Skip to content

Model xgboost regressor

ModelXgboostRegressor

Bases: ModelRegressorMixin, ModelClass

Xgboost model for regression

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
 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
248
249
class ModelXgboostRegressor(ModelRegressorMixin, ModelClass):
    '''Xgboost model for regression'''

    _default_name = 'model_xgboost_regressor'

    def __init__(self, xgboost_params: Union[dict, None] = None, early_stopping_rounds: int = 5, validation_split: float = 0.2, **kwargs) -> None:
        '''Initialization of the class  (see ModelClass & ModelRegressorMixin for more arguments)

        Kwargs:
            xgboost_params (dict): Parameters for the Xgboost
                -> https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.XGBRegressor
            early_stopping_rounds (int): Number of rounds for early stopping
            validation_split (float): Validation split fraction.
                Only used if not validation dataset in the fit input
        '''
        # Init.
        super().__init__(**kwargs)

        # Get logger (must be done after super init)
        self.logger = logging.getLogger(__name__)

        # Set parameters
        if xgboost_params is None:
            xgboost_params = {}
        xgboost_params["random_state"] = self.random_seed
        self.xgboost_params = xgboost_params
        self.early_stopping_rounds = early_stopping_rounds
        self.validation_split = validation_split

        # Set objective (if not in params) & init. model
        if 'objective' not in self.xgboost_params.keys():
            self.xgboost_params['objective'] = 'reg:squarederror'
            #  List of objectives https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters
        self.model = XGBRegressor(**self.xgboost_params)

    def fit(self, x_train, y_train, x_valid=None, y_valid=None, with_shuffle: bool = True, **kwargs) -> None:
        '''Trains the model
           **kwargs permits compatibility with Keras model

        Args:
            x_train (?): Array-like, shape = [n_samples, n_features]
            y_train (?): Array-like, shape = [n_samples,]
        Kwargs:
            x_valid (?): Array-like, shape = [n_samples, n_features]
            y_valid (?): Array-like, shape = [n_samples,]
            with_shuffle (bool): If x, y must be shuffled before fitting
        Raises:
            RuntimeError: If the model is already fitted
        '''
        # TODO: Check if we can continue the training of a xgboost
        if self.trained:
            self.logger.error("We can't train again a xgboost model")
            self.logger.error("Please train a new model")
            raise RuntimeError("We can't train again a xgboost model")

        # We check input format
        x_train, y_train = self._check_input_format(x_train, y_train, fit_function=True)
        # If there is a validation set, we also check the format (but fit_function to False)
        if y_valid is not None and x_valid is not None:
            x_valid, y_valid = self._check_input_format(x_valid, y_valid, fit_function=False)
        # Otherwise, we do a random split
        else:
            self.logger.warning(f"Warning, no validation dataset. We split the training set (fraction valid = {self.validation_split})")
            x_train, x_valid, y_train, y_valid = train_test_split(x_train, y_train, test_size=self.validation_split, random_state=self.random_seed)

        # Shuffle x, y if wanted
        if with_shuffle:
            rng = np.random.RandomState(self.random_seed)
            p = rng.permutation(len(x_train))
            x_train = np.array(x_train)[p]
            y_train = np.array(y_train)[p]
        # Else still transform to numpy array
        else:
            x_train = np.array(x_train)
            y_train = np.array(y_train)

        # Also get x_valid & y_valid as numpy
        x_valid = np.array(x_valid)
        y_valid = np.array(y_valid)

        # Set eval set and train
        eval_set = [(x_train, y_train), (x_valid, y_valid)]  # If there’s more than one item in eval_set, the last entry will be used for early stopping.
        prior_objective = self.model.objective
        self.model.fit(x_train, y_train, eval_set=eval_set, early_stopping_rounds=self.early_stopping_rounds, verbose=True)
        post_objective = self.model.objective
        if prior_objective != post_objective:
            self.logger.warning("Warning: the objective function was automatically changed by XGBOOST")
            self.logger.warning(f"Before: {prior_objective}")
            self.logger.warning(f"After: {post_objective}")

        # Set trained
        self.trained = True
        self.nb_fit += 1

    @utils.trained_needed
    def predict(self, x_test: pd.DataFrame, return_proba: bool = False, **kwargs) -> np.ndarray:
        '''Predictions on test set

        Args:
            x_test (pd.DataFrame): DataFrame with the test data to be predicted
        Kwargs:
            return_proba (bool): Present for compatibility with other models. Raises an error if True
        Raises:
            ValueError: If return_proba is True
        Returns:
            (np.ndarray): Array, shape = [n_samples,]
        '''
        # Manage errors
        if return_proba:
            raise ValueError("Models of type model_xgboost_regressor can't handle probabilities")
        # We check input format
        x_test, _ = self._check_input_format(x_test)
        # Warning, "The method returns the model from the last iteration"
        # But : "Predict with X. If the model is trained with early stopping, then best_iteration is used automatically."
        y_pred = self.model.predict(x_test)
        return y_pred

    @utils.trained_needed
    def predict_proba(self, x_test: pd.DataFrame, **kwargs) -> np.ndarray:
        '''Predicts the probabilities on the test set. Here for compatibility

        Args:
            x_test (pd.DataFrame): Array-like, shape = [n_samples]
        Raises:
            ValueError: Model_xgboost_regressor does not implement predict_proba
        Returns:
            (np.ndarray): Array, shape = [n_samples,]
        '''
        # For compatibility
        raise ValueError("Models of type model_xgboost_regressor do not implement the method predict_proba")

    def save(self, json_data: Union[dict, None] = None) -> None:
        '''Saves the model

        Kwargs:
            json_data (dict): Additional configurations to be saved
        '''
        # Save model
        if json_data is None:
            json_data = {}

        json_data['librairie'] = 'xgboost'
        json_data['xgboost_params'] = self.xgboost_params
        json_data['early_stopping_rounds'] = self.early_stopping_rounds
        json_data['validation_split'] = self.validation_split

        # Save xgboost standalone
        if self.level_save in ['MEDIUM', 'HIGH']:
            if self.trained:
                save_path = os.path.join(self.model_dir, 'xbgoost_standalone.model')
                self.model.save_model(save_path)
            else:
                self.logger.warning("Can't save the XGboost in standalone because it hasn't been already fitted")

        # Save
        super().save(json_data=json_data)

    def reload_from_standalone(self, **kwargs) -> None:
        '''Reloads a model from its configuration and "standalones" files
        - /!\\ Experimental /!\\ -

        Kwargs:
            configuration_path (str): Path to configuration file
            xgboost_path (str): Path to standalone xgboost
            preprocess_pipeline_path (str): Path to preprocess pipeline
        Raises:
            ValueError: If configuration_path is None
            ValueError: If xgboost_path is None
            ValueError: If preprocess_pipeline_path is None
            FileNotFoundError: If the object configuration_path is not an existing file
            FileNotFoundError: If the object xgboost_path is not an existing file
            FileNotFoundError: If the object preprocess_pipeline_path is not an existing file
        '''
        # Retrieve args
        configuration_path = kwargs.get('configuration_path', None)
        xgboost_path = kwargs.get('xgboost_path', None)
        preprocess_pipeline_path = kwargs.get('preprocess_pipeline_path', None)

        # Checks
        if configuration_path is None:
            raise ValueError("The argument configuration_path can't be None")
        if xgboost_path is None:
            raise ValueError("The argument xgboost_path can't be None")
        if preprocess_pipeline_path is None:
            raise ValueError("The argument preprocess_pipeline_path can't be None")
        if not os.path.exists(configuration_path):
            raise FileNotFoundError(f"The file {configuration_path} does not exist")
        if not os.path.exists(xgboost_path):
            raise FileNotFoundError(f"The file {xgboost_path} does not exist")
        if not os.path.exists(preprocess_pipeline_path):
            raise FileNotFoundError(f"The file {preprocess_pipeline_path} does not exist")

        # Load confs
        with open(configuration_path, 'r', encoding='utf-8') as f:
            configs = json.load(f)
        # Set class vars
        # self.model_name = # Keep the created name
        # self.model_dir = # Keep the created folder
        self.nb_fit = configs.get('nb_fit', 1)  # Consider one unique fit by default
        self.trained = configs.get('trained', True)  # Consider trained by default
        # Try to read the following attributes from configs and, if absent, keep the current one
        for attribute in ['model_type', 'x_col', 'y_col', 'columns_in', 'mandatory_columns',
                          'random_seed', 'level_save', 'xgboost_params', 'early_stopping_rounds', 'validation_split']:
            setattr(self, attribute, configs.get(attribute, getattr(self, attribute)))

        # Reload xgboost model
        self.model.load_model(xgboost_path)  # load data

        # Reload pipeline preprocessing
        with open(preprocess_pipeline_path, 'rb') as f:
            self.preprocess_pipeline = pickle.load(f)

__init__(xgboost_params=None, early_stopping_rounds=5, validation_split=0.2, **kwargs)

Initialization of the class (see ModelClass & ModelRegressorMixin for more arguments)

Kwargs

xgboost_params (dict): Parameters for the Xgboost -> https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.XGBRegressor early_stopping_rounds (int): Number of rounds for early stopping validation_split (float): Validation split fraction. Only used if not validation dataset in the fit input

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
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
def __init__(self, xgboost_params: Union[dict, None] = None, early_stopping_rounds: int = 5, validation_split: float = 0.2, **kwargs) -> None:
    '''Initialization of the class  (see ModelClass & ModelRegressorMixin for more arguments)

    Kwargs:
        xgboost_params (dict): Parameters for the Xgboost
            -> https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.XGBRegressor
        early_stopping_rounds (int): Number of rounds for early stopping
        validation_split (float): Validation split fraction.
            Only used if not validation dataset in the fit input
    '''
    # Init.
    super().__init__(**kwargs)

    # Get logger (must be done after super init)
    self.logger = logging.getLogger(__name__)

    # Set parameters
    if xgboost_params is None:
        xgboost_params = {}
    xgboost_params["random_state"] = self.random_seed
    self.xgboost_params = xgboost_params
    self.early_stopping_rounds = early_stopping_rounds
    self.validation_split = validation_split

    # Set objective (if not in params) & init. model
    if 'objective' not in self.xgboost_params.keys():
        self.xgboost_params['objective'] = 'reg:squarederror'
        #  List of objectives https://xgboost.readthedocs.io/en/latest/parameter.html#learning-task-parameters
    self.model = XGBRegressor(**self.xgboost_params)

fit(x_train, y_train, x_valid=None, y_valid=None, with_shuffle=True, **kwargs)

Trains the model **kwargs permits compatibility with Keras model

Parameters:

Name Type Description Default
x_train ?

Array-like, shape = [n_samples, n_features]

 required
y_train ?

Array-like, shape = [n_samples,]

 required

Kwargs: x_valid (?): Array-like, shape = [n_samples, n_features] y_valid (?): Array-like, shape = [n_samples,] with_shuffle (bool): If x, y must be shuffled before fitting Raises: RuntimeError: If the model is already fitted

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
 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
def fit(self, x_train, y_train, x_valid=None, y_valid=None, with_shuffle: bool = True, **kwargs) -> None:
    '''Trains the model
       **kwargs permits compatibility with Keras model

    Args:
        x_train (?): Array-like, shape = [n_samples, n_features]
        y_train (?): Array-like, shape = [n_samples,]
    Kwargs:
        x_valid (?): Array-like, shape = [n_samples, n_features]
        y_valid (?): Array-like, shape = [n_samples,]
        with_shuffle (bool): If x, y must be shuffled before fitting
    Raises:
        RuntimeError: If the model is already fitted
    '''
    # TODO: Check if we can continue the training of a xgboost
    if self.trained:
        self.logger.error("We can't train again a xgboost model")
        self.logger.error("Please train a new model")
        raise RuntimeError("We can't train again a xgboost model")

    # We check input format
    x_train, y_train = self._check_input_format(x_train, y_train, fit_function=True)
    # If there is a validation set, we also check the format (but fit_function to False)
    if y_valid is not None and x_valid is not None:
        x_valid, y_valid = self._check_input_format(x_valid, y_valid, fit_function=False)
    # Otherwise, we do a random split
    else:
        self.logger.warning(f"Warning, no validation dataset. We split the training set (fraction valid = {self.validation_split})")
        x_train, x_valid, y_train, y_valid = train_test_split(x_train, y_train, test_size=self.validation_split, random_state=self.random_seed)

    # Shuffle x, y if wanted
    if with_shuffle:
        rng = np.random.RandomState(self.random_seed)
        p = rng.permutation(len(x_train))
        x_train = np.array(x_train)[p]
        y_train = np.array(y_train)[p]
    # Else still transform to numpy array
    else:
        x_train = np.array(x_train)
        y_train = np.array(y_train)

    # Also get x_valid & y_valid as numpy
    x_valid = np.array(x_valid)
    y_valid = np.array(y_valid)

    # Set eval set and train
    eval_set = [(x_train, y_train), (x_valid, y_valid)]  # If there’s more than one item in eval_set, the last entry will be used for early stopping.
    prior_objective = self.model.objective
    self.model.fit(x_train, y_train, eval_set=eval_set, early_stopping_rounds=self.early_stopping_rounds, verbose=True)
    post_objective = self.model.objective
    if prior_objective != post_objective:
        self.logger.warning("Warning: the objective function was automatically changed by XGBOOST")
        self.logger.warning(f"Before: {prior_objective}")
        self.logger.warning(f"After: {post_objective}")

    # Set trained
    self.trained = True
    self.nb_fit += 1

predict(x_test, return_proba=False, **kwargs)

Predictions on test set

Parameters:

Name Type Description Default
x_test DataFrame

DataFrame with the test data to be predicted

 required

Kwargs: return_proba (bool): Present for compatibility with other models. Raises an error if True Raises: ValueError: If return_proba is True Returns: (np.ndarray): Array, shape = [n_samples,]

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
@utils.trained_needed
def predict(self, x_test: pd.DataFrame, return_proba: bool = False, **kwargs) -> np.ndarray:
    '''Predictions on test set

    Args:
        x_test (pd.DataFrame): DataFrame with the test data to be predicted
    Kwargs:
        return_proba (bool): Present for compatibility with other models. Raises an error if True
    Raises:
        ValueError: If return_proba is True
    Returns:
        (np.ndarray): Array, shape = [n_samples,]
    '''
    # Manage errors
    if return_proba:
        raise ValueError("Models of type model_xgboost_regressor can't handle probabilities")
    # We check input format
    x_test, _ = self._check_input_format(x_test)
    # Warning, "The method returns the model from the last iteration"
    # But : "Predict with X. If the model is trained with early stopping, then best_iteration is used automatically."
    y_pred = self.model.predict(x_test)
    return y_pred

predict_proba(x_test, **kwargs)

Predicts the probabilities on the test set. Here for compatibility

Parameters:

Name Type Description Default
x_test DataFrame

Array-like, shape = [n_samples]

 required

Raises: ValueError: Model_xgboost_regressor does not implement predict_proba Returns: (np.ndarray): Array, shape = [n_samples,]

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
156
157
158
159
160
161
162
163
164
165
166
167
168
@utils.trained_needed
def predict_proba(self, x_test: pd.DataFrame, **kwargs) -> np.ndarray:
    '''Predicts the probabilities on the test set. Here for compatibility

    Args:
        x_test (pd.DataFrame): Array-like, shape = [n_samples]
    Raises:
        ValueError: Model_xgboost_regressor does not implement predict_proba
    Returns:
        (np.ndarray): Array, shape = [n_samples,]
    '''
    # For compatibility
    raise ValueError("Models of type model_xgboost_regressor do not implement the method predict_proba")

reload_from_standalone(**kwargs)

Reloads a model from its configuration and "standalones" files - /! Experimental /! -

Kwargs

configuration_path (str): Path to configuration file xgboost_path (str): Path to standalone xgboost preprocess_pipeline_path (str): Path to preprocess pipeline

Raises: ValueError: If configuration_path is None ValueError: If xgboost_path is None ValueError: If preprocess_pipeline_path is None FileNotFoundError: If the object configuration_path is not an existing file FileNotFoundError: If the object xgboost_path is not an existing file FileNotFoundError: If the object preprocess_pipeline_path is not an existing file

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
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
def reload_from_standalone(self, **kwargs) -> None:
    '''Reloads a model from its configuration and "standalones" files
    - /!\\ Experimental /!\\ -

    Kwargs:
        configuration_path (str): Path to configuration file
        xgboost_path (str): Path to standalone xgboost
        preprocess_pipeline_path (str): Path to preprocess pipeline
    Raises:
        ValueError: If configuration_path is None
        ValueError: If xgboost_path is None
        ValueError: If preprocess_pipeline_path is None
        FileNotFoundError: If the object configuration_path is not an existing file
        FileNotFoundError: If the object xgboost_path is not an existing file
        FileNotFoundError: If the object preprocess_pipeline_path is not an existing file
    '''
    # Retrieve args
    configuration_path = kwargs.get('configuration_path', None)
    xgboost_path = kwargs.get('xgboost_path', None)
    preprocess_pipeline_path = kwargs.get('preprocess_pipeline_path', None)

    # Checks
    if configuration_path is None:
        raise ValueError("The argument configuration_path can't be None")
    if xgboost_path is None:
        raise ValueError("The argument xgboost_path can't be None")
    if preprocess_pipeline_path is None:
        raise ValueError("The argument preprocess_pipeline_path can't be None")
    if not os.path.exists(configuration_path):
        raise FileNotFoundError(f"The file {configuration_path} does not exist")
    if not os.path.exists(xgboost_path):
        raise FileNotFoundError(f"The file {xgboost_path} does not exist")
    if not os.path.exists(preprocess_pipeline_path):
        raise FileNotFoundError(f"The file {preprocess_pipeline_path} does not exist")

    # Load confs
    with open(configuration_path, 'r', encoding='utf-8') as f:
        configs = json.load(f)
    # Set class vars
    # self.model_name = # Keep the created name
    # self.model_dir = # Keep the created folder
    self.nb_fit = configs.get('nb_fit', 1)  # Consider one unique fit by default
    self.trained = configs.get('trained', True)  # Consider trained by default
    # Try to read the following attributes from configs and, if absent, keep the current one
    for attribute in ['model_type', 'x_col', 'y_col', 'columns_in', 'mandatory_columns',
                      'random_seed', 'level_save', 'xgboost_params', 'early_stopping_rounds', 'validation_split']:
        setattr(self, attribute, configs.get(attribute, getattr(self, attribute)))

    # Reload xgboost model
    self.model.load_model(xgboost_path)  # load data

    # Reload pipeline preprocessing
    with open(preprocess_pipeline_path, 'rb') as f:
        self.preprocess_pipeline = pickle.load(f)

save(json_data=None)

Saves the model

Kwargs

json_data (dict): Additional configurations to be saved

Source code in template_num/models_training/regressors/model_xgboost_regressor.py 
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
def save(self, json_data: Union[dict, None] = None) -> None:
    '''Saves the model

    Kwargs:
        json_data (dict): Additional configurations to be saved
    '''
    # Save model
    if json_data is None:
        json_data = {}

    json_data['librairie'] = 'xgboost'
    json_data['xgboost_params'] = self.xgboost_params
    json_data['early_stopping_rounds'] = self.early_stopping_rounds
    json_data['validation_split'] = self.validation_split

    # Save xgboost standalone
    if self.level_save in ['MEDIUM', 'HIGH']:
        if self.trained:
            save_path = os.path.join(self.model_dir, 'xbgoost_standalone.model')
            self.model.save_model(save_path)
        else:
            self.logger.warning("Can't save the XGboost in standalone because it hasn't been already fitted")

    # Save
    super().save(json_data=json_data)