Skip to content

utils

aggregate_to_hierarchy(data: pd.DataFrame, hierarchy: pd.DataFrame) -> pd.DataFrame

Create all aggregate climate values for a given hierarchy from most-detailed data.

Parameters

data The most-detailed climate data to aggregate. hierarchy The hierarchy to aggregate the data to.

Returns

pd.DataFrame The climate data with values for all levels of the hierarchy.

Source code in src/climate_data/special/utils.py 
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
def aggregate_to_hierarchy(data: pd.DataFrame, hierarchy: pd.DataFrame) -> pd.DataFrame:
    """Create all aggregate climate values for a given hierarchy from most-detailed data.

    Parameters
    ----------
    data
        The most-detailed climate data to aggregate.
    hierarchy
        The hierarchy to aggregate the data to.

    Returns
    -------
    pd.DataFrame
        The climate data with values for all levels of the hierarchy.
    """
    agg_cols = sorted(
        set(data.columns) - {"location_id", "year_id", "temperature_zone"}
    )

    results = data.set_index("location_id")

    # Most detailed locations can be at multiple levels of the hierarchy,
    # so we loop over all levels from most detailed to global, aggregating
    # level by level and appending the results to the data.

    for level in reversed(list(range(1, hierarchy.level.max() + 1))):
        level_mask = hierarchy.level == level
        parent_map = hierarchy.loc[level_mask].set_index("location_id").parent_id

        subset = results.loc[results.index.intersection(parent_map.index)]
        subset["parent_id"] = parent_map

        parent_values = (
            subset.groupby(["year_id", "parent_id", "temperature_zone"])[agg_cols]
            .sum()
            .reset_index()
            .rename(columns={"parent_id": "location_id"})
            .set_index("location_id")
        )
        results = pd.concat([results, parent_values])
    results = (
        results.reset_index()
        .sort_values(["location_id", "year_id", "temperature_zone"])
        .reset_index(drop=True)
    )

    return results