v0.2.21

yh202109 · Jul 25, 2024 · 1612fa9 · 1612fa9
1 parent b7dc874
commit 1612fa9
Show file tree

Hide file tree

Showing 2 changed files with 38 additions and 8 deletions.
diff --git a/docs/std_cdisc.ipynb b/docs/std_cdisc.ipynb
@@ -226,12 +226,13 @@
             "cell_type": "markdown",
             "metadata": {},
             "source": [
-                "To get the newest protocol ct package information:\n",
+                "To get the newest Protocol CT package in DataFrame format:\n",
                 "\n",
                 "```python\n",
-                "title = 'Protocol'\n",
-                "cl = accessLib(\"/Users/yh2020/cdisc.txt\")\n",
+                "from mtbp3.stdcdisc.lib import accessLib\n",
+                "cl = accessLib(\"/user/home/name/cdisc.txt\")\n",
                 "cl.get_ct_list()\n",
+                "title = 'Protocol'\n",
                 "cl.get_ct_package(title)\n",
                 "cl.get_ct_codelists_df(title)\n",
                 "print(cl.ct_package[title]['ct_df'][['conceptId', 'name', 'preferredTerm']].head())\n",
@@ -249,6 +250,31 @@
                 "```"
             ]
         },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "To get the newest Glossary CT package in DataFrame format:\n",
+                "\n",
+                "```python\n",
+                "title = 'Glossary'\n",
+                "cl.get_ct_package(title)\n",
+                "cl.get_ct_codelists_df(title)\n",
+                "print(cl.ct_package[title]['ct_df'][['conceptId', 'name', 'group', 'preferredTerm', 'definition']].head())\n",
+                "```\n",
+                "\n",
+                "Output:\n",
+                "\n",
+                "```\n",
+                "  conceptId            name           group                  preferredTerm                                         definition\n",
+                "0    C67497  CDISC Glossary                     CDISC Glossary Terminology  The terminology of the Clinical Data Interchan...\n",
+                "1    C80442                  CDISC Glossary  Premarket Device Notification  510(k). Premarket Notification (PMN) required ...\n",
+                "2    C42610                  CDISC Glossary                   Abbreviation  A set of letters that are drawn from a word or...\n",
+                "3    C71733                  CDISC Glossary          Biological Absorption  The process by which medications reach the blo...\n",
+                "4   C156638                  CDISC Glossary           Accelerated Approval  Regulatory mechanism by which new drugs meant ...\n",
+                "```"
+            ]
+        },
         {
             "cell_type": "markdown",
             "metadata": {},

diff --git a/mtbp3/stdcdisc/lib.py b/mtbp3/stdcdisc/lib.py
@@ -178,21 +178,25 @@ def get_ct_codelists_df(self, title="", max_level = 3):
             remaining_list_label = []
             for index, item in enumerate(codelists):
                 if isinstance(item, dict):
-                    if 'conceptId' in item.keys() and 'name' not in item.keys():
-                        item['name']=""
+                    if 'group' not in item.keys():
+                        item['group']=""
                     if 'synonyms' not in item.keys():
                         item['synonyms']=[]
                     if 'terms' in item.keys():
+                        for i in range(len(item['terms'])):
+                            if 'name' not in item['terms'][i].keys():
+                                item['terms'][i]['name'] = ""
+                                item['terms'][i]['group'] = item['name']
                         nterms = len(item['terms'])
                         remaining_list.extend(item['terms'])
                         remaining_list_label.extend([codelists_label[index]+'.pseudo'+item['conceptId']]*nterms)
                     else:
                         nterms = 0
-                    data.append([codelists_label[index], level, item['conceptId'], item['name'], item['preferredTerm'], item['submissionValue'], '; '.join(item['synonyms']), item['definition'], nterms])
+                    data.append([codelists_label[index], level, item['conceptId'], item['name'], item['group'], item['preferredTerm'], item['submissionValue'], '; '.join(item['synonyms']), item['definition'], nterms])
                 else:
                     not_processed.append(item)
 
-        df = pd.DataFrame(data, columns=['label', 'level', 'conceptId', 'name', 'preferredTerm', 'submissionValue', 'synonyms', 'definition', 'terms'])
+        df = pd.DataFrame(data, columns=['label', 'level', 'conceptId', 'name', 'group', 'preferredTerm', 'submissionValue', 'synonyms', 'definition', 'terms'])
         label = df[['label', 'preferredTerm']]
         df = df.drop('label', axis=1)
 
@@ -202,4 +206,4 @@ def get_ct_codelists_df(self, title="", max_level = 3):
         return 
 
 if __name__ == "__main__":
-    pass
+    pass