tweet_split.py

from fklearn.preprocessing.splitting import space_time_split_dataset

train_set, intime_outspace_hdout, outime_inspace_hdout, outime_outspace_hdout = \
                                        space_time_split_dataset(df,
                                                 train_start_date="2016-12-31",
                                                 train_end_date="2017-01-10",
                                                 holdout_end_date="2017-02-13",
                                                 split_seed=42,
                                                 space_holdout_percentage=0.2,
                                                 space_column="username",
                                                 time_column="publication_date")