final version

Author: gulinan

.DS_Store

@@ -4,7 +4,8 @@ title: 'Week 03: Examples for Data Importing'
 ---
 
 # Load packages
-```{r}
+```{r, warning=F, message=F}
+library(tidyverse)
 library(readr)
 library(readxl)
 ```
@@ -16,6 +17,13 @@ library(readxl)
 getwd()
 ```
 
+
+```{r}
+cth_data <- read_csv("data/CTH_raw_na.csv")
+```
+
+
+
 # Visit Environmental Performance Index at https://epi.yale.edu/
 
 # The Environmental Performance Index (EPI) ranks 180 countries on 32 performance indicators across 11 issue  
@@ -159,7 +167,10 @@ excel_sheets("data/Population-1989-2019.xlsx")
 # read_excel() reads both xls and xlsx files and detects the format from the extension.
 
 ```{r}
-pop <- read_excel("data/Population-1989-2019.xlsx")
+pop <- read_excel("data/Population-1989-2019.xlsx", range= cell_rows(5:40))
+```
+
+```{r}
 View(pop)
 ```
 
@@ -173,6 +184,21 @@ pop_red <- read_excel("data/Population-1989-2019.xlsx", range = cell_rows(5:40))
 View(pop_red)
 ```
 
+
+```{r}
+colnames(pop)[1:2] <- c("Country", "Number")
+```
+
+
+
+```{r}
+colnames(pop)[-(1:2)] <- paste("y", 1989:2019, sep="")
+```
+
+```{r}
+View(pop)
+```
+
 ```{r}
 colnames(pop_red)[1:2] <- c("Country", "Number")
 View(pop_red)

01-importing.Rmd

@@ -19,6 +19,8 @@ getwd()
 
 # Download file from web to your local.
 
+"
+
 ```{r, eval=F}
 # download the file into your local computer
 download.file("https://epi.yale.edu/downloads/epi2020resultsregions20200604.csv", "data/epi2020resultsregions20200604.csv")
@@ -61,6 +63,7 @@ epi_data %>%
   View()
 ```
 
+
 # Remember %>% operator does not save the object, you need
 # to assign RHS to an object at the LHS.
 
@@ -84,11 +87,13 @@ epi_data %>%
   View()
 ```
 
+
 # We can use the %in% operator to deselect certain groups as well, 
 # in this case we have to negate by adding an exclamation mark (Boolean operator)
 # at the beginning of our filter condition.
 
 ```{r}
+#not works with -
 epi_data %>%
   filter(!region %in% c("Asia-Pacific", "Eastern Europe")) %>%
    View()
@@ -101,12 +106,15 @@ epi_data %>%
 # or equal to 50!..
 
 
+
 ```{r}
 epi_data %>%
   filter(EPI.new <= 50) %>%
    View()
 ```
 
+
+
 # Multiple conditions
 # filter(condition1, condition2) will return rows where "both conditions" are met.
 # Let's combine multiple conditions in the same call.
@@ -115,12 +123,14 @@ epi_data %>%
 # 50 <= EPI.new & EPI.new <= 60.
 
 
+
 ```{r}
 epi_data %>%
   filter(50 <= EPI.new & EPI.new <= 60) %>%
    View()
 ```
 
+
 # or use "helper function" between(): 
 
 ```{r}
@@ -146,6 +156,7 @@ epi_data %>%
    View()
 ```
 
+
 # Filter Asia-Pacific countries whose EPI score is greater than the grand mean.
 
 
@@ -186,6 +197,17 @@ dim(cth_data)
 
 ### Caution!!! Discuss with students
 
+
+Eğer cth_raw_1950 kolonunda missing varsa, veriden çıkar
+
+
+```{r}
+cth_data %>% 
+  filter(!is.na(CTH.raw.1950)) %>% 
+  View()
+```
+
+
 ```{r}
 cth_data_filtered <- cth_data %>%
                      filter(!is.na(CTH.raw.1950)) 
@@ -203,6 +225,8 @@ dim(cth_data_filtered)
 # The order in which you add them, will determine the order in which 
 # they appear in the output.
 
+
+
 ```{r}
 epi_data %>%
   select(code, iso, country, region, EPI.new, AIR.new) %>%
@@ -218,6 +242,7 @@ epi_data %>%
   View()
 ```
 
+
 # A side note:
 # ! for taking the complement of a set of variables.
 
@@ -231,6 +256,7 @@ epi_data %>%
 # & and | for selecting the intersection or the union of two sets of variables.
 # c() for combining selections.
 
+
 ```{r}
 epi_data %>%
   select(code:iso & iso:EPI.new) %>%
@@ -249,6 +275,15 @@ epi_data %>%
 # You can also deselect blocks of columns.
 
 
+```{r}
+# negative sign works with !
+epi_data %>% 
+  select(-code) %>% 
+  View()
+```
+
+
+
 ```{r}
 epi_data %>%
   select(-HLT.new,-(PMD.new:WWT.rgn.rank)) %>%
@@ -337,6 +372,15 @@ epi_data %>%
 
 # Sort the data according to the EPI.new variable in ascending order
 
+
+```{r}
+epi_data %>% 
+  arrange(desc(EPI.new)) %>% 
+  View()
+```
+
+
+
 ```{r}
 epi_data %>% 
   arrange(EPI.new) %>% 
@@ -371,6 +415,9 @@ epi_data %>%
 
 # Let's standardize the EPI.new variable
 
+
+
+
 ```{r}
 epi_data %>%
   mutate(EPI.stand = (EPI.new-mean(EPI.new))/sd(EPI.new)) %>%
@@ -386,6 +433,7 @@ epi_data %>%
 # returns TRUE and lastly what to do when it returns FALSE.
 
 
+
 ```{r}
 epi_data %>% 
   mutate(EPI.cat = ifelse(EPI.new >=50,"Good","Bad")) %>% 
@@ -402,10 +450,6 @@ epi_data %>%
 # is not true will continue to be evaluated for the next statement. 
 # For everything that is left at the end just use the TRUE ~ "newname".
 
-EPI.cat such that EPI.new >= 75, "Very Good"
-                  EPI.new >= 50, "Good"
-                  EPI.new < 50, "Not Good"
-
 
 ```{r}
 epi_data %>%
@@ -437,6 +481,14 @@ epi_data %>%
 # You can add multiple summary functions behind each other.
 
 
+```{r}
+epi_data %>% 
+  summarize(nds = n_distinct(region)) %>% 
+  View()
+```
+
+
+
 ```{r}
 ## can you guess the dimension of the output?
 epi_data %>%

02-manipulating.Rmd

@@ -57,7 +57,6 @@ class: left
 * Data tidying with `tidyr` package.
   * 03-tidying.Rmd
 
-  
 ---
 class: middle, center
 

Week_03_Lecture_Notes.Rproj renamed to Week_03_04_Lecture_Notes.Rproj

@@ -4,7 +4,7 @@
     <title>MAT381E-Week 3: Data Importing, Manipulating, and Tidying</title>
     <meta charset="utf-8" />
     <meta name="author" content="Gül İnan" />
-    <meta name="date" content="2021-10-24" />
+    <meta name="date" content="2021-10-30" />
     <script src="intro_tidyverse_files/header-attrs-2.11/header-attrs.js"></script>
     <link href="intro_tidyverse_files/remark-css-0.0.1/default.css" rel="stylesheet" />
     <script src="intro_tidyverse_files/fabric-4.3.1/fabric.min.js"></script>
@@ -26,7 +26,7 @@
 # MAT381E-Week 3: Data Importing, Manipulating, and Tidying
 ### Gül İnan
 ### Department of Mathematics<br/>Istanbul Technical University
-### October 24, 2021
+### October 30, 2021
 
 ---
 
@@ -52,7 +52,6 @@
 * Data tidying with `tidyr` package.
   * 03-tidying.Rmd
 
-  
 ---
 class: middle, center