Merge branch 'main' of https://github.com/7ben18/Daten-Hackdays-BE-2023

.gitignore

@@ -186,4 +186,5 @@ poetry.toml
 # LSP config files
 pyrightconfig.json
 
-# End of https://www.toptal.com/developers/gitignore/api/jupyternotebooks,python
+# End of https://www.toptal.com/developers/gitignore/api/jupyternotebooks,python
+.DS_Store

map/app.R

@@ -74,10 +74,32 @@ sidebar <-dashboardSidebar(
   pickerInput("locInput","Serviceangebot", choices=unique(data$Serviceangebot), options = list(`actions-box` = TRUE),multiple = T)
 )
 
+js_code <- '
+function copyToClipboard(text) {
+    var textarea = document.createElement("textarea");
+    textarea.value = text;
+    document.body.appendChild(textarea);
+    textarea.select();
+    document.execCommand("copy");
+    document.body.removeChild(textarea);
+    alert("Text copied to clipboard: " + text);
+}'
+
+css <- "
+custom-cursor:hover {
+    cursor: pointer;
+}
+"
+
+
 ui <- dashboardPage(
   dashboardHeader(),
   sidebar,
   body,
+  tags$head(
+    tags$script(HTML(js_code)),
+    tags$style(HTML(css))
+  )
 )
 
 server <- function(input, output) {
@@ -113,12 +135,12 @@ server <- function(input, output) {
         popup = ~paste0(
           "<table>",
           "<tr><td style='border-bottom: 1px solid black;' colspan='2'><strong>Total:</strong> ", count, "</td></tr>",
-          "<tr><td style='border-bottom: 1px solid black;' colspan='2'>", Ort, "</td></tr>",
-          "<tr><td>", top_5_names[1, rownum], ":</td><td>", paste0(format(top_5_values[1, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
-          "<tr><td>", top_5_names[2, rownum], ":</td><td>", paste0(format(top_5_values[2, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
-          "<tr><td>", top_5_names[3, rownum], ":</td><td>", paste0(format(top_5_values[3, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
-          "<tr><td>", top_5_names[4, rownum], ":</td><td>", paste0(format(top_5_values[4, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
+          "<tr><td onclick='copyToClipboard(\"", Ort, "\")',id = 'custom-cursor'' style='border-bottom: 1px solid black;' colspan='2'>", Ort, "</td></tr>",
           "<tr><td>", top_5_names[5, rownum], ":</td><td>", paste0(format(top_5_values[5, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
+          "<tr><td>", top_5_names[4, rownum], ":</td><td>", paste0(format(top_5_values[4, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
+          "<tr><td>", top_5_names[3, rownum], ":</td><td>", paste0(format(top_5_values[3, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
+          "<tr><td>", top_5_names[2, rownum], ":</td><td>", paste0(format(top_5_values[2, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
+          "<tr><td>", top_5_names[1, rownum], ":</td><td>", paste0(format(top_5_values[1, rownum] / count * 100, digits = 2), "%"), "</td></tr>",
           "</table>"
         ),
         radius = ~log(count),

pipeline.ipynb

@@ -5,7 +5,19 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Preparing"
+    "# Pipeline\n",
+    "In diesem File findet die ganze Verarbeitung der Daten statt. Die Einstellungen sind im unteren Codeblock zu finden.\n",
+    "\n",
+    "Hier gäbe es performancetechnisch noch einiges zu optimieren, jedoch liegt das ausserhalb des Scopes dieser Arbeit."
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Preparing\n",
+    "Vorbereitung der Packages und Einstellungen"
    ]
   },
   {
@@ -37,7 +49,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Preprocessing"
+    "# Preprocessing\n",
+    "Datenverarbeitung als Grundlage für die nachfolgenden Schritte"
    ]
   },
   {
@@ -304,7 +317,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# TF-IDF"
+    "# TF-IDF\n",
+    "Berechnung der Keywords mittels TF-IDF"
    ]
   },
   {
@@ -383,7 +397,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# OneHotEncoding Top N Words"
+    "# OneHotEncoding Top N Words\n",
+    "OneHotEncodierung der wichtigsten Wörter im ganzen Datensatz"
    ]
   },
   {
@@ -451,7 +466,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Get coordinates "
+    "# Get coordinates \n",
+    "Koordinaten zu den Orten hinzufügen"
    ]
   },
   {