aggr.py 6.01 KB
Newer Older
1 2
import logging
import csv
3
import jinja2
4 5 6 7 8 9 10 11 12 13
import pandas as pd
from .utils import logging as logutils

DEFAULT_CLUSTERS_SUMMARY_CSV_FILE="clusters.csv"
DEFAULT_CX_COURSE_STUDENTS_CSV_FILE="cx_students.csv"

def main(
    clusters_summary_csv_file=DEFAULT_CLUSTERS_SUMMARY_CSV_FILE,
    cx_course_students_csv_file=DEFAULT_CX_COURSE_STUDENTS_CSV_FILE):

scmalte's avatar
scmalte committed
14 15
  logutils.configure_level_and_format()

16 17
  clusters_csv: pd.DataFrame = pd.read_csv(clusters_summary_csv_file)
  
scmalte's avatar
scmalte committed
18
  # Read CX course data, reduce to relevant columns, truncate TotalScore (which are floats), set index column
19
  relevant_course_columns = ["Legi", "Lastname", "Firstname", "Email", "Gender", "TotalScore"]
20
  course_csv: pd.DataFrame = pd.read_csv(cx_course_students_csv_file)
21
  course_csv = course_csv[relevant_course_columns]
scmalte's avatar
scmalte committed
22
  course_csv["TotalScore"] = course_csv["TotalScore"].round(0)
23
  course_csv.set_index("Legi", inplace=True)
24
  ## TODO: Remove staff from course_csv
25

26
  # Analogous for eDoz course data
27
  relevant_edoz_columns = ["Nummer", "Departement"]
28
  edoz1_csv: pd.DataFrame = pd.read_csv("edoz-252083200L.csv", sep="\t")
29
  edoz1_csv = edoz1_csv[relevant_edoz_columns]
30 31 32 33 34 35
  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")
36
  edoz2_csv = edoz2_csv[relevant_edoz_columns]
37 38 39 40
  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))
41

42 43 44 45 46

  ## TODO: Could integrate eDoz data "Leistungskontrollen" to get information whether
  ##       or not a student is a repeater


47 48 49
  # 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])
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
  # print("========== edoz_csv [initial]")
  # print(edoz_csv.shape)
  # print(edoz_csv)
  # edoz_csv.drop_duplicates(inplace=True) # Not applicable here since indices are ignored
  edoz_csv = edoz_csv.loc[~edoz_csv.index.duplicated(keep='first')] # Get rows not in the set of duplicated indices
  # print("========== edoz_csv [unique]")
  # print(edoz_csv.shape)
  # print(edoz_csv)


  ## TODO: Add "Departement" column to course_csv, by joining with edoz_csv


  ### Aggregate course overview statistics
  edoz_departements: pd.DataFrame = edoz_csv["Departement"].value_counts()
  course_genders: pd.DataFrame = course_csv["Gender"].value_counts()

67 68 69 70
  assert edoz_csv.index.is_unique, "Expected unique indices (= legis) in edoz_csv"
  # # Show rows with non-unique indices (https://stackoverflow.com/questions/20199129) 
  # print(edoz_csv[edoz_csv.index.duplicated(keep=False)])
  
71 72 73

  jinja2_file_loader = jinja2.FileSystemLoader(".")
  jinja2_env = jinja2.Environment(loader=jinja2_file_loader)
74
  template = jinja2_env.get_template("./_static/clusters.html.jinja")
75 76 77 78 79 80

  # output = template.render(colors=colors)
  # print(output)

  jinja2_rows = []

81 82
  cluster_groups: pd.DataFrameGroupBy = clusters_csv.groupby("cluster_id")
  for _, cluster in cluster_groups: # cluster: pd.DataFrame
83
    # print("-"*60)
84 85
    # Get all ids (= legis) participating in a cluster
    ids_values: numpy.ndarray = pd.concat([cluster["id1"], cluster["id2"]]).unique()
86
    
87
    # ids = pd.Series(ids_values, name="Legi", index=ids_values)
88 89
    # # Performs an inner join on the keys; here: legis
    # # https://pandas.pydata.org/pandas-docs/stable/getting_started/comparison/comparison_with_sql.html#compare-with-sql-join
90
    # join = pd.merge(ids, course_csv, left_index=True, right_index=True)
91

92
    cluster_course_rows: pd.DataFrame = course_csv.loc[ids_values]
93

94 95 96 97 98 99 100 101 102 103 104 105 106
    # print("========== cluster ")
    # print(cluster.shape)
    # print(cluster)
    # print("========== ids_values ")
    # print(ids_values.shape)
    # print(ids_values)
    # print("========== course_csv")
    # print(course_csv)
    # print("========== cluster_course_rows")
    # print(cluster_course_rows.shape)
    # print(cluster_course_rows)
    # print("========== edoz_csv")
    # print(edoz_csv.shape)
107 108
    # print(edoz_csv)

109 110 111 112 113 114 115 116 117 118 119
    cluster_rows: pd.DataFrame = cluster_course_rows.join(edoz_csv)

    # print("========== cluster_rows")
    # print(cluster_rows.shape)
    # print(cluster_rows)

    # print(cluster)
    # print(cluster["svg_file"].iat[0])

    jinja2_rows.append((cluster, cluster_rows))

scmalte's avatar
scmalte committed
120 121 122 123 124 125 126
  
  ## TODO: Support sorting clusters by max (or average) involved percentage


  plagiarist_count = 0
  for (_, cluster_rows) in jinja2_rows:
    plagiarist_count += cluster_rows.shape[0]
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167


  department_counts = {}
  for (cluster, cluster_rows) in jinja2_rows:
    for index, value in cluster_rows["Departement"].value_counts().iteritems():
      if index in department_counts:
        department_counts[index] += value
      else:
        department_counts[index] = value

  # print(department_counts)

  department_percentage = {}
  for dep in department_counts:
    department_percentage[dep] = department_counts[dep] / edoz_departements[dep] * 100
  
  # print(department_percentage)


  gender_counts = {}
  for (cluster, cluster_rows) in jinja2_rows:
    for index, value in cluster_rows["Gender"].value_counts().iteritems():
      if index in gender_counts:
        gender_counts[index] += value
      else:
        gender_counts[index] = value

  # print(gender_counts)

  gender_percentage = {}
  for dep in gender_counts:
    gender_percentage[dep] = gender_counts[dep] / course_genders[dep] * 100
  
  # print(gender_percentage)

  percentages = {**department_percentage, **gender_percentage}
  for key, value in percentages.items():
    percentages[key] = round(value, 1)

  # print(percentages)

168

169 170 171 172 173
  template.stream(
    title="Clusters",
    clusters=jinja2_rows,
    edoz_count=edoz_csv.shape[0],
    course_count=course_csv.shape[0],
scmalte's avatar
scmalte committed
174
    plagiarist_count=plagiarist_count,
175 176
    percentages=percentages
  ).dump("clusters.html")
177

178 179 180

if __name__ == "__main__":
  main()