Skip to content

stemflow.model.STEM

STEM

Bases: AdaSTEM

A STEM model class (allow fixed grid size)

Parents

stemflow.model.AdaSTEM.AdaSTEM

Children

None

Source code in stemflow/model/STEM.py 
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 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
class STEM(AdaSTEM):
    """A STEM model class (allow fixed grid size)

    Parents:
        stemflow.model.AdaSTEM.AdaSTEM

    Children:
        None

    """

    def __init__(
        self,
        base_model: BaseEstimator,
        task: str = "hurdle",
        ensemble_fold: int = 10,
        min_ensemble_required: int = 7,
        grid_len: [float, int, None] = None,
        points_lower_threshold: int = 50,
        stixel_training_size_threshold: int = None,
        temporal_start: Union[float, int] = 1,
        temporal_end: Union[float, int] = 366,
        temporal_step: Union[float, int] = 20,
        temporal_bin_interval: Union[float, int] = 50,
        temporal_bin_start_jitter: Union[float, int, str] = "adaptive",
        spatio_bin_jitter_magnitude: Union[float, int] = "adaptive",
        save_gridding_plot: bool = True,
        save_tmp: bool = False,
        save_dir: str = "./",
        sample_weights_for_classifier: bool = True,
        Spatio1: str = "longitude",
        Spatio2: str = "latitude",
        Temporal1: str = "DOY",
        use_temporal_to_train: bool = True,
        njobs: int = 1,
        subset_x_names: bool = False,
        ensemble_models_disk_saver: bool = False,
        ensemble_models_disk_saving_dir: str = "./",
        plot_xlims: Tuple[Union[float, int], Union[float, int]] = (-180, 180),
        plot_ylims: Tuple[Union[float, int], Union[float, int]] = (-90, 90),
        verbosity: int = 0,
        plot_empty: bool = False,
    ):
        """Make a STEM object

        Args:
            base_model:
                base model estimator
            task:
                task of the model. One of 'classifier', 'regressor' and 'hurdle'. Defaults to 'hurdle'.
            ensemble_fold:
                Ensembles count. Higher, better for the model performance. Time complexity O(N). Defaults to 10.
            min_ensemble_required:
                Only points with more than this number of model ensembles available are predicted.
                In the training phase, if stixels contain less than `points_lower_threshold` of data records,
                the results are set to np.nan, making them `unpredictable`. Defaults to 7.
            grid_len:
                length of the grids. Defaults to 25.
            points_lower_threshold:
                Do not further split the gird if split results in less samples than this threshold.
                Overriden by grid_len_*_upper_threshold parameters. Defaults to 50.
            stixel_training_size_threshold:
                Do not train the model if the available data records for this stixel is less than this threshold,
                and directly set the value to np.nan. Defaults to 50.
            temporal_start:
                start of the temporal sequence. Defaults to 1.
            temporal_end:
                end of the temporal sequence. Defaults to 366.
            temporal_step:
                step of the sliding window. Defaults to 20.
            temporal_bin_interval:
                size of the sliding window. Defaults to 50.
            temporal_bin_start_jitter:
                jitter of the start of the sliding window.
                If 'adaptive', a random jitter of range (-bin_interval, 0) will be generated
                for the start. Defaults to 'adaptive'.
            spatio_bin_jitter_magnitude:
                jitter of the spatial gridding. Defaults to 'adaptive.
            save_gridding_plot:
                Whether ot save gridding plots. Defaults to True.
            save_tmp:
                Whether to save the ensemble dataframe. Defaults to False.
            save_dir:
                If save_tmp==True, save the ensemble dataframe to this path. Defaults to './'.
            ensemble_models_disk_saver:
                Whether to balance the sample weights of classifier for imbalanced datasets. Defaults to True.
            Spatio1:
                Spatial column name 1 in data. Defaults to 'longitude'.
            Spatio2:
                Spatial column name 2 in data. Defaults to 'latitude'.
            Temporal1:
                Temporal column name 1 in data.  Defaults to 'DOY'.
            use_temporal_to_train:
                Whether to use temporal variable to train. For example in modeling the daily abundance of bird population,
                whether use 'day of year (DOY)' as a training variable. Defaults to True.
            njobs:
                Number of multiprocessing in fitting the model. Defaults to 1.
            subset_x_names:
                Whether to only store variables with std > 0 for each stixel. Set to False will significantly increase the training speed.
            ensemble_disk_saver:
                Whether to save each ensemble of models to dicts instead of saving them in memory.
            ensemble_models_disk_saving_dir:
                Where to save the ensemble models. Only valid if ensemble_disk_saver is True.
            plot_xlims:
                If save_gridding_plot=true, what is the xlims of the plot. Defaults to (-180,180).
            plot_ylims:
                If save_gridding_plot=true, what is the ylims of the plot. Defaults to (-90,90).
            verbosity:
                0 to output nothing and everything otherwise.
            plot_empty:
                Whether to plot the empty grid

        Raises:
            AttributeError: Base model do not have method 'fit' or 'predict'
            AttributeError: task not in one of ['regression', 'classification', 'hurdle']
            AttributeError: temporal_bin_start_jitter not in one of [str, float, int]
            AttributeError: temporal_bin_start_jitter is type str, but not 'random'

        Attributes:
            x_names (list):
                All training variables used.
            stixel_specific_x_names (dict):
                stixel specific x_names (predictor variable names) for each stixel.
                We remove the variables that have no variation for each stixel.
                Therefore, the x_names are different for each stixel.
            ensemble_df (pd.core.frame.DataFrame):
                A dataframe storing the stixel gridding information.
            gridding_plot (matplotlib.figure.Figure):
                Ensemble plot.
            model_dict (dict):
                Dictionary of {stixel_index: trained_model}.
            grid_dict (dict):
                An array of stixels assigned to each ensemble.
            feature_importances_ (pd.core.frame.DataFrame):
                feature importance dataframe for each stixel.

        """
        # Init parent class
        super().__init__(
            base_model,
            task,
            ensemble_fold,
            min_ensemble_required,
            None,
            None,
            points_lower_threshold,
            stixel_training_size_threshold,
            temporal_start,
            temporal_end,
            temporal_step,
            temporal_bin_interval,
            temporal_bin_start_jitter,
            spatio_bin_jitter_magnitude,
            save_gridding_plot,
            save_tmp,
            save_dir,
            sample_weights_for_classifier,
            Spatio1,
            Spatio2,
            Temporal1,
            use_temporal_to_train,
            njobs,
            subset_x_names,
            ensemble_models_disk_saver,
            ensemble_models_disk_saving_dir,
            plot_xlims,
            plot_ylims,
            verbosity,
            plot_empty,
        )

        self.grid_len = grid_len

__init__(base_model, task='hurdle', ensemble_fold=10, min_ensemble_required=7, grid_len=None, points_lower_threshold=50, stixel_training_size_threshold=None, temporal_start=1, temporal_end=366, temporal_step=20, temporal_bin_interval=50, temporal_bin_start_jitter='adaptive', spatio_bin_jitter_magnitude='adaptive', save_gridding_plot=True, save_tmp=False, save_dir='./', sample_weights_for_classifier=True, Spatio1='longitude', Spatio2='latitude', Temporal1='DOY', use_temporal_to_train=True, njobs=1, subset_x_names=False, ensemble_models_disk_saver=False, ensemble_models_disk_saving_dir='./', plot_xlims=(-180, 180), plot_ylims=(-90, 90), verbosity=0, plot_empty=False)

Make a STEM object

Parameters:

  • base_model (BaseEstimator) –

    base model estimator

  • task (str, default: 'hurdle' ) –

    task of the model. One of 'classifier', 'regressor' and 'hurdle'. Defaults to 'hurdle'.

  • ensemble_fold (int, default: 10 ) –

    Ensembles count. Higher, better for the model performance. Time complexity O(N). Defaults to 10.

  • min_ensemble_required (int, default: 7 ) –

    Only points with more than this number of model ensembles available are predicted. In the training phase, if stixels contain less than points_lower_threshold of data records, the results are set to np.nan, making them unpredictable. Defaults to 7.

  • grid_len ([float, int, None], default: None ) –

    length of the grids. Defaults to 25.

  • points_lower_threshold (int, default: 50 ) –

    Do not further split the gird if split results in less samples than this threshold. Overriden by grid_len_*_upper_threshold parameters. Defaults to 50.

  • stixel_training_size_threshold (int, default: None ) –

    Do not train the model if the available data records for this stixel is less than this threshold, and directly set the value to np.nan. Defaults to 50.

  • temporal_start (Union[float, int], default: 1 ) –

    start of the temporal sequence. Defaults to 1.

  • temporal_end (Union[float, int], default: 366 ) –

    end of the temporal sequence. Defaults to 366.

  • temporal_step (Union[float, int], default: 20 ) –

    step of the sliding window. Defaults to 20.

  • temporal_bin_interval (Union[float, int], default: 50 ) –

    size of the sliding window. Defaults to 50.

  • temporal_bin_start_jitter (Union[float, int, str], default: 'adaptive' ) –

    jitter of the start of the sliding window. If 'adaptive', a random jitter of range (-bin_interval, 0) will be generated for the start. Defaults to 'adaptive'.

  • spatio_bin_jitter_magnitude (Union[float, int], default: 'adaptive' ) –

    jitter of the spatial gridding. Defaults to 'adaptive.

  • save_gridding_plot (bool, default: True ) –

    Whether ot save gridding plots. Defaults to True.

  • save_tmp (bool, default: False ) –

    Whether to save the ensemble dataframe. Defaults to False.

  • save_dir (str, default: './' ) –

    If save_tmp==True, save the ensemble dataframe to this path. Defaults to './'.

  • ensemble_models_disk_saver (bool, default: False ) –

    Whether to balance the sample weights of classifier for imbalanced datasets. Defaults to True.

  • Spatio1 (str, default: 'longitude' ) –

    Spatial column name 1 in data. Defaults to 'longitude'.

  • Spatio2 (str, default: 'latitude' ) –

    Spatial column name 2 in data. Defaults to 'latitude'.

  • Temporal1 (str, default: 'DOY' ) –

    Temporal column name 1 in data. Defaults to 'DOY'.

  • use_temporal_to_train (bool, default: True ) –

    Whether to use temporal variable to train. For example in modeling the daily abundance of bird population, whether use 'day of year (DOY)' as a training variable. Defaults to True.

  • njobs (int, default: 1 ) –

    Number of multiprocessing in fitting the model. Defaults to 1.

  • subset_x_names (bool, default: False ) –

    Whether to only store variables with std > 0 for each stixel. Set to False will significantly increase the training speed.

  • ensemble_disk_saver –

    Whether to save each ensemble of models to dicts instead of saving them in memory.

  • ensemble_models_disk_saving_dir (str, default: './' ) –

    Where to save the ensemble models. Only valid if ensemble_disk_saver is True.

  • plot_xlims (Tuple[Union[float, int], Union[float, int]], default: (-180, 180) ) –

    If save_gridding_plot=true, what is the xlims of the plot. Defaults to (-180,180).

  • plot_ylims (Tuple[Union[float, int], Union[float, int]], default: (-90, 90) ) –

    If save_gridding_plot=true, what is the ylims of the plot. Defaults to (-90,90).

  • verbosity (int, default: 0 ) –

    0 to output nothing and everything otherwise.

  • plot_empty (bool, default: False ) –

    Whether to plot the empty grid

Raises:

  • AttributeError –

    Base model do not have method 'fit' or 'predict'

  • AttributeError –

    task not in one of ['regression', 'classification', 'hurdle']

  • AttributeError –

    temporal_bin_start_jitter not in one of [str, float, int]

  • AttributeError –

    temporal_bin_start_jitter is type str, but not 'random'

Attributes:

  • x_names (list) –

    All training variables used.

  • stixel_specific_x_names (dict) –

    stixel specific x_names (predictor variable names) for each stixel. We remove the variables that have no variation for each stixel. Therefore, the x_names are different for each stixel.

  • ensemble_df (DataFrame) –

    A dataframe storing the stixel gridding information.

  • gridding_plot (Figure) –

    Ensemble plot.

  • model_dict (dict) –

    Dictionary of {stixel_index: trained_model}.

  • grid_dict (dict) –

    An array of stixels assigned to each ensemble.

  • feature_importances_ (DataFrame) –

    feature importance dataframe for each stixel.

Source code in stemflow/model/STEM.py 
 21
 22
 23
 24
 25
 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
def __init__(
    self,
    base_model: BaseEstimator,
    task: str = "hurdle",
    ensemble_fold: int = 10,
    min_ensemble_required: int = 7,
    grid_len: [float, int, None] = None,
    points_lower_threshold: int = 50,
    stixel_training_size_threshold: int = None,
    temporal_start: Union[float, int] = 1,
    temporal_end: Union[float, int] = 366,
    temporal_step: Union[float, int] = 20,
    temporal_bin_interval: Union[float, int] = 50,
    temporal_bin_start_jitter: Union[float, int, str] = "adaptive",
    spatio_bin_jitter_magnitude: Union[float, int] = "adaptive",
    save_gridding_plot: bool = True,
    save_tmp: bool = False,
    save_dir: str = "./",
    sample_weights_for_classifier: bool = True,
    Spatio1: str = "longitude",
    Spatio2: str = "latitude",
    Temporal1: str = "DOY",
    use_temporal_to_train: bool = True,
    njobs: int = 1,
    subset_x_names: bool = False,
    ensemble_models_disk_saver: bool = False,
    ensemble_models_disk_saving_dir: str = "./",
    plot_xlims: Tuple[Union[float, int], Union[float, int]] = (-180, 180),
    plot_ylims: Tuple[Union[float, int], Union[float, int]] = (-90, 90),
    verbosity: int = 0,
    plot_empty: bool = False,
):
    """Make a STEM object

    Args:
        base_model:
            base model estimator
        task:
            task of the model. One of 'classifier', 'regressor' and 'hurdle'. Defaults to 'hurdle'.
        ensemble_fold:
            Ensembles count. Higher, better for the model performance. Time complexity O(N). Defaults to 10.
        min_ensemble_required:
            Only points with more than this number of model ensembles available are predicted.
            In the training phase, if stixels contain less than `points_lower_threshold` of data records,
            the results are set to np.nan, making them `unpredictable`. Defaults to 7.
        grid_len:
            length of the grids. Defaults to 25.
        points_lower_threshold:
            Do not further split the gird if split results in less samples than this threshold.
            Overriden by grid_len_*_upper_threshold parameters. Defaults to 50.
        stixel_training_size_threshold:
            Do not train the model if the available data records for this stixel is less than this threshold,
            and directly set the value to np.nan. Defaults to 50.
        temporal_start:
            start of the temporal sequence. Defaults to 1.
        temporal_end:
            end of the temporal sequence. Defaults to 366.
        temporal_step:
            step of the sliding window. Defaults to 20.
        temporal_bin_interval:
            size of the sliding window. Defaults to 50.
        temporal_bin_start_jitter:
            jitter of the start of the sliding window.
            If 'adaptive', a random jitter of range (-bin_interval, 0) will be generated
            for the start. Defaults to 'adaptive'.
        spatio_bin_jitter_magnitude:
            jitter of the spatial gridding. Defaults to 'adaptive.
        save_gridding_plot:
            Whether ot save gridding plots. Defaults to True.
        save_tmp:
            Whether to save the ensemble dataframe. Defaults to False.
        save_dir:
            If save_tmp==True, save the ensemble dataframe to this path. Defaults to './'.
        ensemble_models_disk_saver:
            Whether to balance the sample weights of classifier for imbalanced datasets. Defaults to True.
        Spatio1:
            Spatial column name 1 in data. Defaults to 'longitude'.
        Spatio2:
            Spatial column name 2 in data. Defaults to 'latitude'.
        Temporal1:
            Temporal column name 1 in data.  Defaults to 'DOY'.
        use_temporal_to_train:
            Whether to use temporal variable to train. For example in modeling the daily abundance of bird population,
            whether use 'day of year (DOY)' as a training variable. Defaults to True.
        njobs:
            Number of multiprocessing in fitting the model. Defaults to 1.
        subset_x_names:
            Whether to only store variables with std > 0 for each stixel. Set to False will significantly increase the training speed.
        ensemble_disk_saver:
            Whether to save each ensemble of models to dicts instead of saving them in memory.
        ensemble_models_disk_saving_dir:
            Where to save the ensemble models. Only valid if ensemble_disk_saver is True.
        plot_xlims:
            If save_gridding_plot=true, what is the xlims of the plot. Defaults to (-180,180).
        plot_ylims:
            If save_gridding_plot=true, what is the ylims of the plot. Defaults to (-90,90).
        verbosity:
            0 to output nothing and everything otherwise.
        plot_empty:
            Whether to plot the empty grid

    Raises:
        AttributeError: Base model do not have method 'fit' or 'predict'
        AttributeError: task not in one of ['regression', 'classification', 'hurdle']
        AttributeError: temporal_bin_start_jitter not in one of [str, float, int]
        AttributeError: temporal_bin_start_jitter is type str, but not 'random'

    Attributes:
        x_names (list):
            All training variables used.
        stixel_specific_x_names (dict):
            stixel specific x_names (predictor variable names) for each stixel.
            We remove the variables that have no variation for each stixel.
            Therefore, the x_names are different for each stixel.
        ensemble_df (pd.core.frame.DataFrame):
            A dataframe storing the stixel gridding information.
        gridding_plot (matplotlib.figure.Figure):
            Ensemble plot.
        model_dict (dict):
            Dictionary of {stixel_index: trained_model}.
        grid_dict (dict):
            An array of stixels assigned to each ensemble.
        feature_importances_ (pd.core.frame.DataFrame):
            feature importance dataframe for each stixel.

    """
    # Init parent class
    super().__init__(
        base_model,
        task,
        ensemble_fold,
        min_ensemble_required,
        None,
        None,
        points_lower_threshold,
        stixel_training_size_threshold,
        temporal_start,
        temporal_end,
        temporal_step,
        temporal_bin_interval,
        temporal_bin_start_jitter,
        spatio_bin_jitter_magnitude,
        save_gridding_plot,
        save_tmp,
        save_dir,
        sample_weights_for_classifier,
        Spatio1,
        Spatio2,
        Temporal1,
        use_temporal_to_train,
        njobs,
        subset_x_names,
        ensemble_models_disk_saver,
        ensemble_models_disk_saving_dir,
        plot_xlims,
        plot_ylims,
        verbosity,
        plot_empty,
    )

    self.grid_len = grid_len

STEMClassifier

Bases: AdaSTEMClassifier

STEM model Classifier interface (allow fixed grid size)

Parents

stemflow.model.AdaSTEM.AdaSTEMClassifier

Children

None

Example 
>>> from stemflow.model.STEM import STEMClassifier
>>> from xgboost import XGBClassifier
>>> model = STEMClassifier(base_model=XGBClassifier(tree_method='hist',random_state=42, verbosity = 0, n_jobs=1),
                        save_gridding_plot = True,
                        ensemble_fold=10,
                        min_ensemble_required=7,
                        grid_len=25,
                        points_lower_threshold=50,
                        Spatio1='longitude',
                        Spatio2 = 'latitude',
                        Temporal1 = 'DOY',
                        use_temporal_to_train=True)
>>> model.fit(X_train, y_train)
>>> pred = model.predict(X_test)
Source code in stemflow/model/STEM.py 
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
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
class STEMClassifier(AdaSTEMClassifier):
    """STEM model Classifier interface (allow fixed grid size)

    Parents:
        stemflow.model.AdaSTEM.AdaSTEMClassifier

    Children:
        None

    Example:
        ```
        >>> from stemflow.model.STEM import STEMClassifier
        >>> from xgboost import XGBClassifier
        >>> model = STEMClassifier(base_model=XGBClassifier(tree_method='hist',random_state=42, verbosity = 0, n_jobs=1),
                                save_gridding_plot = True,
                                ensemble_fold=10,
                                min_ensemble_required=7,
                                grid_len=25,
                                points_lower_threshold=50,
                                Spatio1='longitude',
                                Spatio2 = 'latitude',
                                Temporal1 = 'DOY',
                                use_temporal_to_train=True)
        >>> model.fit(X_train, y_train)
        >>> pred = model.predict(X_test)
        ```

    """

    def __init__(
        self,
        base_model,
        task="classification",
        ensemble_fold=10,
        min_ensemble_required=7,
        grid_len=25,
        points_lower_threshold=50,
        stixel_training_size_threshold=None,
        temporal_start=1,
        temporal_end=366,
        temporal_step=20,
        temporal_bin_interval=50,
        temporal_bin_start_jitter="adaptive",
        spatio_bin_jitter_magnitude="adaptive",
        save_gridding_plot=False,
        save_tmp=False,
        save_dir="./",
        sample_weights_for_classifier=True,
        Spatio1="longitude",
        Spatio2="latitude",
        Temporal1="DOY",
        use_temporal_to_train=True,
        njobs=1,
        subset_x_names=False,
        ensemble_models_disk_saver=False,
        ensemble_models_disk_saving_dir="./",
        plot_xlims=(-180, 180),
        plot_ylims=(-90, 90),
        verbosity=0,
        plot_empty=False,
    ):
        super().__init__(
            base_model,
            task,
            ensemble_fold,
            min_ensemble_required,
            None,
            None,
            points_lower_threshold,
            stixel_training_size_threshold,
            temporal_start,
            temporal_end,
            temporal_step,
            temporal_bin_interval,
            temporal_bin_start_jitter,
            spatio_bin_jitter_magnitude,
            save_gridding_plot,
            save_tmp,
            save_dir,
            sample_weights_for_classifier,
            Spatio1,
            Spatio2,
            Temporal1,
            use_temporal_to_train,
            njobs,
            subset_x_names,
            ensemble_models_disk_saver,
            ensemble_models_disk_saving_dir,
            plot_xlims,
            plot_ylims,
            verbosity,
            plot_empty,
        )

        self.grid_len = grid_len

STEMRegressor

Bases: AdaSTEMRegressor

STEM model Regressor interface (allow fixed grid size)

Parents

stemflow.model.AdaSTEM.AdaSTEMRegressor

Children

None

Example: 

>>> from stemflow.model.STEM import STEMRegressor
>>> from xgboost import XGBRegressor
>>> model = STEMRegressor(base_model=XGBRegressor(tree_method='hist',random_state=42, verbosity = 0, n_jobs=1),
                        save_gridding_plot = True,
                        ensemble_fold=10,
                        min_ensemble_required=7,
                        grid_len=25,
                        points_lower_threshold=50,
                        Spatio1='longitude',
                        Spatio2 = 'latitude',
                        Temporal1 = 'DOY',
                        use_temporal_to_train=True)
>>> model.fit(X_train, y_train)
>>> pred = model.predict(X_test)

Source code in stemflow/model/STEM.py 
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
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
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
class STEMRegressor(AdaSTEMRegressor):
    """STEM model Regressor interface (allow fixed grid size)

    Parents:
        stemflow.model.AdaSTEM.AdaSTEMRegressor

    Children:
        None

    Example:
    ```
    >>> from stemflow.model.STEM import STEMRegressor
    >>> from xgboost import XGBRegressor
    >>> model = STEMRegressor(base_model=XGBRegressor(tree_method='hist',random_state=42, verbosity = 0, n_jobs=1),
                            save_gridding_plot = True,
                            ensemble_fold=10,
                            min_ensemble_required=7,
                            grid_len=25,
                            points_lower_threshold=50,
                            Spatio1='longitude',
                            Spatio2 = 'latitude',
                            Temporal1 = 'DOY',
                            use_temporal_to_train=True)
    >>> model.fit(X_train, y_train)
    >>> pred = model.predict(X_test)
    ```

    """

    def __init__(
        self,
        base_model,
        task="regression",
        ensemble_fold=10,
        min_ensemble_required=7,
        grid_len=25,
        points_lower_threshold=50,
        stixel_training_size_threshold=None,
        temporal_start=1,
        temporal_end=366,
        temporal_step=20,
        temporal_bin_interval=50,
        temporal_bin_start_jitter="adaptive",
        spatio_bin_jitter_magnitude="adaptive",
        save_gridding_plot=False,
        save_tmp=False,
        save_dir="./",
        sample_weights_for_classifier=True,
        Spatio1="longitude",
        Spatio2="latitude",
        Temporal1="DOY",
        use_temporal_to_train=True,
        njobs=1,
        subset_x_names=False,
        ensemble_models_disk_saver=False,
        ensemble_models_disk_saving_dir="./",
        plot_xlims=(-180, 180),
        plot_ylims=(-90, 90),
        verbosity=0,
        plot_empty=False,
    ):
        super().__init__(
            base_model,
            task,
            ensemble_fold,
            min_ensemble_required,
            None,
            None,
            points_lower_threshold,
            stixel_training_size_threshold,
            temporal_start,
            temporal_end,
            temporal_step,
            temporal_bin_interval,
            temporal_bin_start_jitter,
            spatio_bin_jitter_magnitude,
            save_gridding_plot,
            save_tmp,
            save_dir,
            sample_weights_for_classifier,
            Spatio1,
            Spatio2,
            Temporal1,
            use_temporal_to_train,
            njobs,
            subset_x_names,
            ensemble_models_disk_saver,
            ensemble_models_disk_saving_dir,
            plot_xlims,
            plot_ylims,
            verbosity,
            plot_empty,
        )

        self.grid_len = grid_len