Linted
This commit is contained in:
1 parent
afd7d1babf
commit
51cd711da8
2 files changed
+90
-123
No files matched your search
+45
-61
@@ -1494,11 +1494,11 @@ border-radius: 0px;
|
||||
|
||||
<div id="preparation" class="section level1" number="1">
|
||||
<h1><span class="header-section-number">1</span> Preparation</h1>
|
||||
<pre class="r"><code>if (!require(tidyverse)){
|
||||
<pre class="r"><code>if (!require(tidyverse)) {
|
||||
install.packages("tidyverse")
|
||||
library(tidyverse)
|
||||
}
|
||||
if (!require(moments)){
|
||||
if (!require(moments)) {
|
||||
install.packages("moments")
|
||||
library(moments)
|
||||
}</code></pre>
|
||||
@@ -1508,28 +1508,26 @@ if (!require(moments)){
|
||||
<div id="frequency-table-ordered-from-wish.com" class="section level2" number="2.1">
|
||||
<h2><span class="header-section-number">2.1</span> Frequency Table
|
||||
ordered from wish.com</h2>
|
||||
<pre class="r"><code>freq <- function(data){
|
||||
na_count = length(data[is.na(data)])
|
||||
valid_count = length(data)-na_count
|
||||
<pre class="r"><code>freq <- function(data) {
|
||||
na_count <- length(data[is.na(data)])
|
||||
valid_count <- length(data) - na_count
|
||||
frequency <- table(data)
|
||||
p <- prop.table(frequency)
|
||||
percent <- round(p*100, digits = 2)
|
||||
percent <- round(p * 100, digits = 2)
|
||||
frequency_sum <- cumsum(frequency)
|
||||
hkum <- cumsum(p)
|
||||
percent_sum <- round(hkum*100, digits = 2)
|
||||
percent_sum <- round(hkum * 100, digits = 2)
|
||||
freq_table <- cbind(frequency, percent, frequency_sum, percent_sum)
|
||||
valid_percent <- round(valid_count / length(data)*100, digits = 2)
|
||||
na_percent <- round(na_count / length(data)*100, digits = 2)
|
||||
|
||||
|
||||
valid_percent <- round(valid_count / length(data) * 100, digits = 2)
|
||||
na_percent <- round(na_count / length(data) * 100, digits = 2)
|
||||
|
||||
|
||||
print(freq_table)
|
||||
|
||||
count <- c(valid_count, na_count, valid_count+na_count)
|
||||
percent <- c(valid_percent, na_percent, valid_percent+na_percent)
|
||||
totall <- c(valid_count+na_count, valid_percent+na_percent)
|
||||
count <- c(valid_count, na_count, valid_count + na_count)
|
||||
percent <- c(valid_percent, na_percent, valid_percent + na_percent)
|
||||
df <- data.frame(count, percent, row.names = c("valid", "NA", "Total"))
|
||||
print(df)
|
||||
|
||||
}</code></pre>
|
||||
<p><em>Source: <a href="https://tellmi.psy.lmu.de/tutorials/deskriptive-statistiken-und-grafiken.html#haeufigkeiten-diskret" class="uri">https://tellmi.psy.lmu.de/tutorials/deskriptive-statistiken-und-grafiken.html#haeufigkeiten-diskret</a>
|
||||
and adapted</em></p>
|
||||
@@ -1537,9 +1535,9 @@ and adapted</em></p>
|
||||
<div id="modus" class="section level2" number="2.2">
|
||||
<h2><span class="header-section-number">2.2</span> Modus</h2>
|
||||
<pre class="r"><code>getmode <- function(v) {
|
||||
uniqv <- unique(v)
|
||||
x <- tabulate(match(v, uniqv))
|
||||
uniqv[which(x==max(x))]
|
||||
uniqv <- unique(v)
|
||||
x <- tabulate(match(v, uniqv))
|
||||
uniqv[which(x == max(x))]
|
||||
}</code></pre>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1816,7 +1814,7 @@ inspection of data</h2>
|
||||
<div id="converting-strings-to-numbers-and-keine-antwort-zu-nan" class="section level2" number="4.1">
|
||||
<h2><span class="header-section-number">4.1</span> Converting Strings to
|
||||
numbers and <em>Keine Antwort</em> zu <em>NaN</em></h2>
|
||||
<pre class="r"><code>litdata <- litdata %>%
|
||||
<pre class="r"><code>litdata <- litdata %>%
|
||||
mutate_all(~ replace(., . == "Stimme voll zu5", 5)) %>%
|
||||
mutate_all(~ replace(., . == "Stimme überhaupt nicht zu1", 1)) %>%
|
||||
mutate_all(~ replace(., . == "Keine Antwort-", NaN))</code></pre>
|
||||
@@ -1826,17 +1824,17 @@ numbers and <em>Keine Antwort</em> zu <em>NaN</em></h2>
|
||||
<p>The following code will <strong>NOT</strong> be run. The Idea is to
|
||||
show a way to automatically edit all columns. It works but some columns
|
||||
are NOT numeric.</p>
|
||||
<pre class="r"><code> # 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]])
|
||||
}</code></pre>
|
||||
<pre class="r"><code># 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]])
|
||||
}</code></pre>
|
||||
<p>First we rename all the columns</p>
|
||||
<pre class="r"><code>litdata <- litdata %>% rename(
|
||||
"A1" = "W001",
|
||||
@@ -1848,7 +1846,6 @@ are NOT numeric.</p>
|
||||
"A7" = "W007",
|
||||
"A8" = "W008",
|
||||
"A9" = "W009",
|
||||
|
||||
"B1" = "K001",
|
||||
"B2" = "K002",
|
||||
"B3" = "K003",
|
||||
@@ -1858,37 +1855,30 @@ are NOT numeric.</p>
|
||||
"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",
|
||||
@@ -1896,23 +1886,15 @@ are NOT numeric.</p>
|
||||
"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"
|
||||
)</code></pre>
|
||||
<p>Then we change the datatype and fix the values</p>
|
||||
@@ -2278,16 +2260,18 @@ Data</h2>
|
||||
tmp <- rename(tmp, value = all_of(column))
|
||||
tmp <- tmp %>%
|
||||
count(value) %>%
|
||||
mutate(percentage = prop.table(n)*100)
|
||||
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))
|
||||
ggplot(
|
||||
tmp,
|
||||
aes(x = value, y = n)
|
||||
) +
|
||||
geom_bar(stat = "identity") +
|
||||
theme(axis.text.x = element_text(angle = 45, hjust = 1))
|
||||
}</code></pre>
|
||||
<div id="a3-w003" class="section level3 unnumbered">
|
||||
<h3 class="unnumbered">A3 (W003)</h3>
|
||||
<pre class="r"><code> displayFunction1(litdata, "A3")</code></pre>
|
||||
<pre class="r"><code>displayFunction1(litdata, "A3")</code></pre>
|
||||
<pre><code>## # A tibble: 6 × 3
|
||||
## value n percentage
|
||||
## <dbl> <int> <dbl>
|
||||
@@ -2302,7 +2286,7 @@ Data</h2>
|
||||
</div>
|
||||
<div id="b3-k003" class="section level3 unnumbered">
|
||||
<h3 class="unnumbered">B3 (K003)</h3>
|
||||
<pre class="r"><code> displayFunction1(litdata, "B3")</code></pre>
|
||||
<pre class="r"><code>displayFunction1(litdata, "B3")</code></pre>
|
||||
<pre><code>## # A tibble: 7 × 3
|
||||
## value n percentage
|
||||
## <dbl> <int> <dbl>
|
||||
@@ -2318,7 +2302,7 @@ Data</h2>
|
||||
</div>
|
||||
<div id="d1_1-h001_001" class="section level3 unnumbered">
|
||||
<h3 class="unnumbered">D1_1 (H001_001)</h3>
|
||||
<pre class="r"><code> displayFunction1(litdata, "D1_1")</code></pre>
|
||||
<pre class="r"><code>displayFunction1(litdata, "D1_1")</code></pre>
|
||||
<pre><code>## # A tibble: 3 × 3
|
||||
## value n percentage
|
||||
## <lgl> <int> <dbl>
|
||||
@@ -2329,7 +2313,7 @@ Data</h2>
|
||||
</div>
|
||||
<div id="d5-h005" class="section level3 unnumbered">
|
||||
<h3 class="unnumbered">D5 (H005)</h3>
|
||||
<pre class="r"><code> displayFunction1(litdata, "D5")</code></pre>
|
||||
<pre class="r"><code>displayFunction1(litdata, "D5")</code></pre>
|
||||
<pre><code>## # A tibble: 18 × 3
|
||||
## value n percentage
|
||||
## <fct> <int> <dbl>
|
||||
@@ -2355,7 +2339,7 @@ Data</h2>
|
||||
</div>
|
||||
<div id="d7-h007" class="section level3 unnumbered">
|
||||
<h3 class="unnumbered">D7 (H007)</h3>
|
||||
<pre class="r"><code> displayFunction1(litdata, "D7")</code></pre>
|
||||
<pre class="r"><code>displayFunction1(litdata, "D7")</code></pre>
|
||||
<pre><code>## # A tibble: 24 × 3
|
||||
## value n percentage
|
||||
## <dbl> <int> <dbl>
|
||||
@@ -2390,7 +2374,7 @@ gibt.</p>
|
||||
</div>
|
||||
<div id="d8-h008" class="section level3 unnumbered">
|
||||
<h3 class="unnumbered">D8 (H008)</h3>
|
||||
<pre class="r"><code> displayFunction1(litdata, "D8")</code></pre>
|
||||
<pre class="r"><code>displayFunction1(litdata, "D8")</code></pre>
|
||||
<pre><code>## # A tibble: 3 × 3
|
||||
## value n percentage
|
||||
## <fct> <int> <dbl>
|
||||
@@ -2407,7 +2391,7 @@ gibt.</p>
|
||||
<pre class="r"><code>birthyears <- litdata$D7
|
||||
# remove NAs
|
||||
birthyears <- birthyears[!is.na(birthyears)]
|
||||
age <- 2021-birthyears</code></pre>
|
||||
age <- 2021 - birthyears</code></pre>
|
||||
<div id="frequency" class="section level2" number="6.1">
|
||||
<h2><span class="header-section-number">6.1</span> Frequency</h2>
|
||||
<pre class="r"><code>freq(age)</code></pre>
|
||||
@@ -2440,7 +2424,7 @@ age <- 2021-birthyears</code></pre>
|
||||
## NA 0 0
|
||||
## Total 106 100</code></pre>
|
||||
<pre class="r"><code># with NA
|
||||
freq(2021-litdata$D7)</code></pre>
|
||||
freq(2021 - litdata$D7)</code></pre>
|
||||
<pre><code>## frequency percent frequency_sum percent_sum
|
||||
## 19 1 0.94 1 0.94
|
||||
## 20 2 1.89 3 2.83
|
||||
@@ -2492,7 +2476,7 @@ Mittelwert</h3>
|
||||
</div>
|
||||
<div id="spannweite" class="section level3" number="6.2.4">
|
||||
<h3><span class="header-section-number">6.2.4</span> Spannweite</h3>
|
||||
<pre class="r"><code>max(age)-min(age)</code></pre>
|
||||
<pre class="r"><code>max(age) - min(age)</code></pre>
|
||||
<pre><code>## [1] 31</code></pre>
|
||||
</div>
|
||||
<div id="quartilsabstand" class="section level3" number="6.2.5">
|
||||
@@ -2643,7 +2627,7 @@ sozialen Herkunft 5.6, er ist also genauso hoch wie in der
|
||||
Gesamtschweiz. Was ist zur Lage dieses Wertes bezogen auf die Verteilung
|
||||
in Graubünden zu sagen? Also: Wie viele Schüler in GR liegen mit ihrem
|
||||
Wert darunter?</p>
|
||||
<pre class="r"><code>pnorm(5.6, mean = 5.1, sd=2.0)</code></pre>
|
||||
<pre class="r"><code>pnorm(5.6, mean = 5.1, sd = 2.0)</code></pre>
|
||||
<pre><code>## [1] 0.5987063</code></pre>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
Reference in new issue
Block a user