Fixed Path Exclusion to no longer show grouped paths with too few elements, too short paths, and sorted output
This commit is contained in:
@@ -72,13 +72,19 @@ def add_longest_common_two_local(df, col="filename_x", new_col="longestcfp", min
|
||||
return df
|
||||
|
||||
|
||||
def export_groups_for_review(df, col="filename_x", group_col="longestcfp"):
|
||||
def export_groups_for_review(df, col, group_col, min_number_in_group, path_length_constant):
|
||||
"""
|
||||
Compute longest common paths, group filepaths, write CSV for review.
|
||||
"""
|
||||
df = add_longest_common_two_local(df, col=col, new_col=group_col)
|
||||
grouped = df.groupby(group_col)[col].apply(list).reset_index()
|
||||
return grouped, df
|
||||
grouped = grouped.sort_values(by=col)
|
||||
print("Before filtering:", len(grouped))
|
||||
grouped = grouped[grouped[col].apply(lambda x: len(x) >= min_number_in_group)]
|
||||
filtered = grouped[grouped[group_col].apply(lambda x: len(os.path.normpath(x).split(os.sep)) >= path_length_constant)]
|
||||
print("After filtering:", len(grouped))
|
||||
|
||||
return filtered, df
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user