|
| 1 | +import djclick as click |
| 2 | +import numpy as np |
| 3 | + |
| 4 | +from openpyxl import Workbook |
| 5 | +from openpyxl import worksheet |
| 6 | +from openpyxl.worksheet.table import Table |
| 7 | +from typing import Any |
| 8 | +from typing import Iterable |
| 9 | + |
| 10 | +from django.contrib.auth import get_user_model |
| 11 | +from django.db.models import Count |
| 12 | +from django.db.models import Q |
| 13 | +from django.db.models import QuerySet |
| 14 | + |
| 15 | +from libraries.models import CommitAuthor |
| 16 | + |
| 17 | +# Set a the number of percentiles to calculate. |
| 18 | +# e.g. 20 means calculate every 5 percent |
| 19 | +NUMBER_OF_PERCENTILES = 20 |
| 20 | +STEP = int(100 / NUMBER_OF_PERCENTILES) |
| 21 | +PERCENTILE_RANKS = list(range(STEP, (NUMBER_OF_PERCENTILES + 1) * STEP, STEP)) |
| 22 | + |
| 23 | + |
| 24 | +def calculate_percentile( |
| 25 | + data_list: Iterable[int], |
| 26 | +): |
| 27 | + a = np.array(data_list) |
| 28 | + res = np.percentile(a, PERCENTILE_RANKS) |
| 29 | + return res |
| 30 | + |
| 31 | + |
| 32 | +def insert_data_into_column( |
| 33 | + column_label: str, |
| 34 | + data_list: Iterable[Any], |
| 35 | + start_index: int, |
| 36 | + worksheet: worksheet, |
| 37 | +): |
| 38 | + index = start_index |
| 39 | + for i in data_list: |
| 40 | + worksheet[f"{column_label}{index}"] = i |
| 41 | + index += 1 |
| 42 | + |
| 43 | + |
| 44 | +def insert_percentile_data_into_column( |
| 45 | + column_label: str, |
| 46 | + data_list: Iterable[int], |
| 47 | + start_index: int, |
| 48 | + worksheet: worksheet, |
| 49 | +): |
| 50 | + percentiles = calculate_percentile(data_list) |
| 51 | + insert_data_into_column(column_label, percentiles, start_index, worksheet) |
| 52 | + |
| 53 | + |
| 54 | +def insert_qs_data_into_percentile_column( |
| 55 | + column_label: str, |
| 56 | + qs: QuerySet, |
| 57 | + start_index: int, |
| 58 | + worksheet: worksheet, |
| 59 | + field_name: str, |
| 60 | +): |
| 61 | + data_list = qs.order_by(field_name).values_list(field_name, flat=True) |
| 62 | + title = " ".join(field_name.split("_")).capitalize() |
| 63 | + worksheet[f"{column_label}{start_index}"] = title |
| 64 | + insert_percentile_data_into_column( |
| 65 | + column_label, data_list, start_index + 1, worksheet |
| 66 | + ) |
| 67 | + |
| 68 | + |
| 69 | +@click.command() |
| 70 | +def command(): |
| 71 | + User = get_user_model() |
| 72 | + |
| 73 | + user_qs = ( |
| 74 | + User.objects.all() |
| 75 | + .annotate( |
| 76 | + library_versions_authored=Count("author_libraryversions", distinct=True), |
| 77 | + libraries_authored=Count("authors", distinct=True), |
| 78 | + ) |
| 79 | + .order_by("-email") |
| 80 | + .exclude(Q(library_versions_authored=0) & Q(libraries_authored=0)) |
| 81 | + ) |
| 82 | + commit_author_qs = ( |
| 83 | + CommitAuthor.objects.all() |
| 84 | + .annotate( |
| 85 | + commits_authored=Count("commit", distinct=True), |
| 86 | + reviews_submitted=Count("submitted_reviews", distinct=True), |
| 87 | + mailing_list_count=Count("emaildata", distinct=True), |
| 88 | + ) |
| 89 | + .exclude( |
| 90 | + Q(commits_authored=0) & Q(reviews_submitted=0) & Q(mailing_list_count=0) |
| 91 | + ) |
| 92 | + ) |
| 93 | + |
| 94 | + wb = Workbook() |
| 95 | + ws = wb.active |
| 96 | + |
| 97 | + # Using the default sheet, Present Library Version Authors and Library Authors |
| 98 | + ws.title = "Library Authors and Versions" |
| 99 | + ws.append( |
| 100 | + [ |
| 101 | + "Email", |
| 102 | + "Libraries Authored", |
| 103 | + "Library Versions Authored", |
| 104 | + ] |
| 105 | + ) |
| 106 | + for user in user_qs: |
| 107 | + ws.append( |
| 108 | + [ |
| 109 | + user.email, |
| 110 | + user.libraries_authored, |
| 111 | + user.library_versions_authored, |
| 112 | + ] |
| 113 | + ) |
| 114 | + tab = Table( |
| 115 | + displayName="LibraryAuthorsandVersions", ref=f"A1:C{user_qs.count() + 1}" |
| 116 | + ) |
| 117 | + ws.add_table(tab) |
| 118 | + |
| 119 | + wb.create_sheet("Commit Author Data") |
| 120 | + ws = wb["Commit Author Data"] |
| 121 | + ws.append( |
| 122 | + [ |
| 123 | + "Name", |
| 124 | + "Commits Authored", |
| 125 | + "Reviews Submitted", |
| 126 | + "Mailing List Contributions", |
| 127 | + ] |
| 128 | + ) |
| 129 | + for user in commit_author_qs: |
| 130 | + ws.append( |
| 131 | + [ |
| 132 | + user.display_name, |
| 133 | + user.commits_authored, |
| 134 | + user.reviews_submitted, |
| 135 | + user.mailing_list_count, |
| 136 | + ] |
| 137 | + ) |
| 138 | + tab = Table( |
| 139 | + displayName="CommitAuthorData", ref=f"A1:D{commit_author_qs.count() + 1}" |
| 140 | + ) |
| 141 | + ws.add_table(tab) |
| 142 | + |
| 143 | + # Add percentile data |
| 144 | + wb.create_sheet("Percentile Analysis") |
| 145 | + ws = wb["Percentile Analysis"] |
| 146 | + insert_data_into_column("A", ["Percentile"] + PERCENTILE_RANKS, 1, ws) |
| 147 | + insert_qs_data_into_percentile_column("B", user_qs, 1, ws, "libraries_authored") |
| 148 | + insert_qs_data_into_percentile_column( |
| 149 | + "C", user_qs, 1, ws, "library_versions_authored" |
| 150 | + ) |
| 151 | + insert_qs_data_into_percentile_column( |
| 152 | + "F", commit_author_qs.exclude(commits_authored=0), 1, ws, "commits_authored" |
| 153 | + ) |
| 154 | + insert_qs_data_into_percentile_column( |
| 155 | + "G", commit_author_qs.exclude(reviews_submitted=0), 1, ws, "reviews_submitted" |
| 156 | + ) |
| 157 | + insert_qs_data_into_percentile_column( |
| 158 | + "H", |
| 159 | + commit_author_qs.exclude(mailing_list_count=0), |
| 160 | + 1, |
| 161 | + ws, |
| 162 | + "mailing_list_count", |
| 163 | + ) |
| 164 | + |
| 165 | + tab = Table(displayName="PercentilData", ref=f"A1:H{NUMBER_OF_PERCENTILES+1}") |
| 166 | + ws.add_table(tab) |
| 167 | + |
| 168 | + wb.save("badge_info.xlsx") |
0 commit comments