U eB@s2ddlZddlmZddlmZGdddZdS)N)learning_curve)check_matplotlib_supportc@seZdZdZddddZdddddddddd d d Zeded d dddddddddej dddddddddddddZ dS)LearningCurveDisplaya Learning Curve visualization. It is recommended to use :meth:`~sklearn.model_selection.LearningCurveDisplay.from_estimator` to create a :class:`~sklearn.model_selection.LearningCurveDisplay` instance. All parameters are stored as attributes. Read more in the :ref:`User Guide `. .. versionadded:: 1.2 Parameters ---------- train_sizes : ndarray of shape (n_unique_ticks,) Numbers of training examples that has been used to generate the learning curve. train_scores : ndarray of shape (n_ticks, n_cv_folds) Scores on training sets. test_scores : ndarray of shape (n_ticks, n_cv_folds) Scores on test set. score_name : str, default=None The name of the score used in `learning_curve`. It will be used to decorate the y-axis. If `None`, the generic name `"Score"` will be used. Attributes ---------- ax_ : matplotlib Axes Axes with the learning curve. figure_ : matplotlib Figure Figure containing the learning curve. errorbar_ : list of matplotlib Artist or None When the `std_display_style` is `"errorbar"`, this is a list of `matplotlib.container.ErrorbarContainer` objects. If another style is used, `errorbar_` is `None`. lines_ : list of matplotlib Artist or None When the `std_display_style` is `"fill_between"`, this is a list of `matplotlib.lines.Line2D` objects corresponding to the mean train and test scores. If another style is used, `line_` is `None`. fill_between_ : list of matplotlib Artist or None When the `std_display_style` is `"fill_between"`, this is a list of `matplotlib.collections.PolyCollection` objects. If another style is used, `fill_between_` is `None`. See Also -------- sklearn.model_selection.learning_curve : Compute the learning curve. Examples -------- >>> import matplotlib.pyplot as plt >>> from sklearn.datasets import load_iris >>> from sklearn.model_selection import LearningCurveDisplay, learning_curve >>> from sklearn.tree import DecisionTreeClassifier >>> X, y = load_iris(return_X_y=True) >>> tree = DecisionTreeClassifier(random_state=0) >>> train_sizes, train_scores, test_scores = learning_curve( ... tree, X, y) >>> display = LearningCurveDisplay(train_sizes=train_sizes, ... train_scores=train_scores, test_scores=test_scores, score_name="Score") >>> display.plot() <...> >>> plt.show() N) score_namecCs||_||_||_||_dS)N train_sizes train_scores test_scoresr)selfr r r rr ^/var/www/html/assets/scripts/venv/lib/python3.8/site-packages/sklearn/model_selection/_plot.py__init__PszLearningCurveDisplay.__init__Ftest fill_between) negate_scorer score_type log_scalestd_display_styleline_kwfill_between_kw errorbar_kwc Csht|jjdddlm} |dkr2| \} }|rJ|j |j } } n|j|j} } |dkrptd|d|dkrtd|d |d krd | i}n|d krd | i}n | | d}|dkr|dkri}g|_ | D]2\}}|j j |j |j |jddfd|i|qd|_d|_|dkr| dkr2i} g|_| D]>\}}|j |j|j |jdd|jddfd|i| q@d\|_ |_n|dkr|dkri}ddi}||}g|_| D]N\}}|j |j|j |jdd|jdd|jdd|jddf|q|dkr$|jn|}||r@|d|d||||_|j|_|S)a;Plot visualization. Parameters ---------- ax : matplotlib Axes, default=None Axes object to plot on. If `None`, a new figure and axes is created. negate_score : bool, default=False Whether or not to negate the scores obtained through :func:`~sklearn.model_selection.learning_curve`. This is particularly useful when using the error denoted by `neg_*` in `scikit-learn`. score_name : str, default=None The name of the score used to decorate the y-axis of the plot. If `None`, the generic name "Score" will be used. score_type : {"test", "train", "both"}, default="test" The type of score to plot. Can be one of `"test"`, `"train"`, or `"both"`. log_scale : bool, default=False Whether or not to use a logarithmic scale for the x-axis. std_display_style : {"errorbar", "fill_between"} or None, default="fill_between" The style used to display the score standard deviation around the mean score. If None, no standard deviation representation is displayed. line_kw : dict, default=None Additional keyword arguments passed to the `plt.plot` used to draw the mean score. fill_between_kw : dict, default=None Additional keyword arguments passed to the `plt.fill_between` used to draw the score standard deviation. errorbar_kw : dict, default=None Additional keyword arguments passed to the `plt.errorbar` used to draw mean score and standard deviation score. Returns ------- display : :class:`~sklearn.model_selection.LearningCurveDisplay` Object that stores computed values. z.plotrN)errorbarrNzUnknown std_display_style: z7. Should be one of 'errorbar', 'fill_between', or None.)rtrainZbothzUnknown score_type: z.. Should be one of 'test', 'train', or 'both'.rTraining metricrTesting metric)rr)rNr)Zaxislabelr)NNralphag?logz%Number of samples in the training set)r __class____name__Zmatplotlib.pyplotZpyplotZsubplotsr r ValueErrorZlines_itemsappendplotr ZmeanZ errorbar_Z fill_between_rZstdrrZlegendZ set_xscaleZ set_xlabelZ set_ylabelZax_ZfigureZfigure_)r axrrrrrrrrZplt_r r ZscoresZ line_labelZscoreZdefault_fill_between_kwr r rr%Vs<                    zLearningCurveDisplay.plotg?g?allr)groupsr cvscoringexploit_incremental_learningn_jobs pre_dispatchverboseshuffle random_state error_score fit_paramsr&rrrrrrrrcCsxt|jd|dkrdn|}t||||||||| | | | | |d|d\}}}|||||d}|j||||||||dS)a;Create a learning curve display from an estimator. Parameters ---------- estimator : object type that implements the "fit" and "predict" methods An object of that type which is cloned for each validation. X : array-like of shape (n_samples, n_features) Training data, where `n_samples` is the number of samples and `n_features` is the number of features. y : array-like of shape (n_samples,) or (n_samples, n_outputs) or None Target relative to X for classification or regression; None for unsupervised learning. groups : array-like of shape (n_samples,), default=None Group labels for the samples used while splitting the dataset into train/test set. Only used in conjunction with a "Group" :term:`cv` instance (e.g., :class:`GroupKFold`). train_sizes : array-like of shape (n_ticks,), default=np.linspace(0.1, 1.0, 5) Relative or absolute numbers of training examples that will be used to generate the learning curve. If the dtype is float, it is regarded as a fraction of the maximum size of the training set (that is determined by the selected validation method), i.e. it has to be within (0, 1]. Otherwise it is interpreted as absolute sizes of the training sets. Note that for classification the number of samples usually have to be big enough to contain at least one sample from each class. cv : int, cross-validation generator or an iterable, default=None Determines the cross-validation splitting strategy. Possible inputs for cv are: - None, to use the default 5-fold cross validation, - int, to specify the number of folds in a `(Stratified)KFold`, - :term:`CV splitter`, - An iterable yielding (train, test) splits as arrays of indices. For int/None inputs, if the estimator is a classifier and `y` is either binary or multiclass, :class:`~sklearn.model_selection.StratifiedKFold` is used. In all other cases, :class:`~sklearn.model_selectionKFold` is used. These splitters are instantiated with `shuffle=False` so the splits will be the same across calls. Refer :ref:`User Guide ` for the various cross-validation strategies that can be used here. scoring : str or callable, default=None A string (see :ref:`scoring_parameter`) or a scorer callable object / function with signature `scorer(estimator, X, y)` (see :ref:`scoring`). exploit_incremental_learning : bool, default=False If the estimator supports incremental learning, this will be used to speed up fitting for different training set sizes. n_jobs : int, default=None Number of jobs to run in parallel. Training the estimator and computing the score are parallelized over the different training and test sets. `None` means 1 unless in a :obj:`joblib.parallel_backend` context. `-1` means using all processors. See :term:`Glossary ` for more details. pre_dispatch : int or str, default='all' Number of predispatched jobs for parallel execution (default is all). The option can reduce the allocated memory. The str can be an expression like '2*n_jobs'. verbose : int, default=0 Controls the verbosity: the higher, the more messages. shuffle : bool, default=False Whether to shuffle training data before taking prefixes of it based on`train_sizes`. random_state : int, RandomState instance or None, default=None Used when `shuffle` is True. Pass an int for reproducible output across multiple function calls. See :term:`Glossary `. error_score : 'raise' or numeric, default=np.nan Value to assign to the score if an error occurs in estimator fitting. If set to 'raise', the error is raised. If a numeric value is given, FitFailedWarning is raised. fit_params : dict, default=None Parameters to pass to the fit method of the estimator. ax : matplotlib Axes, default=None Axes object to plot on. If `None`, a new figure and axes is created. negate_score : bool, default=False Whether or not to negate the scores obtained through :func:`~sklearn.model_selection.learning_curve`. This is particularly useful when using the error denoted by `neg_*` in `scikit-learn`. score_name : str, default=None The name of the score used to decorate the y-axis of the plot. If `None`, the generic `"Score"` name will be used. score_type : {"test", "train", "both"}, default="test" The type of score to plot. Can be one of `"test"`, `"train"`, or `"both"`. log_scale : bool, default=False Whether or not to use a logarithmic scale for the x-axis. std_display_style : {"errorbar", "fill_between"} or None, default="fill_between" The style used to display the score standard deviation around the mean score. If `None`, no representation of the standard deviation is displayed. line_kw : dict, default=None Additional keyword arguments passed to the `plt.plot` used to draw the mean score. fill_between_kw : dict, default=None Additional keyword arguments passed to the `plt.fill_between` used to draw the score standard deviation. errorbar_kw : dict, default=None Additional keyword arguments passed to the `plt.errorbar` used to draw mean score and standard deviation score. Returns ------- display : :class:`~sklearn.model_selection.LearningCurveDisplay` Object that stores computed values. Examples -------- >>> import matplotlib.pyplot as plt >>> from sklearn.datasets import load_iris >>> from sklearn.model_selection import LearningCurveDisplay >>> from sklearn.tree import DecisionTreeClassifier >>> X, y = load_iris(return_X_y=True) >>> tree = DecisionTreeClassifier(random_state=0) >>> LearningCurveDisplay.from_estimator(tree, X, y) <...> >>> plt.show() z.from_estimatorNZScoreF) r*r r+r,r-r.r/r0r1r2r3Z return_timesr4r)r&rrrrrrr)rr!rr%)clsZ estimatorXyr*r r+r,r-r.r/r0r1r2r3r4r&rrrrrrrrr r Zvizr r rfrom_estimatorsJ0 z#LearningCurveDisplay.from_estimator)N) r! __module__ __qualname____doc__rr% classmethodnpZlinspacenanr8r r r rrsJH  r)numpyr=rutilsrrr r r rs