updating with new approach to modeling the phabricator tasks

.sh_history

@@ -20,3 +20,12 @@ rm -r -f .local
 cd rfc_df <- read.csv("/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/0220_ve_rfcs_text.csv")
 cd /gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/
 ls
+rm wide-testing_0312_extensions_ve_weekly_commit_count_data.csv
+rm wide-testing_0312_mediawiki_core_weekly_commit_count_data.csv
+ls
+rm en-testing_0312_extensions_ve_weekly_commit_count_data.csv 
+rm en-testing_0312_mediawiki_core_weekly_commit_count_data.csv 
+l
+ls
+rm en-testing_0312_mediawiki_core_weekly_commit_count_data.csv
+ls

mgaughan-rstudio-server_24810962.out

@@ -15,3 +15,4 @@ When done using RStudio Server, terminate the job by:
 2. Issue the following command on the login node:
 
       scancel -f 24810962
+slurmstepd: error: *** JOB 24810962 ON n3439 CANCELLED AT 2025-03-12T21:58:24 DUE TO TIME LIMIT ***

text_analysis/case1/.ipynb_checkpoints/ve_dependency-checkpoint.ipynb

@@ -483,7 +483,7 @@
    "source": [
     "def extract_dependency_tree(sentence):\n",
     "    doc = nlp(sentence)\n",
-    "    return [(token.text,  token.lemma_, token.dep_, token.head.text, token.ancestors, token.subtree, token.children) for token in doc]"
+    "    return [(token.text, token.dep_, token.head.text, token.ancestors, token.subtree, token.children) for token in doc]"
    ]
   },
   {

text_analysis/case1/coref_resolution.ipynb

@@ -211,7 +211,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.9.21"
   }
  },
  "nbformat": 4,

text_analysis/case1/ve_dependency.ipynb

@@ -1811,7 +1811,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.9.21"
   }
  },
  "nbformat": 4,