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.
139 lines
3.9 KiB
139 lines
3.9 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 DataFrameFunction(ABC):
|
|
"""A command that may be applied in-place to a dataframe."""
|
|
|
|
@abstractmethod
|
|
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
|
|
"""Apply the current function to the given dataframe, in-place.
|
|
|
|
The series is described by its label and dataframe."""
|
|
return df
|
|
|
|
|
|
class MVStrategy(DataFrameFunction):
|
|
"""A way to handle missing values in a dataframe."""
|
|
|
|
@staticmethod
|
|
def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
|
|
"""Get all the strategies that can be used."""
|
|
choices = [DropStrategy(), ModeStrategy()]
|
|
if is_numeric_dtype(series):
|
|
choices.extend((MeanStrategy(), MedianStrategy(), LinearRegressionStrategy()))
|
|
return choices
|
|
|
|
|
|
class ScalingStrategy(DataFrameFunction):
|
|
"""A way to handle missing values in a dataframe."""
|
|
|
|
@staticmethod
|
|
def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
|
|
"""Get all the strategies that can be used."""
|
|
choices = [KeepStrategy()]
|
|
if is_numeric_dtype(series):
|
|
choices.extend((MinMaxStrategy(), ZScoreStrategy()))
|
|
if series.sum() != 0:
|
|
choices.append(UnitLengthStrategy())
|
|
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"
|
|
|
|
|
|
class LinearRegressionStrategy(MVStrategy):
|
|
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
|
|
series.interpolate(inplace=True)
|
|
return df
|
|
|
|
def __str__(self) -> str:
|
|
return "Use linear regression"
|
|
|
|
|
|
class KeepStrategy(ScalingStrategy):
|
|
#@typing.override
|
|
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
|
|
return df
|
|
|
|
def __str__(self) -> str:
|
|
return "No-op"
|
|
|
|
|
|
class MinMaxStrategy(ScalingStrategy):
|
|
#@typing.override
|
|
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
|
|
minimum = series.min()
|
|
maximum = series.max()
|
|
df[label] = (series - minimum) / (maximum - minimum)
|
|
return df
|
|
|
|
def __str__(self) -> str:
|
|
return "Min-max"
|
|
|
|
|
|
class ZScoreStrategy(ScalingStrategy):
|
|
#@typing.override
|
|
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
|
|
df[label] = (series - series.mean()) / series.std()
|
|
return df
|
|
|
|
def __str__(self) -> str:
|
|
return "Z-Score"
|
|
|
|
|
|
class UnitLengthStrategy(ScalingStrategy):
|
|
#@typing.override
|
|
def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
|
|
df[label] = series / series.sum()
|
|
return df
|
|
|
|
def __str__(self) -> str:
|
|
return "Unit length"
|