To receive notifications about scheduled maintenance, please subscribe to the mailing-list gitlab-operations@sympa.ethz.ch. You can subscribe to the mailing-list at https://sympa.ethz.ch

aggr.py 5.86 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):

14
15
16
  clusters_csv: pd.DataFrame = pd.read_csv(clusters_summary_csv_file)
  
  # Read CX course data, reduce to relevant columns, set index column
17
  relevant_course_columns = ["Legi", "Lastname", "Firstname", "Email", "Gender", "TotalScore"]
18
  course_csv: pd.DataFrame = pd.read_csv(cx_course_students_csv_file)
19
  course_csv = course_csv[relevant_course_columns]
20
  course_csv.set_index("Legi", inplace=True)
21
  ## TODO: Remove staff from course_csv
22

23
  # Analogous for eDoz course data
24
  relevant_edoz_columns = ["Nummer", "Departement"]
25
  edoz1_csv: pd.DataFrame = pd.read_csv("edoz-252083200L.csv", sep="\t")
26
  edoz1_csv = edoz1_csv[relevant_edoz_columns]
27
28
29
30
31
32
  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")
33
  edoz2_csv = edoz2_csv[relevant_edoz_columns]
34
35
36
37
  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))
38

39
40
41
42
43

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


44
45
46
  # 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])
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
  # 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()

64
65
66
67
  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)])
  
68
69
70
71
72
73
74
75
76
77

  jinja2_file_loader = jinja2.FileSystemLoader(".")
  jinja2_env = jinja2.Environment(loader=jinja2_file_loader)
  template = jinja2_env.get_template("clusters.html.jinja")

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

  jinja2_rows = []

78
79
  cluster_groups: pd.DataFrameGroupBy = clusters_csv.groupby("cluster_id")
  for _, cluster in cluster_groups: # cluster: pd.DataFrame
80
    # print("-"*60)
81
82
    # Get all ids (= legis) participating in a cluster
    ids_values: numpy.ndarray = pd.concat([cluster["id1"], cluster["id2"]]).unique()
83
    
84
    # ids = pd.Series(ids_values, name="Legi", index=ids_values)
85
86
    # # 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
87
    # join = pd.merge(ids, course_csv, left_index=True, right_index=True)
88

89
    cluster_course_rows: pd.DataFrame = course_csv.loc[ids_values]
90

91
92
93
94
95
96
97
98
99
100
101
102
103
    # 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)
104
105
    # print(edoz_csv)

106
107
108
109
110
111
112
113
114
115
116
    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
117
118
119
120
121
122
123
  
  ## 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]
124
125
126
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


  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)

165

166
167
168
169
170
  template.stream(
    title="Clusters",
    clusters=jinja2_rows,
    edoz_count=edoz_csv.shape[0],
    course_count=course_csv.shape[0],
scmalte's avatar
scmalte committed
171
    plagiarist_count=plagiarist_count,
172
173
    percentages=percentages
  ).dump("clusters.html")
174

175
176
177

if __name__ == "__main__":
  main()