timeseries_shaper.filter.numeric_filter

 1import pandas as pd
 2from ..base import Base
 3
 4class IntegerFilter(Base):
 5    """
 6    Provides class methods for filtering integer columns in a pandas DataFrame.
 7    """
 8
 9    @classmethod
10    def filter_value_integer_match(cls, dataframe: pd.DataFrame, column_name: str = 'value_integer', integer_value: int = 0) -> pd.DataFrame:
11        """Filters rows where 'value_integer' matches the specified integer."""
12        return dataframe[dataframe[column_name] == integer_value]
13
14    @classmethod
15    def filter_value_integer_not_match(cls, dataframe: pd.DataFrame, column_name: str = 'value_integer', integer_value: int = 0) -> pd.DataFrame:
16        """Filters rows where 'value_integer' does not match the specified integer."""
17        return dataframe[dataframe[column_name] != integer_value]
18
19    @classmethod
20    def filter_value_integer_between(cls, dataframe: pd.DataFrame, column_name: str = 'value_integer', min_value: int = 0, max_value: int = 100) -> pd.DataFrame:
21        """Filters rows where 'value_integer' is between the specified min and max values (inclusive)."""
22        return dataframe[(dataframe[column_name] >= min_value) & (dataframe[column_name] <= max_value)]
23
24
25class DoubleFilter(Base):
26    """
27    Provides class methods for filtering double (floating-point) columns in a pandas DataFrame,
28    particularly focusing on NaN values.
29    """
30    
31    @classmethod
32    def filter_nan_value_double(cls, dataframe: pd.DataFrame, column_name: str = 'value_double') -> pd.DataFrame:
33        """Filters out rows where 'value_double' is NaN."""
34        return dataframe[dataframe[column_name].notna()]
35
36    @classmethod
37    def filter_value_double_between(cls, dataframe: pd.DataFrame, column_name: str = 'value_double', min_value: float = 0.0, max_value: float = 100.0) -> pd.DataFrame:
38        """Filters rows where 'value_double' is between the specified min and max values (inclusive)."""
39        return dataframe[(dataframe[column_name] >= min_value) & (dataframe[column_name] <= max_value)]