ó ¾÷Xc@@s¦ddlmZddlZddlZddlZddlZddlmZddl m Z de fd„ƒYZ de fd „ƒYZ d e fd „ƒYZdS( i(tabsolute_importNi(tto_categorical(t Sequentialt BaseWrappercB@sJeZdZdd„Zd„Zd„Zd„Zd„Zdd„Z RS(s8Base class for the Keras scikit-learn wrapper. Warning: This class should not be used directly. Use descendant classes instead. # Arguments build_fn: callable function or class instance **sk_params: model parameters & fitting parameters The build_fn should construct, compile and return a Keras model, which will then be used to fit/predict. One of the following three values could be passed to build_fn: 1. A function 2. An instance of a class that implements the __call__ method 3. None. This means you implement a class that inherits from either `KerasClassifier` or `KerasRegressor`. The __call__ method of the present class will then be treated as the default build_fn. `sk_params` takes both model parameters and fitting parameters. Legal model parameters are the arguments of `build_fn`. Note that like all other estimators in scikit-learn, 'build_fn' should provide default values for its arguments, so that you could create the estimator without passing any values to `sk_params`. `sk_params` could also accept parameters for calling `fit`, `predict`, `predict_proba`, and `score` methods (e.g., `epochs`, `batch_size`). fitting (predicting) parameters are selected in the following order: 1. Values passed to the dictionary arguments of `fit`, `predict`, `predict_proba`, and `score` methods 2. Values passed to `sk_params` 3. The default values of the `keras.models.Sequential` `fit`, `predict`, `predict_proba` and `score` methods When using scikit-learn's `grid_search` API, legal tunable parameters are those you could pass to `sk_params`, including fitting parameters. In other words, you could use `grid_search` to search for the best `batch_size` or `epochs` as well as the model parameters. cK@s#||_||_|j|ƒdS(N(tbuild_fnt sk_paramst check_params(tselfRR((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyt__init__6s  cC@stjtjtjtjg}|jdkr@|j|jƒnRt |jt j ƒ r‚t |jt j ƒ r‚|j|jjƒn|j|jƒg}x%|D]}|t j|ƒd7}qŸWt|ƒ}xA|D]9}||krÓ|dkr tdj|ƒƒ‚q qÓqÓWdS(sÚChecks for user typos in "params". # Arguments params: dictionary; the parameters to be checked # Raises ValueError: if any member of `params` is not a valid argument. itnb_epochs{} is not a legal parameterN(Rtfittpredicttpredict_classestevaluateRtNonetappendt__call__t isinstancettypest FunctionTypet MethodTypetinspectt getargspectsett ValueErrortformat(Rtparamstlegal_params_fnst legal_paramstfnt params_name((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR;s"      cK@s-tj|jƒ}|ji|jd6ƒ|S(sÓGets parameters for this estimator. # Arguments **params: ignored (exists for API compatiblity). # Returns Dictionary of parameter names mapped to their values. R(tcopytdeepcopyRtupdateR(RRtres((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyt get_paramsYs cK@s!|j|ƒ|jj|ƒ|S(s´Sets the parameters of this estimator. # Arguments **params: Dictionary of parameter names mapped to their values. # Returns self (RRR!(RR((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyt set_paramsfs cK@s9|jdkr0|j|j|jƒ|_nnt|jtjƒ r€t|jtjƒ r€|j|j|jjƒ|_n|j|j|jƒ|_|jj }t |dƒrÅ|j }n|dkrõt |j ƒdkrõt|ƒ}ntj|jtjƒƒ}|j|ƒ|jj|||}|S(stConstructs a new model with `build_fn` & fit the model to `(x, y)`. # Arguments x : array-like, shape `(n_samples, n_features)` Training samples where n_samples in the number of samples and n_features is the number of features. y : array-like, shape `(n_samples,)` or `(n_samples, n_outputs)` True labels for X. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.fit` # Returns history : object details about the training history at each epoch. t__name__tcategorical_crossentropyiN(RRRtfilter_sk_paramstmodelRRRRtlossthasattrR%tlentshapeRRR RR R!(Rtxtytkwargst loss_nametfit_argsthistory((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR ss !  ! cC@sy|p i}i}tj|ƒd}x@|jjƒD]/\}}||kr5|ji||6ƒq5q5W|j|ƒ|S(s@Filters `sk_params` and return those in `fn`'s arguments. # Arguments fn : arbitrary function override: dictionary, values to override sk_params # Returns res : dictionary dictionary containing variables in both sk_params and fn's arguments. i(RRRtitemsR!(RRtoverrideR"tfn_argstnametvalue((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR'™s   N( R%t __module__t__doc__RRRR#R$R R'(((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR s'   &tKerasClassifiercB@s2eZdZd„Zd„Zd„Zd„ZRS(sAImplementation of the scikit-learn classifier API for Keras. cK@s•tj|ƒ}t|jƒdkr@tj|jdƒ|_n'tj|ƒ|_tj|j|ƒ}t|jƒ|_t t |ƒj |||S(stConstructs a new model with `build_fn` & fit the model to `(x, y)`. # Arguments x : array-like, shape `(n_samples, n_features)` Training samples where n_samples in the number of samples and n_features is the number of features. y : array-like, shape `(n_samples,)` or `(n_samples, n_outputs)` True labels for X. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.fit` # Returns history : object details about the training history at each epoch. i( tnptarrayR+R,tarangetclasses_tuniquet searchsortedt n_classes_tsuperR:R (RR-R.R/((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR ²scK@s5|jtj|ƒ}|jj||}|j|S(sReturns the class predictions for the given test data. # Arguments x: array-like, shape `(n_samples, n_features)` Test samples where n_samples in the number of samples and n_features is the number of features. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.predict_classes`. # Returns preds: array-like, shape `(n_samples,)` Class predictions. (R'RR R(R>(RR-R/tclasses((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR ËscK@s]|jtj|ƒ}|jj||}|jddkrYtjd||gƒ}n|S(sÿReturns class probability estimates for the given test data. # Arguments x: array-like, shape `(n_samples, n_features)` Test samples where n_samples in the number of samples and n_features is the number of features. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.predict_classes`. # Returns proba: array-like, shape `(n_samples, n_outputs)` Class probability estimates. In the case of binary classification, tp match the scikit-learn API, will return an array of shape '(n_samples, 2)' (instead of `(n_sample, 1)` as in Keras). i(R'Rt predict_probaR(R,R;thstack(RR-R/tprobs((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyRDÞs cK@sútj|j|ƒ}|jtj|ƒ}|jj}t|dƒrQ|j }n|dkrt |j ƒdkrt |ƒ}n|jj|||}t |tƒs´|g}nx3t|jj|ƒD]\}}|dkrÊ|SqÊWtdƒ‚dS(s9Returns the mean accuracy on the given test data and labels. # Arguments x: array-like, shape `(n_samples, n_features)` Test samples where n_samples in the number of samples and n_features is the number of features. y: array-like, shape `(n_samples,)` or `(n_samples, n_outputs)` True labels for x. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.evaluate`. # Returns score: float Mean accuracy of predictions on X wrt. y. # Raises ValueError: If the underlying model isn't configured to compute accuracy. You should pass `metrics=["accuracy"]` to the `.compile()` method of the model. R%R&itaccsxThe model is not configured to compute accuracy. You should pass `metrics=["accuracy"]` to the `model.compile()` method.N(R;R@R>R'RR R(R)R*R%R+R,RRtlisttzipt metrics_namesR(RR-R.R/R0toutputsR6toutput((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pytscoreús  ! " (R%R8R9R R RDRM(((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR:®s    tKerasRegressorcB@s eZdZd„Zd„ZRS(s@Implementation of the scikit-learn regressor API for Keras. cK@s1|jtj|ƒ}tj|jj||ƒS(sßReturns predictions for the given test data. # Arguments x: array-like, shape `(n_samples, n_features)` Test samples where n_samples in the number of samples and n_features is the number of features. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.predict`. # Returns preds: array-like, shape `(n_samples,)` Predictions. (R'RR R;tsqueezeR((RR-R/((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyR 'scK@sH|jtj|ƒ}|jj|||}t|tƒrD|dS|S(sAReturns the mean loss on the given test data and labels. # Arguments x: array-like, shape `(n_samples, n_features)` Test samples where n_samples in the number of samples and n_features is the number of features. y: array-like, shape `(n_samples,)` True labels for X. **kwargs: dictionary arguments Legal arguments are the arguments of `Sequential.evaluate`. # Returns score: float Mean accuracy of predictions on X wrt. y. i(R'RR R(RRH(RR-R.R/R)((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyRM8s (R%R8R9R RM(((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyRN#s (t __future__RRRRtnumpyR;tutils.np_utilsRtmodelsRtobjectRR:RN(((s:/tmp/pip-build-isqEY4/keras/keras/wrappers/scikit_learn.pyts    ¡u