stalker_stalkee_pandas.py

checkins_by_loc = (checkins_df[['user_id', 'checkin_ts', 'location_id']] 
                      .set_index('location_id') ) 

chin_pairs = checkins_by_loc.join( checkins_by_loc, lsuffix='_ee', rsuffix='_er' ) 

pairs_filtered = (chin_pairs[(chin_pairs.checkin_ts_ee < chin_pairs.checkin_ts_er) &                                                 
                             (chin_pairs.user_id_ee != chin_pairs.user_id_er )]
                      .rename( columns= {"user_id_er" : "stalker",
                                         "user_id_ee" : "stalkee" }) 
                      .reset_index()
                      [["stalkee", "stalker", "location_id"]] )

final_result = ( pairs_filtered.drop_duplicates()                 
                     .groupby(["stalkee", "stalker"])
                     .agg( {"location_id" : "count"})
                     .rename( columns = { "location_id" : "location_count" } )                 
                     .sort_values('location_count', ascending=False) )