MCPcopy Create free account
hub / github.com/catboost/catboost / eval_metrics

Method eval_metrics

catboost/python-package/catboost/core.py:3234–3281  ·  view source on GitHub ↗

Calculate metrics. Parameters ---------- data : catboost.Pool Data to evaluate metrics on. metrics : list of strings or catboost.metrics.BuiltinMetric List of evaluated metrics. ntree_start: int, optional (default=0)

(self, data, metrics, ntree_start=0, ntree_end=0, eval_period=1, thread_count=-1, tmp_dir=None, plot=False, plot_file=None, log_cout=None, log_cerr=None)

Source from the content-addressed store, hash-verified

3232 return dict(zip(metric_names, metrics_score))
3233
3234 def eval_metrics(self, data, metrics, ntree_start=0, ntree_end=0, eval_period=1, thread_count=-1, tmp_dir=None, plot=False, plot_file=None, log_cout=None, log_cerr=None):
3235 """
3236 Calculate metrics.
3237
3238 Parameters
3239 ----------
3240 data : catboost.Pool
3241 Data to evaluate metrics on.
3242
3243 metrics : list of strings or catboost.metrics.BuiltinMetric
3244 List of evaluated metrics.
3245
3246 ntree_start: int, optional (default=0)
3247 Model is applied on the interval [ntree_start, ntree_end) (zero-based indexing).
3248
3249 ntree_end: int, optional (default=0)
3250 Model is applied on the interval [ntree_start, ntree_end) (zero-based indexing).
3251 If value equals to 0 this parameter is ignored and ntree_end equal to tree_count_.
3252
3253 eval_period: int, optional (default=1)
3254 Model is applied on the interval [ntree_start, ntree_end) with the step eval_period (zero-based indexing).
3255
3256 thread_count : int (default=-1)
3257 The number of threads to use when applying the model.
3258 Allows you to optimize the speed of execution. This parameter doesn't affect results.
3259 If -1, then the number of threads is set to the number of CPU cores.
3260
3261 tmp_dir : string or os.PathLike (default=None)
3262 The name of the temporary directory for intermediate results.
3263 If None, then the name will be generated.
3264
3265 plot : bool, optional (default=False)
3266 If True, draw train and eval error in Jupyter notebook
3267
3268 plot_file : file-like or str, optional (default=None)
3269 If not None, save train and eval error graphs to file
3270
3271 log_cout: output stream or callback for logging (default=None)
3272 If None is specified, sys.stdout is used
3273
3274 log_cerr: error stream or callback for logging (default=None)
3275 If None is specified, sys.stderr is used
3276
3277 Returns
3278 -------
3279 prediction : dict: metric -> array of shape [(ntree_end - ntree_start) / eval_period]
3280 """
3281 return self._eval_metrics(data, metrics, ntree_start, ntree_end, eval_period, thread_count, _get_train_dir(self._init_params), tmp_dir, plot, plot_file, log_cout, log_cerr)
3282
3283 def compare(self, model, data, metrics, ntree_start=0, ntree_end=0, eval_period=1, thread_count=-1, tmp_dir=None, plot_file=None, log_cout=None, log_cerr=None):
3284 """

Calls 2

_eval_metricsMethod · 0.95
_get_train_dirFunction · 0.85