Skip to content

openaq_aws

OpenAQ archive data on AWS.

https://openaq.org/ https://registry.opendata.aws/openaq/ https://docs.openaq.org/aws/about

OpenAQAWSReader

Bases: PointReader

Reader for OpenAQ archive data on AWS S3.

Source code in monetio/readers/openaq_aws.py 
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 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
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
@register_reader("openaq_aws")
class OpenAQAWSReader(PointReader):
    """
    Reader for OpenAQ archive data on AWS S3.
    """

    def open_dataset(
        self,
        files: str | list[str] = None,
        dates: pd.DatetimeIndex | list[datetime] | datetime | str = None,
        siteid: str | list[str] = None,
        country: str | list[str] = None,
        provider: str | list[str] = None,
        find_paths: bool = True,
        wide_fmt: bool = False,
        as_xarray: bool = True,
        lazy: bool = False,
        **kwargs,
    ) -> Union[pd.DataFrame, xr.Dataset, "dd.DataFrame"]:
        """
        Retrieves OpenAQ archive data from AWS Open Data.

        Parameters
        ----------
        files : Union[str, List[str]], optional
            File path, list of paths, or glob pattern.
        dates : Union[pd.DatetimeIndex, List[datetime], datetime, str], optional
            Dates to retrieve if files are not provided.
        siteid : Union[str, List[str]], optional
            Site ID(s) (location_id) to filter by.
        country : Union[str, List[str]], optional
            Country code(s) to filter by.
        provider : Union[str, List[str]], optional
            Provider name(s) to filter by.
        find_paths : bool, optional
            Whether to find paths via S3 listing (slow), by default True.
        wide_fmt : bool, optional
            Whether to return data in wide format, by default True.
        as_xarray : bool, optional
            Whether to return an xarray.Dataset, by default True.
        lazy : bool, optional
            Whether to return a dask-backed object, by default False.
        **kwargs : dict
            Additional arguments passed to the reader and driver.

        Returns
        -------
        Union[pd.DataFrame, xr.Dataset, dd.DataFrame]
            The loaded dataset.

        Examples
        --------
        >>> reader = OpenAQAWSReader()
        >>> ds = reader.open_dataset(dates='2023-01-01', siteid='7073', wide_fmt=True)
        """

        # For backward compatibility, if the first argument looks like dates, swap them.
        if (
            files is not None
            and dates is None
            and isinstance(files, pd.DatetimeIndex | datetime | pd.Timestamp | list | str)
        ):
            if isinstance(files, pd.DatetimeIndex | datetime | pd.Timestamp):
                dates = files
                files = None
            elif isinstance(files, list) and len(files) > 0 and isinstance(files[0], datetime):
                dates = files
                files = None

        read_func = read_openaq_aws_csv

        if files is None and dates is not None:
            dates = _to_datetime_index(dates).dropna()
            if dates.empty:
                raise ValueError("must provide at least one datetime-like")

            if find_paths:
                paths = get_paths(dates, siteid=siteid, country=country, provider=provider)
                files = [f"s3://{p}" for p in paths]
            else:
                if siteid is None:
                    raise ValueError("must provide `siteid` when `find_paths` is false")
                files = build_urls(dates, siteid)
                read_func = read_openaq_aws_csv_robust

        if not files:
            # Handle empty
            if lazy:
                import dask.dataframe as dd

                df = dd.from_pandas(pd.DataFrame(), npartitions=1)
            else:
                df = pd.DataFrame()
            if as_xarray:
                return xr.Dataset()
            return df

        # Use base class to open
        # We pass wide_fmt=False here and handle it in to_xarray to maintain laziness.
        df = super().open_dataset(
            files,
            read_method=read_func,
            as_xarray=False,
            lazy=lazy,
            **kwargs,
        )

        if as_xarray:
            # Defer wide_fmt expansion to to_xarray (via ds_to_2d) to keep it lazy.
            ds = self.to_xarray(df, expand2d=wide_fmt, **kwargs)

            # Update history
            ds = update_history(ds, "Read OpenAQ AWS archive data.")
            return ds

        # For pandas path, we can apply wide_fmt here if requested
        if wide_fmt:
            from ..util import long_to_wide

            df = long_to_wide(df)

        return df

    def harmonize(
        self, df: Union[pd.DataFrame, "dd.DataFrame"]
    ) -> Union[pd.DataFrame, "dd.DataFrame"]:
        """
        Harmonize OpenAQ AWS data.

        Parameters
        ----------
        df : Union[pd.DataFrame, dd.DataFrame]
            Input dataframe.

        Returns
        -------
        Union[pd.DataFrame, dd.DataFrame]
            Harmonized dataframe.
        """
        # Rename parameter/unit to variable/units for MONETIO consistency
        df = df.rename(columns={"parameter": "variable", "unit": "units", "value": "obs"})

        # Unit Conversions (Lazy friendly)
        # Consistent with real-time OpenAQ reader
        ppm_to_ugm3 = {
            "o3": 1990,
            "co": 1160,
            "no2": 1900,
            "no": 1240,
            "so2": 2650,
            "ch4": 664,
            "co2": 1820,
        }
        ppm_to_ugm3["nox"] = ppm_to_ugm3["no2"]

        def _convert_units(df_part):
            if df_part.empty:
                return df_part
            for vn, f in ppm_to_ugm3.items():
                if "variable" in df_part.columns and "units" in df_part.columns:
                    # Match both standard and special characters
                    is_ug = (df_part.variable == vn) & (
                        df_part.units.isin(["µg/m³", "ug/m3", "ugm-3", "µgm-3"])
                    )
                    df_part.loc[is_ug, "obs"] /= f
                    df_part.loc[is_ug, "units"] = "ppm"
            return df_part

        try:
            import dask.dataframe as dd

            is_dask = isinstance(df, dd.DataFrame)
        except ImportError:
            is_dask = False

        if is_dask:
            df = df.map_partitions(_convert_units)
        else:
            df = _convert_units(df)

        # Update history
        df = update_history(df, "Harmonized OpenAQ AWS columns and converted units.")

        return super().harmonize(df)

    def to_xarray(
        self, df: Union[pd.DataFrame, "dd.DataFrame"], expand2d: bool = True, **kwargs
    ) -> xr.Dataset:
        """
        Convert to Xarray with consistent naming for OpenAQ variables.
        """
        ds = super().to_xarray(df, expand2d=expand2d, **kwargs)

        if expand2d:
            # Rename variables to match MONETIO convention (e.g. o3_ppm, pm25_ugm3)
            # consistent with real-time OpenAQReader.
            ppm_vars = ["o3", "co", "no2", "no", "so2", "ch4", "co2", "nox"]
            ugm3_vars = ["pm1", "pm25", "pm4", "pm10", "bc"]

            rename_dict = {}
            for v in ppm_vars:
                if v in ds.data_vars:
                    rename_dict[v] = f"{v}_ppm"
                    if f"{v}_unit" in ds.data_vars:
                        ds = ds.drop_vars(f"{v}_unit")
            for v in ugm3_vars:
                if v in ds.data_vars:
                    rename_dict[v] = f"{v}_ugm3"
                    if f"{v}_unit" in ds.data_vars:
                        ds = ds.drop_vars(f"{v}_unit")

            if rename_dict:
                ds = ds.rename(rename_dict)

            # Scientific Hygiene: update units in attributes if not already set correctly
            for v in ds.data_vars:
                if "_ppm" in v:
                    ds[v].attrs["units"] = "ppm"
                elif "_ugm3" in v:
                    ds[v].attrs["units"] = "µg m-3"

        return ds

harmonize(df)

Harmonize OpenAQ AWS data.

Parameters:

Name Type Description Default
df Union[DataFrame, DataFrame]

Input dataframe.

 required

Returns:

Type Description
Union[DataFrame, DataFrame]

Harmonized dataframe.
Source code in monetio/readers/openaq_aws.py 
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
def harmonize(
    self, df: Union[pd.DataFrame, "dd.DataFrame"]
) -> Union[pd.DataFrame, "dd.DataFrame"]:
    """
    Harmonize OpenAQ AWS data.

    Parameters
    ----------
    df : Union[pd.DataFrame, dd.DataFrame]
        Input dataframe.

    Returns
    -------
    Union[pd.DataFrame, dd.DataFrame]
        Harmonized dataframe.
    """
    # Rename parameter/unit to variable/units for MONETIO consistency
    df = df.rename(columns={"parameter": "variable", "unit": "units", "value": "obs"})

    # Unit Conversions (Lazy friendly)
    # Consistent with real-time OpenAQ reader
    ppm_to_ugm3 = {
        "o3": 1990,
        "co": 1160,
        "no2": 1900,
        "no": 1240,
        "so2": 2650,
        "ch4": 664,
        "co2": 1820,
    }
    ppm_to_ugm3["nox"] = ppm_to_ugm3["no2"]

    def _convert_units(df_part):
        if df_part.empty:
            return df_part
        for vn, f in ppm_to_ugm3.items():
            if "variable" in df_part.columns and "units" in df_part.columns:
                # Match both standard and special characters
                is_ug = (df_part.variable == vn) & (
                    df_part.units.isin(["µg/m³", "ug/m3", "ugm-3", "µgm-3"])
                )
                df_part.loc[is_ug, "obs"] /= f
                df_part.loc[is_ug, "units"] = "ppm"
        return df_part

    try:
        import dask.dataframe as dd

        is_dask = isinstance(df, dd.DataFrame)
    except ImportError:
        is_dask = False

    if is_dask:
        df = df.map_partitions(_convert_units)
    else:
        df = _convert_units(df)

    # Update history
    df = update_history(df, "Harmonized OpenAQ AWS columns and converted units.")

    return super().harmonize(df)

open_dataset(files=None, dates=None, siteid=None, country=None, provider=None, find_paths=True, wide_fmt=False, as_xarray=True, lazy=False, **kwargs)

Retrieves OpenAQ archive data from AWS Open Data.

Parameters:

Name Type Description Default
files Union[str, List[str]]

File path, list of paths, or glob pattern.

 None
dates Union[DatetimeIndex, List[datetime], datetime, str]

Dates to retrieve if files are not provided.

 None
siteid Union[str, List[str]]

Site ID(s) (location_id) to filter by.

 None
country Union[str, List[str]]

Country code(s) to filter by.

 None
provider Union[str, List[str]]

Provider name(s) to filter by.

 None
find_paths bool

Whether to find paths via S3 listing (slow), by default True.

 True
wide_fmt bool

Whether to return data in wide format, by default True.

 False
as_xarray bool

Whether to return an xarray.Dataset, by default True.

 True
lazy bool

Whether to return a dask-backed object, by default False.

 False
**kwargs dict

Additional arguments passed to the reader and driver.

 {}

Returns:

Type Description
Union[DataFrame, Dataset, DataFrame]

The loaded dataset.

Examples:

>>> reader = OpenAQAWSReader()
>>> ds = reader.open_dataset(dates='2023-01-01', siteid='7073', wide_fmt=True)
Source code in monetio/readers/openaq_aws.py 
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 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
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
def open_dataset(
    self,
    files: str | list[str] = None,
    dates: pd.DatetimeIndex | list[datetime] | datetime | str = None,
    siteid: str | list[str] = None,
    country: str | list[str] = None,
    provider: str | list[str] = None,
    find_paths: bool = True,
    wide_fmt: bool = False,
    as_xarray: bool = True,
    lazy: bool = False,
    **kwargs,
) -> Union[pd.DataFrame, xr.Dataset, "dd.DataFrame"]:
    """
    Retrieves OpenAQ archive data from AWS Open Data.

    Parameters
    ----------
    files : Union[str, List[str]], optional
        File path, list of paths, or glob pattern.
    dates : Union[pd.DatetimeIndex, List[datetime], datetime, str], optional
        Dates to retrieve if files are not provided.
    siteid : Union[str, List[str]], optional
        Site ID(s) (location_id) to filter by.
    country : Union[str, List[str]], optional
        Country code(s) to filter by.
    provider : Union[str, List[str]], optional
        Provider name(s) to filter by.
    find_paths : bool, optional
        Whether to find paths via S3 listing (slow), by default True.
    wide_fmt : bool, optional
        Whether to return data in wide format, by default True.
    as_xarray : bool, optional
        Whether to return an xarray.Dataset, by default True.
    lazy : bool, optional
        Whether to return a dask-backed object, by default False.
    **kwargs : dict
        Additional arguments passed to the reader and driver.

    Returns
    -------
    Union[pd.DataFrame, xr.Dataset, dd.DataFrame]
        The loaded dataset.

    Examples
    --------
    >>> reader = OpenAQAWSReader()
    >>> ds = reader.open_dataset(dates='2023-01-01', siteid='7073', wide_fmt=True)
    """

    # For backward compatibility, if the first argument looks like dates, swap them.
    if (
        files is not None
        and dates is None
        and isinstance(files, pd.DatetimeIndex | datetime | pd.Timestamp | list | str)
    ):
        if isinstance(files, pd.DatetimeIndex | datetime | pd.Timestamp):
            dates = files
            files = None
        elif isinstance(files, list) and len(files) > 0 and isinstance(files[0], datetime):
            dates = files
            files = None

    read_func = read_openaq_aws_csv

    if files is None and dates is not None:
        dates = _to_datetime_index(dates).dropna()
        if dates.empty:
            raise ValueError("must provide at least one datetime-like")

        if find_paths:
            paths = get_paths(dates, siteid=siteid, country=country, provider=provider)
            files = [f"s3://{p}" for p in paths]
        else:
            if siteid is None:
                raise ValueError("must provide `siteid` when `find_paths` is false")
            files = build_urls(dates, siteid)
            read_func = read_openaq_aws_csv_robust

    if not files:
        # Handle empty
        if lazy:
            import dask.dataframe as dd

            df = dd.from_pandas(pd.DataFrame(), npartitions=1)
        else:
            df = pd.DataFrame()
        if as_xarray:
            return xr.Dataset()
        return df

    # Use base class to open
    # We pass wide_fmt=False here and handle it in to_xarray to maintain laziness.
    df = super().open_dataset(
        files,
        read_method=read_func,
        as_xarray=False,
        lazy=lazy,
        **kwargs,
    )

    if as_xarray:
        # Defer wide_fmt expansion to to_xarray (via ds_to_2d) to keep it lazy.
        ds = self.to_xarray(df, expand2d=wide_fmt, **kwargs)

        # Update history
        ds = update_history(ds, "Read OpenAQ AWS archive data.")
        return ds

    # For pandas path, we can apply wide_fmt here if requested
    if wide_fmt:
        from ..util import long_to_wide

        df = long_to_wide(df)

    return df

to_xarray(df, expand2d=True, **kwargs)

Convert to Xarray with consistent naming for OpenAQ variables.

Source code in monetio/readers/openaq_aws.py 
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
def to_xarray(
    self, df: Union[pd.DataFrame, "dd.DataFrame"], expand2d: bool = True, **kwargs
) -> xr.Dataset:
    """
    Convert to Xarray with consistent naming for OpenAQ variables.
    """
    ds = super().to_xarray(df, expand2d=expand2d, **kwargs)

    if expand2d:
        # Rename variables to match MONETIO convention (e.g. o3_ppm, pm25_ugm3)
        # consistent with real-time OpenAQReader.
        ppm_vars = ["o3", "co", "no2", "no", "so2", "ch4", "co2", "nox"]
        ugm3_vars = ["pm1", "pm25", "pm4", "pm10", "bc"]

        rename_dict = {}
        for v in ppm_vars:
            if v in ds.data_vars:
                rename_dict[v] = f"{v}_ppm"
                if f"{v}_unit" in ds.data_vars:
                    ds = ds.drop_vars(f"{v}_unit")
        for v in ugm3_vars:
            if v in ds.data_vars:
                rename_dict[v] = f"{v}_ugm3"
                if f"{v}_unit" in ds.data_vars:
                    ds = ds.drop_vars(f"{v}_unit")

        if rename_dict:
            ds = ds.rename(rename_dict)

        # Scientific Hygiene: update units in attributes if not already set correctly
        for v in ds.data_vars:
            if "_ppm" in v:
                ds[v].attrs["units"] = "ppm"
            elif "_ugm3" in v:
                ds[v].attrs["units"] = "µg m-3"

    return ds

add_data(dates, *, siteid=None, country=None, provider=None, find_paths=True, wide_fmt=False, n_procs=1, **kwargs)

Helper for consistency.

Source code in monetio/readers/openaq_aws.py 
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
def add_data(
    dates,
    *,
    siteid=None,
    country=None,
    provider=None,
    find_paths=True,
    wide_fmt=False,
    n_procs=1,
    **kwargs,
):
    """Helper for consistency."""
    return OpenAQAWSReader().open_dataset(
        dates=dates,
        siteid=siteid,
        country=country,
        provider=provider,
        find_paths=find_paths,
        wide_fmt=wide_fmt,
        as_xarray=False,  # Return DataFrame by default for add_data legacy
        **kwargs,
    )

build_urls(dates, sites, *, protocol='s3')

Naively build URLs for OpenAQ archive data on AWS.

Source code in monetio/readers/openaq_aws.py 
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
def build_urls(dates, sites, *, protocol="s3"):
    """Naively build URLs for OpenAQ archive data on AWS."""
    dates = _to_datetime_index(dates)
    sites = _maybe_to_list(sites, not_none=True)

    if protocol.lower() == "s3":
        pref = "s3://openaq-data-archive"
    elif protocol.lower() in {"http", "https"}:
        pref = f"{protocol.lower()}://openaq-data-archive.s3.amazonaws.com"
    else:
        raise ValueError(f"protocol: {protocol!r}")

    urls = []
    for site in sites:
        for date in dates.floor("D").unique():
            urls.append(
                f"{pref}/records/csv.gz/"
                f"locationid={site}/year={date:%Y}/month={date:%m}/"
                f"location-{site}-{date:%Y%m%d}.csv.gz"
            )

    return urls

get_locations(*, provider=None, country=None)

Get location IDs corresponding to provider(s) and/or country(ies).

Source code in monetio/readers/openaq_aws.py 
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
def get_locations(*, provider=None, country=None):
    """Get location IDs corresponding to provider(s) and/or country(ies)."""
    import re

    from ..util import _import_required

    s3fs = _import_required("s3fs")

    fs = s3fs.S3FileSystem(anon=True)
    country = _maybe_to_list(country)
    if provider is None:
        providers = get_providers()
    else:
        providers = _maybe_to_list(provider, not_none=True)

    paths = []
    for prvdr in providers:
        if country is None:
            countries = get_provider_countries(prvdr)
        else:
            countries = country

        for cntry in countries:
            glb = (
                "openaq-data-archive/records/csv.gz/"
                f"provider={prvdr.lower()}/country={cntry.lower()}/"
            )
            prvdr_cntry_paths = fs.find(glb, withdirs=True, maxdepth=1)
            paths.extend(prvdr_cntry_paths)

    rows = []
    for p in paths:
        m = re.fullmatch(
            r"openaq-data-archive/records/csv\.gz/"
            r"provider=([a-z0-9\-]+)/country=([a-z]{2}|\-\-|99|mobile)/"
            r"locationid=([0-9]+)",
            p,
        )
        if m is not None:
            rows.append(m.groups())

    df = pd.DataFrame(rows, columns=["provider", "country", "siteid"])
    return df

get_paths(dates, *, siteid=None, country=None, provider=None)

Get site-day paths, searching independently by location ID, country, and provider.

Source code in monetio/readers/openaq_aws.py 
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
def get_paths(dates, *, siteid=None, country=None, provider=None):
    """Get site-day paths, searching independently by location ID, country, and provider."""
    from ..util import _import_required

    s3fs = _import_required("s3fs")

    fs = s3fs.S3FileSystem(anon=True)

    dates = _to_datetime_index(dates)
    location_ids = _maybe_to_list(siteid)
    providers = _maybe_to_list(provider)
    countries = _maybe_to_list(country)

    if location_ids is None and providers is None and countries is None:
        warnings.warn(
            "location ID(s) not provided; using all locations, which may be quite slow",
            stacklevel=2,
        )
        location_ids = ["*"]

    unique_dates = dates.floor("D").unique()

    paths = []

    if location_ids is not None:
        tpl = (
            "openaq-data-archive/records/csv.gz/"
            "locationid={loc}/year={date:%Y}/month={date:%m}/"
            "location-{loc}-{date:%Y%m%d}.csv.gz"
        )
        for date in unique_dates:
            for loc in location_ids:
                glb = tpl.format(loc=loc, date=date)
                if "*" in glb:
                    loc_date_paths = fs.glob(glb)
                    paths.extend(loc_date_paths)
                else:
                    if fs.exists(glb):
                        paths.append(glb)

    if providers is not None:
        tpl = (
            "openaq-data-archive/records/csv.gz/"
            "provider={prvdr}/country=*/locationid={loc}/"
            "year={date:%Y}/month={date:%m}/"
            "location-{loc}-{date:%Y%m%d}.csv.gz"
        )
        for date in unique_dates:
            for prvdr in providers:
                glb = tpl.format(prvdr=prvdr.lower(), loc="*", date=date)
                prvdr_date_paths = fs.glob(glb)
                paths.extend(prvdr_date_paths)

    if countries is not None:
        tpl = (
            "openaq-data-archive/records/csv.gz/"
            "provider=*/country={cntry}/locationid={loc}/"
            "year={date:%Y}/month={date:%m}/"
            "location-{loc}-{date:%Y%m%d}.csv.gz"
        )
        for date in unique_dates:
            for cntry in countries:
                glb = tpl.format(cntry=cntry.lower(), loc="*", date=date)
                cntry_date_paths = fs.glob(glb)
                paths.extend(cntry_date_paths)

    return sorted(set(paths))

get_provider_countries(provider)

Get countries for a given provider.

Source code in monetio/readers/openaq_aws.py 
431
432
433
434
435
436
437
438
439
440
441
def get_provider_countries(provider):
    """Get countries for a given provider."""
    from ..util import _import_required

    s3fs = _import_required("s3fs")

    fs = s3fs.S3FileSystem(anon=True)
    glb = f"openaq-data-archive/records/csv.gz/provider={provider.lower()}/country=*"
    paths = fs.glob(glb, maxdepth=1)
    countries = [p.split("=")[2] for p in paths]
    return countries

get_providers()

Get OpenAQ data providers by searching the bucket paths.

Source code in monetio/readers/openaq_aws.py 
419
420
421
422
423
424
425
426
427
428
def get_providers():
    """Get OpenAQ data providers by searching the bucket paths."""
    from ..util import _import_required

    s3fs = _import_required("s3fs")

    fs = s3fs.S3FileSystem(anon=True)
    paths = fs.glob("openaq-data-archive/records/csv.gz/provider=*", maxdepth=1)
    providers = [p.split("=")[1] for p in paths]
    return providers

read(fp, **kwargs)

Legacy wrapper.

Source code in monetio/readers/openaq_aws.py 
518
519
520
def read(fp, **kwargs):
    """Legacy wrapper."""
    return read_openaq_aws_csv(fp, **kwargs)

read_openaq_aws_csv(fp, **kwargs)

Read OpenAQ archive data from a file-like object.

Parameters:

Name Type Description Default
fp str

File path or URL.

 required
**kwargs dict

Additional arguments passed to pd.read_csv.

 {}

Returns:

Type Description
DataFrame

OpenAQ archive data.
Source code in monetio/readers/openaq_aws.py 
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
def read_openaq_aws_csv(fp: str, **kwargs) -> pd.DataFrame:
    """
    Read OpenAQ archive data from a file-like object.

    Parameters
    ----------
    fp : str
        File path or URL.
    **kwargs : dict
        Additional arguments passed to pd.read_csv.

    Returns
    -------
    pd.DataFrame
        OpenAQ archive data.
    """
    # Filter out MONETIO internal keywords to prevent TypeError in pd.read_csv
    skip = ["lazy", "as_xarray", "wide_fmt", "dates", "siteid", "country", "provider", "find_paths"]
    csv_kwargs = {k: v for k, v in kwargs.items() if k not in skip}

    df = pd.read_csv(
        fp,
        dtype={
            0: str,  # location_id
            1: str,  # sensor_id
            2: str,  # location
            3: str,  # datetime
            4: float,  # lat
            5: float,  # lon
            6: str,  # parameter
            7: str,  # unit
            8: float,  # value
        },
        parse_dates=["datetime"],
        **csv_kwargs,
    )

    # Normalize to web API column names
    if "sensors_id" in df.columns:
        df = df.rename(columns={"sensors_id": "sensor_id"})
    if "unit" in df.columns:
        df = df.rename(columns={"unit": "units"})

    df = df.rename(
        columns={
            "location_id": "siteid",
            "datetime": "time",
            "lat": "latitude",
            "lon": "longitude",
        }
    )

    # Convert to UTC, non-localized
    if not df.empty:
        if df["time"].dt.tz is not None:
            df["time"] = df["time"].dt.tz_convert("UTC").dt.tz_localize(None)

    return df

read_openaq_aws_csv_robust(fp, **kwargs)

Try to read a file, returning empty DF if not found.

Source code in monetio/readers/openaq_aws.py 
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
def read_openaq_aws_csv_robust(fp: str, **kwargs) -> pd.DataFrame:
    """Try to read a file, returning empty DF if not found."""
    try:
        return read_openaq_aws_csv(fp, **kwargs)
    except Exception:
        # Many archive files might be missing or empty
        return pd.DataFrame(
            columns=[
                "siteid",
                "sensor_id",
                "location",
                "time",
                "latitude",
                "longitude",
                "parameter",
                "units",
                "value",
            ]
        )