Skip to content

base

datasets._base

Base classes for Datasets.

HuggingFaceDataset 

HuggingFaceDataset(
    path: str,
    version: Optional[str] = None,
    type: Optional[str] = None,
    numerical_columns: Optional[list[str]] = None,
    categorical_columns: Optional[list[str]] = None,
    target: Optional[str] = None,
    resolution: Optional[int] = None,
)

Bases: ABC

Abstract class for HuggingFace datasets.

Source code in srai/datasets/_base.py 
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
def __init__(
    self,
    path: str,
    version: Optional[str] = None,
    type: Optional[str] = None,
    numerical_columns: Optional[list[str]] = None,
    categorical_columns: Optional[list[str]] = None,
    target: Optional[str] = None,
    resolution: Optional[int] = None,
) -> None:
    self.path = path
    self.version = version
    self.numerical_columns = numerical_columns
    self.categorical_columns = categorical_columns
    self.target = target
    self.type = type
    self.train_gdf = None
    self.test_gdf = None
    self.val_gdf = None
    self.resolution = resolution

get_h3_with_labels

abstractmethod 
get_h3_with_labels() -> (
    tuple[
        gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]
    ]
)

Returns indexes with target labels from the dataset depending on dataset and task type.

RETURNS DESCRIPTION
tuple[GeoDataFrame, Optional[GeoDataFrame], Optional[GeoDataFrame]]

tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]: Train, Val, Test indexes with target labels in GeoDataFrames
Source code in srai/datasets/_base.py 
151
152
153
154
155
156
157
158
159
160
161
162
163
164
@abc.abstractmethod
def get_h3_with_labels(
    self,
    # resolution: Optional[int] = None,
    # target_column: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]:
    """
    Returns indexes with target labels from the dataset depending on dataset and task type.

    Returns:
        tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]: \
            Train, Val, Test indexes with target labels in GeoDataFrames
    """
    raise NotImplementedError

load 

load(
    version: Optional[Union[int, str]] = None, hf_token: Optional[str] = None
) -> dict[str, gpd.GeoDataFrame]

Method to load dataset.

PARAMETER DESCRIPTION
hf_token

If needed, a User Access Token needed to authenticate to the Hugging Face Hub. Environment variable HF_TOKEN can be also used. Defaults to None.

TYPE: str DEFAULT: None

version

version of a dataset

TYPE: str or int DEFAULT: None

RETURNS DESCRIPTION
dict[str, GeoDataFrame]

dict[str, gpd.GeoDataFrame]: Dictionary with all splits loaded from the dataset. Will contain keys "train" and "test" if available.
Source code in srai/datasets/_base.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 load(
    self,
    version: Optional[Union[int, str]] = None,
    hf_token: Optional[str] = None,
) -> dict[str, gpd.GeoDataFrame]:
    """
    Method to load dataset.

    Args:
        hf_token (str, optional): If needed, a User Access Token needed to authenticate to
            the Hugging Face Hub. Environment variable `HF_TOKEN` can be also used.
            Defaults to None.
        version (str or int, optional): version of a dataset

    Returns:
        dict[str, gpd.GeoDataFrame]: Dictionary with all splits loaded from the dataset. Will
             contain keys "train" and "test" if available.
    """
    from datasets import load_dataset

    result = {}

    self.train_gdf, self.val_gdf, self.test_gdf = None, None, None
    dataset_name = self.path
    self.version = str(version)

    if (
        self.resolution is None
        and self.version in ("8", "9", "10")
        or (self.version in ("8", "9", "10") and str(self.resolution) != self.version)
    ):
        with suppress(ValueError):
            # Try to parse version as int (e.g. "8" or "9")
            self.resolution = int(self.version)

    data = load_dataset(dataset_name, str(version), token=hf_token, trust_remote_code=True)
    train = data["train"].to_pandas()
    processed_train = self._preprocessing(train)
    self.train_gdf = processed_train
    result["train"] = processed_train
    if "test" in data:
        test = data["test"].to_pandas()
        processed_test = self._preprocessing(test)
        self.test_gdf = processed_test
        result["test"] = processed_test

    return result

train_test_split

abstractmethod 
train_test_split(
    target_column: Optional[str] = None,
    resolution: Optional[int] = None,
    test_size: float = 0.2,
    n_bins: int = 7,
    random_state: Optional[int] = None,
    validation_split: bool = False,
    force_split: bool = False,
    task: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]

Method to generate train/test or train/val split from GeoDataFrame.

PARAMETER DESCRIPTION
target_column

Target column name for Points, trajectories id column fortrajectory datasets. Defaults to preset dataset target column.

TYPE: Optional[str] DEFAULT: None

resolution

H3 resolution, subclasses mayb use this argument to regionalize data. Defaults to default value from the dataset.

TYPE: int DEFAULT: None

test_size

Percentage of test set. Defaults to 0.2.

TYPE: float DEFAULT: 0.2

n_bins

Bucket number used to stratify target data.

TYPE: int DEFAULT: 7

random_state

Controls the shuffling applied to the data before applying the split. Pass an int for reproducible output across multiple function. Defaults to None.

TYPE: int DEFAULT: None

validation_split

If True, creates a validation split from existing train split and assigns it to self.val_gdf.

TYPE: bool DEFAULT: False

force_split

If True, forces a new split to be created, even if an existing train/test or validation split is already present. - With validation_split=False, regenerates and overwrites the test split. - With validation_split=True, regenerates and overwrites the validation split.

TYPE: bool DEFAULT: False

task

Task identifier. Subclasses may use this argument to determine stratification logic (e.g., by duration or spatial pattern). Defaults to None.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
tuple

Train-test or Train-val split made on previous train subset.

TYPE: (GeoDataFrame, GeoDataFrame)

Source code in srai/datasets/_base.py 
 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
@abc.abstractmethod
def train_test_split(
    self,
    target_column: Optional[str] = None,
    resolution: Optional[int] = None,
    test_size: float = 0.2,
    n_bins: int = 7,
    random_state: Optional[int] = None,
    validation_split: bool = False,
    force_split: bool = False,
    task: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]:
    """
    Method to generate train/test or train/val split from GeoDataFrame.

    Args:
        target_column (Optional[str], optional): Target column name for Points, trajectories id\
            column fortrajectory datasets. Defaults to preset dataset target column.
        resolution (int, optional): H3 resolution, subclasses mayb use this argument to\
            regionalize data. Defaults to default value from the dataset.
        test_size (float, optional): Percentage of test set. Defaults to 0.2.
        n_bins (int, optional): Bucket number used to stratify target data.
        random_state (int, optional):  Controls the shuffling applied to the data before \
            applying the split.
            Pass an int for reproducible output across multiple function. Defaults to None.
        validation_split (bool): If True, creates a validation split from existing train split\
            and assigns it to self.val_gdf.
        force_split: If True, forces a new split to be created, even if an existing train/test\
            or validation split is already present.
            - With `validation_split=False`, regenerates and overwrites the test split.
            - With `validation_split=True`, regenerates and overwrites the validation split.
        task (Optional[str], optional): Task identifier. Subclasses may use this argument to
            determine stratification logic (e.g., by duration or spatial pattern).\
                Defaults to None.

    Returns:
        tuple(gpd.GeoDataFrame, gpd.GeoDataFrame): Train-test or Train-val split made on\
            previous train subset.
    """
    raise NotImplementedError

PointDataset 

PointDataset(
    path: str,
    version: Optional[str] = None,
    type: Optional[str] = None,
    numerical_columns: Optional[list[str]] = None,
    categorical_columns: Optional[list[str]] = None,
    target: Optional[str] = None,
    resolution: Optional[int] = None,
)

Bases: HuggingFaceDataset

Abstract class for HuggingFace datasets with Point Data.

Source code in srai/datasets/_base.py 
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
def __init__(
    self,
    path: str,
    version: Optional[str] = None,
    type: Optional[str] = None,
    numerical_columns: Optional[list[str]] = None,
    categorical_columns: Optional[list[str]] = None,
    target: Optional[str] = None,
    resolution: Optional[int] = None,
) -> None:
    import_optional_dependencies(dependency_group="datasets", modules=["datasets"])
    self.path = path
    self.version = version
    self.numerical_columns = numerical_columns
    self.categorical_columns = categorical_columns
    self.target = target
    self.type = type
    self.train_gdf = None
    self.test_gdf = None
    self.val_gdf = None
    self.resolution = resolution

get_h3_with_labels 

get_h3_with_labels() -> (
    tuple[
        gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]
    ]
)

Returns h3 indexes with target labels from the dataset.

Points are aggregated to hexes and target column values are averaged or if target column is None, then the number of points is calculted within a hex and scaled to [0,1].

RETURNS DESCRIPTION
tuple[GeoDataFrame, Optional[GeoDataFrame], Optional[GeoDataFrame]]

tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]: Train, Val, Test hexes with target labels in GeoDataFrames
Source code in srai/datasets/_base.py 
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
def get_h3_with_labels(
    self,
    # resolution: Optional[int] = None,
    # target_column: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]:
    """
    Returns h3 indexes with target labels from the dataset.

    Points are aggregated to hexes and target column values are averaged or if target column \
    is None, then the number of points is calculted within a hex and scaled to [0,1].

    Returns:
        tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]:\
            Train, Val, Test hexes with target labels in GeoDataFrames
    """
    # if target_column is None:
    #     target_column = "count"

    # resolution = resolution if resolution is not None else self.resolution

    assert self.train_gdf is not None
    # If resolution is still None, raise an error
    if self.resolution is None:
        raise ValueError(
            "No preset resolution for the dataset in self.resolution. Please"
            "provide a resolution."
        )
    # elif self.resolution is not None and resolution != self.resolution:
    #     raise ValueError(
    #         "Resolution provided is different from the preset resolution for the"
    #         "dataset. This may result in a data leak between splits."
    #     )

    _train_gdf = self._aggregate_hexes(self.train_gdf, self.resolution, self.target)

    if self.test_gdf is not None:
        _test_gdf = self._aggregate_hexes(self.test_gdf, self.resolution, self.target)
    else:
        _test_gdf = None

    if self.val_gdf is not None:
        _val_gdf = self._aggregate_hexes(self.val_gdf, self.resolution, self.target)
    else:
        _val_gdf = None

    # Scale the "count" column to [0, 1] if it is the target column
    if self.target == "count":
        scaler = MinMaxScaler()
        # Fit the scaler on the train dataset and transform
        _train_gdf["count"] = scaler.fit_transform(_train_gdf[["count"]])
        if _test_gdf is not None:
            _test_gdf["count"] = scaler.transform(_test_gdf[["count"]])
            _test_gdf["count"] = np.clip(_test_gdf["count"], 0, 1)
        if _val_gdf is not None:
            _val_gdf["count"] = scaler.transform(_val_gdf[["count"]])
            _val_gdf["count"] = np.clip(_val_gdf["count"], 0, 1)

    return _train_gdf, _val_gdf, _test_gdf

load 

load(
    version: Optional[Union[int, str]] = None, hf_token: Optional[str] = None
) -> dict[str, gpd.GeoDataFrame]

Method to load dataset.

PARAMETER DESCRIPTION
hf_token

If needed, a User Access Token needed to authenticate to the Hugging Face Hub. Environment variable HF_TOKEN can be also used. Defaults to None.

TYPE: str DEFAULT: None

version

version of a dataset

TYPE: str or int DEFAULT: None

RETURNS DESCRIPTION
dict[str, GeoDataFrame]

dict[str, gpd.GeoDataFrame]: Dictionary with all splits loaded from the dataset. Will contain keys "train" and "test" if available.
Source code in srai/datasets/_base.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 load(
    self,
    version: Optional[Union[int, str]] = None,
    hf_token: Optional[str] = None,
) -> dict[str, gpd.GeoDataFrame]:
    """
    Method to load dataset.

    Args:
        hf_token (str, optional): If needed, a User Access Token needed to authenticate to
            the Hugging Face Hub. Environment variable `HF_TOKEN` can be also used.
            Defaults to None.
        version (str or int, optional): version of a dataset

    Returns:
        dict[str, gpd.GeoDataFrame]: Dictionary with all splits loaded from the dataset. Will
             contain keys "train" and "test" if available.
    """
    from datasets import load_dataset

    result = {}

    self.train_gdf, self.val_gdf, self.test_gdf = None, None, None
    dataset_name = self.path
    self.version = str(version)

    if (
        self.resolution is None
        and self.version in ("8", "9", "10")
        or (self.version in ("8", "9", "10") and str(self.resolution) != self.version)
    ):
        with suppress(ValueError):
            # Try to parse version as int (e.g. "8" or "9")
            self.resolution = int(self.version)

    data = load_dataset(dataset_name, str(version), token=hf_token, trust_remote_code=True)
    train = data["train"].to_pandas()
    processed_train = self._preprocessing(train)
    self.train_gdf = processed_train
    result["train"] = processed_train
    if "test" in data:
        test = data["test"].to_pandas()
        processed_test = self._preprocessing(test)
        self.test_gdf = processed_test
        result["test"] = processed_test

    return result

train_test_split 

train_test_split(
    target_column: Optional[str] = None,
    resolution: Optional[int] = None,
    test_size: float = 0.2,
    n_bins: int = 7,
    random_state: Optional[int] = None,
    validation_split: bool = False,
    force_split: bool = False,
    task: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]

Method to generate splits from GeoDataFrame, based on the target_column values.

PARAMETER DESCRIPTION
target_column

Target column name. If None, split is generated based on number of points within a hex of a given resolution. Defaults to preset dataset target column.

TYPE: Optional[str] DEFAULT: None

resolution

h3 resolution to regionalize data. Defaults to default value from the dataset.

TYPE: int DEFAULT: None

test_size

Percentage of test set. Defaults to 0.2.

TYPE: float DEFAULT: 0.2

n_bins

Bucket number used to stratify target data. Defaults to 7.

TYPE: int DEFAULT: 7

random_state

Controls the shuffling applied to the data before applying the split. Pass an int for reproducible output across multiple function. Defaults to None.

TYPE: int DEFAULT: None

validation_split

If True, creates a validation split from existing train split and assigns it to self.val_gdf.

TYPE: bool DEFAULT: False

force_split

If True, forces a new split to be created, even if an existing train/test or validation split is already present. - With validation_split=False, regenerates and overwrites the test split. - With validation_split=True, regenerates and overwrites the validation split.

TYPE: bool DEFAULT: False

task

Currently not supported. Ignored in this subclass.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
tuple

Train-test or train-val split made on previous train subset.

TYPE: (GeoDataFrame, GeoDataFrame)

Source code in srai/datasets/_base.py 
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
248
249
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
def train_test_split(
    self,
    target_column: Optional[str] = None,
    resolution: Optional[int] = None,
    test_size: float = 0.2,
    n_bins: int = 7,
    random_state: Optional[int] = None,
    validation_split: bool = False,
    force_split: bool = False,
    task: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]:
    """
    Method to generate splits from GeoDataFrame, based on the target_column values.

    Args:
        target_column (Optional[str], optional): Target column name. If None, split is\
            generated based on number of points within a hex of a given resolution.\
            Defaults to preset dataset target column.
        resolution (int, optional): h3 resolution to regionalize data. Defaults to default\
            value from the dataset.
        test_size (float, optional): Percentage of test set. Defaults to 0.2.
        n_bins (int, optional): Bucket number used to stratify target data.\
            Defaults to 7.
        random_state (int, optional):  Controls the shuffling applied to the data before\
            applying the split. \
            Pass an int for reproducible output across multiple function. Defaults to None.
        validation_split (bool): If True, creates a validation split from existing train split\
            and assigns it to self.val_gdf.
        force_split: If True, forces a new split to be created, even if an existing train/test\
            or validation split is already present.
            - With `validation_split=False`, regenerates and overwrites the test split.
            - With `validation_split=True`, regenerates and overwrites the validation split.
        task (Optional[str], optional): Currently not supported. Ignored in this subclass.

    Returns:
        tuple(gpd.GeoDataFrame, gpd.GeoDataFrame): Train-test or train-val split made on\
            previous train subset.
    """
    assert self.train_gdf is not None

    if (self.val_gdf is not None and validation_split and not force_split) or (
        self.test_gdf is not None and not validation_split and not force_split
    ):
        raise ValueError(
            "A split already exists. Use `force_split=True` to overwrite the existing "
            f"{'validation' if validation_split else 'test'} split."
        )

    resolution = resolution or self.resolution

    if resolution is None:
        raise ValueError(
            "No preset resolution for the dataset in self.resolution. Please "
            "provide a resolution."
        )
    elif self.resolution is not None and resolution != self.resolution:
        raise ValueError(
            "Resolution provided is different from the preset resolution for the "
            "dataset. This may result in a data leak between splits."
        )

    if self.resolution is None:
        self.resolution = resolution
    target_column = target_column if target_column is not None else self.target
    if target_column is None:
        target_column = "count"

    gdf = self.train_gdf
    gdf_ = gdf.copy()

    train, test = train_test_spatial_split(
        gdf_,
        parent_h3_resolution=resolution,
        target_column=target_column,
        test_size=test_size,
        n_bins=n_bins,
        random_state=random_state,
    )

    self.train_gdf = train
    if not validation_split:
        self.test_gdf = test
        test_len = len(self.test_gdf) if self.test_gdf is not None else 0
        print(
            f"Created new train_gdf and test_gdf. Train len: {len(self.train_gdf)},"
            f"test len: {test_len}"
        )
    else:
        self.val_gdf = test
        val_len = len(self.val_gdf) if self.val_gdf is not None else 0
        test_len = len(self.test_gdf) if self.test_gdf is not None else 0
        print(
            f"Created new train_gdf and val_gdf. Test split remains unchanged."
            f"Train len: {len(self.train_gdf)}, val len: {val_len},"
            f"test len: {test_len}"
        )
    return train, test

TrajectoryDataset 

TrajectoryDataset(
    path: str,
    version: Optional[str] = None,
    type: Optional[str] = None,
    numerical_columns: Optional[list[str]] = None,
    categorical_columns: Optional[list[str]] = None,
    target: Optional[str] = None,
    resolution: Optional[int] = None,
)

Bases: HuggingFaceDataset

Abstract class for HuggingFace datasets with Trajectory data.

Source code in srai/datasets/_base.py 
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
def __init__(
    self,
    path: str,
    version: Optional[str] = None,
    type: Optional[str] = None,
    numerical_columns: Optional[list[str]] = None,
    categorical_columns: Optional[list[str]] = None,
    target: Optional[str] = None,
    resolution: Optional[int] = None,
) -> None:
    import_optional_dependencies(dependency_group="datasets", modules=["datasets"])
    self.path = path
    self.version = version
    self.numerical_columns = numerical_columns
    self.categorical_columns = categorical_columns
    self.target = target
    self.type = type
    self.train_gdf = None
    self.test_gdf = None
    self.val_gdf = None
    self.resolution = resolution

get_h3_with_labels 

get_h3_with_labels() -> (
    tuple[
        gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]
    ]
)

Returns ids, h3 indexes sequences, with target labels from the dataset.

Points are aggregated to hex trajectories and target column values are calculated for each trajectory (time duration for TTE task, future movement sequence for HMP task).

RETURNS DESCRIPTION
tuple[GeoDataFrame, Optional[GeoDataFrame], Optional[GeoDataFrame]]

tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]: Train, Val, Test hexes sequences with target labels in GeoDataFrames
Source code in srai/datasets/_base.py 
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
def get_h3_with_labels(
    self,
    # resolution: Optional[int] = None,
    # target_column: Optional[str] = None,
) -> tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]:
    """
    Returns ids, h3 indexes sequences, with target labels from the dataset.

    Points are aggregated to hex trajectories and target column values are calculated \
        for each trajectory (time duration for TTE task, future movement sequence for HMP task).

    Returns:
        tuple[gpd.GeoDataFrame, Optional[gpd.GeoDataFrame], Optional[gpd.GeoDataFrame]]: Train,\
            Val, Test hexes sequences with target labels in GeoDataFrames
    """
    # resolution = resolution if resolution is not None else self.resolution

    assert self.train_gdf is not None
    # If resolution is still None, raise an error
    if self.resolution is None:
        raise ValueError(
            "No preset resolution for the dataset in self.resolution. Please"
            "provide a resolution."
        )
    # elif self.resolution is not None and resolution != self.resolution:
    #     raise ValueError(
    #         "Resolution provided is different from the preset resolution for the"
    #         "dataset. This may result in a data leak between splits."
    #     )

    if self.version == "TTE":
        _train_gdf = self.train_gdf[[self.target, "h3_sequence", "duration"]]

        if self.test_gdf is not None:
            _test_gdf = self.test_gdf[[self.target, "h3_sequence", "duration"]]
        else:
            _test_gdf = None

        if self.val_gdf is not None:
            _val_gdf = self.val_gdf[[self.target, "h3_sequence", "duration"]]
        else:
            _val_gdf = None

    elif self.version == "HMP":
        _train_gdf = self.train_gdf[[self.target, "h3_sequence_x", "h3_sequence_y"]]

        if self.test_gdf is not None:
            _test_gdf = self.test_gdf[[self.target, "h3_sequence_x", "h3_sequence_y"]]
        else:
            _test_gdf = None

        if self.val_gdf is not None:
            _val_gdf = self.val_gdf[[self.target, "h3_sequence_x", "h3_sequence_y"]]
        else:
            _val_gdf = None

    elif self.version == "all":
        raise TypeError(
            "Could not provide target labels, as version 'all'\
        of dataset does not provide one."
        )

    return _train_gdf, _val_gdf, _test_gdf

load 

load(
    version: Optional[Union[int, str]] = None, hf_token: Optional[str] = None
) -> dict[str, gpd.GeoDataFrame]

Method to load dataset.

PARAMETER DESCRIPTION
hf_token

If needed, a User Access Token needed to authenticate to the Hugging Face Hub. Environment variable HF_TOKEN can be also used. Defaults to None.

TYPE: str DEFAULT: None

version

version of a dataset

TYPE: str or int DEFAULT: None

RETURNS DESCRIPTION
dict[str, GeoDataFrame]

dict[str, gpd.GeoDataFrame]: Dictionary with all splits loaded from the dataset. Will contain keys "train" and "test" if available.
Source code in srai/datasets/_base.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 load(
    self,
    version: Optional[Union[int, str]] = None,
    hf_token: Optional[str] = None,
) -> dict[str, gpd.GeoDataFrame]:
    """
    Method to load dataset.

    Args:
        hf_token (str, optional): If needed, a User Access Token needed to authenticate to
            the Hugging Face Hub. Environment variable `HF_TOKEN` can be also used.
            Defaults to None.
        version (str or int, optional): version of a dataset

    Returns:
        dict[str, gpd.GeoDataFrame]: Dictionary with all splits loaded from the dataset. Will
             contain keys "train" and "test" if available.
    """
    from datasets import load_dataset

    result = {}

    self.train_gdf, self.val_gdf, self.test_gdf = None, None, None
    dataset_name = self.path
    self.version = str(version)

    if (
        self.resolution is None
        and self.version in ("8", "9", "10")
        or (self.version in ("8", "9", "10") and str(self.resolution) != self.version)
    ):
        with suppress(ValueError):
            # Try to parse version as int (e.g. "8" or "9")
            self.resolution = int(self.version)

    data = load_dataset(dataset_name, str(version), token=hf_token, trust_remote_code=True)
    train = data["train"].to_pandas()
    processed_train = self._preprocessing(train)
    self.train_gdf = processed_train
    result["train"] = processed_train
    if "test" in data:
        test = data["test"].to_pandas()
        processed_test = self._preprocessing(test)
        self.test_gdf = processed_test
        result["test"] = processed_test

    return result

train_test_split 

train_test_split(
    target_column: Optional[str] = None,
    resolution: Optional[int] = None,
    test_size: float = 0.2,
    n_bins: int = 4,
    random_state: Optional[int] = None,
    validation_split: bool = False,
    force_split: bool = False,
    task: Optional[str] = "TTE",
) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]

Generate train/test split or train/val split from trajectory GeoDataFrame.

Train-test/train-val split is generated by splitting train_gdf.

PARAMETER DESCRIPTION
target_column

Column identifying each trajectory (contains trajectory ids).

TYPE: str DEFAULT: None

test_size

Fraction of data to be used as test set.

TYPE: float DEFAULT: 0.2

n_bins

Number of stratification bins.

TYPE: int DEFAULT: 4

random_state

Controls the shuffling applied to the data before applying the split. Pass an int for reproducible output across multiple function. Defaults to None.

TYPE: int DEFAULT: None

validation_split

If True, creates a validation split from existing train split and assigns it to self.val_gdf.

TYPE: bool DEFAULT: False

force_split

If True, forces a new split to be created, even if an existing train/test or validation split is already present. - With validation_split=False, regenerates and overwrites the test split. - With validation_split=True, regenerates and overwrites the validation split.

TYPE: bool DEFAULT: False

resolution

H3 resolution to regionalize data. Currently ignored in this subclass, different resolutions splits not supported yet. Defaults to default value from the dataset.

TYPE: int DEFAULT: None

task

Task type. Stratifies by duration (TTE) or hex length (HMP).

TYPE: Literal[TTE, HMP] DEFAULT: 'TTE'

RETURNS DESCRIPTION
tuple[GeoDataFrame, GeoDataFrame]

Tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]: Train/test or train/val GeoDataFrames.
Source code in srai/datasets/_base.py 
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
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
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
def train_test_split(
    self,
    target_column: Optional[str] = None,
    resolution: Optional[int] = None,
    test_size: float = 0.2,
    n_bins: int = 4,
    random_state: Optional[int] = None,
    validation_split: bool = False,
    force_split: bool = False,
    task: Optional[str] = "TTE",
) -> tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]:
    """
    Generate train/test split or train/val split from trajectory GeoDataFrame.

    Train-test/train-val split is generated by splitting train_gdf.

    Args:
        target_column (str): Column identifying each trajectory (contains trajectory ids).
        test_size (float): Fraction of data to be used as test set.
        n_bins (int): Number of stratification bins.
        random_state (int, optional):  Controls the shuffling applied to the data before\
            applying the split. Pass an int for reproducible output across multiple function.\
                Defaults to None.
        validation_split (bool): If True, creates a validation split from existing train split\
            and assigns it to self.val_gdf.
        force_split: If True, forces a new split to be created, even if an existing train/test\
            or validation split is already present.
            - With `validation_split=False`, regenerates and overwrites the test split.
            - With `validation_split=True`, regenerates and overwrites the validation split.
        resolution (int, optional): H3 resolution to regionalize data. Currently ignored in\
            this subclass, different resolutions splits not supported yet.\
                Defaults to default value from the dataset.
        task (Literal["TTE", "HMP"]): Task type. Stratifies by duration
            (TTE) or hex length (HMP).


    Returns:
        Tuple[gpd.GeoDataFrame, gpd.GeoDataFrame]: Train/test or train/val GeoDataFrames.
    """
    if (self.val_gdf is not None and validation_split and not force_split) or (
        self.test_gdf is not None and not validation_split and not force_split
    ):
        raise ValueError(
            "A split already exists. Use `force_split=True` to overwrite the existing "
            f"{'validation' if validation_split else 'test'} split."
        )
    assert self.train_gdf is not None
    trajectory_id_column = target_column or self.target
    gdf_copy = self.train_gdf.copy()

    if task not in {"TTE", "HMP"}:
        raise ValueError(f"Unsupported task: {task}")

    if task == "TTE":
        self.version = "TTE"
        # Calculate duration in seconds from timestamps list

        if "duration" in gdf_copy.columns:
            gdf_copy["stratify_col"] = gdf_copy["duration"]
        elif "duration" not in gdf_copy.columns and "timestamp" in gdf_copy.columns:
            gdf_copy["stratify_col"] = gdf_copy["timestamp"].apply(
                #     lambda ts: (0.0 if len(ts) < 2 else (ts[-1] - ts[0]).total_seconds())
                # )
                lambda ts: (
                    0.0 if len(ts) < 2 else pd.Timedelta(ts[-1] - ts[0]).total_seconds()
                )
            )
        else:
            raise ValueError(
                "Duration column and timestamp column does not exist.\
                              Can't stratify it."
            )

    elif task == "HMP":
        self.version = "HMP"

        def split_sequence(seq):
            split_idx = int(len(seq) * 0.85)
            if split_idx == len(seq):
                split_idx = len(seq) - 1
            return seq[:split_idx], seq[split_idx:]

        if "h3_sequence_x" not in gdf_copy.columns:
            split_result = gdf_copy["h3_sequence"].apply(split_sequence)
            gdf_copy["h3_sequence_x"] = split_result.apply(operator.itemgetter(0))
            gdf_copy["h3_sequence_y"] = split_result.apply(operator.itemgetter(1))

        # Calculate trajectory length in unique hexagons
        gdf_copy["x_len"] = gdf_copy["h3_sequence_x"].apply(lambda seq: len(set(seq)))
        gdf_copy["y_len"] = gdf_copy["h3_sequence_y"].apply(lambda seq: len(set(seq)))
        gdf_copy["stratify_col"] = gdf_copy.apply(
            lambda row: row["x_len"] + row["y_len"], axis=1
        )
    else:
        raise ValueError(f"Unsupported task type: {task}")

    gdf_copy["stratification_bin"] = pd.cut(gdf_copy["stratify_col"], bins=n_bins, labels=False)

    trajectory_indices = gdf_copy[trajectory_id_column].unique()
    duration_bins = (
        gdf_copy[[trajectory_id_column, "stratification_bin"]]
        .drop_duplicates()
        .set_index(trajectory_id_column)["stratification_bin"]
    )

    train_indices, test_indices = train_test_split(
        trajectory_indices,
        test_size=test_size,
        stratify=duration_bins.loc[trajectory_indices],
        random_state=random_state,
    )

    train_gdf = gdf_copy[gdf_copy[trajectory_id_column].isin(train_indices)]
    test_gdf = gdf_copy[gdf_copy[trajectory_id_column].isin(test_indices)]

    test_gdf = test_gdf.drop(
        columns=[
            col
            for col in (
                "x_len",
                "y_len",
                "stratification_bin",
                "stratify_col",
            )
            if col in test_gdf.columns
        ],
    )
    train_gdf = train_gdf.drop(
        columns=[
            col
            for col in (
                "x_len",
                "y_len",
                "stratification_bin",
                "stratify_col",
            )
            if col in test_gdf.columns
        ],
    )

    self.train_gdf = train_gdf
    if not validation_split:
        self.test_gdf = test_gdf
        test_len = len(self.test_gdf) if self.test_gdf is not None else 0
        print(
            f"Created new train_gdf and test_gdf. Train len: {len(self.train_gdf)}, "
            f"test len: {test_len}"
        )
    else:
        self.val_gdf = test_gdf
        val_len = len(self.val_gdf) if self.val_gdf is not None else 0
        test_len = len(self.test_gdf) if self.test_gdf is not None else 0
        print(
            f"Created new train_gdf and val_gdf. Test split remains unchanged. "
            f"Train len: {len(self.train_gdf)}, val len: {val_len}, "
            f"test len: {test_len}"
        )
    return train_gdf, test_gdf