cdplib/import_process_instances/CleanRs2.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Sep 30 10:06:48 2019

@author: tanya
"""

import pandas as pd
import os
import sys

sys.path.append(os.getcwd())

from libraries.import_process_instances.CleanProcessTable import CleanProcessTable


class CleanRs2(CleanProcessTable):
    '''
    '''
    def __init__(self):
        '''
        '''
        super().__init__(
                mapping_path=os.path.join(".", "migration_mappings",
                                          "rs2_mapping.json"),
                inconsist_report_table="inconsist_rs2",
                sort_columns=["radsatznummer", "ende_der_bearbeitung"],
                index_columns=["radsatznummer", "positionsnummer"],
                log_name="CleanRs2")

    def filter_invalid_ende_der_bearbeitung(self, data: pd.DataFrame
                                            ) -> pd.DataFrame:
        '''
        We filter out all the rows that have missing ende_der_bearbeitung,
         it means that the activities we planned, but not executed.
        '''
        self.error_column_abscence(columns=["radsatznummer",
                                            "ende_der_bearbeitung"],
                                   data=data)

        is_invalid = (data["ende_der_bearbeitung"].isnull())

        data = self._filter_invalid_data(
                    data=data,
                    invalid_mask=is_invalid,
                    reason="invalid ende der bearbeitung")

        data["ende_der_bearbeitung"] =\
            pd.to_datetime(data["ende_der_bearbeitung"])

        return data

    def filter_invalid_taetigkeitsname(self, data: pd.DataFrame
                                       ) -> pd.DataFrame:
        '''
        In the configuration we store a list of activities
         execution of which means that the wheel-set is scrap.
         After execution of this activities the process history should end.
        '''
        from libraries.configuration import default as cfg

        self.error_column_abscence(columns=["radsatznummer",
                                            "taetigkeitsname"],
                                   data=data)

        data.sort_values(by=self._sort_columns, inplace=True)

        is_last_station = (
            data["radsatznummer"] !=
            data["radsatznummer"].shift(-1))

        is_invalid = (
                ~is_last_station &
                (data["taetigkeitsname"].isin(cfg.schrott_taetigkeiten)))

        data = self._filter_invalid_data(
                    data=data,
                    invalid_mask=is_invalid,
                    reason="invalid taetigkeit")

        return data