Refactor submissions processor so we can grab the cells data from it

.gitignore

@@ -1,8 +1,12 @@
 
-# ignore results saved to data dir:
-data/*.csv
-data/*.png
-data/*.html
+# ignore artifacts saved to results dir:
+results/*.csv
+results/*.png
+results/*.html
+
+#test/results/*
+
+
 
 
 # Byte-compiled / optimized / DLL files

README.md

@@ -71,23 +71,21 @@ python -m app.submissions_manager
 Process the starter file:
 
 ```sh
-python -m app.jobs.starter
+python -m app.starter_doc_processor
 
-# FIG_SHOW=false python -m app.jobs.starter
+# FIG_SHOW=false python -m app.starter_doc_processor
 
-# FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 python -m app.jobs.starter
+# FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 python -m app.starter_doc_processor
 
-# FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 SIMILARITY_THRESHOLD=0.75 python -m app.jobs.starter
+# FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 SIMILARITY_THRESHOLD=0.75 python -m app.starter_doc_processor
 ```
 
 Process all submission files:
 
 ```sh
-python -m app.jobs.submissions
+python -m app.submissions_processor
 
-#FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 python -m app.jobs.submissions
-
-# FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 SIMILARITY_THRESHOLD=0.75 python -m app.jobs.submissions
+#FIG_SHOW=false CHUNK_SIZE=600 CHUNK_OVERLAP=0 python -m app.submissions_processor
 ```
 
 ## Testing

app/__init__.py

@@ -3,4 +3,4 @@
 
 import os
 
-DATA_DIRPATH = os.path.join(os.path.dirname(__file__), "..", "data")
+RESULTS_DIRPATH = os.path.join(os.path.dirname(__file__), "..", "results")

app/submissions_manager.py

@@ -15,9 +15,10 @@
 
 class SubmissionsManager:
 
-    def __init__(self, dirpath=SUBMISSIONS_DIRPATH, file_ext=".IPYNB"):
+    def __init__(self, dirpath=SUBMISSIONS_DIRPATH, file_ext=".IPYNB", starter_filename=None):
         self.dirpath = dirpath
         self.file_ext = file_ext
+        self.starter_filename = starter_filename
 
     @cached_property
     def filenames(self):
@@ -34,19 +35,19 @@ def find_filepath(self, substr):
         return None
 
 
-    #@cached_property
-    #def starter_filepath(self):
-    #    return self.find_filepath("STARTER")
+    @cached_property
+    def starter_filepath(self):
+        if self.starter_filename:
+            return os.path.join(self.dirpath, self.starter_filename)
+        else:
+            return self.find_filepath("STARTER")
 
 
 
 if __name__ == "__main__":
 
 
     sm = SubmissionsManager()
-    print(sm.dirpath)
-    print(len(sm.filenames))
-
-    starter_filepath = sm.find_filepath("STARTER")
-
-    print(starter_filepath)
+    print("SUBMISSIONS DIRPATH:", sm.dirpath)
+    print("FILES:", len(sm.filenames))
+    print("STARTER DOC:", sm.starter_filepath)