diff --git a/.Rhistory b/.Rhistory index 25085c8c3cdf8263077fedea74dc691908b5581f..259ab6bb6d6133d9dc841111e551b2b3a2a587ce 100644 --- a/.Rhistory +++ b/.Rhistory @@ -10,3 +10,5 @@ library(learnr) install.packages(readxl) install.packages("readxl") library("readxl") +install.packages("knitr") +install.packages("knitr") diff --git a/DCProject.Rmd b/DCProject.Rmd index 1164d79460e12ba5c1a27f8a27744b3f841abcec..7594cc4e0d66b11b83e7a4adfd57946621bf5b58 100644 --- a/DCProject.Rmd +++ b/DCProject.Rmd @@ -18,6 +18,9 @@ runtime: shiny_prerendered ```{r setup, include=FALSE} library(learnr) library(readxl) +library(knitr) +library(dplyr) + current_dir = getwd() data <- read_excel(file.path(current_dir, "Datensatz.xlsx")) @@ -237,10 +240,12 @@ Für die 2. Hypothese können wir die Lineare Regression und die Koeffizienz ber ```{r} daten <- data.frame( Jahr = c(1998:2021), - Frauen = c(as.numeric(unlist(data[-1 ,9]))), - Männer = c(as.numeric(unlist(data[-1 ,8]))) + Frauen = c(as.numeric(unlist(data[2:25 ,9]))), + Männer = c(as.numeric(unlist(data[2:25 ,8]))) ) +kable(daten$Frauen) + daten$Frauen_Anteil <- daten$Frauen / (daten$Frauen + daten$Männer) * 100 daten$Männer_Anteil <- daten$Männer / (daten$Frauen + daten$Männer) * 100 diff --git a/DCProject.html b/DCProject.html index 528fd4d5d6cbc2b9ad7655e5f55b97e432ab26c8..c1d29ac1222e53c7f8901578d6326f4f69e44ccb 100644 --- a/DCProject.html +++ b/DCProject.html @@ -647,31 +647,373 @@ class="section level3"> </div> <div id="section-datenanalyse" class="section level2"> <h2>Datenanalyse</h2> -<p>Hier ist uner tatsächlicher Datensatz:</p> -<pre class="r"><code>print(data)</code></pre> -<pre><code>## # A tibble: 31 × 10 -## Semester Deutsche ...3 ...4 Ausländer ...6 ...7 Insgesamt ...9 ...10 -## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> -## 1 <NA> männlich weibli… Insg… männlich weib… Insg… männlich weib… Insg… -## 2 WS 1998/99 907403 727254 1634… 92321 73673 1659… 999724 8009… 1800… -## 3 WS 1999/00 872178 723246 1595… 95460 79605 1750… 967638 8028… 1770… -## 4 WS 2000/01 870016 741820 1611… 99906 87121 1870… 969922 8289… 1798… -## 5 WS 2001/02 887462 774628 1662… 107831 98410 2062… 995293 8730… 1868… -## 6 WS 2002/03 903218 808567 1711… 117205 1098… 2270… 1020423 9183… 1938… -## 7 WS 2003/04 935718 837611 1773… 125826 1203… 2461… 1061544 9579… 2019… -## 8 WS 2004/05 901979 814795 1716… 124220 1221… 2463… 1026199 9369… 1963… -## 9 WS 2005/06 912696 824712 1737… 124447 1239… 2483… 1037143 9486… 1985… -## 10 WS 2006/07 909740 822934 1732… 122923 1234… 2463… 1032663 9463… 1979… -## # ℹ 21 more rows</code></pre> +<p><em>Information: Die hier dargestellten Tabellen beinhalten zur +Veranschaulichung jeweils nur die ersten 10 Zeilen. Unser Datensatz +besteht aus 24 Zeilen.</em></p> +<p>Hier ist uner tatsächlicher Datensatz aus der Excel-Datei:</p> +<pre class="r"><code>kable(head(data, 10))</code></pre> +<table style="width:100%;"> +<colgroup> +<col width="11%" /> +<col width="9%" /> +<col width="9%" /> +<col width="10%" /> +<col width="10%" /> +<col width="9%" /> +<col width="10%" /> +<col width="10%" /> +<col width="9%" /> +<col width="10%" /> +</colgroup> +<thead> +<tr class="header"> +<th align="left">Semester</th> +<th align="left">Deutsche</th> +<th align="left">…3</th> +<th align="left">…4</th> +<th align="left">Ausländer</th> +<th align="left">…6</th> +<th align="left">…7</th> +<th align="left">Insgesamt</th> +<th align="left">…9</th> +<th align="left">…10</th> +</tr> +</thead> +<tbody> +<tr class="odd"> +<td align="left">NA</td> +<td align="left">männlich</td> +<td align="left">weiblich</td> +<td align="left">Insgesamt</td> +<td align="left">männlich</td> +<td align="left">weiblich</td> +<td align="left">Insgesamt</td> +<td align="left">männlich</td> +<td align="left">weiblich</td> +<td align="left">Insgesamt</td> +</tr> +<tr class="even"> +<td align="left">WS 1998/99</td> +<td align="left">907403</td> +<td align="left">727254</td> +<td align="left">1634657</td> +<td align="left">92321</td> +<td align="left">73673</td> +<td align="left">165994</td> +<td align="left">999724</td> +<td align="left">800927</td> +<td align="left">1800651</td> +</tr> +<tr class="odd"> +<td align="left">WS 1999/00</td> +<td align="left">872178</td> +<td align="left">723246</td> +<td align="left">1595424</td> +<td align="left">95460</td> +<td align="left">79605</td> +<td align="left">175065</td> +<td align="left">967638</td> +<td align="left">802851</td> +<td align="left">1770489</td> +</tr> +<tr class="even"> +<td align="left">WS 2000/01</td> +<td align="left">870016</td> +<td align="left">741820</td> +<td align="left">1611836</td> +<td align="left">99906</td> +<td align="left">87121</td> +<td align="left">187027</td> +<td align="left">969922</td> +<td align="left">828941</td> +<td align="left">1798863</td> +</tr> +<tr class="odd"> +<td align="left">WS 2001/02</td> +<td align="left">887462</td> +<td align="left">774628</td> +<td align="left">1662090</td> +<td align="left">107831</td> +<td align="left">98410</td> +<td align="left">206241</td> +<td align="left">995293</td> +<td align="left">873038</td> +<td align="left">1868331</td> +</tr> +<tr class="even"> +<td align="left">WS 2002/03</td> +<td align="left">903218</td> +<td align="left">808567</td> +<td align="left">1711785</td> +<td align="left">117205</td> +<td align="left">109821</td> +<td align="left">227026</td> +<td align="left">1020423</td> +<td align="left">918388</td> +<td align="left">1938811</td> +</tr> +<tr class="odd"> +<td align="left">WS 2003/04</td> +<td align="left">935718</td> +<td align="left">837611</td> +<td align="left">1773329</td> +<td align="left">125826</td> +<td align="left">120310</td> +<td align="left">246136</td> +<td align="left">1061544</td> +<td align="left">957921</td> +<td align="left">2019465</td> +</tr> +<tr class="even"> +<td align="left">WS 2004/05</td> +<td align="left">901979</td> +<td align="left">814795</td> +<td align="left">1716774</td> +<td align="left">124220</td> +<td align="left">122114</td> +<td align="left">246334</td> +<td align="left">1026199</td> +<td align="left">936909</td> +<td align="left">1963108</td> +</tr> +<tr class="odd"> +<td align="left">WS 2005/06</td> +<td align="left">912696</td> +<td align="left">824712</td> +<td align="left">1737408</td> +<td align="left">124447</td> +<td align="left">123910</td> +<td align="left">248357</td> +<td align="left">1037143</td> +<td align="left">948622</td> +<td align="left">1985765</td> +</tr> +<tr class="even"> +<td align="left">WS 2006/07</td> +<td align="left">909740</td> +<td align="left">822934</td> +<td align="left">1732674</td> +<td align="left">122923</td> +<td align="left">123446</td> +<td align="left">246369</td> +<td align="left">1032663</td> +<td align="left">946380</td> +<td align="left">1979043</td> +</tr> +</tbody> +</table> <div id="section-eigenschaften-der-daten" class="section level3"> <h3>Eigenschaften der Daten</h3> +<p>Nun können wir Eigenschaften wie Mittelwert, Meidan, Varianz und die +Standartabweichung berechnen. Dazu nutzen wir die 8. und 9. Spalte. +Diese enthalten die gesamte Anzahl der Männlichen und Weiblichen +Student:innen der Jahre:</p> +<pre class="r"><code>selected_data <- data[ ,8:9] +kable(head(selected_data, 10))</code></pre> +<table> +<thead> +<tr class="header"> +<th align="left">Insgesamt</th> +<th align="left">…9</th> +</tr> +</thead> +<tbody> +<tr class="odd"> +<td align="left">männlich</td> +<td align="left">weiblich</td> +</tr> +<tr class="even"> +<td align="left">999724</td> +<td align="left">800927</td> +</tr> +<tr class="odd"> +<td align="left">967638</td> +<td align="left">802851</td> +</tr> +<tr class="even"> +<td align="left">969922</td> +<td align="left">828941</td> +</tr> +<tr class="odd"> +<td align="left">995293</td> +<td align="left">873038</td> +</tr> +<tr class="even"> +<td align="left">1020423</td> +<td align="left">918388</td> +</tr> +<tr class="odd"> +<td align="left">1061544</td> +<td align="left">957921</td> +</tr> +<tr class="even"> +<td align="left">1026199</td> +<td align="left">936909</td> +</tr> +<tr class="odd"> +<td align="left">1037143</td> +<td align="left">948622</td> +</tr> +<tr class="even"> +<td align="left">1032663</td> +<td align="left">946380</td> +</tr> +</tbody> +</table> +<p>Wir teilen die Daten in männlich und weiblich. Zusätzlich werden die +Spalten etwas konvertiert:</p> +<pre class="r"><code>data_male <- as.numeric(unlist(selected_data[-1 ,1])) +data_female <- as.numeric(unlist(selected_data[-1 ,2]))</code></pre> +<p>Und Berechnen:</p> +<pre class="r"><code>print(paste("Median male: ", median(data_male), "Median female: ", median(data_female)))</code></pre> +<pre><code>## [1] "Median male: NA Median female: NA"</code></pre> +<pre class="r"><code>print(paste("Varianz male: ", var(data_male), "Varianz female: ", var(data_female)))</code></pre> +<pre><code>## [1] "Varianz male: NA Varianz female: NA"</code></pre> +<pre class="r"><code>print(paste("Std. Abweichung male: ", sd(data_male), "Std. Abweichung female: ", sd(data_female)))</code></pre> +<pre><code>## [1] "Std. Abweichung male: NA Std. Abweichung female: NA"</code></pre> </div> <div id="section-hypothesentest" class="section level3"> <h3>Hypothesentest</h3> +<p>In der Datenbasis haben wir 2 Hypothesen aufgestellt:</p> +<ul> +<li>Die Anzahl der Ausländischen Studenten in Deutschland hat sich seit +dem WS 00/01 verdoppelt.</li> +<li>Der %-Anteil an studierenden Frauen (insgesamt) gegenüber +studierenden Männern (insgesamt) hat sich seit dem WS 98/99 stetig +erhöht.</li> +</ul> +<p>Für die erste Hypothese müssen wir ledeglich die Summe der +Ausländischen Student:innen vom Wintersemester 2000 mit dem aktuellstem +Wintersemester vergleichen und schauen, ob der Wert vom Aktuellen +Semester größer oder gleich doppelt so groß ist wie vom altem +Wintersemester:</p> +<pre class="r"><code>old_ws <- as.numeric(data[2,7]) +new_ws <- as.numeric(data[25,7]) + +faktor <- 2 +old_ws_double <- old_ws * faktor + +print(paste("Stimmt es, dass die Anzahl an ausländischen Student:innen sich seid dem WS 2000 mindestens verdoppelt hat: ", new_ws >= old_ws_double))</code></pre> +<pre><code>## [1] "Stimmt es, dass die Anzahl an ausländischen Student:innen sich seid dem WS 2000 mindestens verdoppelt hat: TRUE"</code></pre> +<p>Für die 2. Hypothese können wir die Lineare Regression und die +Koeffizienz berechnen.</p> +<pre class="r"><code>daten <- data.frame( + Jahr = c(1998:2021), + Frauen = c(as.numeric(unlist(data[2:25 ,9]))), + Männer = c(as.numeric(unlist(data[2:25 ,8]))) +) + +kable(daten$Frauen)</code></pre> +<table> +<thead> +<tr class="header"> +<th align="right">x</th> +</tr> +</thead> +<tbody> +<tr class="odd"> +<td align="right">800927</td> +</tr> +<tr class="even"> +<td align="right">802851</td> +</tr> +<tr class="odd"> +<td align="right">828941</td> +</tr> +<tr class="even"> +<td align="right">873038</td> +</tr> +<tr class="odd"> +<td align="right">918388</td> +</tr> +<tr class="even"> +<td align="right">957921</td> +</tr> +<tr class="odd"> +<td align="right">936909</td> +</tr> +<tr class="even"> +<td align="right">948622</td> +</tr> +<tr class="odd"> +<td align="right">946380</td> +</tr> +<tr class="even"> +<td align="right">926644</td> +</tr> +<tr class="odd"> +<td align="right">967501</td> +</tr> +<tr class="even"> +<td align="right">1014728</td> +</tr> +<tr class="odd"> +<td align="right">1059809</td> +</tr> +<tr class="even"> +<td align="right">1125602</td> +</tr> +<tr class="odd"> +<td align="right">1185392</td> +</tr> +<tr class="even"> +<td align="right">1245241</td> +</tr> +<tr class="odd"> +<td align="right">1290376</td> +</tr> +<tr class="even"> +<td align="right">1323673</td> +</tr> +<tr class="odd"> +<td align="right">1353385</td> +</tr> +<tr class="even"> +<td align="right">1380335</td> +</tr> +<tr class="odd"> +<td align="right">1402244</td> +</tr> +<tr class="even"> +<td align="right">1426182</td> +</tr> +<tr class="odd"> +<td align="right">1467779</td> +</tr> +<tr class="even"> +<td align="right">1475633</td> +</tr> +</tbody> +</table> +<pre class="r"><code>daten$Frauen_Anteil <- daten$Frauen / (daten$Frauen + daten$Männer) * 100 +daten$Männer_Anteil <- daten$Männer / (daten$Frauen + daten$Männer) * 100 + +trend_f <- lm(Frauen_Anteil ~ Jahr, data = daten) +trend_m <- lm(Männer_Anteil ~ Jahr, data = daten) + +print(coef(trend_f))</code></pre> +<pre><code>## (Intercept) Jahr +## -257.9118506 0.1520867</code></pre> +<pre class="r"><code>print(coef(trend_m))</code></pre> +<pre><code>## (Intercept) Jahr +## 357.9118506 -0.1520867</code></pre> </div> </div> <div id="section-ergebnispräsentation" class="section level2"> <h2>Ergebnispräsentation</h2> +<p>In der Datenanalyse haben wir bei der 2. Hypothese geschaut, ob die +Anzahl an Frauen im vergleich zu Männern stetig erhöt hat. Hierzu eine +Visualisierung:</p> +<pre class="r"><code>plot(daten$Jahr, daten$Frauen_Anteil, xlab = "Jahr", ylab = "% Anteil Frauen", main = "Trend der Frauenanteile") + +abline(trend_f, col = "red")</code></pre> +<p><img src="DCProject_files/figure-html/unnamed-chunk-7-1.png" width="624" /></p> +<pre class="r"><code>plot(daten$Jahr, daten$Männer_Anteil, xlab = "Jahr", ylab = "% Anteil Männer", main = "Trend der Männeranteile") + +abline(trend_m, col = "blue")</code></pre> +<p><img src="DCProject_files/figure-html/unnamed-chunk-8-1.png" width="624" /></p> +<p>Wie man sieht ist es tatsächlich so, dass der Frauenanteil stetig +gestiegen ist, im vergleich zum Männeranteil.</p> </div> <div id="section-teaminfos" class="section level2"> <h2>Teaminfos</h2> @@ -683,6 +1025,9 @@ class="section level3"> <script type="application/shiny-prerendered" data-context="server-start"> library(learnr) library(readxl) +library(knitr) +library(dplyr) + current_dir = getwd() data <- read_excel(file.path(current_dir, "Datensatz.xlsx")) @@ -715,7 +1060,7 @@ session$onSessionEnded(function() { <!--/html_preserve--> <!--html_preserve--> <script type="application/shiny-prerendered" data-context="execution_dependencies"> -{"type":"list","attributes":{"names":{"type":"character","attributes":{},"value":["packages"]}},"value":[{"type":"list","attributes":{"names":{"type":"character","attributes":{},"value":["packages","version"]},"class":{"type":"character","attributes":{},"value":["data.frame"]},"row.names":{"type":"integer","attributes":{},"value":[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51]}},"value":[{"type":"character","attributes":{},"value":["backports","base","bslib","cachem","cellranger","checkmate","cli","compiler","datasets","digest","ellipsis","evaluate","fansi","fastmap","fontawesome","glue","graphics","grDevices","htmltools","htmlwidgets","httpuv","jquerylib","jsonlite","knitr","later","learnr","lifecycle","magrittr","methods","mime","pillar","pkgconfig","promises","R6","Rcpp","readxl","rlang","rmarkdown","rprojroot","sass","shiny","stats","tibble","tools","utf8","utils","vctrs","withr","xfun","xtable","yaml"]},{"type":"character","attributes":{},"value":["1.4.1","4.3.1","0.5.0","1.0.8","1.1.0","2.2.0","3.6.1","4.3.1","4.3.1","0.6.32","0.3.2","0.21","1.0.4","1.1.1","0.5.1","1.6.2","4.3.1","4.3.1","0.5.5","1.6.2","1.6.11","0.1.4","1.8.5","1.43","1.3.1","0.11.4","1.0.3","2.0.3","4.3.1","0.12","1.9.0","2.0.3","1.2.0.1","2.5.1","1.0.10","1.4.2","1.1.1","2.22","2.0.3","0.4.6","1.7.4","4.3.1","3.2.1","4.3.1","1.2.3","4.3.1","0.6.3","2.5.0","0.39","1.8-4","2.3.7"]}]}]} +{"type":"list","attributes":{"names":{"type":"character","attributes":{},"value":["packages"]}},"value":[{"type":"list","attributes":{"names":{"type":"character","attributes":{},"value":["packages","version"]},"class":{"type":"character","attributes":{},"value":["data.frame"]},"row.names":{"type":"integer","attributes":{},"value":[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55]}},"value":[{"type":"character","attributes":{},"value":["backports","base","bslib","cachem","cellranger","checkmate","cli","compiler","datasets","digest","dplyr","ellipsis","evaluate","fansi","fastmap","fontawesome","generics","glue","graphics","grDevices","highr","htmltools","htmlwidgets","httpuv","jquerylib","jsonlite","knitr","later","learnr","lifecycle","magrittr","methods","mime","pillar","pkgconfig","promises","R6","Rcpp","readxl","rlang","rmarkdown","rprojroot","sass","shiny","stats","tibble","tidyselect","tools","utf8","utils","vctrs","withr","xfun","xtable","yaml"]},{"type":"character","attributes":{},"value":["1.4.1","4.2.3","0.5.0","1.0.8","1.1.0","2.2.0","3.6.1","4.2.3","4.2.3","0.6.31","1.1.2","0.3.2","0.20","1.0.4","1.1.1","0.5.1","0.1.3","1.6.2","4.2.3","4.2.3","0.10","0.5.5","1.6.2","1.6.11","0.1.4","1.8.4","1.43","1.3.1","0.11.4","1.0.3","2.0.3","4.2.3","0.12","1.9.0","2.0.3","1.2.0.1","2.5.1","1.0.10","1.4.2","1.1.0","2.22","2.0.3","0.4.6","1.7.4","4.2.3","3.2.1","1.2.0","4.2.3","1.2.3","4.2.3","0.6.1","2.5.0","0.39","1.8-4","2.3.7"]}]}]} </script> <!--/html_preserve--> </div> diff --git a/DCProject_files/figure-html/unnamed-chunk-7-1.png b/DCProject_files/figure-html/unnamed-chunk-7-1.png new file mode 100644 index 0000000000000000000000000000000000000000..71a4d952386c0c28baad02a720f29c93c3ce787a Binary files /dev/null and b/DCProject_files/figure-html/unnamed-chunk-7-1.png differ diff --git a/DCProject_files/figure-html/unnamed-chunk-8-1.png b/DCProject_files/figure-html/unnamed-chunk-8-1.png new file mode 100644 index 0000000000000000000000000000000000000000..5426a0edafb5544d3699f2c4aa936ead6e3a6cc0 Binary files /dev/null and b/DCProject_files/figure-html/unnamed-chunk-8-1.png differ