ML之catboost：catboost的CatBoostRegressor函数源代码简介、解读之详细攻略

ML之catboost：catboost的CatBoostRegressor函数源代码简介、解读之详细攻略catboost的CatBoostRegressor函数源代码简介、解读class CatBoostRegressor Found at: catboost.coreclass CatBoostRegressor(CatBoost):_estimator_type = 'regressor'"""Implementation of the scikit-learn API for CatBoost regression.Parameters----------Like in CatBoostClassifier, except loss_function, classes_count, class_names and class_weightsloss_function : string, [default='RMSE']'RMSE''MAE''Quantile:alpha=value''LogLinQuantile:alpha=value''Poisson''MAPE''Lq:q=value'"""实现scikit-learn API的CatBoost回归。参数----------像CatBoostClassifier，除了loss_function, classes_count, class_names和class_weightsdef __init__(self,iterations=None,learning_rate=None,depth=None,l2_leaf_reg=None,model_size_reg=None,rsm=None,loss_function='RMSE',border_count=None,feature_border_type=None,per_float_feature_quantization=None,input_borders=None,output_borders=None,fold_permutation_block=None,od_pval=None,od_wait=None,od_type=None,nan_mode=None,counter_calc_method=None,leaf_estimation_iterations=None,leaf_estimation_method=None,thread_count=None,random_seed=None,use_best_model=None,best_model_min_trees=None,verbose=None,silent=None,logging_level=None,metric_period=None,ctr_leaf_count_limit=None,store_all_simple_ctr=None,max_ctr_complexity=None,has_time=None,allow_const_label=None,target_border=None,one_hot_max_size=None,random_strength=None,name=None,ignored_features=None,train_dir=None,custom_metric=None,eval_metric=None,bagging_temperature=None,save_snapshot=None,snapshot_file=None,snapshot_interval=None,fold_len_multiplier=None,used_ram_limit=None,gpu_ram_part=None,pinned_memory_size=None,allow_writing_files=None,final_ctr_computation_mode=None,approx_on_full_history=None,boosting_type=None,simple_ctr=None,combinations_ctr=None,per_feature_ctr=None,ctr_description=None,ctr_target_border_count=None,task_type=None,device_config=None,devices=None,bootstrap_type=None,subsample=None,mvs_reg=None,sampling_frequency=None,sampling_unit=None,dev_score_calc_obj_block_size=None,dev_efb_max_buckets=None,sparse_features_conflict_fraction=None,max_depth=None,n_estimators=None,num_boost_round=None,num_trees=None,colsample_bylevel=None,random_state=None,reg_lambda=None,objective=None,eta=None,max_bin=None,gpu_cat_features_storage=None,data_partition=None,metadata=None,early_stopping_rounds=None,cat_features=None,grow_policy=None,min_data_in_leaf=None,min_child_samples=None,max_leaves=None,num_leaves=None,score_function=None,leaf_estimation_backtracking=None,ctr_history_unit=None,monotone_constraints=None,feature_weights=None,penalties_coefficient=None,first_feature_use_penalties=None,per_object_feature_penalties=None,model_shrink_rate=None,model_shrink_mode=None,langevin=None,diffusion_temperature=None,posterior_sampling=None,boost_from_average=None):params = {}not_params = ["not_params", "self", "params", "__class__"]for key, value in iteritems(locals().copy()):if key not in not_params and value is not None:params[key] = valuesuper(CatBoostRegressor, self).__init__(params)def fit(self, X, y=None, cat_features=None, sample_weight=None, baseline=None,use_best_model=None,eval_set=None, verbose=None, logging_level=None, plot=False,column_description=None,verbose_eval=None, metric_period=None, silent=None, early_stopping_rounds=None,save_snapshot=None, snapshot_file=None, snapshot_interval=None, init_model=None):"""Fit the CatBoost model.Parameters----------X : catboost.Pool or list or numpy.ndarray or pandas.DataFrame or pandas.Series. If not catboost.Pool, 2 dimensional Feature matrix or string - file with dataset.y : list or numpy.ndarray or pandas.DataFrame or pandas.Series, optional (default=None). Labels, 1 dimensional array like. Use only if X is not catboost.Pool.cat_features : list or numpy.ndarray, optional (default=None). If not None, giving the list of Categ columns indices.Use only if X is not catboost.Pool.sample_weight : list or numpy.ndarray or pandas.DataFrame or pandas.Series, optional (default=None). Instance weights, 1 dimensional array like.baseline : list or numpy.ndarray, optional (default=None). If not None, giving 2 dimensional array like data. Use only if X is not catboost.Pool.use_best_model : bool, optional (default=None). Flag to use best modeleval_set : catboost.Pool or list, optional (default=None). A list of (X, y) tuple pairs to use as a validation set for early-stoppingmetric_period : int. Frequency of evaluating metrics.verbose : bool or int. If verbose is bool, then if set to True, logging_level is set to Verbose, if set to False, logging_level is set to Silent. If verbose is int, it determines the frequency of writing metrics to output and logging_level is set to Verbose.silent : bool. If silent is True, logging_level is set to Silent.  If silent is False, logging_level is set to Verbose.logging_level : string, optional (default=None). Possible values:- 'Silent'- 'Verbose'- 'Info'- 'Debug'plot : bool, optional (default=False). If True, draw train and eval error in Jupyter notebookverbose_eval : bool or int.  Synonym for verbose. Only one of these parameters should be set.early_stopping_rounds : int. Activates Iter overfitting detector with od_wait set to early_stopping_rounds.save_snapshot : bool, [default=None]. Enable progress snapshotting for restoring progress after crashes or interruptionssnapshot_file : string, [default=None]. Learn progress snapshot file path, if None will use default filename  snapshot_interval: int, [default=600]. Interval between saving snapshots (seconds)init_model : CatBoost class or string, [default=None]. Continue training starting from the existing model. If this parameter is a string, load initial model from the path specified by this string.Returns-------model : CatBoost"""params = deepcopy(self._init_params)_process_synonyms(params)if 'loss_function' in params:X: catboost。pool或list或numpy。ndarray或pandas.DataFrame或pandas.Series。如果不是catboost。Pool，二维特征矩阵或字符串文件与数据集。y: list或numpy。ndarray或pandas.DataFrame或pandas.Series。可选(默认= None)。标签，类似于一维数组。仅当X不是catboost.Pool时使用。cat_features: list或numpy.ndarray,可选(默认= None)。如果不是None，则给出类别列索引的列表。仅当X不是catboost.Pool时使用。sample_weight:列表或numpy。ndarray或pandas.DataFrame或pandas.Series,可选(默认= None)。实例权重，类似于一维数组。baseline:列表或numpy。ndarray,可选(默认= None)。如果不是None，则给出像data这样的二维数组。仅当X不是catboost.Pool时使用。use_best_model: bool，可选(默认为None)。标记使用最佳模型eval_set: catboost。Pool或列表，可选(默认为None)。(X, y)元组对的列表，用作早期停止的验证集。metric_period: int。评估指标的频率。verbose: bool或int。如果verbose是bool，那么如果设置为True, logging_level将设置为verbose，如果设置为False, logging_level将设置为Silent。如果verbose为int，则它确定向输出写入指标的频率，并将logging_level设置为verbose。silent : bool。如果silent为True, loging_level设置为silent。如果silent为False, loging_level设置为Verbose。logging_level:字符串，可选(默认为None)。可能的值:——“沉默”——“详细”——“信息”——“调试”plot: bool，可选(默认=False)。如果为真，在Jupyter中绘制训练集和测试集的errorverbose_eval: bool或int。详细的同义词。应该只设置这些参数中的一个。early_stopping_rounds: int。激活Iter过拟合检测器，od_wait设置为early_stopping_rounds。save_snapshot: bool， [default=None]。启用进度快照，以便在崩溃或中断后恢复进度snapshot_file: string， [default=None]。学习进度快照文件路径，如果没有将使用默认文件名snapshot_interval: int，[默认=600]。保存快照的时间间隔(秒)init_model: CatBoost类或字符串，[default=None]。从现有的模式开始继续培训。如果该参数为字符串，则从该字符串指定的路径加载初始模型。self._check_is_regressor_loss(params['loss_function'])return self._fit(X, y, cat_features, None, None, None, sample_weight, None, None, None,None, baseline,use_best_model, eval_set, verbose, logging_level, plot, column_description,verbose_eval, metric_period, silent, early_stopping_rounds,save_snapshot, snapshot_file, snapshot_interval, init_model)def predict(self, data, prediction_type=None, ntree_start=0, ntree_end=0, thread_count=-1, verbose=None):"""Predict with data.Parameters----------data : catboost.Pool or list of features or list of lists or numpy.ndarray or pandas. DataFrame or pandas.Series or catboost.FeaturesData. Data to apply model on. If data is a simple list (not list of lists) or a one-dimensional numpy.ndarray it is interpreted as a list of features for a single object.prediction_type : string, optional (default='RawFormulaVal').  Can be:- 'RawFormulaVal' : return raw formula value.- 'Exponent' : return Exponent of raw formula value.ntree_start: int, optional (default=0)Model is applied on the interval [ntree_start, ntree_end) (zero-based indexing).ntree_end: int, optional (default=0)Model is applied on the interval [ntree_start, ntree_end) (zero-based indexing). If value equals to 0 this parameter is ignored and ntree_end equal to tree_count_.thread_count : int (default=-1). The number of threads to use when applying the model. Allows you to optimize the speed of execution. This parameter doesn't affect results. If -1, then the number of threads is set to the number of CPU cores.verbose : bool. If True, writes the evaluation metric measured set to stderr.Returns-------prediction : If data is for a single object, the return value is single float formula return value otherwise one-dimensional numpy.ndarray of formula return values for each object."""if prediction_type is None:prediction_type = self._get_default_prediction_type()return self._predict(data, prediction_type, ntree_start, ntree_end, thread_count, verbose,'predict')参数---------data : catboost。池或特性列表或列表的列表或numpy。ndarray或熊猫。DataFrame或熊猫。系列或catboost.FeaturesData。应用模型的数据。如果data是一个简单的列表(不是列表的列表)或一维numpy。ndarray它被解释为一个对象的特性列表。prediction_type :字符串，可选(默认为'RawFormulaVal')。可以是:- 'RawFormulaVal':返回原始公式值。- 'Exponent':返回原始公式值的指数。ntree_start: int，可选(默认为0)模型应用于区间[ntree_start, ntree_end)(从零开始索引)。ntree_end:  int，可选(默认为0)模型应用于区间[ntree_start, ntree_end)(从零开始索引)。如果value等于0，则忽略该参数，ntree_end等于tree_count_。thread_count :int(默认=-1)。应用模型时要使用的线程数。允许您优化执行速度。此参数不影响结果。如果-1，则线程数设置为CPU核数。verbose :bool。如果为真，则将评估度量值写入stderr。返回-------prediction：如果数据是针对单个对象的，则返回值为单个float公式返回值，否则为一维numpy。ndarray的公式返回每个对象的值。def staged_predict(self, data, prediction_type='RawFormulaVal', ntree_start=0,ntree_end=0, eval_period=1, thread_count=-1, verbose=None):"""Predict target at each stage for data.Parameters----------data : catboost.Pool or list of features or list of lists or numpy.ndarray or pandas. DataFrame or pandas.Series or catboost.FeaturesData. Data to apply model on. If data is a simple list (not list of lists) or a one-dimensional numpy.ndarray it is interpreted as a list of features for a single object.ntree_start: int, optional (default=0). Model is applied on the interval [ntree_start, ntree_end) with the step eval_period (zero-based indexing).ntree_end: int, optional (default=0).Model is applied on the interval [ntree_start, ntree_end) with the step eval_period (zero-based indexing). If value equals to 0 this parameter is ignored and ntree_end equal to tree_count_.eval_period: int, optional (default=1). Model is applied on the interval [ntree_start, ntree_end) with the step eval_period (zero-based indexing).thread_count : int (default=-1). The number of threads to use when applying the model. Allows you to optimize the speed of execution. This parameter doesn't affect results. If -1, then the number of threads is set to the number of CPU cores.verbose : bool. If True, writes the evaluation metric measured set to stderr.Returns-------prediction : generator for each iteration that generates:If data is for a single object, the return value is single float formula return value  otherwise one-dimensional numpy.ndarray of formula return values for each object."""return self._staged_predict(data, prediction_type, ntree_start, ntree_end, eval_period,thread_count, verbose, 'staged_predict')data : catboost。池或特性列表或列表的列表或numpy。ndarray或DataFrame 或pandas.Series or catboost.FeaturesData。应用模型的数据。如果data是一个简单的列表(不是列表的列表)或一维numpy。ndarray它被解释为一个对象的特性列表。ntree_start: int，可选(默认为0)。模型应用于间隔[ntree_start, ntree_end)，步长为eval_period(从零开始索引)。ntree_end:int，可选(默认为0)。模型应用于间隔[ntree_start, ntree_end)，步长为eval_period(从零开始索引)。如果value等于0，则忽略该参数，ntree_end等于tree_count_。eval_period:  int，可选(默认为1)。模型应用于间隔[ntree_start, ntree_end)，步长为eval_period(从零开始索引)。thread_count : int(默认=-1)。应用模型时要使用的线程数。允许您优化执行速度。此参数不影响结果。如果-1，则线程数设置为CPU核数。verbose :bool。如果为真，则将评估度量值写入stderr。返回-------prediction :为每个迭代生成的生成器:如果数据是针对单个对象的，则返回值为单个float公式返回值，否则为一维numpy。ndarray的公式返回每个对象的值。def score(self, X, y=None):"""Calculate R^2.Parameters----------X : catboost.Pool or list or numpy.ndarray or pandas.DataFrame or pandas.Series.Data to apply model on.y : list or numpy.ndarray.True labels.Returns-------R^2 : float"""if isinstance(X, Pool):if y is not None:raise CatBoostError("Wrong initializing y: X is catboost.Pool object, y must beinitialized inside catboost.Pool.")y = X.get_label()if y is None:raise CatBoostError("Label in X has not initialized.")elif y is None:raise CatBoostError("y should be specified.")y = np.array(y, dtype=np.float64)predictions = self._predict(X,prediction_type=self._get_default_prediction_type(),ntree_start=0,ntree_end=0,thread_count=-1,verbose=None,parent_method_name='score')loss = self._object._get_loss_function_name()if loss == 'RMSEWithUncertainty':predictions = predictions[:0]total_sum_of_squares = np.sum((y - y.mean(axis=0)) ** 2)residual_sum_of_squares = np.sum((y - predictions) ** 2)return 1 - residual_sum_of_squares / total_sum_of_squaresdef _check_is_regressor_loss(self, loss_function):is_regression = self._is_regression_objective(loss_function) or self._is_multiregression_objective(loss_function)if isinstance(loss_function, str) and not is_regression:raise CatBoostError("Invalid loss_function='{}': for regressor use ""RMSE, MultiRMSE, MAE, Quantile, LogLinQuantile, Poisson, MAPE, Lq or customobjective object".format(loss_function))def _get_default_prediction_type(self):# TODO(ilyzhin) change on get_all_params after MLTOOLS-4758params = deepcopy(self._init_params)_process_synonyms(params)loss_function = params.get('loss_function')if loss_function and isinstance(loss_function, str):if loss_function.startswith('Poisson') or loss_function.startswith('Tweedie'):return 'Exponent'if loss_function == 'RMSEWithUncertainty':return 'RMSEWithUncertainty'return 'RawFormulaVal'