slides online

cqp.Rmd

@@ -1,6 +1,6 @@
 ---
-title: "Cooking with GermaParl"
-date: "2023-06-01"
+title: "Cooking with GermaParl: Spicy Queries"
+date: "2023-11-23"
 output: 
   xaringan::moon_reader:
     css: ["./css/default.css", "./css/metropolis.css", "./css/robot-fonts.css", './css/polminify.css']
@@ -14,11 +14,14 @@ editor_options:
 library(DiagrammeR)
 library(xml2)
 library(kableExtra)
-library(polmineR)
 library(dplyr)
 library(purrr)
 ```
 
+```{r load_polmineR, echo = FALSE, message = FALSE, warning = FALSE}
+library(polmineR)
+```
+
 # Data formats and structures
 
 * TEI-inspired XML: <br/>https://github.com/PolMine/GermaParlTEI
@@ -30,7 +33,7 @@ See the [landing page at Zenodo](https://zenodo.org/record/7949074) for further
 
 ---
 
-# Data Preparation Workflow
+# GermaParl: Data Preparation Workflow
 
 ```{r make_diagrammeR", echo = FALSE, fig.width = 11}
 grViz("
@@ -68,7 +71,7 @@ PARSE -> XML -> ENRICH-> XML2 -> ANNOTATE -> VRT -> ENCODE -> CWB
 # XML/TEI
 
 * structural annotation (metadata on document and speaker level)
-* quasi standardization, inspired by the standards of the Text Encoding Initiative
+* quasi standardization, inspired by the standards of the Text Encoding Initiative (TEI)
 
 ```{r read_xml, echo = FALSE}
 xml2::read_xml(x = "~/Lab/github/GermaParlTEI/01/BT_01_003.xml") %>%
@@ -252,6 +255,7 @@ corpus("GERMAPARL2") |>
 ```{r, eval = FALSE}
 x <- corpus("GERMAPARL2") %>% 
   subset(ne_type = "PERSON") %>% 
+  split(s_attribute = "ne_type") %>% 
   get_token_stream(p_attribute = "word") %>% 
   table()
 ```
@@ -271,16 +275,16 @@ corpus("GERMAPARL2") %>%
   dispersion(query = look_up, cqp = TRUE, s_attribute = "protocol_date") %>%
   as_tibble() %>%
   mutate(date = as.Date(protocol_date)) %>%
-  mutate(month = floor_date(date, unit = "quarter")) %>%
-  filter(!is.na(month)) %>%
-  select(count, month) %>%
-  group_by(month) %>%
+  mutate(year = floor_date(date, unit = "year")) %>%
+  filter(!is.na(year)) %>%
+  select(count, year) %>%
+  group_by(year) %>%
   summarise(sum = sum(count)) %>%
-  as.xts(x = .$sum, order.by = .$month) %>%
+  as.xts(x = .$sum, order.by = .$year) %>%
   plot(
     main = "'FDGO' in Bundestag Plenary Debates (N/quarter)",
-    xlab = "total per quarter",
-    ylim = c(0, 40), type = "h", col = "darkblue", main.timespan = FALSE
+    xlab = "total per year",
+    ylim = c(0, 100), col = "darkblue", main.timespan = FALSE
   )
 ```
 

docs/cqp_files/DiagrammeR-styles-0.2/styles.css

@@ -0,0 +1,14 @@
+.DiagrammeR,.grViz pre {
+  white-space: pre-wrap;       /* CSS 3 */
+  white-space: -moz-pre-wrap;  /* Mozilla, since 1999 */
+  white-space: -pre-wrap;      /* Opera 4-6 */
+  white-space: -o-pre-wrap;    /* Opera 7 */
+  word-wrap: break-word;       /* Internet Explorer 5.5+ */
+}
+
+.DiagrammeR g .label {
+  font-family: Helvetica;
+  font-size: 14px;
+  color: #333333;
+}
+

docs/cqp_files/grViz-binding-1.0.10/grViz.js

@@ -0,0 +1,91 @@
+HTMLWidgets.widget({
+
+  name: 'grViz',
+
+  type: 'output',
+
+  initialize: function(el, width, height) {
+
+    return {
+      // TODO: add instance fields as required
+    };
+  },
+
+  renderValue: function(el, x, instance) {
+    //  Use this to sort of make our diagram responsive
+    //  or at a minimum fit within the bounds set by htmlwidgets
+    //  for the parent container
+    function makeResponsive(el){
+       var svg = el.getElementsByTagName("svg")[0];
+       if (svg) {
+        if (svg.width) {svg.removeAttribute("width")}
+        if (svg.height) {svg.removeAttribute("height")}
+        svg.style.width = "100%";
+        svg.style.height = "100%";
+       }
+    }
+
+    if (x.diagram !== "") {
+
+      if (typeof x.config === "undefined"){
+        x.config = {};
+        x.config.engine = "dot";
+        x.config.options = {};
+      }
+
+      try {
+
+        el.innerHTML = Viz(x.diagram, format="svg", engine=x.config.engine, options=x.config.options);
+
+        makeResponsive(el);
+
+        if (HTMLWidgets.shinyMode) {
+          // Get widget id
+          var id = el.id;
+
+          $("#" + id + " .node").click(function(e) {
+            // Get node id
+            var nodeid = e.currentTarget.id;
+            // Get node text object and make an array
+            var node_texts = $("#" + id + " #" + nodeid + " text");
+            //var node_path = $("#" + nodeid + " path")[0];
+            var text_array = node_texts.map(function() {return $(this).text(); }).toArray();
+            // Build return object *obj* with node-id, node text values and node fill
+            var obj = {
+              id: nodeid,
+              //fill: node_path.attributes.fill.nodeValue,
+              //outerHMTL: node_path.outerHTML,
+              nodeValues: text_array
+            };
+            // Send *obj* to Shiny's inputs (input$[id]+_click  e.g.: input$vtree_click))
+            Shiny.setInputValue(id + "_click", obj, {priority: "event"});
+          });
+        }
+
+        // set up a container for tasks to perform after completion
+        //  one example would be add callbacks for event handling
+        //  styling
+        if (typeof x.tasks !== "undefined") {
+          if ((typeof x.tasks.length === "undefined") ||
+           (typeof x.tasks === "function")) {
+             // handle a function not enclosed in array
+             // should be able to remove once using jsonlite
+             x.tasks = [x.tasks];
+          }
+          x.tasks.map(function(t){
+            // for each tasks add it to the mermaid.tasks with el
+            t.call(el);
+          });
+        }
+      } catch(e){
+        var p = document.createElement("pre");
+        p.innerText = e;
+        el.appendChild(p);
+      }
+    }
+
+  },
+
+  resize: function(el, width, height, instance) {
+  }
+});

docs/cqp_files/header-attrs-2.22/header-attrs.js

@@ -0,0 +1,12 @@
+// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
+// be compatible with the behavior of Pandoc < 2.8).
+document.addEventListener('DOMContentLoaded', function(e) {
+  var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
+  var i, h, a;
+  for (i = 0; i < hs.length; i++) {
+    h = hs[i];
+    if (!/^h[1-6]$/i.test(h.tagName)) continue;  // it should be a header h1-h6
+    a = h.attributes;
+    while (a.length > 0) h.removeAttribute(a[0].name);
+  }
+});

docs/cqp_files/header-attrs-2.25/header-attrs.js

@@ -0,0 +1,12 @@
+// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
+// be compatible with the behavior of Pandoc < 2.8).
+document.addEventListener('DOMContentLoaded', function(e) {
+  var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
+  var i, h, a;
+  for (i = 0; i < hs.length; i++) {
+    h = hs[i];
+    if (!/^h[1-6]$/i.test(h.tagName)) continue;  // it should be a header h1-h6
+    a = h.attributes;
+    while (a.length > 0) h.removeAttribute(a[0].name);
+  }
+});