numeric_stats

numeric_stats

NumericStatistics

NumericStatistics(
    dataframe: DataFrame, time_column: str = "systime"
)

Bases: Base

Provides class methods to calculate statistics on numeric columns in a pandas DataFrame.

column_mean classmethod

column_mean(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the mean of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The mean of the non-missing values; NaN when there is none.

column_median classmethod

column_median(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the median of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The median of the non-missing values; NaN when there is none.

column_std classmethod

column_std(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the standard deviation of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The sample standard deviation (ddof=1); NaN for fewer than 2 values.

column_variance classmethod

column_variance(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the variance of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The sample variance (ddof=1); NaN for fewer than 2 values.

column_min classmethod

column_min(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the minimum value of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The smallest value; NaN when there is none.

column_max classmethod

column_max(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the maximum value of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The largest value; NaN when there is none.

column_sum classmethod

column_sum(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the sum of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The sum of the values; 0 when there is none.

column_kurtosis classmethod

column_kurtosis(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the kurtosis of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The bias-corrected excess kurtosis; NaN for fewer than 4 values.

column_skewness classmethod

column_skewness(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the skewness of a specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The bias-corrected skewness; NaN for fewer than 3 values.

column_quantile classmethod

column_quantile(
    dataframe: DataFrame, value_column: str, quantile: float
) -> float

Calculate a specific quantile of the column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required
quantile	float	Quantile to compute, between 0 and 1 (0.5 is the median).	required

Returns:

Type	Description
float	The quantile (linear interpolation); NaN when there is no value.

column_iqr classmethod

column_iqr(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the interquartile range of the column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	Third minus first quartile of the non-missing values; NaN when there is none.

column_range classmethod

column_range(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the range of the column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	Largest minus smallest value; NaN when there is none.

column_mad classmethod

column_mad(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the mean absolute deviation of the column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The mean absolute deviation from the mean; NaN when there is no value.

column_mode classmethod

column_mode(
    dataframe: DataFrame, value_column: str
) -> float | None

Calculate the mode of a specified column. Returns None if column is empty.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float | None	The most frequent value (the smallest on a tie), or None when there is no value.

coefficient_of_variation classmethod

coefficient_of_variation(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the coefficient of variation of the column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	Standard deviation divided by the mean, or float("nan") when the
float	mean is 0 (the ratio is undefined).

standard_error_mean classmethod

standard_error_mean(
    dataframe: DataFrame, value_column: str
) -> float

Calculate the standard error of the mean for the column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
float	The standard error of the mean; NaN for fewer than 2 values.

describe classmethod

describe(dataframe: DataFrame) -> pd.DataFrame

Provide a statistical summary for numeric columns in the DataFrame.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame; every numeric column is described.	required

Returns:

Type	Description
DataFrame	The output of DataFrame.describe(): one column per numeric column, rows count, mean, std, min, 25%, 50%, 75% and max.

summary_as_dict classmethod

summary_as_dict(
    dataframe: DataFrame, value_column: str
) -> dict[str, float | int | None]

Returns a dictionary with comprehensive numeric statistics for the specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
dict[str, float | int | None]	Dict with keys min, max, mean, median, std, var, sum, kurtosis, skewness, q1, q3, iqr, range, mad, coeff_var, sem, mode, percentile_90 and percentile_10.

summary_as_dataframe classmethod

summary_as_dataframe(
    dataframe: DataFrame, value_column: str
) -> pd.DataFrame

Returns a DataFrame with comprehensive numeric statistics for the specified column.

Parameters:

Name	Type	Description	Default
dataframe	DataFrame	Input DataFrame.	required
value_column	str	Name of the numeric column to analyze.	required

Returns:

Type	Description
DataFrame	One-row DataFrame with the keys of summary_as_dict as columns.