openavmkit.horizontal_equity_study

HorizontalEquityClusterSummary

HorizontalEquityClusterSummary(id, count, chd, min, max, median)

Summary for an individual horizontal equity cluster.

Attributes:

Name	Type	Description
id	str	Identifier of the cluster.
count	int	Number of records in the cluster.
chd	float	CHD value for the cluster.
min	float	Minimum value in the cluster.
max	float	Maximum value in the cluster.
median	float	Median value in the cluster.

Initialize a HorizontalEquityClusterSummary instance.

Parameters:

Name	Type	Description	Default
id	str	Cluster identifier.	required
count	int	Number of records in the cluster.	required
chd	float	COD value for the cluster.	required
min	float	Minimum value in the cluster.	required
max	float	Maximum value in the cluster.	required
median	float	Median value in the cluster.	required

Source code in openavmkit/horizontal_equity_study.py

def __init__(
    self, id: str, count: int, chd: float, min: float, max: float, median: float
):
    """
    Initialize a HorizontalEquityClusterSummary instance.

    Parameters
    ----------
    id : str
        Cluster identifier.
    count : int
        Number of records in the cluster.
    chd : float
        COD value for the cluster.
    min : float
        Minimum value in the cluster.
    max : float
        Maximum value in the cluster.
    median : float
        Median value in the cluster.
    """
    self.id = id
    self.count = count
    self.chd = chd
    self.min = min
    self.max = max
    self.median = median

HorizontalEquityStudy

HorizontalEquityStudy(df, field_cluster, field_value)

Perform horizontal equity analysis and summarize the results.

Attributes:

Name	Type	Description
summary	HorizontalEquitySummary	Overall summary statistics.
cluster_summaries	dict[str, HorizontalEquityClusterSummary]	Dictionary mapping cluster IDs to their summaries.

Initialize a HorizontalEquityStudy instance by computing cluster summaries.

Parameters:

Name	Type	Description	Default
df	DataFrame	Input DataFrame containing data for horizontal equity analysis.	required
field_cluster	str	Column name indicating cluster membership.	required
field_value	str	Column name of the values to analyze.	required

Source code in openavmkit/horizontal_equity_study.py

def __init__(self, df: pd.DataFrame, field_cluster: str, field_value: str):
    """
    Initialize a HorizontalEquityStudy instance by computing cluster summaries.

    Parameters
    ----------
    df : pandas.DataFrame
        Input DataFrame containing data for horizontal equity analysis.
    field_cluster : str
        Column name indicating cluster membership.
    field_value : str
        Column name of the values to analyze.
    """

    clusters = df[field_cluster].unique()
    self.cluster_summaries = {}

    chds = np.array([])
    for cluster in clusters:
        df_cluster = df[df[field_cluster].eq(cluster)]
        count = len(df_cluster)
        if count > 0:
            chd = stats.calc_cod(df_cluster[field_value].values)
            min_value = df_cluster[field_value].min()
            max_value = df_cluster[field_value].max()
            median_value = df_cluster[field_value].median()
        else:
            chd = float("nan")
            min_value = float("nan")
            max_value = float("nan")
            median_value = float("nan")
        summary = HorizontalEquityClusterSummary(
            cluster, count, chd, min_value, max_value, median_value
        )
        self.cluster_summaries[cluster] = summary
        chds = np.append(chds, chd)

    if len(chds) > 0:
        min_chd = np.min(chds)
        max_chd = np.max(chds)
        med_chd = float(np.median(chds))
    else:
        min_chd = float("nan")
        max_chd = float("nan")
        med_chd = float("nan")

    self.summary = HorizontalEquitySummary(
        len(df), len(clusters), min_chd, max_chd, med_chd
    )

HorizontalEquitySummary

HorizontalEquitySummary(rows, clusters, min_chd, max_chd, median_chd)

Summary statistics for horizontal equity analysis.

Attributes:

Name	Type	Description
rows	int	Total number of rows in the input DataFrame.
clusters	int	Total number of clusters identified.
min_chd	float	Minimum CHD (Coefficient of Horizontal Dispersion) value of any cluster.
max_chd	float	Maximum CHD value of any cluster.
median_chd	float	Median CHD value of all clusters.

Initialize a HorizontalEquitySummary instance.

Parameters:

Name	Type	Description	Default
rows	int	Total number of rows in the DataFrame.	required
clusters	int	Total number of clusters.	required
min_chd	float	Minimum COD value.	required
max_chd	float	Maximum COD value.	required
median_chd	float	Median COD value.	required

Source code in openavmkit/horizontal_equity_study.py

def __init__(
    self,
    rows: int,
    clusters: int,
    min_chd: float,
    max_chd: float,
    median_chd: float,
):
    """
    Initialize a HorizontalEquitySummary instance.

    Parameters
    ----------
    rows : int
        Total number of rows in the DataFrame.
    clusters : int
        Total number of clusters.
    min_chd : float
        Minimum COD value.
    max_chd : float
        Maximum COD value.
    median_chd : float
        Median COD value.
    """
    self.rows = rows
    self.clusters = clusters
    self.min_chd = min_chd
    self.max_chd = max_chd
    self.median_chd = median_chd

mark_horizontal_equity_clusters

mark_horizontal_equity_clusters(df, settings, verbose=False, settings_object='horizontal_equity', id_name='he_id', output_folder='', t=None)

Compute and mark horizontal equity clusters in the DataFrame.

Uses clustering (via make_clusters) based on a location field and categorical/numeric fields specified in settings to generate a horizontal equity cluster ID which is stored in the specified id_name column.

Parameters:

Name	Type	Description	Default
df	DataFrame	Input DataFrame.	required
settings	dict	Settings dictionary.	required
verbose	bool	If True, prints progress information.	False
settings_object	str	The settings object to use for horizontal equity analysis.	'horizontal_equity'
id_name	str	Name of the column to store the horizontal equity cluster ID.	'he_id'
output_folder	str	Output folder path (stores information about the clusters for later use).	''
t	TimingData	TimingData object to record performance metrics.	None

Returns:

Type	Description
DataFrame	DataFrame with a new cluster ID column (id_name).

Source code in openavmkit/horizontal_equity_study.py

def mark_horizontal_equity_clusters(
    df: pd.DataFrame,
    settings: dict,
    verbose: bool = False,
    settings_object: str = "horizontal_equity",
    id_name: str = "he_id",
    output_folder: str = "",
    t: TimingData = None,
) -> pd.DataFrame:
    """
    Compute and mark horizontal equity clusters in the DataFrame.

    Uses clustering (via `make_clusters`) based on a location field and categorical/numeric
    fields specified in settings to generate a horizontal equity cluster ID which is stored
    in the specified `id_name` column.

    Parameters
    ----------
    df : pandas.DataFrame
        Input DataFrame.
    settings : dict
        Settings dictionary.
    verbose : bool, optional
        If True, prints progress information.
    settings_object : str, optional
        The settings object to use for horizontal equity analysis.
    id_name : str, optional
        Name of the column to store the horizontal equity cluster ID.
    output_folder : str, optional
        Output folder path (stores information about the clusters for later use).
    t : TimingData, optional
        TimingData object to record performance metrics.

    Returns
    -------
    pandas.DataFrame
        DataFrame with a new cluster ID column (`id_name`).
    """

    he = settings.get("analysis", {}).get(settings_object, {})
    location = he.get("location", None)
    fields_categorical = he.get("fields_categorical", [])
    fields_numeric = he.get("fields_numeric", None)
    df[id_name], _, _ = make_clusters(
        df,
        location,
        fields_categorical,
        fields_numeric,
        verbose=verbose,
        output_folder=output_folder,
    )
    return df

mark_horizontal_equity_clusters_per_model_group_sup

mark_horizontal_equity_clusters_per_model_group_sup(sup, settings, verbose=False, use_cache=True, do_land_clusters=True, do_impr_clusters=True)

Mark horizontal equity clusters on the 'universe' DataFrame of a SalesUniversePair.

Updates the 'universe' DataFrame with horizontal equity clusters by calling mark_horizontal_equity_clusters and then sets the updated DataFrame in sup.

Parameters:

Name	Type	Description	Default
sup	SalesUniversePair	SalesUniversePair containing sales and universe data.	required
settings	dict	Settings dictionary.	required
verbose	bool	If True, prints progress information.	False
use_cache	bool	If True, uses cached DataFrame if available.	True
do_land_clusters	bool	If True, marks land horizontal equity clusters.	True
do_impr_clusters	bool	If True, marks improvement horizontal equity clusters.	True

Returns:

Type	Description
SalesUniversePair	Updated SalesUniversePair with marked horizontal equity clusters.

Source code in openavmkit/horizontal_equity_study.py

def mark_horizontal_equity_clusters_per_model_group_sup(
    sup: SalesUniversePair,
    settings: dict,
    verbose: bool = False,
    use_cache: bool = True,
    do_land_clusters: bool = True,
    do_impr_clusters: bool = True,
) -> SalesUniversePair:
    """
    Mark horizontal equity clusters on the 'universe' DataFrame of a SalesUniversePair.

    Updates the 'universe' DataFrame with horizontal equity clusters by calling
    `mark_horizontal_equity_clusters` and then sets the updated DataFrame in `sup`.

    Parameters
    ----------
    sup : SalesUniversePair
        SalesUniversePair containing sales and universe data.
    settings : dict
        Settings dictionary.
    verbose : bool, optional
        If True, prints progress information.
    use_cache : bool, optional
        If True, uses cached DataFrame if available.
    do_land_clusters : bool, optional
        If True, marks land horizontal equity clusters.
    do_impr_clusters : bool, optional
        If True, marks improvement horizontal equity clusters.

    Returns
    -------
    SalesUniversePair
        Updated SalesUniversePair with marked horizontal equity clusters.
    """

    df_universe = sup["universe"]
    if verbose:
        print("")
        print("Marking horizontal equity clusters...")
    df_universe = _mark_horizontal_equity_clusters_per_model_group(
        df_universe,
        settings,
        verbose,
        output_folder="horizontal_equity/general",
        use_cache=use_cache,
    )
    if do_land_clusters:
        if verbose:
            print("")
            print("Marking LAND horizontal equity clusters...")
        df_universe = _mark_horizontal_equity_clusters_per_model_group(
            df_universe,
            settings,
            verbose,
            settings_object="land_equity",
            id_name="land_he_id",
            output_folder="horizontal_equity/land",
            use_cache=use_cache,
        )
    if do_impr_clusters:
        if verbose:
            print("")
            print("Marking IMPROVEMENT horizontal equity clusters...")
        df_universe = _mark_horizontal_equity_clusters_per_model_group(
            df_universe,
            settings,
            verbose,
            settings_object="impr_equity",
            id_name="impr_he_id",
            output_folder="horizontal_equity/improvement",
            use_cache=use_cache,
        )
        sup.set("universe", df_universe)
    return sup