sdmxabs

38class CacheError(Exception):
39    """A problem retrieving data from the cache."""

45class GetFileKwargs(TypedDict):
46    """TypedDict for acqure_url function arguments."""
47
48    verbose: NotRequired[bool]
49    """If True, print information about the data retrieval process."""
50    modality: NotRequired[ModalityType]
51    """Kind of retrieval: "prefer_cache", "prefer_url"."""

34class HttpError(Exception):
35    """A problem retrieving data using HTTP."""

17class MatchType(Enum):
18    """Enumeration for match types."""
19
20    EXACT = 1
21    PARTIAL = 2
22    REGEX = 3

 96@cache
 97def code_lists(cl_id: str, **kwargs: Unpack[GetFileKwargs]) -> FlowMetaDict:
 98    """Get the code list metadata from the ABS SDMX API.
 99
100    Args:
101        cl_id (str): The ID of the code list to retrieve.
102        **kwargs: Additional keyword arguments passed to acquire_url().
103
104    Returns:
105        FlowMetaDict: A dictionary containing the codes and
106            their associated key=value pairs. A "name" key should always
107            be present. A "parent" key may also be present.
108
109    Raises:
110        HttpError: If there is an issue with the HTTP request.
111        CacheError: If there is an issue with the cache.
112        ValueError: If no XML root is found in the response.
113
114    Note:
115        You will get a CacheError if the codelist is not found on the ABS SDMX API.
116        (This package tries the website first, then the cache.)
117
118    Guarantees for the inner dictionary:
119        - The inner dictionary will always have a "name" key.
120        - The inner dictionary may have a "parent" key if the code has a parent.
121
122    """
123    tree = acquire_xml(f"{URL_STEM}/codelist/ABS/{cl_id}", **kwargs)
124
125    codes: FlowMetaDict = {}
126    for code in tree.findall(".//str:Code", NAME_SPACES):
127        code_id = code.get("id", None)
128        if code_id is None:
129            continue
130        elements: dict[str, str] = {}
131
132        # - get the name
133        name = code.find("com:Name", NAME_SPACES)
134        if name is None or not name.text:
135            # guarantee that we name key and value pair
136            print(f"Warning: Code {code_id} in {cl_id}has no name, skipping.")
137            continue  # skip if no name
138        elements["name"] = name.text
139
140        # - get the parent
141        parent = code.find("str:Parent", NAME_SPACES)
142        parent_id = ""
143        if parent is not None:
144            ref = parent.find("Ref", NAME_SPACES)
145            if ref is not None:
146                parent_id = str(ref.get("id", ""))
147        if parent_id:  # Only add if not empty
148            elements["parent"] = parent_id
149
150        codes[code_id] = elements
151
152    return codes

55@cache
56def data_dimensions(flow_id: str, **kwargs: Unpack[GetFileKwargs]) -> FlowMetaDict:
57    """Get the data dimensions and attributes metadata from the ABS SDMX API.
58
59    Args:
60        flow_id (str): The ID of the dataflow to retrieve dimensions for.
61        **kwargs: Additional keyword arguments passed to acquire_url().
62
63    Returns:
64        dict[str, dict[str, str]]: A dictionary containing the dimensions and
65            their metadata in key=value pairs.
66
67    Raises:
68        HttpError: If there is an issue with the HTTP request.
69        CacheError: If there is an issue with the cache.
70        ValueError: If no XML root is found in the response.
71
72    Note:
73        The dimensions metadata includes a "position" for each dimmension.
74        The attributes metadata does not have "position" information.
75
76    """
77    tree = acquire_xml(f"{URL_STEM}/datastructure/ABS/{flow_id}", **kwargs)
78
79    elements = {}
80    for ident in ["Dimension", "Attribute"]:
81        for elem in tree.findall(f".//str:{ident}", NAME_SPACES):
82            element_id = elem.get("id")
83            if element_id is None:
84                continue
85            contents = {}
86            if ident == "Dimension":
87                contents["position"] = elem.get("position", "")
88            if (lr := elem.find("str:LocalRepresentation", NAME_SPACES)) is not None and (
89                enumer := lr.find("str:Enumeration/Ref", NAME_SPACES)
90            ) is not None:
91                contents = contents | enumer.attrib
92            elements[element_id] = contents
93    return elements

22@cache
23def data_flows(flow_id: str = "all", **kwargs: Unpack[GetFileKwargs]) -> FlowMetaDict:
24    """Get the toplevel metadata from the ABS SDMX API.
25
26    Args:
27        flow_id (str): The ID of the dataflow to retrieve. Defaults to "all".
28        **kwargs: Additional keyword arguments passed to acquire_url().
29
30    Returns:
31        dict[str, dict[str, str]]: A dictionary containing the dataflow IDs
32            and their metadatain key=value pairs.
33
34    Raises:
35        HttpError: If there is an issue with the HTTP request.
36        CacheError: If there is an issue with the cache.
37        ValueError: If no XML root is found in the response.
38
39    """
40    tree = acquire_xml(f"{URL_STEM}/dataflow/ABS/{flow_id}", **kwargs)
41
42    d_flows: FlowMetaDict = {}
43    for dataflow in tree.findall(".//str:Dataflow", NAME_SPACES):
44        attributes: dict[str, str] = dataflow.attrib.copy()
45        if "id" not in attributes:
46            continue
47        df_id = attributes.pop("id")
48        name_elem = dataflow.find("com:Name", NAME_SPACES)
49        df_name = name_elem.text if name_elem is not None else "(missing name)"
50        attributes["name"] = str(df_name)  # str(...) because pylance complains about it being None
51        d_flows[df_id] = attributes
52    return d_flows

200def fetch(
201    flow_id: str,
202    dims: dict[str, str] | None = None,
203    parameters: dict[str, str] | None = None,
204    *,
205    validate: bool = False,
206    **kwargs: Unpack[GetFileKwargs],
207) -> tuple[pd.DataFrame, pd.DataFrame]:
208    """Fetch data from the ABS SDMX API.
209
210    Args:
211        flow_id (str): The ID of the data flow from which to retrieve data items.
212        dims (dict[str, str], optional): A dictionary of dimensions to select the
213            data items. If None, the ABS fetch request will be for all data items,
214            which can be slow.
215        parameters (dict[str, str], optional): A dictionary of SDMX parameters to apply
216            to the data request. Supported parameters include:
217            - 'startPeriod': Start period for data filtering (e.g., '2020-Q1')
218            - 'endPeriod': End period for data filtering (e.g., '2023-Q4')
219            - 'detail': Level of detail ('full', 'dataonly', 'serieskeysonly', 'nodata')
220            If None, no parameters are applied.
221        validate (bool, optional): If True, validate `dims` against the flow's
222            required dimensions when generating the URL key. Defaults to False.
223        **kwargs (GetFileKwargs): Additional keyword arguments passed to acquire_xml().
224
225    Returns: a tuple of two DataFrames:
226        - The first DataFrame contains the fetched data.
227        - The second DataFrame contains the metadata.
228
229    Raises:
230        HttpError: If there is an issue with the HTTP request.
231        CacheError: If there is an issue with the cache.
232        ValueError: If no XML root is found in the response.
233        ValueError: If invalid parameter values are provided.
234
235    Notes:
236        If the `dims` argument is not valid you should get a CacheError or HttpError.
237        If the `flow_id` is not valid, you should get a ValueError.
238
239    """
240    # --- report the parameters used if requested
241    verbose = kwargs.get("verbose", False)
242    if verbose:
243        print(f"fetch(): {flow_id=} {dims=} {parameters=} {validate=} {kwargs=}")
244
245    # --- validate parameters
246    valid_detail_values = {"full", "dataonly", "serieskeysonly", "nodata"}
247    if parameters:
248        detail_value = parameters.get("detail")
249        if detail_value and detail_value not in valid_detail_values:
250            raise ValueError(f"Invalid detail value '{detail_value}'. Must be one of: {valid_detail_values}")
251
252    # --- prepare to get the XML root from the ABS SDMX API
253    # prefer fresh data every time
254    kwargs["modality"] = kwargs.get("modality", "prefer-url")
255    key = build_key(flow_id, dims, validate=validate)
256
257    # --- build URL with optional parameters
258    url = f"{URL_STEM}/data/{flow_id}/{key}"
259    if parameters:
260        url_params = []
261        if "startPeriod" in parameters:
262            url_params.append(f"startPeriod={parameters['startPeriod']}")
263        if "endPeriod" in parameters:
264            url_params.append(f"endPeriod={parameters['endPeriod']}")
265        if "detail" in parameters:
266            url_params.append(f"detail={parameters['detail']}")
267        if url_params:
268            url += "?" + "&".join(url_params)
269
270    xml_root = acquire_xml(url, **kwargs)
271    return _extract(flow_id, xml_root)

18def fetch_gdp(
19    seasonality: Literal["o", "s", "t"] = "o",
20    price_measure: Literal["cp", "cvm"] = "cp",
21    parameters: dict[str, str] | None = None,
22    *,
23    validate: bool = False,
24    **kwargs: Unpack[GetFileKwargs],
25) -> tuple[pd.DataFrame, pd.DataFrame]:
26    """Fetch quarterly GDP data in $ from the ABS SDMX API.
27
28    Args:
29        seasonality (str): Type of seasonal adjustment to apply:
30            - "o": Original data without seasonal adjustment (default)
31            - "s": Seasonally adjusted data
32            - "t": Trend data
33        price_measure (str): Price measure type:
34            - "cp": Current prices (default)
35            - "cvm": Chain volume measures
36        parameters (dict[str, str] | None): Additional parameters for the API request,
37            such as 'startPeriod'.
38        validate (bool, optional): If True, validate the selection against the flow's
39            required dimensions when generating the URL key. Defaults to False.
40        **kwargs: Additional arguments passed to the fetch_selection() function
41
42    Returns:
43        tuple[pd.DataFrame, pd.DataFrame]: A tuple containing the GDP data and metadata
44
45    Raises:
46        ValueError: If invalid seasonality or price_measure values are provided
47
48    """
49    # report the parameters used if requested
50    verbose = kwargs.get("verbose", False)
51    if verbose:
52        print(f"fetch_gdp(): {seasonality=}, {price_measure=} {validate=} {kwargs=}")
53
54    # Validate inputs
55    if seasonality not in SEAS_MAP:
56        error = f"Invalid '{seasonality=}'. Must be one of: {list(SEAS_MAP.keys())}"
57        raise ValueError(error)
58    if price_measure not in PRICE_MAP:
59        error = f"Invalid '{price_measure=}'. Must be one of: {list(PRICE_MAP.keys())}"
60        raise ValueError(error)
61
62    # build a selection criteria
63    selection_criteria = []
64    selection_criteria.append(match_item(SEAS_MAP[seasonality], "TSEST", Mt.EXACT))
65    selection_criteria.append(match_item(PRICE_MAP[price_measure], "MEASURE", Mt.EXACT))
66    selection_criteria.append(match_item("Gross domestic product", "DATA_ITEM", Mt.EXACT))
67
68    # return the data
69    flow_id = "ANA_AGG"
70    return fetch_selection(flow_id, selection_criteria, parameters, validate=validate, **kwargs)

116def fetch_multi(
117    wanted: pd.DataFrame,
118    parameters: dict[str, str] | None = None,
119    *,
120    validate: bool = False,
121    **kwargs: Unpack[GetFileKwargs],
122) -> tuple[pd.DataFrame, pd.DataFrame]:
123    """Fetch multiple SDMX datasets based on a DataFrame of desired datasets.
124
125    Args:
126        wanted: A DataFrame with rows for each desired data set (of one or more series).
127                Each row should contain the necessary identifiers to fetch the dataset.
128                The columns will be 'flow_id', plus the ABS dimensions relevant to the flow.
129                The 'flow_id' column is mandatory, and the rest are optional.
130                Note: the DataFrame index is not used in the fetching process.
131        parameters: A dictionary of additional parameters to pass to the fetch function.
132        validate: If True, the function will validate dimensions and values against
133                  the ABS SDMX API codelists. Defaults to False.
134        **kwargs: Additional keyword arguments passed to the underlying data fetching function.
135
136    Returns:
137        A tuple containing two DataFrames:
138        - The first DataFrame contains the fetched data.
139        - The second DataFrame contains metadata about the fetched datasets.
140
141    Raises:
142        ValueError: If the 'flow_id' column is missing from the `wanted` DataFrame.
143
144    Note:
145        CacheError and HttpError are raised by the fetch function.
146        These will be caught and reported to standard output.
147
148    Note:
149        The function validates that all datasets have compatible index types.
150        A ValueError will be raised if incompatible index types are detected
151        (e.g., mixing quarterly and monthly data).
152
153    """
154    # --- report the parameters used if requested
155    verbose = kwargs.get("verbose", False)
156    if verbose:
157        print(f"fetch_multi(): {wanted=}, {parameters=}, {validate=}, {kwargs=}")
158
159    # --- quick sanity checks
160    if wanted.empty:
161        print("wanted DataFrame is empty, returning empty DataFrames.")
162        return pd.DataFrame(), pd.DataFrame()
163    if "flow_id" not in wanted.columns:
164        raise ValueError("The 'flow_id' column is required in the 'wanted' DataFrame.")
165
166    # --- do the work
167    return _extract(wanted, parameters, validate=validate, **kwargs)

107def fetch_pop(
108    source: Literal["erp", "na"] = "erp",
109    parameters: dict[str, str] | None = None,
110    *,
111    projection: bool = False,
112    validate: bool = False,
113    **kwargs: Unpack[GetFileKwargs],
114) -> tuple[pd.DataFrame, pd.DataFrame]:
115    """Fetch Estimated Resident Population (ERP) data from the ABS SDMX API.
116
117    Args:
118        source (str): Source of the population data:
119            - "erp": ABS published Estimated Resident Population (default)
120            - "na": Implied population from the ABS National Accounts
121        parameters (dict[str, str] | None): Additional parameters for the API request,
122            such as 'startPeriod'.
123        projection (bool, optional): If True, and data is available for the most recent year,
124            make a projection forward to the current quarter, based on growth over the last 4 quarters.
125        validate (bool, optional): If True, validate the selection against the flow's
126            required dimensions when generating the URL key. Defaults to False.
127        **kwargs: Additional arguments passed to the fetch_selection() function
128
129    Returns:
130        tuple[pd.DataFrame, pd.DataFrame]: A tuple containing the population data and metadata
131
132    """
133    # report the parameters used if requested
134    verbose = kwargs.get("verbose", False)
135    if verbose:
136        print(f"fetch_pop(): {source=} {validate=} {kwargs=}")
137
138    # build a selection criteria and fetch the relevant data
139    match source:
140        case "erp":
141            data, meta = _erp_population(parameters, validate=validate, **kwargs)
142        case "na":
143            data, meta = _na_population(parameters, validate=validate, **kwargs)
144        case _:
145            raise ValueError(f"Invalid source '{source}'. Must be one of: ['erp', 'na']")
146
147    # if requested, make a projection of the data
148    if projection:
149        data = _make_projection(data)
150
151    return data, meta

203def fetch_selection(
204    flow_id: str,
205    criteria: MatchCriteria,
206    parameters: dict[str, str] | None = None,
207    *,
208    validate: bool = False,
209    **kwargs: Unpack[GetFileKwargs],
210) -> tuple[pd.DataFrame, pd.DataFrame]:
211    """Fetch data based on a selection criteria for items.
212
213    Args:
214        flow_id (str): The ID of the data flow to fetch.
215        criteria (MatchCriteria): A sequence of match criteria to filter the data.
216        parameters (dict[str, str] | None, optional): Additional parameters for the fetch.
217        validate (bool, optional): If True, validate the selection against the flow's
218            required dimensions when generating the URL key. Defaults to False.
219        **kwargs: Additional keyword arguments for the fetch_multi function.
220
221    Returns:
222        tuple[pd.DataFrame, pd.DataFrame]: A tuple containing the fetched data and metadata.
223
224    """
225    verbose = kwargs.get("verbose", False)
226    if verbose:
227        print(f"fetch_selection(): {flow_id=} {criteria=} {parameters=} {validate=} {kwargs=}")
228
229    selection = make_wanted(flow_id, criteria)
230    return fetch_multi(selection, parameters, validate=validate, **kwargs)

169def make_wanted(
170    flow_id: str,
171    criteria: MatchCriteria,
172) -> pd.DataFrame:
173    """Build a `wanted` Dataframe for use by fetch_multi() by matching flow metadata.
174
175    Args:
176        flow_id (str): The ID of the data flow to select items from.
177        criteria (MatchCriteria): A sequence of tuples containing the pattern,
178            dimension name, and match-type (exact, partial, or regex).
179
180    Returns:
181        pd.DataFrame: A DataFrame containing the selected items, which can be dropped
182            into the call of the function fetch_multi().
183
184    Raises:
185        ValueError: If the flow_id is not valid or if no items match the criteria.
186
187    Notes:
188    -   Should build a one line DataFrame. This Frame may select multiple data series,
189        when passed to fetch_multi. It also can be concatenated with other DataFrames
190        to build a larger selection.
191    -   If two match elements refer to the same dimension, only the `intersection` of the
192        matches will be returned.
193
194    """
195    dimensions = _validate_flow_and_dimensions(flow_id)
196    result_dict = _process_match_criteria(criteria, flow_id, dimensions)
197
198    # Add flow_id and return as DataFrame
199    result_dict["flow_id"] = flow_id
200    return pd.DataFrame([result_dict]).astype(str)

150def match_item(
151    pattern: str,
152    dimension: str,
153    match_type: MatchType = MatchType.PARTIAL,
154) -> MatchItem:
155    """Create a new MatchItem for use in select_items() and fetch_selection().
156
157    Args:
158        pattern (str): The pattern to match.
159        dimension (str): The dimension to match against.
160        match_type (MatchType, optional): The type of match to perform. Defaults to MatchType.EXACT.
161
162    Returns:
163        MatchElement: A tuple representing the match element.
164
165    """
166    return (pattern, dimension, match_type)

107def measure_names(meta: pd.DataFrame) -> pd.Series:
108    """Get the measure names for each row in the metadata DataFrame - (for y-axis labels).
109
110    Args:
111        meta (pd.DataFrame): The metadata DataFrame.
112
113    Returns:
114        pd.Series: A Series containing the measure names, indexed by the row labels.
115
116    """
117    series = pd.Series(dtype=str)
118    duplicate_number: str = " Number"
119    for label, row in meta.iterrows():
120        name: str = str(label)  # worst case scenario
121        if "UNIT_MEASURE" in row:
122            name = str(row["UNIT_MEASURE"])
123        if row.get("UNIT_MULT"):
124            try:
125                index = int(row["UNIT_MULT"])
126                if index in INDICIES and index > 0:
127                    name = f"{INDICIES[index]} {name}"
128            except ValueError:
129                pass
130        name = name.removesuffix(duplicate_number)
131        series[label] = name
132    return series

135def recalibrate(
136    data: pd.DataFrame, units: pd.Series, *, as_a_whole: bool = False
137) -> tuple[pd.DataFrame, pd.Series]:
138    """Recalibrate the data so that its maximum value is between 1 and 1000.
139
140    Args:
141        units (pd.Series): The units of measure (as returned by measure_names()).
142        data (pd.DataFrame): The data to recalibrate.
143        as_a_whole (bool): If True, recalibrate the data as a whole, otherwise
144            recalibrate each column separately.
145
146    Returns:
147        tuple[pd.Series, pd.DataFrame]: The recalibrated units and recalibrated data.
148
149    Why recalibrate?
150        So that the chart is easier to read and interpret, in units that are more familiar.
151
152    """
153    # --- data/argument validation
154    if units.empty:
155        raise ValueError("The units Series is empty.")
156    if len(units) != len(data.columns):
157        raise ValueError("The units Series must have the same length as the data DataFrame's columns.")
158    if as_a_whole and not _is_all_the_same(units):
159        raise ValueError("Cannot recalibrate as a whole when there are multiple units of measure.")
160    if not all(x in data.columns for x in units.index):
161        raise ValueError("The units Series must all be indexed by the data DataFrame's columns.")
162
163    if as_a_whole:
164        label = units.iloc[0]
165        datax, label = refactor(data, label)
166        units.index = pd.Index([label] * len(units))
167        return pd.DataFrame(datax), units
168
169    for column in data.columns:
170        label = units[column]
171        series = data[column]
172        seriesx, label = refactor(series, label)
173        data[column] = cast("pd.Series", seriesx)
174        units[column] = label
175
176    return data, units

179def recalibrate_series(series: pd.Series, label: str) -> tuple[pd.Series, str]:
180    """Recalibrate a Series with a label.
181
182    Args:
183        series (pd.Series): The Series to recalibrate.
184        label (str): The label for the Series.
185
186    Returns:
187        tuple[pd.Series, str]: The recalibrated Series and label.
188
189    """
190    seriesx, label = refactor(series, label)
191    return cast("pd.Series", seriesx), label