aggr.py 7.41 KB
Newer Older
1
import os
2
3
import logging
import csv
4
import jinja2
5
6
7
import pandas as pd
from .utils import logging as logutils

8
9
10
DEFAULT_CLUSTER_FILES_DIR="_clusters"
DEFAULT_CLUSTERS_MATCHES_CSV_FILE="clusters-matches.csv"
DEFAULT_CLUSTER_STUDENTS_CSV_FILE_PATTERN="cluster-students-{}.csv"
11
DEFAULT_CX_COURSE_STUDENTS_CSV_FILE="cx_students.csv"
12
DEFAULT_JINJA_CLUSTER_TEMPLATE_FILE="./_static/clusters.html.jinja"
13
14

def main(
15
16
17
    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,
18
19
    cx_course_students_csv_file=DEFAULT_CX_COURSE_STUDENTS_CSV_FILE,
    jinja_cluster_template_file=DEFAULT_JINJA_CLUSTER_TEMPLATE_FILE):
20

scmalte's avatar
scmalte committed
21
22
  logutils.configure_level_and_format()

23
24
  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))
25
26
27
28

  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))

29
  clusters_csv: pd.DataFrame = pd.read_csv(clusters_matches_csv_file)
30
  
scmalte's avatar
scmalte committed
31
  # Read CX course data, reduce to relevant columns, truncate TotalScore (which are floats), set index column
32
  relevant_course_columns = ["Legi", "Lastname", "Firstname", "Email", "Gender", "TotalScore"]
33
  course_csv: pd.DataFrame = pd.read_csv(cx_course_students_csv_file)
34
  course_csv = course_csv[relevant_course_columns]
scmalte's avatar
scmalte committed
35
  course_csv["TotalScore"] = course_csv["TotalScore"].round(0)
36
  course_csv.set_index("Legi", inplace=True)
37
  ## TODO: Remove staff from course_csv
38

39
40
41
42
43
  ## TODO: Make eDoz files configurable
  ## TODO: Make eDoz files optional
  ## TODO: Could integrate eDoz data "Leistungskontrollen" to get information whether
  ##       or not a student is a repeater  

44
  # Analogous for eDoz course data
45
  relevant_edoz_columns = ["Nummer", "Departement"]
46
  edoz1_csv: pd.DataFrame = pd.read_csv("edoz-252083200L.csv", sep="\t")
47
  edoz1_csv = edoz1_csv[relevant_edoz_columns]
48
49
50
51
52
53
  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")
54
  edoz2_csv = edoz2_csv[relevant_edoz_columns]
55
56
57
58
  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))
59

60
61
62
  # 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])
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
  # 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()

80
81
82
83
  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)])
  
84
85
86

  jinja2_file_loader = jinja2.FileSystemLoader(".")
  jinja2_env = jinja2.Environment(loader=jinja2_file_loader)
87
88
89
90
91

  try:
    template = jinja2_env.get_template(jinja_cluster_template_file)
  except jinja2.exceptions.TemplateNotFound as exception:
    raise RuntimeError("Couldn't load Jinja2 template {}. Should have been created by mu-init.".format(jinja_cluster_template_file))   
92
93
94
95
96
97

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

  jinja2_rows = []

98
  cluster_groups: pd.DataFrameGroupBy = clusters_csv.groupby("cluster_id")
99
  for cluster_id, cluster in cluster_groups: # cluster: pd.DataFrame
100
    # print("-"*60)
101
102
    # Get all ids (= legis) participating in a cluster
    ids_values: numpy.ndarray = pd.concat([cluster["id1"], cluster["id2"]]).unique()
103
    
104
    # ids = pd.Series(ids_values, name="Legi", index=ids_values)
105
106
    # # 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
107
    # join = pd.merge(ids, course_csv, left_index=True, right_index=True)
108

109
    cluster_course_rows: pd.DataFrame = course_csv.loc[ids_values]
110

111
112
113
114
115
116
117
118
119
120
121
122
123
    # 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)
124
125
    # print(edoz_csv)

126
127
    cluster_rows: pd.DataFrame = cluster_course_rows.join(edoz_csv)

128
129
130
131
132
133
134
    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)

135
136
137
    # print("========== cluster_rows")
    # print(cluster_rows.shape)
    # print(cluster_rows)
138
    # print(name)
139
140
141
142
143
144

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

    jinja2_rows.append((cluster, cluster_rows))

scmalte's avatar
scmalte committed
145
146
147
148
149
150
151
  
  ## 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]
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192


  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)

193

194
195
196
197
198
  template.stream(
    title="Clusters",
    clusters=jinja2_rows,
    edoz_count=edoz_csv.shape[0],
    course_count=course_csv.shape[0],
scmalte's avatar
scmalte committed
199
    plagiarist_count=plagiarist_count,
200
201
    percentages=percentages
  ).dump("clusters.html")
202

203
204
205

if __name__ == "__main__":
  main()