:ef04b3eb-b47d-412e-9b09-4f5e08fc66f9
- 5     46 Chirodzo 2016-11-17 00:00:00 uuid:35f297e0-aa5d-4149-9b7b-4965004cfc37
- 6     55 Chirodzo 2016-11-16 00:00:00 uuid:883c0433-9891-4121-bc63-744f082c1fa0
- 7    199 Chirodzo 2017-06-04 00:00:00 uuid:ffc83162-ff24-4a87-8709-eff17abc0b3b
- 8     10 Chirodzo 2016-12-16 00:00:00 uuid:8f4e49bc-da81-4356-ae34-e0d794a23721
+ 1     70 Chirodzo 2016-11-16 00:00:00 uuid:1feb0108-4599-4bf9-8a07-1f5e66a50a0a
+ 2     69 Chirodzo 2016-11-16 00:00:00 uuid:f86933a5-12b8-4427-b821-43c5b039401d
+ 3     43 Chirodzo 2016-11-17 00:00:00 uuid:b4dff49f-ef27-40e5-a9d1-acf287b47358
+ 4     50 Chirodzo 2016-11-16 00:00:00 uuid:4267c33c-53a7-46d9-8bd6-b96f58a4f92c
+ 5     35 Chirodzo 2016-11-17 00:00:00 uuid:ff7496e7-984a-47d3-a8a1-13618b5683ce
+ 6      9 Chirodzo 2016-11-16 00:00:00 uuid:846103d2-b1db-4055-b502-9cd510bb7b37
+ 7    192 Chirodzo 2017-06-03 00:00:00 uuid:f94409a6-e461-4e4c-a6fb-0072d3d58b00
+ 8     47 Chirodzo 2016-11-17 00:00:00 uuid:2d0b1936-4f82-4ec3-a3b5-7c3c8cd6cc2b
  9    127 Chirodzo 2016-11-16 00:00:00 uuid:f6d04b41-b539-4e00-868a-0f62b427587d
-10     54 Chirodzo 2016-11-16 00:00:00 uuid:273ab27f-9be3-4f3b-83c9-d3e1592de919
+10     64 Chirodzo 2016-11-16 00:00:00 uuid:28cfd718-bf62-4d90-8100-55fafbe45d06
 ```
 
 We notice that the layout or format of the `interviews` data is in a format that
@@ -524,7 +524,7 @@ this data frame to our `data_output` directory.
 
 
 ``` r
-write_csv (interviews_plotting, file = "data_output/interviews_plotting.csv")
+write_csv(interviews_plotting, file = "data_output/interviews_plotting.csv")
 ```
 
 

05-ggplot2.md

@@ -9,9 +9,16 @@ source: Rmd
 
 :::: instructor
 
-- This lesson is a broad overview of ggplot2 and focuses on (1) getting familiar
-  with the layering system of ggplot2, (2) using the argument `group` in the
-  `aes()` function, (3) basic customization of the plots.
+- This episode is a broad overview of ggplot2 and focuses on (1) getting
+  familiar with the layering system of ggplot2, (2) using the argument `group`
+  in the `aes()` function, (3) basic customization of the plots.
+- The episode depends on data created in the Data Wrangling with tidyr
+  episode. If you did not get to or through all of the tidyr episode,
+  you can have the learners access the data by either downloading it or
+  quickly creating it using the tidyr code below. You will probably want to
+  copy the code into the Etherpad.
+- If you did skip the tidyr episode, you might want to go over the exporting
+  data section in that episode.
 
 ::::::::::::
 
@@ -63,11 +70,23 @@ dttm  (1): interview_date
 ```
 
 If you were unable to complete the previous lesson or did not save the data,
-then you can create it now.
+then you can create it now. Either download it using `read_csv()` (Option 1)
+or create it with the **dplyr** and **tidyr** code (Option 2).
+
+::: tab
+
+### Option 1: Download the data
+
+
+``` r
+interviews_plotting <- read_csv("https://raw.githubusercontent.com/datacarpentry/r-socialsci/main/episodes/data/interviews_plotting.csv")
+```
+
+### Option 2: Create the data
 
 
 ``` r
-## Not run, but can be used to load in data from previous lesson!
+## Can be used to load in data from previous lesson!
 interviews_plotting <- interviews %>%
   ## pivot wider by items_owned
   separate_rows(items_owned, sep = ";") %>%
@@ -88,6 +107,8 @@ interviews_plotting <- interviews %>%
   mutate(number_items = rowSums(select(., bicycle:car)))
 ```
 
+:::
+
 ## Plotting with **`ggplot2`**
 
 **`ggplot2`** is a plotting package that makes it simple to create complex plots

data/download_data.R

@@ -8,16 +8,44 @@ if (!dir.exists("data"))
 if (! file.exists("data/SAFI_clean.csv")) {
   download.file("https://ndownloader.figshare.com/files/11492171",
                 "data/SAFI_clean.csv", mode = "wb")
-  
+
   # Clean data
   df <- read.csv("data/SAFI_clean.csv",
                  stringsAsFactors = FALSE)
-  
+
   # Remove white space
   df$respondent_wall_type <- trimws(df$respondent_wall_type, which = "both")
   # Replace duplicate ids
   df[[2, 1]] <- 2
   df[[53, 1]] <- 53
-  
+
   write.csv(df, "data/SAFI_clean.csv", row.names = FALSE)
 }
+
+# Plotting data -----------------------------------------------------------
+
+# Create plotting data for ggplot episode
+library(tidyr)
+library(dplyr)
+
+if (! file.exists("data/interviews_plotting.csv")) {
+  # Copy code from ggplot episode to create data
+  interviews_plotting <- df %>%
+    separate_rows(items_owned, sep = ";") %>%
+    replace_na(list(items_owned = "no_listed_items")) %>%
+    mutate(items_owned_logical = TRUE) %>%
+    pivot_wider(names_from = items_owned,
+                values_from = items_owned_logical,
+                values_fill = list(items_owned_logical = FALSE)) %>%
+    separate_rows(months_lack_food, sep = ";") %>%
+    mutate(months_lack_food_logical = TRUE) %>%
+    pivot_wider(names_from = months_lack_food,
+                values_from = months_lack_food_logical,
+                values_fill = list(months_lack_food_logical = FALSE)) %>%
+    mutate(number_months_lack_food = rowSums(select(., Jan:May))) %>%
+    mutate(number_items = rowSums(select(., bicycle:car)))
+
+  write.csv(interviews_plotting, "data/interviews_plotting.csv", row.names = FALSE)
+}
+
+