cluster.py, aggr.py: different cluster CSV files, one with matches, individual ones with students

mossutils/aggr.py

@@ -5,22 +5,26 @@ import jinja2
 import pandas as pd
 from .utils import logging as logutils
 
-DEFAULT_CLUSTERS_SUMMARY_CSV_FILE="clusters.csv"
+DEFAULT_CLUSTER_FILES_DIR="_clusters"
+DEFAULT_CLUSTERS_MATCHES_CSV_FILE="clusters-matches.csv"
+DEFAULT_CLUSTER_STUDENTS_CSV_FILE_PATTERN="cluster-students-{}.csv"
 DEFAULT_CX_COURSE_STUDENTS_CSV_FILE="cx_students.csv"
 
 def main(
-    clusters_summary_csv_file=DEFAULT_CLUSTERS_SUMMARY_CSV_FILE,
+    cluster_files_dir=DEFAULT_CLUSTER_FILES_DIR,
+    clusters_matches_csv_file=DEFAULT_CLUSTERS_MATCHES_CSV_FILE,
+    cluster_students_csv_file_pattern=DEFAULT_CLUSTER_STUDENTS_CSV_FILE_PATTERN,
     cx_course_students_csv_file=DEFAULT_CX_COURSE_STUDENTS_CSV_FILE):
 
   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(clusters_matches_csv_file):
+    raise RuntimeError("CSV file {} with matches per clusters doesn't exist. Should have been created by mu-cluster.".format(clusters_matches_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)
+  clusters_csv: pd.DataFrame = pd.read_csv(clusters_matches_csv_file)
   
   # Read CX course data, reduce to relevant columns, truncate TotalScore (which are floats), set index column
   relevant_course_columns = ["Legi", "Lastname", "Firstname", "Email", "Gender", "TotalScore"]
@@ -86,7 +90,7 @@ def main(
   jinja2_rows = []
 
   cluster_groups: pd.DataFrameGroupBy = clusters_csv.groupby("cluster_id")
-  for _, cluster in cluster_groups: # cluster: pd.DataFrame
+  for cluster_id, cluster in cluster_groups: # cluster: pd.DataFrame
     # print("-"*60)
     # Get all ids (= legis) participating in a cluster
     ids_values: numpy.ndarray = pd.concat([cluster["id1"], cluster["id2"]]).unique()
@@ -115,9 +119,17 @@ def main(
 
     cluster_rows: pd.DataFrame = cluster_course_rows.join(edoz_csv)
 
+    students_per_clusters_file = os.path.join(
+        cluster_files_dir, 
+        cluster_students_csv_file_pattern.format(cluster_id))
+    
+    logging.info("Writing students per clusters to file {}".format(students_per_clusters_file))
+    cluster_rows.to_csv(students_per_clusters_file)
+
     # print("========== cluster_rows")
     # print(cluster_rows.shape)
     # print(cluster_rows)
+    # print(name)
 
     # print(cluster)
     # print(cluster["svg_file"].iat[0])

mossutils/cluster.py

@@ -27,7 +27,7 @@ DEFAULT_CLUSTER_FILE_PATTERN="cluster-{}.{}"
 DEFAULT_THRESHOLD_PERCENTAGE=90
 DEFAULT_THRESHOLD_LINES=50
 DEFAULT_CREATE_SVG_FILES=True
-DEFAULT_SUMMARY_CSV_FILE="clusters.csv"
+DEFAULT_CLUSTERS_MATCHES_CSV_FILE="clusters-matches.csv"
 
 @dataclasses.dataclass
 class MossResult:
@@ -184,11 +184,11 @@ def create_clusters(graph, cluster_file_pattern, create_svg_files):
 
   return cluster_entries
 
-def create_summary_csv_file(cluster_entries, summary_csv_file):
-  logging.info("Writing summary file {}".format(summary_csv_file))
+def create_clusters_matches_csv_file(cluster_entries, clusters_matches_csv_file):
+  logging.info("Writing file with matches per clusters {}".format(clusters_matches_csv_file))
 
   if cluster_entries:
-    with open(summary_csv_file, "w", newline="") as csv_fh:
+    with open(clusters_matches_csv_file, "w", newline="") as csv_fh:
       csv_writer = csv.writer(csv_fh)
 
       csv_writer.writerow(cluster_entries[0].fields_flattened())
@@ -204,7 +204,7 @@ def main(
     percentage_threshold=DEFAULT_THRESHOLD_PERCENTAGE,
     lines_threshold=DEFAULT_THRESHOLD_LINES,
     create_svg_files=DEFAULT_CREATE_SVG_FILES,
-    summary_csv_file=DEFAULT_SUMMARY_CSV_FILE):
+    clusters_matches_csv_file=DEFAULT_CLUSTERS_MATCHES_CSV_FILE):
 
   logutils.configure_level_and_format()
 
@@ -222,7 +222,7 @@ def main(
       os.path.join(cluster_files_dir, cluster_file_pattern),
       create_svg_files)
 
-  create_summary_csv_file(cluster_entries, summary_csv_file)
+  create_clusters_matches_csv_file(cluster_entries, clusters_matches_csv_file)
 
 
 if __name__ == "__main__":