Skip to content

ts_shape.features.stats.numeric_stats ¤

Classes:

  • NumericStatistics –

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

NumericStatistics ¤

NumericStatistics(dataframe: DataFrame, column_name: str = 'systime')

Bases: Base

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

Parameters:

  • dataframe ¤

    (DataFrame) –

    The DataFrame to be processed.

  • column_name ¤

    (str, default: 'systime' ) –

    The column to sort by. Default is 'systime'. If the column is not found or is not a time column, the class will attempt to detect other time columns.

Methods:

  • coefficient_of_variation –

    Calculate the coefficient of variation of the column.

  • column_iqr –

    Calculate the interquartile range of the column.

  • column_kurtosis –

    Calculate the kurtosis of a specified column.

  • column_mad –

    Calculate the mean absolute deviation of the column.

  • column_max –

    Calculate the maximum value of a specified column.

  • column_mean –

    Calculate the mean of a specified column.

  • column_median –

    Calculate the median of a specified column.

  • column_min –

    Calculate the minimum value of a specified column.

  • column_quantile –

    Calculate a specific quantile of the column.

  • column_range –

    Calculate the range of the column.

  • column_skewness –

    Calculate the skewness of a specified column.

  • column_std –

    Calculate the standard deviation of a specified column.

  • column_sum –

    Calculate the sum of a specified column.

  • column_variance –

    Calculate the variance of a specified column.

  • describe –

    Provide a statistical summary for numeric columns in the DataFrame.

  • get_dataframe –

    Returns the processed DataFrame.

  • standard_error_mean –

    Calculate the standard error of the mean for the column.

  • summary_as_dataframe –

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

  • summary_as_dict –

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

Source code in src/ts_shape/utils/base.py 
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
def __init__(self, dataframe: pd.DataFrame, column_name: str = 'systime') -> pd.DataFrame:
    """
    Initializes the Base with a DataFrame, detects time columns, converts them to datetime,
    and sorts the DataFrame by the specified column (or the detected time column if applicable).

    Args:
        dataframe (pd.DataFrame): The DataFrame to be processed.
        column_name (str): The column to sort by. Default is 'systime'. If the column is not found or is not a time column, the class will attempt to detect other time columns.
    """
    self.dataframe = dataframe.copy()

    # Attempt to convert the specified column_name to datetime if it exists
    if column_name in self.dataframe.columns:
        self.dataframe[column_name] = pd.to_datetime(self.dataframe[column_name], errors='coerce')
    else:
        # If the column_name is not in the DataFrame, fallback to automatic time detection
        time_columns = [col for col in self.dataframe.columns if 'time' in col.lower() or 'date' in col.lower()]

        # Convert all detected time columns to datetime, if any
        for col in time_columns:
            self.dataframe[col] = pd.to_datetime(self.dataframe[col], errors='coerce')

        # If any time columns are detected, sort by the first one; otherwise, do nothing
        if time_columns:
            column_name = time_columns[0]

    # Sort by the datetime column (either specified or detected)
    if column_name in self.dataframe.columns:
        self.dataframe = self.dataframe.sort_values(by=column_name)

coefficient_of_variation classmethod ¤

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

Calculate the coefficient of variation of the column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
76
77
78
79
80
@classmethod
def coefficient_of_variation(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the coefficient of variation of the column."""
    mean = cls.column_mean(dataframe, column_name)
    return cls.column_std(dataframe, column_name) / mean if mean != 0 else None

column_iqr classmethod ¤

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

Calculate the interquartile range of the column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
61
62
63
64
@classmethod
def column_iqr(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the interquartile range of the column."""
    return stats.iqr(dataframe[column_name])

column_kurtosis classmethod ¤

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

Calculate the kurtosis of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
46
47
48
49
@classmethod
def column_kurtosis(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the kurtosis of a specified column."""
    return dataframe[column_name].kurt()

column_mad classmethod ¤

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

Calculate the mean absolute deviation of the column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
71
72
73
74
@classmethod
def column_mad(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the mean absolute deviation of the column."""
    return dataframe[column_name].mad()

column_max classmethod ¤

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

Calculate the maximum value of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
36
37
38
39
@classmethod
def column_max(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the maximum value of a specified column."""
    return dataframe[column_name].max()

column_mean classmethod ¤

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

Calculate the mean of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
11
12
13
14
@classmethod
def column_mean(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the mean of a specified column."""
    return dataframe[column_name].mean()

column_median classmethod ¤

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

Calculate the median of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
16
17
18
19
@classmethod
def column_median(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the median of a specified column."""
    return dataframe[column_name].median()

column_min classmethod ¤

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

Calculate the minimum value of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
31
32
33
34
@classmethod
def column_min(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the minimum value of a specified column."""
    return dataframe[column_name].min()

column_quantile classmethod ¤

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

Calculate a specific quantile of the column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
56
57
58
59
@classmethod
def column_quantile(cls, dataframe: pd.DataFrame, column_name: str, quantile: float) -> float:
    """Calculate a specific quantile of the column."""
    return dataframe[column_name].quantile(quantile)

column_range classmethod ¤

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

Calculate the range of the column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
66
67
68
69
@classmethod
def column_range(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the range of the column."""
    return cls.column_max(dataframe, column_name) - cls.column_min(dataframe, column_name)

column_skewness classmethod ¤

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

Calculate the skewness of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
51
52
53
54
@classmethod
def column_skewness(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the skewness of a specified column."""
    return dataframe[column_name].skew()

column_std classmethod ¤

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

Calculate the standard deviation of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
21
22
23
24
@classmethod
def column_std(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the standard deviation of a specified column."""
    return dataframe[column_name].std()

column_sum classmethod ¤

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

Calculate the sum of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
41
42
43
44
@classmethod
def column_sum(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the sum of a specified column."""
    return dataframe[column_name].sum()

column_variance classmethod ¤

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

Calculate the variance of a specified column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
26
27
28
29
@classmethod
def column_variance(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the variance of a specified column."""
    return dataframe[column_name].var()

describe classmethod ¤

describe(dataframe: DataFrame) -> DataFrame

Provide a statistical summary for numeric columns in the DataFrame.

Source code in src/ts_shape/features/stats/numeric_stats.py 
87
88
89
90
@classmethod
def describe(cls, dataframe: pd.DataFrame) -> pd.DataFrame:
    """Provide a statistical summary for numeric columns in the DataFrame."""
    return dataframe.describe()

get_dataframe ¤

get_dataframe() -> DataFrame

Returns the processed DataFrame.

Source code in src/ts_shape/utils/base.py 
34
35
36
def get_dataframe(self) -> pd.DataFrame:
    """Returns the processed DataFrame."""
    return self.dataframe

standard_error_mean classmethod ¤

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

Calculate the standard error of the mean for the column.

Source code in src/ts_shape/features/stats/numeric_stats.py 
82
83
84
85
@classmethod
def standard_error_mean(cls, dataframe: pd.DataFrame, column_name: str) -> float:
    """Calculate the standard error of the mean for the column."""
    return dataframe[column_name].sem()

summary_as_dataframe classmethod ¤

summary_as_dataframe(dataframe: DataFrame, column_name: str) -> DataFrame

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

Source code in src/ts_shape/features/stats/numeric_stats.py 
118
119
120
121
122
@classmethod
def summary_as_dataframe(cls, dataframe: pd.DataFrame, column_name: str) -> pd.DataFrame:
    """Returns a DataFrame with comprehensive numeric statistics for the specified column."""
    summary_data = cls.summary_as_dict(dataframe, column_name)
    return pd.DataFrame([summary_data])

summary_as_dict classmethod ¤

summary_as_dict(dataframe: DataFrame, column_name: str) -> Dict[str, Union[float, int]]

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

Source code in src/ts_shape/features/stats/numeric_stats.py 
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
@classmethod
def summary_as_dict(cls, dataframe: pd.DataFrame, column_name: str) -> Dict[str, Union[float, int]]:
    """Returns a dictionary with comprehensive numeric statistics for the specified column."""
    series = dataframe[column_name]
    return {
        'min': cls.column_min(dataframe, column_name),
        'max': cls.column_max(dataframe, column_name),
        'mean': cls.column_mean(dataframe, column_name),
        'median': cls.column_median(dataframe, column_name),
        'std': cls.column_std(dataframe, column_name),
        'var': cls.column_variance(dataframe, column_name),
        'sum': cls.column_sum(dataframe, column_name),
        'kurtosis': cls.column_kurtosis(dataframe, column_name),
        'skewness': cls.column_skewness(dataframe, column_name),
        'q1': cls.column_quantile(dataframe, column_name, 0.25),
        'q3': cls.column_quantile(dataframe, column_name, 0.75),
        'iqr': cls.column_iqr(dataframe, column_name),
        'range': cls.column_range(dataframe, column_name),
        'mad': cls.column_mad(dataframe, column_name),
        'coeff_var': cls.coefficient_of_variation(dataframe, column_name),
        'sem': cls.standard_error_mean(dataframe, column_name),
        'mode': cls.column_mode(dataframe, column_name),
        'percentile_90': cls.column_quantile(dataframe, column_name, 0.90),
        'percentile_10': cls.column_quantile(dataframe, column_name, 0.10),
    }