quantitative-methods-hs22/report.rmd

---
title: "Quantitative Methods HS22"
author: "Marc Gauch"
date: "`r Sys.Date()`"
output:
  html_document:
    toc: true
    toc_depth: 2
    toc_float: true
    number_sections: true
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

# Preparation

```{r, message=FALSE}
if (!require(tidyverse)){
  install.packages("tidyverse")
  library(tidyverse)
}
```

# Load Data
## Load from CSV
``` {r loadData}
litdata <- read_csv("DataLit_R.csv", show_col_types = FALSE)
litdata <- as_tibble(litdata)
```

## First inspection of data {.tabset}
### Summary
``` {r}
summary(litdata)
```
### Glimpse
``` {r}
glimpse(litdata)
```
### Print
``` {r}
print(litdata)
```
### Head
``` {r}
head(litdata)
```

# Data cleaning
## Converting Strings to numbers and *Keine Antwort* zu *NaN*
``` {r}
litdata <- litdata %>% 
  mutate_all(~ replace(., . == "Stimme voll zu5", 5)) %>%
  mutate_all(~ replace(., . == "Stimme überhaupt nicht zu1", 1)) %>%
  mutate_all(~ replace(., . == "Keine Antwort-", NaN))
```

## Make it numeric
The following code will **NOT** be run. The Idea is to show a way to automatically edit all columns. It works but some columns are NOT numeric.
```{r, eval=FALSE}
  # All colnames that exist
  litdataColnames <- colnames(litdata)
  # the ones we don't want to change
  litdataNonNumericCols <- c("submitdate", "startlanguage", "startdate", "datestamp", "lastpage", "seed")
  # the colnames that should be changed
  litdataColsToMakeNumeric <- litdataColnames[!(litdataColnames %in% litdataNonNumericCols)]
  print(litdataColsToMakeNumeric)
  litdataColsToMakeNumeric <- c("R1")
  for (col in litdataColsToMakeNumeric) {
    litdata[[col]] <- as.numeric(litdata[[col]])
  }
```

First we rename all the columns
```{r}
litdata <- litdata %>% rename(
  "A1" = "W001",
  "A2" = "W002",
  "A3" = "W003",
  "A4" = "W004",
  "A5" = "W005",
  "A6" = "W006",
  "A7" = "W007",
  "A8" = "W008",
  "A9" = "W009",
  
  "B1" = "K001",
  "B2" = "K002",
  "B3" = "K003",
  "B4" = "K004",
  "B5" = "K005",
  "B6" = "K006",
  "B7" = "K007",
  "B8" = "K008",
  "B9" = "K009",
  
  "C1_1" = "TK001_01",
  "C1_2" = "TK001_02",
  "C1_3" = "TK001_03",
  "C1_4" = "TK001_04",
  
  "C2_1" = "TK002_01",
  "C2_2" = "TK002_02",
  "C2_3" = "TK002_03",
  "C2_4" = "TK002_04",
  
  "C3_1" = "TK003_01",
  "C3_2" = "TK003_02",
  "C3_3" = "TK003_03",
  "C3_4" = "TK003_04",
  
  "C4_1" = "TK004_01",
  "C4_2" = "TK004_02",
  "C4_3" = "TK004_03",
  "C4_4" = "TK004_04",
  
  "C5_1" = "TK005_01",
  "C5_2" = "TK005_02",
  "C5_3" = "TK005_03",
  "C5_4" = "TK005_04",
  
  "C6_1" = "TK006_01",
  "C6_2" = "TK006_02",
  "C6_3" = "TK006_03",
  "C6_4" = "TK006_04",
  
  "D1_1" = "H001_001",
  "D1_2" = "H001_002",
  "D1_3" = "H001_003",
  "D1_4" = "H001_004",
  "D1_5" = "H001_005",
  "D1_6" = "H001_006",
  "D1_7" = "H001_007",
  
  "D2" = "H002",
  
  "D3" = "H003",
  
  "D4" = "H004",
  "D4_comment" = "H004_other",
  
  "D5" = "H005",
  "D5_comment" = "H005_other",
  
  "D6" = "H006",
  
  "D7" = "H007",
  
  "D8" = "H008",
  
  "E1" = "R1"
)
```
Then we change the datatype and fix the values
```{r}
litdata$A1 <- as.numeric(litdata$A1)
litdata$A2 <- as.numeric(litdata$A2)
litdata$A3 <- as.numeric(litdata$A3)
litdata$A4 <- as.numeric(litdata$A4)
litdata$A5 <- as.numeric(litdata$A5)
litdata$A6 <- as.numeric(litdata$A6)
litdata$A7 <- as.numeric(litdata$A7)
litdata$A8 <- as.numeric(litdata$A8)
litdata$A9 <- as.numeric(litdata$A9)

litdata$B1 <- as.numeric(litdata$B1)
litdata$B2 <- as.numeric(litdata$B2)
litdata$B3 <- as.numeric(litdata$B3)
litdata$B4 <- as.numeric(litdata$B4)
litdata$B5 <- as.numeric(litdata$B5)
litdata$B6 <- as.numeric(litdata$B6)
litdata$B7 <- as.numeric(litdata$B7)
litdata$B8 <- as.numeric(litdata$B8)
litdata$B9 <- as.numeric(litdata$B9)

litdata$C1_1 <- as.numeric(litdata$C1_1)
litdata$C1_2 <- as.numeric(litdata$C1_2)
litdata$C1_3 <- as.numeric(litdata$C1_3)
litdata$C1_4 <- as.numeric(litdata$C1_4)
litdata$C2_1 <- as.numeric(litdata$C2_1)
litdata$C2_2 <- as.numeric(litdata$C2_2)
litdata$C2_3 <- as.numeric(litdata$C2_3)
litdata$C2_4 <- as.numeric(litdata$C2_4)
litdata$C3_1 <- as.numeric(litdata$C3_1)
litdata$C3_2 <- as.numeric(litdata$C3_2)
litdata$C3_3 <- as.numeric(litdata$C3_3)
litdata$C3_4 <- as.numeric(litdata$C3_4)
litdata$C4_1 <- as.numeric(litdata$C4_1)
litdata$C4_2 <- as.numeric(litdata$C4_2)
litdata$C4_3 <- as.numeric(litdata$C4_3)
litdata$C4_4 <- as.numeric(litdata$C4_4)
litdata$C5_1 <- as.numeric(litdata$C5_1)
litdata$C5_2 <- as.numeric(litdata$C5_2)
litdata$C5_3 <- as.numeric(litdata$C5_3)
litdata$C5_4 <- as.numeric(litdata$C5_4)
litdata$C6_1 <- as.numeric(litdata$C6_1)
litdata$C6_2 <- as.numeric(litdata$C6_2)
litdata$C6_3 <- as.numeric(litdata$C6_3)
litdata$C6_4 <- as.numeric(litdata$C6_4)

litdata <- litdata %>% mutate(D1_1 = ifelse(D1_1 == "Ja", TRUE, ifelse(D1_1 == "Nicht Gewählt", FALSE, D1_1)))
litdata$D1_1 <- as.logical(litdata$D1_1)

litdata <- litdata %>% mutate(D1_2 = ifelse(D1_2 == "Ja", TRUE, ifelse(D1_2 == "Nicht Gewählt", FALSE, D1_2)))
litdata$D1_2 <- as.logical(litdata$D1_2)

litdata <- litdata %>% mutate(D1_3 = ifelse(D1_3 == "Ja", TRUE, ifelse(D1_3 == "Nicht Gewählt", FALSE, D1_3)))
litdata$D1_3 <- as.logical(litdata$D1_3)

litdata <- litdata %>% mutate(D1_4 = ifelse(D1_4 == "Ja", TRUE, ifelse(D1_4 == "Nicht Gewählt", FALSE, D1_4)))
litdata$D1_4 <- as.logical(litdata$D1_4)

litdata <- litdata %>% mutate(D1_5 = ifelse(D1_5 == "Ja", TRUE, ifelse(D1_5 == "Nicht Gewählt", FALSE, D1_5)))
litdata$D1_5 <- as.logical(litdata$D1_5)

litdata <- litdata %>% mutate(D1_6 = ifelse(D1_6 == "Ja", TRUE, ifelse(D1_6 == "Nicht Gewählt", FALSE, D1_6)))
litdata$D1_6 <- as.logical(litdata$D1_6)

litdata <- litdata %>% mutate(D1_7 = ifelse(D1_7 == "Ja", TRUE, ifelse(D1_7 == "Nicht Gewählt", FALSE, D1_7)))
litdata$D1_7 <- as.logical(litdata$D1_7)

litdata <- litdata %>% mutate(D2 = ifelse(D2 == "Ja", TRUE, ifelse(D2 == "Nein", FALSE, D2)))
litdata$D2 <- as.logical(litdata$D2)

# skipping D3 because it's just a free text

litdata$D4 <- as.factor(litdata$D4)

# skipping D4_comment because it's a free text

litdata$D5 <- as.factor(litdata$D5)

# skipping D5_comment because it's a free text

# can't be a number as there is a 2010 or earlier option.
litdata$D6 <- as.factor(litdata$D6)

litdata$D7 <- as.numeric(litdata$D7)

litdata$D8 <- as.factor(litdata$D8)

# skipping E1 because it's a free text

```


## Second inspection of data {.tabset}
### Summary
``` {r}
summary(litdata)
```
### Glimpse
``` {r}
glimpse(litdata)
```
### Print
``` {r}
print(litdata)
```
### Head
``` {r}
head(litdata)
```

# Selbststudium 1
*Berechnen Sie die Häufigkeiten für die Variablen W003, K003, H001_001, H005, H007 und H008.*

## Data {.tabset}
```{r}
displayFunction1 <- function(table, column) {
  tmp <- table[column]
  tmp <- rename(tmp, value = all_of(column))
  tmp <- tmp %>%
    count(value) %>%
    mutate(percentage = prop.table(n)*100)
  print(tmp, n = 100)
  ggplot(tmp, 
          aes(x = value, y=n)) +
          geom_bar(stat = "identity") +
          theme(axis.text.x = element_text(angle = 45, hjust = 1))
}
```
### A3 (W003) {-}
```{r}
  displayFunction1(litdata, "A3")
```

### B3 (K003) {-}
```{r}
  displayFunction1(litdata, "B3")
```

### D1_1 (H001_001) {-}
```{r}
  displayFunction1(litdata, "D1_1")
```

### D5 (H005) {-}
```{r}
  displayFunction1(litdata, "D5")
```

### D7 (H007) {-}
```{r}
  displayFunction1(litdata, "D7")
```

Die Warnung ist resultiert daraus, dass es sehr viele *NA* gibt.

### D8 (H008) {-}
```{r}
  displayFunction1(litdata, "D8")
```