aggr.py: include more detailed statistics in generated clusters.html

mossutils/aggr.py

@@ -4,6 +4,7 @@ import csv
 import jinja2
 import argparse
 import pandas as pd
+from dataclasses import dataclass
 from .utils import logging as logutils
 
 DEFAULT_CLUSTER_FILES_DIR="_clusters"
@@ -12,6 +13,16 @@ DEFAULT_CLUSTERS_STUDENTS_CSV_FILE="clusters-students.csv"
 DEFAULT_CLUSTER_STUDENTS_CSV_FILE_PATTERN="cluster-students-{}.csv"
 DEFAULT_JINJA_CLUSTER_TEMPLATE_FILE="./_static/clusters.html.jinja"
 
+@dataclass
+class RelativeDataPoint:
+  name: str # Data point's name
+  part: float # Relevant elements (i.e. numerator)
+  base: float # All elements (i.e. denominator)
+
+  @property
+  def percentage(self, round_to_digits=1):
+    return round(self.part * 100 / self.base, 1)
+
 ## TODO: Refactor function into separate ones
 def aggregate(
     edoz_exports, # List of argparse.FileType objects
@@ -174,11 +185,16 @@ def aggregate(
 
   # print(department_counts)
 
-  department_percentage = {}
+  department_data = []
   for dep in department_counts:
-    department_percentage[dep] = department_counts[dep] / edoz_departements[dep] * 100
+    data = RelativeDataPoint(
+      dep, 
+      department_counts[dep], 
+      edoz_departements[dep])
+    
+    department_data.append(data)
   
-  # print(department_percentage)
+  # print(department_data)
 
 
   gender_counts = {}
@@ -191,17 +207,19 @@ def aggregate(
 
   # print(gender_counts)
 
-  gender_percentage = {}
+  gender_data = []
   for dep in gender_counts:
-    gender_percentage[dep] = gender_counts[dep] / course_genders[dep] * 100
+    data = RelativeDataPoint(
+      dep, 
+      gender_counts[dep],
+      course_genders[dep])
     
-  # print(gender_percentage)
+    gender_data.append(data)    
   
-  percentages = {**department_percentage, **gender_percentage}
-  for key, value in percentages.items():
-    percentages[key] = round(value, 1)
+  # print(gender_data)
 
-  # print(percentages)
+  datapoints = department_data + gender_data
+  # print(datapoints)
 
 
   template.stream(
@@ -210,21 +228,21 @@ def aggregate(
     edoz_count=edoz_csv.shape[0],
     course_count=course_csv.shape[0],
     plagiarist_count=plagiarist_count,
-    percentages=percentages
+    datapoints=datapoints
   ).dump("clusters.html")
 
 
 def configure_cli_parser(parser):
   parser.add_argument(
     "-ee", "--edoz-exports",
-    type=argparse.FileType('r'),
+    type=argparse.FileType("r", encoding="utf-8"),
     nargs="+",
     help="eDoz student list exports (CSV)",
     required=True)
 
   parser.add_argument(
     "-ce", "--code-expert-export",
-    type=argparse.FileType('r'),
+    type=argparse.FileType("r", encoding="utf-8"),
     help="Code Expert student data export (CSV)",
     required=True)
 

mossutils/data/clusters.html.jinja

@@ -15,8 +15,8 @@
     No. of eDoz students: {{ edoz_count }} <br>
     No. of CX students: {{ course_count }} <span style="color: #999999">(may include staff)</span><br>
     No. of plagiarists: {{ plagiarist_count }} <br>
-    {% for key, value in percentages.items() %}
-      {{ key }}: {{ value }}% <br>
+    {% for data in datapoints %}
+      {{ data.name }}: {{ data.percentage }}% ({{ data.part }}/{{ data.base }}) <br>
     {% endfor %}
     <table style="border-spacing: 1em 2em">
       <thead>