You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
miner/frontend/mvstrategy.py

71 lines
1.9 KiB

from abc import ABC, abstractmethod
from pandas import DataFrame, Series
from pandas.api.types import is_numeric_dtype
from typing import Any, Union
class MVStrategy(ABC):
"""A way to handle missing values in a dataframe."""
@abstractmethod
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
"""Apply the current strategy to the given series.
The series is described by its label and dataframe."""
return df
@staticmethod
def list_available(series: Series) -> list['MVStrategy']:
"""Get all the strategies that can be used."""
choices = [DropStrategy(), ModeStrategy()]
if is_numeric_dtype(series):
choices.extend((MeanStrategy(), MedianStrategy()))
return choices
class DropStrategy(MVStrategy):
#@typing.override
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
df.dropna(subset=label, inplace=True)
return df
def __str__(self) -> str:
return "Drop"
class PositionStrategy(MVStrategy):
#@typing.override
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
series.fillna(self.get_value(series), inplace=True)
return df
@abstractmethod
def get_value(self, series: Series) -> Any:
pass
class MeanStrategy(PositionStrategy):
#@typing.override
def get_value(self, series: Series) -> Union[int, float]:
return series.mean()
def __str__(self) -> str:
return "Use mean"
class MedianStrategy(PositionStrategy):
#@typing.override
def get_value(self, series: Series) -> Union[int, float]:
return series.median()
def __str__(self) -> str:
return "Use median"
class ModeStrategy(PositionStrategy):
#@typing.override
def get_value(self, series: Series) -> Any:
return series.mode()[0]
def __str__(self) -> str:
return "Use mode"