1
0

updating with more clearly labeled possible ones

This commit is contained in:
Matthew Gaughan 2026-01-29 20:32:14 -08:00
parent 5f39c6f3cf
commit 7c587413aa
2 changed files with 258 additions and 258 deletions

File diff suppressed because it is too large Load Diff

View File

@ -58,7 +58,7 @@ c1_relevant <- core_df |>
filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |> filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |>
filter(isVE == TRUE)|> filter(isVE == TRUE)|>
mutate(case = "c1") |> mutate(case = "c1") |>
select(authored_date, commit_date, author_name, author_email, message) select(authored_date, commit_date, author_name, author_email, message, case)
c2_relevant <- core_df |> c2_relevant <- core_df |>
mutate(week_index = relative_week(commit_date, c2_event_date)) |> mutate(week_index = relative_week(commit_date, c2_event_date)) |>
@ -66,7 +66,7 @@ c2_relevant <- core_df |>
filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |> filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |>
filter(is_http) |> filter(is_http) |>
mutate(case = "c1") |> mutate(case = "c1") |>
select(authored_date, commit_date, author_name, author_email, message) select(authored_date, commit_date, author_name, author_email, message, case)
c3_relevant <- core_df |> c3_relevant <- core_df |>
mutate(week_index = relative_week(commit_date, c3_event_date)) |> mutate(week_index = relative_week(commit_date, c3_event_date)) |>
@ -74,7 +74,7 @@ c3_relevant <- core_df |>
filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |> filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |>
filter(is_http) |> filter(is_http) |>
mutate(case = "c1") |> mutate(case = "c1") |>
select(authored_date, commit_date, author_name, author_email, message) select(authored_date, commit_date, author_name, author_email, message, case)
possibly_relevant <- rbind(c1_relevant, c2_relevant, c3_relevant) possibly_relevant <- rbind(c1_relevant, c2_relevant, c3_relevant)
write.csv(possibly_relevant, "012926_possibly_relevant_sample.csv", row.names = FALSE) write.csv(possibly_relevant, "012926_possibly_relevant_sample.csv", row.names = FALSE)