Source code for dataprep.clean.clean_lv_pvn

"""
Clean and validate a DataFrame column containing Latvian PVN (VAT) numbers (PVNs).
"""
# pylint: disable=too-many-lines, too-many-arguments, too-many-branches
from typing import Any, Union
from operator import itemgetter

import dask.dataframe as dd
import numpy as np
import pandas as pd

from stdnum.lv import pvn
from ..progress_bar import ProgressBar
from .utils import NULL_VALUES, to_dask


[docs]def clean_lv_pvn( df: Union[pd.DataFrame, dd.DataFrame], column: str, output_format: str = "standard", inplace: bool = False, errors: str = "coerce", progress: bool = True, ) -> pd.DataFrame: """ Clean Latvian PVN (VAT) numbers (PVNs) type data in a DataFrame column. Parameters ---------- df A pandas or Dask DataFrame containing the data to be cleaned. col The name of the column containing data of PVN type. output_format The output format of standardized number string. If output_format = 'compact', return string without any separators or whitespace. If output_format = 'standard', return string with proper separators and whitespace. If output_format = 'birthdate', return the birthdate of the person. Note only when PVN refers to a person (but not a legal entity) this format will be available. Note: in the case of PVN, the compact format is the same as the standard one. (default: "standard") inplace If True, delete the column containing the data that was cleaned. Otherwise, keep the original column. (default: False) errors How to handle parsing errors. - ‘coerce’: invalid parsing will be set to NaN. - ‘ignore’: invalid parsing will return the input. - ‘raise’: invalid parsing will raise an exception. (default: 'coerce') progress If True, display a progress bar. (default: True) Examples -------- Clean a column of PVN data. >>> df = pd.DataFrame({{ "pvn": [ '161175-19997', '40003521601',] }) >>> clean_lv_pvn(df, 'pvn') pvn pvn_clean 0 161175-19997 16117519997 1 40003521601 NaN """ if output_format not in {"compact", "standard", "birthdate"}: raise ValueError( f"output_format {output_format} is invalid. " 'It needs to be "compact", "standard" or "birthdate".' ) # convert to dask df = to_dask(df) # To clean, create a new column "clean_code_tup" which contains # the cleaned values and code indicating how the initial value was # changed in a tuple. Then split the column of tuples and count the # amount of different codes to produce the report df["clean_code_tup"] = df[column].map_partitions( lambda srs: [_format(x, output_format, errors) for x in srs], meta=object, ) df = df.assign( _temp_=df["clean_code_tup"].map(itemgetter(0)), ) df = df.rename(columns={"_temp_": f"{column}_clean"}) df = df.drop(columns=["clean_code_tup"]) if inplace: df[column] = df[f"{column}_clean"] df = df.drop(columns=f"{column}_clean") df = df.rename(columns={column: f"{column}_clean"}) with ProgressBar(minimum=1, disable=not progress): df = df.compute() return df
[docs]def validate_lv_pvn( df: Union[str, pd.Series, dd.Series, pd.DataFrame, dd.DataFrame], column: str = "", ) -> Union[bool, pd.Series, pd.DataFrame]: """ Validate if a data cell is PVN in a DataFrame column. For each cell, return True or False. Parameters ---------- df A pandas or Dask DataFrame containing the data to be validated. col The name of the column to be validated. """ if isinstance(df, (pd.Series, dd.Series)): return df.apply(pvn.is_valid) elif isinstance(df, (pd.DataFrame, dd.DataFrame)): if column != "": return df[column].apply(pvn.is_valid) else: return df.applymap(pvn.is_valid) return pvn.is_valid(df)
def _format(val: Any, output_format: str = "standard", errors: str = "coarse") -> Any: """ Reformat a number string with proper separators and whitespace. Parameters ---------- val The value of number string. output_format If output_format = 'compact', return string without any separators or whitespace. If output_format = 'standard', return string with proper separators and whitespace. If output_format = 'birthdate', return the birthdate of the person. Note only when PVN refers to a person (but not a legal entity) this format will be available. Note: in the case of PVN, the compact format is the same as the standard one. """ # pylint: disable=bare-except val = str(val) result: Any = [] if val in NULL_VALUES: return [np.nan] if not validate_lv_pvn(val): if errors == "raise": raise ValueError(f"Unable to parse value {val}") error_result = val if errors == "ignore" else np.nan return [error_result] if output_format in {"compact", "standard"}: result = [pvn.compact(val)] + result elif output_format == "birthdate": try: result = [pvn.get_birth_date(val)] + result except: # PVN stands for a legal entity return [np.nan] return result