Set up the data in case of running initialization for multiple time Parameters ---------- init_type : str The type `IT_*` listed above. enable_cache : bool default value is false: - if `enable_cache` == True:
(self, init_type: str = IT_FIT_SEQ, **kwargs)
| 632 | IT_LS = "load_state" # The state of the object has been load by pickle |
| 633 | |
| 634 | def setup_data(self, init_type: str = IT_FIT_SEQ, **kwargs): |
| 635 | """ |
| 636 | Set up the data in case of running initialization for multiple time |
| 637 | |
| 638 | Parameters |
| 639 | ---------- |
| 640 | init_type : str |
| 641 | The type `IT_*` listed above. |
| 642 | enable_cache : bool |
| 643 | default value is false: |
| 644 | |
| 645 | - if `enable_cache` == True: |
| 646 | |
| 647 | the processed data will be saved on disk, and handler will load the cached data from the disk directly |
| 648 | when we call `init` next time |
| 649 | """ |
| 650 | # init raw data |
| 651 | super().setup_data(**kwargs) |
| 652 | |
| 653 | with TimeInspector.logt("fit & process data"): |
| 654 | if init_type == DataHandlerLP.IT_FIT_IND: |
| 655 | self.fit() |
| 656 | self.process_data() |
| 657 | elif init_type == DataHandlerLP.IT_LS: |
| 658 | self.process_data() |
| 659 | elif init_type == DataHandlerLP.IT_FIT_SEQ: |
| 660 | self.fit_process_data() |
| 661 | else: |
| 662 | raise NotImplementedError(f"This type of input is not supported") |
| 663 | |
| 664 | # TODO: Be able to cache handler data. Save the memory for data processing |
| 665 | |
| 666 | def _get_df_by_key(self, data_key: DATA_KEY_TYPE = DataHandlerABC.DK_I) -> pd.DataFrame: |
| 667 | if data_key == self.DK_R and self.drop_raw: |
nothing calls this directly
no test coverage detected