rank_collaborator.py

import pandas as pd

MEANINGFUL_COLLABORATION_DAYS = 15

def _rank_collaborators(df, keep_meaningful_collaborations=True):
    df_copy = df.copy()

    if keep_meaningful_collaborations:
        meaningful_collaborations_mask = df_copy["collaboration_days"] >= MEANINGFUL_COLLABORATION_DAYS
        df_copy = df_copy.loc[meaningful_collaborations_mask]

    # Rank collaborator higher if they have more collaboration days
    df_copy.loc[:, "reviewer_ranking"] = df_copy.groupby("employee")["collaboration_days"].rank(ascending=False)
    # Rank employee higher if they have more collaboration days with reviewers
    df_copy.loc[:, "reviewe_ranking"] = df_copy.groupby("collaborator_employee")["collaboration_days"].rank(ascending=False)

    # Rank reviewer-reviewee pairs higher if they rank higher in each other's list
    df_copy.loc[:, "sum_ranking"] = df_copy.loc[:, "reviewer_ranking"] + df_copy.loc[:, "reviewe_ranking"]
    df_copy.loc[:, "overall_ranking"] = df_copy["sum_ranking"].rank()
    df_copy = df_copy.sort_values(by="overall_ranking")
    return df_copy

ranked_team_df = _rank_collaborators(team_df)
ranked_cross_team_df = _rank_collaborators(cross_team_df)