From e3e13b4b56bcce9f40ab7ff8d65327d89427fa99 Mon Sep 17 00:00:00 2001
From: Malte Schwerhoff <malte.schwerhoff@inf.ethz.ch>
Date: Sun, 8 Nov 2020 11:38:22 +0100
Subject: [PATCH] aggr.py: added CLI option for specifying eDoz CSV files

---
 mossutils/aggr.py | 67 +++++++++++++++++++++++++++++++++++------------
 1 file changed, 50 insertions(+), 17 deletions(-)

diff --git a/mossutils/aggr.py b/mossutils/aggr.py
index 854ab63..2fda8a9 100644
--- a/mossutils/aggr.py
+++ b/mossutils/aggr.py
@@ -2,6 +2,7 @@ import os
 import logging
 import csv
 import jinja2
+import argparse
 import pandas as pd
 from .utils import logging as logutils
 
@@ -12,7 +13,8 @@ DEFAULT_CLUSTER_STUDENTS_CSV_FILE_PATTERN="cluster-students-{}.csv"
 DEFAULT_CX_COURSE_STUDENTS_CSV_FILE="cx_students.csv"
 DEFAULT_JINJA_CLUSTER_TEMPLATE_FILE="./_static/clusters.html.jinja"
 
-def main(
+def aggregate(
+    edoz_exports, # List of argparse.FileType objects
     cluster_files_dir=DEFAULT_CLUSTER_FILES_DIR,
     clusters_matches_csv_file=DEFAULT_CLUSTERS_MATCHES_CSV_FILE,
     clusters_students_csv_file=DEFAULT_CLUSTERS_STUDENTS_CSV_FILE,
@@ -43,25 +45,21 @@ def main(
   ## 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")
-  edoz1_csv = edoz1_csv[relevant_edoz_columns]
-  edoz1_csv.rename(columns={"Nummer": "Legi"}, inplace=True)
-  edoz1_csv.set_index("Legi", inplace=True)
-  # print(edoz1_csv)
-  # print("edoz1_csv.index.is_unique = {}".format(edoz1_csv.index.is_unique))
-  
-  edoz2_csv: pd.DataFrame = pd.read_csv("edoz-252084800L.csv", sep="\t")
-  edoz2_csv = edoz2_csv[relevant_edoz_columns]
-  edoz2_csv.rename(columns={"Nummer": "Legi"}, inplace=True)
-  edoz2_csv.set_index("Legi", inplace=True)
-  # print(edoz2_csv.index)
-  # print("edoz2_csv.index.is_unique = {}".format(edoz2_csv.index.is_unique))
+  individual_edoz_csv_frames = []
+  for csvfile in edoz_exports:
+    relevant_edoz_columns = ["Nummer", "Departement"]
+    edoz_csv: pd.DataFrame = pd.read_csv(csvfile, sep="\t")
+    edoz_csv = edoz_csv[relevant_edoz_columns]
+    edoz_csv.rename(columns={"Nummer": "Legi"}, inplace=True)
+    edoz_csv.set_index("Legi", inplace=True)    
+    # print(edoz1_csv)
+    # print("edoz1_csv.index.is_unique = {}".format(edoz1_csv.index.is_unique))    
+
+    individual_edoz_csv_frames.append(edoz_csv)
 
   # 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])
+  edoz_csv: pd.DataFrame = pd.concat(individual_edoz_csv_frames)
   # print("========== edoz_csv [initial]")
   # print(edoz_csv.shape)
   # print(edoz_csv)
@@ -215,5 +213,40 @@ def main(
   ).dump("clusters.html")
 
 
+def configure_cli_parser(parser):
+  parser.add_argument(
+    "-e", "--edoz-exports",
+    type=argparse.FileType('r'),
+    nargs="+",
+    help="eDoz student list exports (CSV)",
+    required=True)
+
+  logutils.add_loglevel_argument(parser)
+
+
+def main(
+    cluster_files_dir=DEFAULT_CLUSTER_FILES_DIR,
+    clusters_matches_csv_file=DEFAULT_CLUSTERS_MATCHES_CSV_FILE,
+    clusters_students_csv_file=DEFAULT_CLUSTERS_STUDENTS_CSV_FILE,
+    cluster_students_csv_file_pattern=DEFAULT_CLUSTER_STUDENTS_CSV_FILE_PATTERN,
+    cx_course_students_csv_file=DEFAULT_CX_COURSE_STUDENTS_CSV_FILE,
+    jinja_cluster_template_file=DEFAULT_JINJA_CLUSTER_TEMPLATE_FILE):
+
+  parser = argparse.ArgumentParser()
+  configure_cli_parser(parser)
+  args = parser.parse_args()
+
+  logutils.configure_level_and_format(args.log_level)    
+
+  aggregate(
+    args.edoz_exports,
+    cluster_files_dir,
+    clusters_matches_csv_file,
+    clusters_students_csv_file,
+    cluster_students_csv_file_pattern,
+    cx_course_students_csv_file,
+    jinja_cluster_template_file)
+
+
 if __name__ == "__main__":
   main()
-- 
GitLab