Refine Wordcloud to be more universal & language agnostic

Author: JohT

cypher/Overview/Words_for_universal_Wordcloud.cypher

@@ -0,0 +1,17 @@
+// Words for universal Wordcloud
+
+MATCH (named:!Key&!Primitive&!PrimitiveType&!Void&!JavaType&!ResolvedDuplicateType&!ExternalType)
+WHERE named.name > ''
+  AND named.name <> 'package-info'
+  AND named.name <> '<init>'
+  AND named.name <> '<clinit>'
+ WITH apoc.text.replace(named.name, '(?<!^)([-_A-Z\W])', ' $1') AS words
+ WITH apoc.text.replace(words, '[-_0-9\W]', ' ')                AS words
+ WITH apoc.text.replace(words, '\s+', ' ')                      AS words
+ WITH split(toLower(trim(words)), ' ')                          AS words
+UNWIND words AS word
+  WITH word  AS word
+ WHERE size(word) > 1
+RETURN word
+//      ,count(*) as numberOfAppearances
+//ORDER BY numberOfAppearances DESC, word

jupyter/Wordcloud.ipynb

@@ -125,8 +125,8 @@
    "outputs": [],
    "source": [
     "# Query data from graph database\n",
-    "words = query_cypher_to_data_frame(\"../cypher/Overview/Words_for_Wordcloud.cypher\")\n",
-    "words.head(20)"
+    "words = query_cypher_to_data_frame(\"../cypher/Overview/Words_for_universal_Wordcloud.cypher\")\n",
+    "words.head(30)"
    ]
   },
   {
@@ -141,11 +141,22 @@
     "number_of_words=len(words.word)\n",
     "print(\"There are {} words in the dataset.\".format(number_of_words))\n",
     "\n",
+    "# Define stop words\n",
+    "stopwords = set(STOPWORDS)\n",
+    "stopwords.update(['builder', 'exception', 'abstract', 'helper', 'util', 'callback', 'factory', 'result',\n",
+    "                 'handler', 'type', 'module', 'name', 'parameter', 'lambda', 'access', 'create', 'message', \n",
+    "                 'ts', 'js', 'tsx', 'jsx', 'css', 'htm', 'html', 'props', 'use', 'id', 'ref', 'hook', 'event', \n",
+    "                 'span', 'data', 'context', 'form', 'get', 'set', 'object', 'null', 'new'])\n",
+    "\n",
     "if number_of_words > 0:\n",
-    "    # Define stop words\n",
-    "    stopwords = set(STOPWORDS)\n",
-    "    stopwords.update(['builder', 'exception', 'abstract', 'helper', 'util', 'callback', 'factory', 'handler', 'repository', 'result'])\n",
-    "    wordcloud = WordCloud(stopwords=stopwords, background_color='white', colormap='viridis').generate(text)\n",
+    "    wordcloud = WordCloud(\n",
+    "        width=800, \n",
+    "        height=400,\n",
+    "        max_words=400, \n",
+    "        stopwords=stopwords,\n",
+    "        background_color='white', \n",
+    "        colormap='viridis'\n",
+    "    ).generate(text)\n",
     "\n",
     "    # Plot the word cloud\n",
     "    plot.figure(figsize=(15,10))\n",