U 3dM@sdZddlmZddlmZmZmZddlZddl m Z ddl m Z ddl mZmZdd lmZdd lmZd d d ddgZd%ddZddZd&ddZdde jdfddZde jddddZd'de jeddd Zd(ddZd)dd Zddd!d"d Zd#dZ Gd$d d eZ!dS)*zj The :mod:`sklearn.feature_extraction.image` submodule gathers utilities to extract features from images. )product)IntegralNumberRealN)sparse) as_strided) check_arraycheck_random_state)Interval) BaseEstimatorPatchExtractorextract_patches_2d grid_to_graph img_to_graphreconstruct_from_patches_2dcCst||||||f}t|ddddddf|ddddddff}t|ddddf|ddddff}t|dd|ddf}t|||f}|S)a%Returns a list of edges for a 3D image. Parameters ---------- n_x : int The size of the grid in the x direction. n_y : int The size of the grid in the y direction. n_z : integer, default=1 The size of the grid in the z direction, defaults to 1 Nr)nparangereshapeZvstackravelhstack)n_xn_yn_zZverticesZ edges_deepZ edges_rightZ edges_downedgesrD/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/feature_extraction/image.py_make_edges_3d"s B6&rc Cs|j\}}}t||d|||d||||d|||f||d|||d||||d|||f}|S)Nrr)shaperabs)rimg_rrZgradientrrr_compute_gradient_3d6s"  r$cCst|j}||}tt|d|t|d|}|dd|f}|dk r\||}t|rr|}nd}tt |t|d}||}|dkr|S||fSdS)z'Apply a mask to edges (weighted or not)rrN) rrsizer logical_andZin1dlenmaxZ searchsortedZ flatnonzero)maskrweightsZindsZind_maskmaxvalorderrrr_mask_edges_weightsJs  $  r-cCspt|||}|dkr(|dkr"t}n|j}|dk rzt|}t||}|dk rjt|||\}}||} n|} | j } nh|dk r|j t dd}tj |t d}t||}t |} n |||} tj|jd|d}tj| |d} t| } t|d|df} t|d|df} tjt||| ft| | ft| | fff| | f|d}|tjkrh|S||S)z5Auxiliary function for img_to_graph and grid_to_graphNF)dtypecopy)r.rr)rintr.r atleast_3dr$r-Zsqueezerr%ZastypeboolZasarraysumZonesr rrr coo_matrixZndarrayZtoarray)rrrr)r" return_asr.rr*ZdiagZn_voxelsZdiag_idxZi_idxZj_idxgraphrrr _to_graph^sD        r7r)r5r.cCs*t|}|j\}}}t|||||||S)aGraph of the pixel-to-pixel gradient connections. Edges are weighted with the gradient values. Read more in the :ref:`User Guide `. Parameters ---------- img : ndarray of shape (height, width) or (height, width, channel) 2D or 3D image. mask : ndarray of shape (height, width) or (height, width, channel), dtype=bool, default=None An optional mask of the image, to consider only part of the pixels. return_as : np.ndarray or a sparse matrix class, default=sparse.coo_matrix The class to use to build the returned adjacency matrix. dtype : dtype, default=None The data of the returned sparse matrix. By default it is the dtype of img. Returns ------- graph : ndarray or a sparse matrix class The computed adjacency matrix. Notes ----- For scikit-learn versions 0.14.1 and prior, return_as=np.ndarray was handled by returning a dense np.matrix instance. Going forward, np.ndarray returns an np.ndarray, as expected. For compatibility, user code relying on this method should wrap its calls in ``np.asarray`` to avoid type issues. )rr1r r7)r"r)r5r.rrrrrrrs$  cCst||||||dS)a`Graph of the pixel-to-pixel connections. Edges exist if 2 voxels are connected. Parameters ---------- n_x : int Dimension in x axis. n_y : int Dimension in y axis. n_z : int, default=1 Dimension in z axis. mask : ndarray of shape (n_x, n_y, n_z), dtype=bool, default=None An optional mask of the image, to consider only part of the pixels. return_as : np.ndarray or a sparse matrix class, default=sparse.coo_matrix The class to use to build the returned adjacency matrix. dtype : dtype, default=int The data of the returned sparse matrix. By default it is int. Returns ------- graph : np.ndarray or a sparse matrix class The computed adjacency matrix. Notes ----- For scikit-learn versions 0.14.1 and prior, return_as=np.ndarray was handled by returning a dense np.matrix instance. Going forward, np.ndarray returns an np.ndarray, as expected. For compatibility, user code relying on this method should wrap its calls in ``np.asarray`` to avoid type issues. r8)r7)rrrr)r5r.rrrrs&cCs||d}||d}||}|rt|tr:||kr:|St|trP||krP|St|tr~d|krndkr~nn t||Std|n|SdS)a%Compute the number of patches that will be extracted in an image. Read more in the :ref:`User Guide `. Parameters ---------- i_h : int The image height i_w : int The image with p_h : int The height of a patch p_w : int The width of a patch max_patches : int or float, default=None The maximum number of patches to extract. If max_patches is a float between 0 and 1, it is taken to be a proportion of the total number of patches. rrz!Invalid value for max_patches: %rN) isinstancerrr0 ValueError)i_hi_wp_hp_w max_patchesn_hn_wZ all_patchesrrr_compute_n_patchess  " rBc Cs|j}t|trt|g|}t|tr6t|g|}|j}tdd|D}||j}t|jt|t|d}tt|t|}tt|t|} t ||| d} | S)ayExtracts patches of any n-dimensional array in place using strides. Given an n-dimensional array it will return a 2n-dimensional array with the first n dimensions indexing patch position and the last n indexing the patch content. This operation is immediate (O(1)). A reshape performed on the first n dimensions will cause numpy to copy data, leading to a list of extracted patches. Read more in the :ref:`User Guide `. Parameters ---------- arr : ndarray n-dimensional array of which patches are to be extracted patch_shape : int or tuple of length arr.ndim.default=8 Indicates the shape of the patches to be extracted. If an integer is given, the shape will be a hypercube of sidelength given by its value. extraction_step : int or tuple of length arr.ndim, default=1 Indicates step size at which extraction shall be performed. If integer is given, then the step is uniform in all dimensions. Returns ------- patches : strided ndarray 2n-dimensional array indexing patches on first n dimensions and containing patches on the last n dimensions. These dimensions are fake, but this way no data is copied. A simple reshape invokes a copying operation to obtain a list of patches: result.reshape([-1] + list(patch_shape)) css|]}tdd|VqdSN)slice).0strrr 6sz#_extract_patches..r)r strides) ndimr9rtuplerIrarrayr listr) Zarr patch_shapeextraction_stepZarr_ndimZ patch_stridesZslicesZindexing_stridesZpatch_indices_shaper rIpatchesrrr_extract_patches s$   rQr? random_statecCs|jdd\}}|\}}||kr*td||kr:tdt|dd}|||df}|jd}t||||fdd } t|||||} |rt|} | j||d| d } | j||d| d } | | | d f}n| }|d|||}|jddkr|| ||fS|SdS) a_Reshape a 2D image into a collection of patches. The resulting patches are allocated in a dedicated array. Read more in the :ref:`User Guide `. Parameters ---------- image : ndarray of shape (image_height, image_width) or (image_height, image_width, n_channels) The original image data. For color images, the last dimension specifies the channel: a RGB image would have `n_channels=3`. patch_size : tuple of int (patch_height, patch_width) The dimensions of one patch. max_patches : int or float, default=None The maximum number of patches to extract. If `max_patches` is a float between 0 and 1, it is taken to be a proportion of the total number of patches. random_state : int, RandomState instance, default=None Determines the random number generator used for random sampling when `max_patches` is not None. Use an int to make the randomness deterministic. See :term:`Glossary `. Returns ------- patches : array of shape (n_patches, patch_height, patch_width) or (n_patches, patch_height, patch_width, n_channels) The collection of patches extracted from the image, where `n_patches` is either `max_patches` or the total number of patches that can be extracted. Examples -------- >>> from sklearn.datasets import load_sample_image >>> from sklearn.feature_extraction import image >>> # Use the array data from the first image in this dataset: >>> one_image = load_sample_image("china.jpg") >>> print('Image shape: {}'.format(one_image.shape)) Image shape: (427, 640, 3) >>> patches = image.extract_patches_2d(one_image, (2, 2)) >>> print('Patches shape: {}'.format(patches.shape)) Patches shape: (272214, 2, 2, 3) >>> # Here are just two of these patches: >>> print(patches[1]) [[[174 201 231] [174 201 231]] [[173 200 230] [173 200 230]]] >>> print(patches[800]) [[[187 214 243] [188 215 244]] [[187 214 243] [188 215 244]]] Nrz@Height of the patch should be less than the height of the image.z>Width of the patch should be less than the width of the image.T)Zallow_ndrr)rNrO)r%r)r r:r rrQrBr randint)image patch_sizer?rSr;r<r=r>Zn_colorsZextracted_patches n_patchesrngZi_sZj_srPrrrrDs:;  c Cs|dd\}}|jdd\}}t|}||d}||d}t|tt|t|D]0\} \} } || | || | |f| 7<q\t|D]N} t|D]@} || | ftt| d||| t| d||| <qq|S)aReconstruct the image from all of its patches. Patches are assumed to overlap and the image is constructed by filling in the patches from left to right, top to bottom, averaging the overlapping regions. Read more in the :ref:`User Guide `. Parameters ---------- patches : ndarray of shape (n_patches, patch_height, patch_width) or (n_patches, patch_height, patch_width, n_channels) The complete set of patches. If the patches contain colour information, channels are indexed along the last dimension: RGB patches would have `n_channels=3`. image_size : tuple of int (image_height, image_width) or (image_height, image_width, n_channels) The size of the image that will be reconstructed. Returns ------- image : ndarray of shape image_size The reconstructed image. Nrr)r rzerosziprrangefloatmin) rPZ image_sizer;r<r=r>r"r@rApijrrrrs   $&  @c @sveZdZUdZedgdeeddddeeddddgdgd Ze e d <dddd d d Z dd dZ ddZ ddZdS)r aExtracts patches from a collection of images. Read more in the :ref:`User Guide `. .. versionadded:: 0.9 Parameters ---------- patch_size : tuple of int (patch_height, patch_width), default=None The dimensions of one patch. max_patches : int or float, default=None The maximum number of patches per image to extract. If `max_patches` is a float in (0, 1), it is taken to mean a proportion of the total number of patches. random_state : int, RandomState instance, default=None Determines the random number generator used for random sampling when `max_patches is not None`. Use an int to make the randomness deterministic. See :term:`Glossary `. See Also -------- reconstruct_from_patches_2d : Reconstruct image from all of its patches. Examples -------- >>> from sklearn.datasets import load_sample_images >>> from sklearn.feature_extraction import image >>> # Use the array data from the second image in this dataset: >>> X = load_sample_images().images[1] >>> print('Image shape: {}'.format(X.shape)) Image shape: (427, 640, 3) >>> pe = image.PatchExtractor(patch_size=(2, 2)) >>> pe_fit = pe.fit(X) >>> pe_trans = pe.transform(X) >>> print('Patches shape: {}'.format(pe_trans.shape)) Patches shape: (545706, 2, 2) NrrZneither)closedleftrSrVr?rS_parameter_constraintscCs||_||_||_dSrDrd)selfrVr?rSrrr__init__szPatchExtractor.__init__cCs ||S)aDo nothing and return the estimator unchanged. This method is just there to implement the usual API and hence work in pipelines. Parameters ---------- X : array-like of shape (n_samples, n_features) Training data. y : Ignored Not used, present for API consistency by convention. Returns ------- self : object Returns the instance itself. )Z_validate_params)rfXyrrrfit szPatchExtractor.fitcCst|j|_|jdd\}}}t||||df}|jd}|jdkrZ|d|df}n|j}|\}}t|||||j} || f|} |dkr| |f7} t| } t |D]0\} } t | ||j|jd| | | | d| <q| S)aTransform the image samples in `X` into a matrix of patch data. Parameters ---------- X : ndarray of shape (n_samples, image_height, image_width) or (n_samples, image_height, image_width, n_channels) Array of images from which to extract patches. For color images, the last dimension specifies the channel: a RGB image would have `n_channels=3`. Returns ------- patches : array of shape (n_patches, patch_height, patch_width) or (n_patches, patch_height, patch_width, n_channels) The collection of patches extracted from the images, where `n_patches` is either `n_samples * max_patches` or the total number of patches that can be extracted. NrYr rrR) r rSr rrrVrBr?empty enumerater)rfrhZn_imagesr;r<Z n_channelsrVr=r>rWZ patches_shaperPiirUrrr transforms*     zPatchExtractor.transformcCs ddgiS)NZX_typesZ3darrayr)rfrrr _more_tagsMszPatchExtractor._more_tags)N)__name__ __module__ __qualname____doc__rKr rrredict__annotations__rgrjrorprrrrr s *  .)r)N)r)N)rCr)"rt itertoolsrZnumbersrrrZnumpyrZscipyrZnumpy.lib.stride_tricksrutilsr r Zutils._param_validationr baser __all__rr$r-r4r7rr0rrBrQrrr rrrrsD        0* - % ;a+