aggr.py, cluster.py: added assertions and todos

mossutils/aggr.py

+import os
 import logging
 import csv
 import jinja2
@@ -13,6 +14,12 @@ def main(
 
   logutils.configure_level_and_format()
 
+  if not os.path.isfile(clusters_summary_csv_file):
+    raise RuntimeError("Cluster summary CSV file {} doesn't exist. Should have been created by mu-cluster.".format(clusters_summary_csv_file))
+
+  if not os.path.isfile(cx_course_students_csv_file):
+    raise RuntimeError("Code Expert course data CSV file {} doesn't exist. Download it from Code Expert as follows: My Courses -> Students -> Export to CSV.".format(cx_course_students_csv_file))
+
   clusters_csv: pd.DataFrame = pd.read_csv(clusters_summary_csv_file)
   
   # Read CX course data, reduce to relevant columns, truncate TotalScore (which are floats), set index column
@@ -23,6 +30,11 @@ def main(
   course_csv.set_index("Legi", inplace=True)
   ## TODO: Remove staff from course_csv
 
+  ## TODO: Make eDoz files configurable
+  ## TODO: Make eDoz files optional
+  ## TODO: Could integrate eDoz data "Leistungskontrollen" to get information whether
+  ##       or not a student is a repeater  
+
   # Analogous for eDoz course data
   relevant_edoz_columns = ["Nummer", "Departement"]
   edoz1_csv: pd.DataFrame = pd.read_csv("edoz-252083200L.csv", sep="\t")
@@ -39,11 +51,6 @@ def main(
   # print(edoz2_csv.index)
   # print("edoz2_csv.index.is_unique = {}".format(edoz2_csv.index.is_unique))
 
-
-  ## TODO: Could integrate eDoz data "Leistungskontrollen" to get information whether
-  ##       or not a student is a repeater
-
-
   # Vertically concat eDoz data. Since students may be enrolled into multiple
   # courses, duplicated rows are afterwards dropped.
   edoz_csv: pd.DataFrame = pd.concat([edoz1_csv, edoz2_csv])

mossutils/cluster.py

@@ -10,6 +10,13 @@ import networkx as nx
 from dataclass_csv import DataclassReader
 from .utils import logging as logutils
 
+## TODO: cluster.py could create a first, less detailed version of the 
+##       clusters.html report, by extracting the strictly necessary information
+##       (student name and e-mail address) from the details.json file located
+##       in the CX export. This information would already be enough to generate
+##       e-mails afterwards.
+##       aggr.py would then be optional, if a more detailed cluster report is desired.
+
 DEFAULT_RESULTS_CSV_FILE="moss-report.csv"
 DEFAULT_TOTAL_GRAPH_DOT_FILE="moss-report.dot"
 DEFAULT_CLUSTERS_DOT_FILE="clusters.dot"