U 3dV8@sFddlZddlZddlmZddlmZddlmZGdddZdS)N)check_matplotlib_support)check_random_state)_safe_indexingc@sdeZdZdZddZdddddddZedd ddddd d d Zedd ddddd d dZdS)PredictionErrorDisplayaVisualization of the prediction error of a regression model. This tool can display "residuals vs predicted" or "actual vs predicted" using scatter plots to qualitatively assess the behavior of a regressor, preferably on held-out data points. See the details in the docstrings of :func:`~sklearn.metrics.PredictionErrorDisplay.from_estimator` or :func:`~sklearn.metrics.PredictionErrorDisplay.from_predictions` to create a visualizer. All parameters are stored as attributes. For general information regarding `scikit-learn` visualization tools, read more in the :ref:`Visualization Guide `. For details regarding interpreting these plots, refer to the :ref:`Model Evaluation Guide `. .. versionadded:: 1.2 Parameters ---------- y_true : ndarray of shape (n_samples,) True values. y_pred : ndarray of shape (n_samples,) Prediction values. Attributes ---------- line_ : matplotlib Artist Optimal line representing `y_true == y_pred`. Therefore, it is a diagonal line for `kind="predictions"` and a horizontal line for `kind="residuals"`. errors_lines_ : matplotlib Artist or None Residual lines. If `with_errors=False`, then it is set to `None`. scatter_ : matplotlib Artist Scatter data points. ax_ : matplotlib Axes Axes with the different matplotlib axis. figure_ : matplotlib Figure Figure containing the scatter and lines. See Also -------- PredictionErrorDisplay.from_estimator : Prediction error visualization given an estimator and some data. PredictionErrorDisplay.from_predictions : Prediction error visualization given the true and predicted targets. Examples -------- >>> import matplotlib.pyplot as plt >>> from sklearn.datasets import load_diabetes >>> from sklearn.linear_model import Ridge >>> from sklearn.metrics import PredictionErrorDisplay >>> X, y = load_diabetes(return_X_y=True) >>> ridge = Ridge().fit(X, y) >>> y_pred = ridge.predict(X) >>> display = PredictionErrorDisplay(y_true=y, y_pred=y_pred) >>> display.plot() <...> >>> plt.show() cCs||_||_dS)Ny_truey_pred)selfrr r D/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/metrics/_plot/regression.py__init__NszPredictionErrorDisplay.__init__Nresidual_vs_predicted)kindscatter_kwargs line_kwargscCst|jjdd}||kr:tdd|d|dddlm}|dkrRi}|dkr^i}d d d }d d dd}||}||}|dkr|\} }|dkrXtt |j t |j } t t |j t |j } |j | | g| | gf|d|_|j |j } } d\}}|j| | f||_|jddd|t j| | dd|t j| | ddnR|j t |j t |j gddgf|d|_|j|j |j |j f||_d\}}|j||d||_|j|_|S)aPlot visualization. Extra keyword arguments will be passed to matplotlib's ``plot``. Parameters ---------- ax : matplotlib axes, default=None Axes object to plot on. If `None`, a new figure and axes is created. kind : {"actual_vs_predicted", "residual_vs_predicted"}, default="residual_vs_predicted" The type of plot to draw: - "actual_vs_predicted" draws the the observed values (y-axis) vs. the predicted values (x-axis). - "residual_vs_predicted" draws the residuals, i.e difference between observed and predicted values, (y-axis) vs. the predicted values (x-axis). scatter_kwargs : dict, default=None Dictionary with keywords passed to the `matplotlib.pyplot.scatter` call. line_kwargs : dict, default=None Dictionary with keyword passed to the `matplotlib.pyplot.plot` call to draw the optimal line. Returns ------- display : :class:`~sklearn.metrics.plot.PredictionErrorDisplay` Object that stores computed values. z.plot)actual_vs_predictedrz`kind` must be one of z, z. Got z instead.rNztab:blueg?)coloralphaZblackgffffff?z--)rrZ linestyler)Predicted valuesz Actual valuesequalZdatalim)Z adjustable)num)rzResiduals (actual - predicted))xlabelylabel)r __class____name__ ValueErrorjoinZmatplotlib.pyplotZpyplotZsubplotsmaxnprr minplotZline_ZscatterZscatter_Z set_aspectZ set_xticksZlinspaceZ set_ytickssetZax_figureZfigure_)r axrrrZ expected_kindZpltZdefault_scatter_kwargsZdefault_line_kwargs_Z max_valueZ min_valueZx_dataZy_datarrr r r r"Rsj)      zPredictionErrorDisplay.ploti)r subsample random_stater%rrc Cs4t|jd||} |j|| |||||| dS)a8 Plot the prediction error given a regressor and some data. For general information regarding `scikit-learn` visualization tools, read more in the :ref:`Visualization Guide `. For details regarding interpreting these plots, refer to the :ref:`Model Evaluation Guide `. .. versionadded:: 1.2 Parameters ---------- estimator : estimator instance Fitted regressor or a fitted :class:`~sklearn.pipeline.Pipeline` in which the last estimator is a regressor. X : {array-like, sparse matrix} of shape (n_samples, n_features) Input values. y : array-like of shape (n_samples,) Target values. kind : {"actual_vs_predicted", "residual_vs_predicted"}, default="residual_vs_predicted" The type of plot to draw: - "actual_vs_predicted" draws the the observed values (y-axis) vs. the predicted values (x-axis). - "residual_vs_predicted" draws the residuals, i.e difference between observed and predicted values, (y-axis) vs. the predicted values (x-axis). subsample : float, int or None, default=1_000 Sampling the samples to be shown on the scatter plot. If `float`, it should be between 0 and 1 and represents the proportion of the original dataset. If `int`, it represents the number of samples display on the scatter plot. If `None`, no subsampling will be applied. by default, a 1000 samples or less will be displayed. random_state : int or RandomState, default=None Controls the randomness when `subsample` is not `None`. See :term:`Glossary ` for details. ax : matplotlib axes, default=None Axes object to plot on. If `None`, a new figure and axes is created. scatter_kwargs : dict, default=None Dictionary with keywords passed to the `matplotlib.pyplot.scatter` call. line_kwargs : dict, default=None Dictionary with keyword passed to the `matplotlib.pyplot.plot` call to draw the optimal line. Returns ------- display : :class:`~sklearn.metrics.PredictionErrorDisplay` Object that stores the computed values. See Also -------- PredictionErrorDisplay : Prediction error visualization for regression. PredictionErrorDisplay.from_predictions : Prediction error visualization given the true and predicted targets. Examples -------- >>> import matplotlib.pyplot as plt >>> from sklearn.datasets import load_diabetes >>> from sklearn.linear_model import Ridge >>> from sklearn.metrics import PredictionErrorDisplay >>> X, y = load_diabetes(return_X_y=True) >>> ridge = Ridge().fit(X, y) >>> disp = PredictionErrorDisplay.from_estimator(ridge, X, y) >>> plt.show() z.from_estimator)rr rr'r(r%rr)rrZpredictfrom_predictions) clsZ estimatorXyrr'r(r%rrr r r r from_estimatorsZ z%PredictionErrorDisplay.from_estimatorc Cst|jdt|}t|} t|tjrF|dkr~td|dn8t|tjr~|dksb|dkrrtd|dt | |}|dk r|| kr|j t | |d } t || dd }t || dd }t||d } | j||||d S) a Plot the prediction error given the true and predicted targets. For general information regarding `scikit-learn` visualization tools, read more in the :ref:`Visualization Guide `. For details regarding interpreting these plots, refer to the :ref:`Model Evaluation Guide `. .. versionadded:: 1.2 Parameters ---------- y_true : array-like of shape (n_samples,) True target values. y_pred : array-like of shape (n_samples,) Predicted target values. kind : {"actual_vs_predicted", "residual_vs_predicted"}, default="residual_vs_predicted" The type of plot to draw: - "actual_vs_predicted" draws the the observed values (y-axis) vs. the predicted values (x-axis). - "residual_vs_predicted" draws the residuals, i.e difference between observed and predicted values, (y-axis) vs. the predicted values (x-axis). subsample : float, int or None, default=1_000 Sampling the samples to be shown on the scatter plot. If `float`, it should be between 0 and 1 and represents the proportion of the original dataset. If `int`, it represents the number of samples display on the scatter plot. If `None`, no subsampling will be applied. by default, a 1000 samples or less will be displayed. random_state : int or RandomState, default=None Controls the randomness when `subsample` is not `None`. See :term:`Glossary ` for details. ax : matplotlib axes, default=None Axes object to plot on. If `None`, a new figure and axes is created. scatter_kwargs : dict, default=None Dictionary with keywords passed to the `matplotlib.pyplot.scatter` call. line_kwargs : dict, default=None Dictionary with keyword passed to the `matplotlib.pyplot.plot` call to draw the optimal line. Returns ------- display : :class:`~sklearn.metrics.PredictionErrorDisplay` Object that stores the computed values. See Also -------- PredictionErrorDisplay : Prediction error visualization for regression. PredictionErrorDisplay.from_estimator : Prediction error visualization given an estimator and some data. Examples -------- >>> import matplotlib.pyplot as plt >>> from sklearn.datasets import load_diabetes >>> from sklearn.linear_model import Ridge >>> from sklearn.metrics import PredictionErrorDisplay >>> X, y = load_diabetes(return_X_y=True) >>> ridge = Ridge().fit(X, y) >>> y_pred = ridge.predict(X) >>> disp = PredictionErrorDisplay.from_predictions(y_true=y, y_pred=y_pred) >>> plt.show() z.from_predictionsrzWhen an integer, subsample=z should be positive.z!When a floating-point, subsample=z should be in the (0, 1) range.N)size)Zaxisr)r%rrr)rrrlen isinstancenumbersIntegralrRealintchoicer Zarangerrr") r*rr rr'r(r%rrZ n_samplesindicesZvizr r r r)s8V     z'PredictionErrorDisplay.from_predictions)N) r __module__ __qualname____doc__r r" classmethodr-r)r r r r r s0C dhr)r2Znumpyr utilsrrrrr r r r s