def test_insert_before_ext(self): self.assertEqual( libmag.insert_before_ext("foo/bar/item.py", "totest", "_"), "foo/bar/item_totest.py") self.assertEqual(libmag.insert_before_ext("foo/bar/item.py", "totest"), "foo/bar/itemtotest.py") self.assertEqual( libmag.insert_before_ext("foo/bar/item", "totest", "_"), "foo/bar/item_totest")
def merge_images(img_paths, reg_name, prefix=None, suffix=None, fn_combine=np.sum): """Merge images from multiple paths. Assumes that the images are relatively similar in size, but will resize them to the size of the first image to combine the images. Args: img_paths: Paths from which registered paths will be found. reg_name: Registration suffix to load for the given paths in ``img_paths``. prefix: Start of output path; defaults to None to use the first path in ``img_paths`` instead. suffix: Portion of path to be combined with each path in ``img_paths`` and output path; defaults to None. fn_combine: Function to apply to combine images with ``axis=0``. Defaults to :func:``np.sum``. If None, each image will be inserted as a separate channel. Returns: The combined image in SimpleITK format. """ if len(img_paths) < 1: return None img_sitk = None img_nps = [] for img_path in img_paths: mod_path = img_path if suffix is not None: # adjust image path with suffix mod_path = libmag.insert_before_ext(mod_path, suffix) print("loading", mod_path) # load and resize images to shape of first loaded image img, _ = _load_reg_img_to_combine(mod_path, reg_name, img_nps) if img_sitk is None: img_sitk = img # combine images and write single combo image if fn_combine is None: # combine raw images into separate channels img_combo = np.stack(img_nps, axis=img_nps[0].ndim) else: # merge by custom function img_combo = fn_combine(img_nps, axis=0) combined_sitk = replace_sitk_with_numpy(img_sitk, img_combo) # fallback to using first image's name as base output_base = img_paths[0] if prefix is None else prefix if suffix is not None: output_base = libmag.insert_before_ext(output_base, suffix) output_reg = libmag.combine_paths(reg_name, config.RegNames.COMBINED.value) write_reg_images({output_reg: combined_sitk}, output_base) return combined_sitk
def make_labels_diff_img(img_path, df_path, meas, fn_avg, prefix=None, show=False, level=None, meas_path_name=None, col_wt=None): """Replace labels in an image with the differences in metrics for each given region between two conditions. Args: img_path: Path to the base image from which the corresponding registered image will be found. df_path: Path to data frame with metrics for the labels. meas: Name of colum in data frame with the chosen measurement. fn_avg: Function to apply to the set of measurements, such as a mean. Can be None if ``df_path`` points to a stats file from which to extract metrics directly in :meth:``vols.map_meas_to_labels``. prefix: Start of path for output image; defaults to None to use ``img_path`` instead. show: True to show the images after generating them; defaults to False. level: Ontological level at which to look up and show labels. Assume that labels level image corresponding to this value has already been generated by :meth:``make_labels_level_img``. Defaults to None to use only drawn labels. meas_path_name: Name to use in place of `meas` in output path; defaults to None. col_wt (str): Name of column to use for weighting; defaults to None. """ # load labels image and data frame before generating map for the # given metric of the chosen measurement print("Generating labels difference image for", meas, "from", df_path) reg_name = (config.RegNames.IMG_LABELS.value if level is None else config.RegNames.IMG_LABELS_LEVEL.value.format(level)) labels_sitk = sitk_io.load_registered_img(img_path, reg_name, get_sitk=True) labels_np = sitk.GetArrayFromImage(labels_sitk) df = pd.read_csv(df_path) labels_diff = vols.map_meas_to_labels( labels_np, df, meas, fn_avg, reverse=True, col_wt=col_wt) if labels_diff is None: return labels_diff_sitk = sitk_io.replace_sitk_with_numpy(labels_sitk, labels_diff) # save and show labels difference image using measurement name in # output path or overriding with custom name meas_path = meas if meas_path_name is None else meas_path_name reg_diff = libmag.insert_before_ext( config.RegNames.IMG_LABELS_DIFF.value, meas_path, "_") if fn_avg is not None: # add function name to output path if given reg_diff = libmag.insert_before_ext( reg_diff, fn_avg.__name__, "_") imgs_write = {reg_diff: labels_diff_sitk} out_path = prefix if prefix else img_path sitk_io.write_reg_images(imgs_write, out_path) if show: for img in imgs_write.values(): if img: sitk.Show(img)
def meas_plot_zscores(path, metric_cols, extra_cols, composites, size=None, show=True): """Measure and plot z-scores for given columns in a data frame. Args: path (str): Path to data frame. metric_cols (List[str]): Sequence of column names for which to compute z-scores. extra_cols (List[str]): Additional columns to included in the output data frame. composites (List[Enum]): Sequence of enums specifying the combination, typically from :class:`vols.MetricCombos`. size (List[int]): Sequence of ``width, height`` to size the figure; defaults to None. show (bool): True to display the image; defaults to True. """ # generate z-scores df = pd.read_csv(path) df = df_io.zscore_df(df, "Region", metric_cols, extra_cols, True) # generate composite score column df_comb = df_io.combine_cols(df, composites) df_io.data_frames_to_csv( df_comb, libmag.insert_before_ext(config.filename, "_zhomogeneity")) # shift metrics from each condition to separate columns conds = np.unique(df["Condition"]) df = df_io.cond_to_cols_df(df, ["Sample", "Region"], "Condition", "original", metric_cols) path = libmag.insert_before_ext(config.filename, "_zscore") df_io.data_frames_to_csv(df, path) # display as probability plot lims = (-3, 3) plot_2d.plot_probability(path, conds, metric_cols, "Volume", xlim=lims, ylim=lims, title="Region Match Z-Scores", fig_size=size, show=show, suffix=None, df=df)
def make_subimage_name( base: str, offset: Optional[Tuple[int, int, int]] = None, shape: Optional[Tuple[int, int, int]] = None, suffix: Optional[str] = None) -> str: """Make name of subimage for a given offset and shape. The order of ``offset`` and ``shape`` are assumed to be in ``z, y, x`` but will be reversed for the output name since the user-oriented ordering is ``x, y, z``. Args: base: Start of name, which can include full parent path. offset: Offset as a tuple; defaults to None to ignore sub-image. shape: Shape as a tuple; defaults to None to ignore sub-image. suffix: Suffix to append, replacing any existing extension in ``base``; defaults to None. Returns: Name (or path) to subimage. """ name = base if offset is not None and shape is not None: # sub-image offset/shape stored as z,y,x, but file named as x,y,z roi_site = "{}x{}".format(offset[::-1], shape[::-1]).replace(" ", "") name = libmag.insert_before_ext(base, roi_site, "_") if suffix: name = libmag.combine_paths(name, suffix) print("subimage name: {}".format(name)) return name
def get_transposed_image_path(img_path: str, scale: float = None, target_size: Sequence[int] = None) -> str: """Get path modified for any transposition. Args: img_path: Unmodified image path. scale: Scaling factor, which takes precedence over ``target_size``; defaults to None. target_size: Target size in ``x, y, z``, typically given by an atlas profile; defaults to None. Returns: Modified path for the given transposition, or ``img_path`` unmodified if all transposition factors are None. """ img_path_modified = img_path if scale is not None or target_size is not None: # use scaled image for pixel comparison, retrieving # saved scaling as of v.0.6.0 if scale is not None: # scale takes priority as command-line argument modifier = make_modifier_scale(scale) print("loading scaled file with {} modifier".format(modifier)) else: # otherwise assume set target size modifier = make_modifier_resized(target_size) print("loading resized file with {} modifier".format(modifier)) img_path_modified = libmag.insert_before_ext(img_path, "_" + modifier) return img_path_modified
def get_transposed_image_path(img_path, scale=None, target_size=None): """Get path, modified for any transposition by :func:``transpose_npy`` naming conventions. Args: img_path: Unmodified image path. scale: Scaling factor; defaults to None, which ignores scaling. target_size: Target size, typically given by a register profile; defaults to None, which ignores target size. Returns: Modified path for the given transposition, or ``img_path`` unmodified if all transposition factors are None. """ img_path_modified = img_path if scale is not None or target_size is not None: # use scaled image for pixel comparison, retrieving # saved scaling as of v.0.6.0 modifier = None if scale is not None: # scale takes priority as command-line argument modifier = make_modifier_scale(scale) print("loading scaled file with {} modifier".format(modifier)) else: # otherwise assume set target size modifier = make_modifier_resized(target_size) print("loading resized file with {} modifier".format(modifier)) img_path_modified = libmag.insert_before_ext(img_path, "_" + modifier) return img_path_modified
def cluster_blobs(img_path, suffix=None): """Cluster blobs and save to Numpy archive. Args: img_path (str): Base path from which registered labels and blobs files will be found and output blobs file save location will be constructed. suffix (str): Suffix for ``path``; defaults to None. Returns: """ mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(img_path, suffix) labels_img_np = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value) blobs = detector.Blobs().load_blobs(np_io.img_to_blobs_path(img_path)) scaling, res = np_io.find_scaling(img_path, labels_img_np.shape) if blobs is None: libmag.warn("unable to load nuclei coordinates") return # append label IDs to blobs and scale to make isotropic blobs_clus = ClusterByLabel.cluster_by_label(blobs.blobs[:, :3], labels_img_np, scaling, res) print(blobs_clus) out_path = libmag.combine_paths(mod_path, config.SUFFIX_BLOB_CLUSTERS) np.save(out_path, blobs_clus)
def meas_plot_coefvar(path, id_cols, cond_col, cond_base, metric_cols, composites, size_col=None, size=None, show=True): """Measure and plot coefficient of variation (CV) as a scatter plot. CV is computed two ways: - Based on columns and equation specified in ``composites``, applied across all samples regardless of group - For each metric in ``metric_cols``, separated by groups Args: path (str): Path to data frame. id_cols (List[str]): Sequence of columns to serve as index/indices. cond_col (str): Name of the condition column. cond_base (str): Name of the condition to which all other conditions will be normalized. metric_cols (List[str]): Sequence of column names for which to compute z-scores. composites (List[Enum]): Sequence of enums specifying the combination, typically from :class:`vols.MetricCombos`. size_col (str): Name of weighting column for coefficient of variation measurement; defaults to None. size (List[int]): Sequence of ``width, height`` to size the figure; defaults to None. show (bool): True to display the image; defaults to True. """ # measure coefficient of variation per sample-region regardless of group df = pd.read_csv(path) df = df_io.combine_cols(df, composites) df_io.data_frames_to_csv( df, libmag.insert_before_ext(config.filename, "_coefvar")) # measure CV within each condition and shift metrics from each # condition to separate columns df = df_io.coefvar_df(df, [*id_cols, cond_col], metric_cols, size_col) conds = np.unique(df[cond_col]) df = df_io.cond_to_cols_df(df, id_cols, cond_col, cond_base, metric_cols) path = libmag.insert_before_ext(config.filename, "_coefvartransp") df_io.data_frames_to_csv(df, path) # display CV measured by condition as probability plot lims = (0, 0.7) plot_2d.plot_probability( path, conds, metric_cols, "Volume", xlim=lims, ylim=lims, title="Coefficient of Variation", fig_size=size, show=show, suffix=None, df=df)
def animate_imgs(base_path, plotted_imgs, delay, ext=None, suffix=None): """Export to an animated image. Defaults to an animated GIF unless ``ext`` specifies otherwise. Requires ``FFMpeg`` for MP4 file format exports and ``ImageMagick`` for all other types of exports. Args: base_path (str): String from which an output path will be constructed. plotted_imgs (List[:obj:`matplotlib.image.AxesImage]): Sequence of images to include in the animation. delay (int): Delay between image display in ms. If None, the delay will defaul to 100ms. ext (str): Extension to use when saving, without the period. Defaults to None, in which case "gif" will be used. suffix (str): String to append to output path before extension; defaults to None to ignore. """ # set up animation output path and time interval if ext is None: ext = "gif" out_path = libmag.combine_paths(base_path, "animated", ext=ext) if suffix: out_path = libmag.insert_before_ext(out_path, suffix, "_") libmag.backup_file(out_path) if delay is None: delay = 100 if plotted_imgs and len(plotted_imgs[0]) > 0: fig = plotted_imgs[0][0].figure else: libmag.warn("No images available to animate") return # WORKAROUND: FFMpeg may give a "height not divisible by 2" error, fixed # by padding with a pixel # TODO: check if needed for width # TODO: account for difference in FFMpeg height and fig height for fn, size in { # fig.set_figwidth: fig.get_figwidth(), fig.set_figheight: fig.get_figheight() }.items(): if size * fig.dpi % 2 != 0: fn(size + 1. / fig.dpi) print("Padded size with", fn, fig.get_figwidth(), "to new size of", fig.get_figheight()) # generate and save animation anim = animation.ArtistAnimation(fig, plotted_imgs, interval=delay, repeat_delay=0, blit=False) try: writer = "ffmpeg" if ext == "mp4" else "imagemagick" anim.save(out_path, writer=writer) print("saved animation file to {}".format(out_path)) except ValueError as e: print(e) libmag.warn("No animation writer available for Matplotlib")
def animate_imgs(base_path, plotted_imgs, delay, ext=None, suffix=None): """Export to an animated image. Defaults to an animated GIF unless ``ext`` specifies otherwise. Requires ``FFMpeg`` for MP4 file format exports and ``ImageMagick`` for all other types of exports. Args: base_path (str): String from which an output path will be constructed. plotted_imgs (List[:obj:`matplotlib.image.AxesImage]): Sequence of images to include in the animation. delay (int): Delay between image display in ms. If None, the delay will defaul to 100ms. ext (str): Extension to use when saving, without the period. Defaults to None, in which case "gif" will be used. suffix (str): String to append to output path before extension; defaults to None to ignore. """ if ext is None: ext = "gif" out_path = libmag.combine_paths(base_path, "animated", ext=ext) if suffix: out_path = libmag.insert_before_ext(out_path, suffix, "_") libmag.backup_file(out_path) if delay is None: delay = 100 if plotted_imgs and len(plotted_imgs[0]) > 0: fig = plotted_imgs[0][0].figure else: libmag.warn("No images available to animate") return anim = animation.ArtistAnimation(fig, plotted_imgs, interval=delay, repeat_delay=0, blit=False) try: writer = "ffmpeg" if ext == "mp4" else "imagemagick" anim.save(out_path, writer=writer) print("saved animation file to {}".format(out_path)) except ValueError as e: print(e) libmag.warn("No animation writer available for Matplotlib")
def make_sub_segmented_labels(img_path, suffix=None): """Divide each label based on anatomical borders to create a sub-segmented image. The segmented labels image will be loaded, or if not available, the non-segmented labels will be loaded instead. Args: img_path: Path to main image from which registered images will be loaded. suffix: Modifier to append to end of ``img_path`` basename for registered image files that were output to a modified name; defaults to None. Returns: Sub-segmented image as a Numpy array of the same shape as the image at ``img_path``. """ # adjust image path with suffix mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(mod_path, suffix) # load labels labels_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) # atlas edge image is associated with original, not modified image atlas_edge = sitk_io.load_registered_img( img_path, config.RegNames.IMG_ATLAS_EDGE.value) # sub-divide the labels and save to file labels_img_np = sitk.GetArrayFromImage(labels_sitk) labels_subseg = segmenter.sub_segment_labels(labels_img_np, atlas_edge) labels_subseg_sitk = sitk_io.replace_sitk_with_numpy( labels_sitk, labels_subseg) sitk_io.write_reg_images( {config.RegNames.IMG_LABELS_SUBSEG.value: labels_subseg_sitk}, mod_path) return labels_subseg
def make_subimage_name(base, offset, shape, suffix=None): """Make name of subimage for a given offset and shape. The order of ``offset`` and ``shape`` are assumed to be in z,y,x but will be reversed for the output name since the user-oriented ordering is x,y,z. Args: base (str): Start of name, which can include full parent path. offset (Tuple[int]): Offset, generally given as a tuple. shape (Tuple[int]): Shape, generally given as a tuple. suffix (str): Suffix to append, replacing any existing extension in ``base``; defaults to None. Returns: str: Name (or path) to subimage. """ # sub-image offset/shape stored as z,y,x, but file named as x,y,z roi_site = "{}x{}".format(offset[::-1], shape[::-1]).replace(" ", "") name = libmag.insert_before_ext(base, roi_site, "_") if suffix: name = libmag.combine_paths(name, suffix) print("subimage name: {}".format(name)) return name
def process_file( path: str, proc_type: Enum, proc_val: Optional[Any] = None, series: Optional[int] = None, subimg_offset: Optional[List[int]] = None, subimg_size: Optional[List[int]] = None, roi_offset: Optional[List[int]] = None, roi_size: Optional[List[int]] = None ) -> Tuple[Optional[Any], Optional[str]]: """Processes a single image file non-interactively. Assumes that the image has already been set up. Args: path: Path to image from which MagellanMapper-style paths will be generated. proc_type: Processing type, which should be a one of :class:`config.ProcessTypes`. proc_val: Processing value associated with ``proc_type``; defaults to None. series: Image series number; defaults to None. subimg_offset: Sub-image offset as (z,y,x) to load; defaults to None. subimg_size: Sub-image size as (z,y,x) to load; defaults to None. roi_offset: Region of interest offset as (x, y, z) to process; defaults to None. roi_size: Region of interest size of region to process, given as ``(x, y, z)``; defaults to None. Returns: Tuple of stats from processing, or None if no stats, and text feedback from the processing, or None if no feedback. """ # PROCESS BY TYPE stats = None fdbk = None filename_base = importer.filename_to_base(path, series) print("{}\n".format("-" * 80)) if proc_type is config.ProcessTypes.LOAD: # loading completed return None, None elif proc_type is config.ProcessTypes.LOAD: # already imported so does nothing print("imported {}, will exit".format(path)) elif proc_type is config.ProcessTypes.EXPORT_ROIS: # export ROIs; assumes that info_proc was already loaded to # give smaller region from which smaller ROIs from the truth DB # will be extracted from magmap.io import export_rois db = config.db if config.truth_db is None else config.truth_db export_path = naming.make_subimage_name(filename_base, subimg_offset, subimg_size) export_rois.export_rois(db, config.image5d, config.channel, export_path, config.plot_labels[config.PlotLabels.PADDING], config.unit_factor, config.truth_db_mode, os.path.basename(export_path)) elif proc_type is config.ProcessTypes.TRANSFORM: # transpose, rescale, and/or resize whole large image transformer.transpose_img( path, series, plane=config.plane, rescale=config.transform[config.Transforms.RESCALE], target_size=config.roi_size) elif proc_type in (config.ProcessTypes.EXTRACT, config.ProcessTypes.ANIMATED): # generate animated GIF or extract single plane export_stack.stack_to_img(config.filenames, roi_offset, roi_size, series, subimg_offset, subimg_size, proc_type is config.ProcessTypes.ANIMATED, config.suffix) elif proc_type is config.ProcessTypes.EXPORT_BLOBS: # export blobs to CSV file from magmap.io import export_rois export_rois.blobs_to_csv(config.blobs.blobs, filename_base) elif proc_type in (config.ProcessTypes.DETECT, config.ProcessTypes.DETECT_COLOC): # detect blobs in the full image, +/- co-localization coloc = proc_type is config.ProcessTypes.DETECT_COLOC stats, fdbk, _ = stack_detect.detect_blobs_stack( filename_base, subimg_offset, subimg_size, coloc) elif proc_type is config.ProcessTypes.COLOC_MATCH: if config.blobs is not None and config.blobs.blobs is not None: # colocalize blobs in separate channels by matching blobs shape = subimg_size if shape is None: # get shape from loaded image, falling back to its metadata if config.image5d is not None: shape = config.image5d.shape[1:] else: shape = config.img5d.meta[config.MetaKeys.SHAPE][1:] matches = colocalizer.StackColocalizer.colocalize_stack( shape, config.blobs.blobs) # insert matches into database colocalizer.insert_matches(config.db, matches) else: print("No blobs loaded to colocalize, skipping") elif proc_type in (config.ProcessTypes.EXPORT_PLANES, config.ProcessTypes.EXPORT_PLANES_CHANNELS): # export each plane as a separate image file export_stack.export_planes( config.image5d, config.savefig, config.channel, proc_type is config.ProcessTypes.EXPORT_PLANES_CHANNELS) elif proc_type is config.ProcessTypes.EXPORT_RAW: # export the main image as a raw data file out_path = libmag.combine_paths(config.filename, ".raw", sep="") libmag.backup_file(out_path) np_io.write_raw_file(config.image5d, out_path) elif proc_type is config.ProcessTypes.EXPORT_TIF: # export the main image as a TIF files for each channel np_io.write_tif(config.image5d, config.filename) elif proc_type is config.ProcessTypes.PREPROCESS: # pre-process a whole image and save to file # TODO: consider chunking option for larger images out_path = config.prefix if not out_path: out_path = libmag.insert_before_ext(config.filename, "_preproc") transformer.preprocess_img(config.image5d, proc_val, config.channel, out_path) return stats, fdbk
def meas_improvement(path, col_effect, col_p, thresh_impr=0, thresh_p=0.05, col_wt=None, suffix=None, df=None): """Measure overall improvement and worsening for a column in a data frame. Args: path (str): Path of file to load into data frame. col_effect (str): Name of column with metric to measure. col_p (str): Name of column with p-values. thresh_impr (float): Threshold of effects below which are considered improved. thresh_p (float): Threshold of p-values below which are considered statistically significant. col_wt (str): Name of column for weighting. suffix (str): Output path suffix; defaults to None. df (:obj:`pd.DataFrame`): Data fram to use instead of loading from ``path``; defaults to None. Returns: :obj:`pd.DataFrame`: Data frame with improvement measurements. The data frame will be saved to a filename based on ``path``. """ def add_wt(mask_cond, mask_cond_ss, name): # add weighted metrics for the given condition, such as improved # vs. worsened metrics[col_wt] = [np.sum(df[col_wt])] wt_cond = df.loc[mask_cond, col_wt] wt_cond_ss = df.loc[mask_cond_ss, col_wt] # sum of weighting column fitting the condition (all and statistically # significant) metrics["{}_{}".format(col_wt, name)] = [np.sum(wt_cond)] metrics["{}_{}_ss".format(col_wt, name)] = [np.sum(wt_cond_ss)] # sum of filtered effect multiplied by weighting metrics["{}_{}_by_{}".format(col_effect, name, col_wt)] = [ np.sum(wt_cond.multiply(df.loc[mask_cond, col_effect])) ] metrics["{}_{}_by_{}_ss".format(col_effect, name, col_wt)] = [ np.sum(wt_cond_ss.multiply(df.loc[mask_cond_ss, col_effect])) ] if df is None: df = pd.read_csv(path) # masks of improved and worsened, all and statistically significant # for each, where improvement is above the given threshold effects = df[col_effect] mask_impr = effects > thresh_impr mask_ss = df[col_p] < thresh_p mask_impr_ss = mask_impr & mask_ss mask_wors = effects < thresh_impr mask_wors_ss = mask_wors & mask_ss metrics = { "n": [len(effects)], "n_impr": [np.sum(mask_impr)], "n_impr_ss": [np.sum(mask_impr_ss)], "n_wors": [np.sum(mask_wors)], "n_wors_ss": [np.sum(mask_wors_ss)], col_effect: [np.sum(effects)], "{}_impr".format(col_effect): [np.sum(effects[mask_impr])], "{}_impr_ss".format(col_effect): [np.sum(effects[mask_impr_ss])], "{}_wors".format(col_effect): [np.sum(effects[mask_wors])], "{}_wors_ss".format(col_effect): [np.sum(effects[mask_wors_ss])], } if col_wt: # add columns based on weighting column add_wt(mask_impr, mask_impr_ss, "impr") add_wt(mask_wors, mask_wors_ss, "wors") out_path = libmag.insert_before_ext(path, "_impr") if suffix: out_path = libmag.insert_before_ext(out_path, suffix) df_impr = df_io.dict_to_data_frame(metrics, out_path) # display transposed version for more compact view given large number # of columns, but save un-transposed to preserve data types df_io.print_data_frame(df_impr.T, index=True, header=False) return df_impr
def plot_clusters_by_label(path, z, suffix=None, show=True, scaling=None): """Plot separate sets of clusters for each label. Args: path (str): Base path to blobs file with clusters. z (int): z-plane to plot. suffix (str): Suffix for ``path``; defaults to None. show (bool): True to show; defaults to True. scaling (List): Sequence of scaling from blobs' coordinate space to that of :attr:`config.labels_img`. """ mod_path = path if suffix is not None: mod_path = libmag.insert_before_ext(path, suffix) blobs = np.load(libmag.combine_paths(mod_path, config.SUFFIX_BLOB_CLUSTERS)) label_ids = np.unique(blobs[:, 3]) fig, gs = plot_support.setup_fig( 1, 1, config.plot_labels[config.PlotLabels.SIZE]) ax = fig.add_subplot(gs[0, 0]) plot_support.hide_axes(ax) # plot underlying atlas np_io.setup_images(mod_path) if config.reg_suffixes[config.RegSuffixes.ATLAS]: # use atlas if explicitly set img = config.image5d else: # default to black background img = np.zeros_like(config.labels_img)[None] stacker = export_stack.setup_stack(img, mod_path, slice_vals=(z, z + 1), labels_imgs=(config.labels_img, config.borders_img)) stacker.build_stack(ax, config.plot_labels[config.PlotLabels.SCALE_BAR]) # export_stack.reg_planes_to_img( # (np.zeros(config.labels_img.shape[1:], dtype=int), # config.labels_img[z]), ax=ax) if scaling is not None: print("scaling blobs cluster coordinates by", scaling) blobs = blobs.astype(float) blobs[:, :3] = np.multiply(blobs[:, :3], scaling) blobs[:, 0] = np.floor(blobs[:, 0]) # plot nuclei by label, colored based on cluster size within each label colors = colormaps.discrete_colormap(len(np.unique(blobs[:, 4])), prioritize_default="cn") / 255. col_noise = (1, 1, 1, 1) for label_id in label_ids: if label_id == 0: # skip blobs in background continue # sort blobs within label by cluster size (descending order), # including clusters within all z-planes to keep same order across zs blobs_lbl = blobs[blobs[:, 3] == label_id] clus_lbls, clus_lbls_counts = np.unique(blobs_lbl[:, 4], return_counts=True) clus_lbls = clus_lbls[np.argsort(clus_lbls_counts)][::-1] blobs_lbl = blobs_lbl[blobs_lbl[:, 0] == z] for i, (clus_lbl, color) in enumerate(zip(clus_lbls, colors)): blobs_clus = blobs_lbl[blobs_lbl[:, 4] == clus_lbl] if len(blobs_clus) < 1: continue # default to small, translucent dominant cluster points size = 0.1 alpha = 0.5 if clus_lbl == -1: # color all noise points the same and emphasize points color = col_noise size = 0.5 alpha = 1 print(label_id, clus_lbl, color, len(blobs_clus)) ax.scatter(blobs_clus[:, 2], blobs_clus[:, 1], color=color, s=size, alpha=alpha) plot_support.save_fig(mod_path, config.savefig, "_clusplot") if show: plot_support.show()
def list_s3_bucket(name, keys=None, prefix=None, suffix=None, versions=False): """List all objects or object versions in an AWS S3 bucket. Args: name (str): Name of bucket. keys (List[str]): Sequence of keys within the bucket to include sizes of only these files; defaults to None. prefix (str): Filter only keys starting with this string; defaults to None. suffix (str): String to append to output CSV file; defaults to None. versions (bool): True to get all object versions, including deleted objects; False to get only the current versions; defaults to False. Returns: float, :obj:`pd.DataFrame`, :obj:`pd.DataFrame`: Size of bucket in bytes; a dataframe of keys and associated sizes; and a dataframe of missing keys from ``keys``, or None if ``keys`` is not given. """ s3 = boto3.resource("s3") bucket = s3.Bucket(name) tot_size = 0 obj_sizes = {} # get latest version of objects or all object version, filtering # for paths starting with prefix if set objs = bucket.object_versions if versions else bucket.objects objs = objs.filter(Prefix=prefix) if prefix else objs.all() for obj in objs: if not keys or obj.key in keys: # only check keys in list if given obj_sizes.setdefault("Bucket", []).append(bucket.name) obj_sizes.setdefault("Key", []).append(obj.key) size = obj.size obj_sizes.setdefault("Size", []).append(size) if size: # skip delete markers, which have a size of None tot_size += obj.size if versions: # add columns for version info obj_sizes.setdefault("Version_id", []).append(obj.version_id) obj_sizes.setdefault("Last_modified", []).append(obj.last_modified) out_path = "bucket_{}".format(bucket.name) if suffix: out_path = libmag.insert_before_ext(out_path, suffix, "_") df_missing = None if keys: # if list of keys given, show all keys that were not found keys_missing = [] obj_keys = obj_sizes.keys() for key in keys: if key not in obj_keys: keys_missing.append(key) # print("Missing keys:\n", "\n".join(keys_missing)) df_missing = df_io.dict_to_data_frame({"Keys_missing": keys_missing}, libmag.insert_before_ext( out_path, "_missing")) df = df_io.dict_to_data_frame(obj_sizes, out_path) print("{} bucket total tot_size (GiB): {}".format( bucket.name, libmag.convert_bin_magnitude(tot_size, 3))) return tot_size, df, df_missing
def process_file(path, proc_mode, series=None, subimg_offset=None, subimg_size=None, roi_offset=None, roi_size=None): """Processes a single image file non-interactively. Assumes that the image has already been set up. Args: path (str): Path to image from which MagellanMapper-style paths will be generated. proc_mode (str): Processing mode, which should be a key in :class:`config.ProcessTypes`, case-insensitive. series (int): Image series number; defaults to None. subimg_offset (List[int]): Sub-image offset as (z,y,x) to load; defaults to None. subimg_size (List[int]): Sub-image size as (z,y,x) to load; defaults to None. roi_offset (List[int]): Region of interest offset as (x, y, z) to process; defaults to None. roi_size (List[int]): Region of interest size of region to process, given as (x, y, z); defaults to None. Returns: Tuple of stats from processing, or None if no stats, and text feedback from the processing, or None if no feedback. """ # PROCESS BY TYPE stats = None fdbk = None filename_base = importer.filename_to_base(path, series) proc_type = libmag.get_enum(proc_mode, config.ProcessTypes) if proc_type is config.ProcessTypes.LOAD: # loading completed return None, None elif proc_type is config.ProcessTypes.LOAD: # already imported so does nothing print("imported {}, will exit".format(path)) elif proc_type is config.ProcessTypes.EXPORT_ROIS: # export ROIs; assumes that info_proc was already loaded to # give smaller region from which smaller ROIs from the truth DB # will be extracted from magmap.io import export_rois db = config.db if config.truth_db is None else config.truth_db export_rois.export_rois(db, config.image5d, config.channel, filename_base, config.plot_labels[config.PlotLabels.PADDING], config.unit_factor, config.truth_db_mode, os.path.basename(config.filename)) elif proc_type is config.ProcessTypes.TRANSFORM: # transpose, rescale, and/or resize whole large image transformer.transpose_img( path, series, plane=config.plane, rescale=config.transform[config.Transforms.RESCALE], target_size=config.roi_size) elif proc_type in (config.ProcessTypes.EXTRACT, config.ProcessTypes.ANIMATED): # generate animated GIF or extract single plane from magmap.io import export_stack export_stack.stack_to_img(config.filenames, roi_offset, roi_size, series, subimg_offset, subimg_size, proc_type is config.ProcessTypes.ANIMATED, config.suffix) elif proc_type is config.ProcessTypes.EXPORT_BLOBS: # export blobs to CSV file from magmap.io import export_rois export_rois.blobs_to_csv(config.blobs, filename_base) elif proc_type is config.ProcessTypes.DETECT: # detect blobs in the full image stats, fdbk, segments_all = stack_detect.detect_blobs_large_image( filename_base, config.image5d, subimg_offset, subimg_size, config.truth_db_mode is config.TruthDBModes.VERIFY, not config.grid_search_profile, config.image5d_is_roi) elif proc_type is config.ProcessTypes.EXPORT_PLANES: # export each plane as a separate image file from magmap.io import export_stack export_stack.export_planes(config.image5d, config.prefix, config.savefig, config.channel) elif proc_type is config.ProcessTypes.EXPORT_RAW: # export the main image as a raw data file out_path = libmag.combine_paths(config.filename, ".raw", sep="") libmag.backup_file(out_path) np_io.write_raw_file(config.image5d, out_path) elif proc_type is config.ProcessTypes.PREPROCESS: # pre-process a whole image and save to file # TODO: consider chunking option for larger images profile = config.get_roi_profile(0) out_path = config.prefix if not out_path: out_path = libmag.insert_before_ext(config.filename, "_preproc") transformer.preprocess_img(config.image5d, profile["preprocess"], config.channel, out_path) return stats, fdbk
def merge_atlas_segmentations(img_paths, show=True, atlas=True, suffix=None): """Merge atlas segmentations for a list of files as a multiprocessing wrapper for :func:``merge_atlas_segmentations``, after which edge image post-processing is performed separately since it contains tasks also performed in multiprocessing. Args: img_paths (List[str]): Sequence of image paths to load. show (bool): True if the output images should be displayed; defaults to True. atlas (bool): True if the image is an atlas; defaults to True. suffix (str): Modifier to append to end of ``img_path`` basename for registered image files that were output to a modified name; defaults to None. """ start_time = time() # erode all labels images into markers for watershed; not multiprocessed # since erosion is itself multiprocessed erode = config.atlas_profile["erode_labels"] erosion = config.atlas_profile[profiles.RegKeys.EDGE_AWARE_REANNOTATION] erosion_frac = config.atlas_profile["erosion_frac"] mirrored = atlas and _is_profile_mirrored() mirror_mult = _get_mirror_mult() dfs_eros = [] for img_path in img_paths: mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(mod_path, suffix) labels_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) print("Eroding labels to generate markers for atlas segmentation") df = None if erode["markers"]: # use default minimal post-erosion size (not setting erosion frac) markers, df = erode_labels( sitk.GetArrayFromImage(labels_sitk), erosion, mirrored=mirrored, mirror_mult=mirror_mult) labels_sitk_markers = sitk_io.replace_sitk_with_numpy( labels_sitk, markers) sitk_io.write_reg_images( {config.RegNames.IMG_LABELS_MARKERS.value: labels_sitk_markers}, mod_path) df_io.data_frames_to_csv( df, "{}_markers.csv".format(os.path.splitext(mod_path)[0])) dfs_eros.append(df) pool = chunking.get_mp_pool() pool_results = [] for img_path, df in zip(img_paths, dfs_eros): print("setting up atlas segmentation merge for", img_path) # convert labels image into markers exclude = df.loc[ np.isnan(df[config.SmoothingMetrics.FILTER_SIZE.value]), config.AtlasMetrics.REGION.value] print("excluding these labels from re-segmentation:\n", exclude) pool_results.append(pool.apply_async( edge_aware_segmentation, args=(img_path, show, atlas, suffix, exclude, mirror_mult))) for result in pool_results: # edge distance calculation and labels interior image generation # are multiprocessed, so run them as post-processing tasks to # avoid nested multiprocessing path = result.get() mod_path = path if suffix is not None: mod_path = libmag.insert_before_ext(path, suffix) # make edge distance images and stats labels_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_np = sitk.GetArrayFromImage(labels_sitk) dist_to_orig, labels_edge = edge_distances( labels_np, path=path, spacing=labels_sitk.GetSpacing()[::-1]) dist_sitk = sitk_io.replace_sitk_with_numpy(labels_sitk, dist_to_orig) labels_sitk_edge = sitk_io.replace_sitk_with_numpy( labels_sitk, labels_edge) labels_sitk_interior = None if erode["interior"]: # make interior images from labels using given targeted # post-erosion frac interior, _ = erode_labels( labels_np, erosion, erosion_frac=erosion_frac, mirrored=mirrored, mirror_mult=mirror_mult) labels_sitk_interior = sitk_io.replace_sitk_with_numpy( labels_sitk, interior) # write images to same directory as atlas imgs_write = { config.RegNames.IMG_LABELS_DIST.value: dist_sitk, config.RegNames.IMG_LABELS_EDGE.value: labels_sitk_edge, config.RegNames.IMG_LABELS_INTERIOR.value: labels_sitk_interior, } sitk_io.write_reg_images(imgs_write, mod_path) if show: for img in imgs_write.values(): if img: sitk.Show(img) print("finished {}".format(path)) pool.close() pool.join() print("time elapsed for merging atlas segmentations:", time() - start_time)
def make_edge_images(path_img, show=True, atlas=True, suffix=None, path_atlas_dir=None): """Make edge-detected atlas and associated labels images. The atlas is assumed to be a sample (eg microscopy) image on which an edge-detection filter will be applied. The labels image is assumed to be an annotated image whose edges will be found by obtaining the borders of all separate labels. Args: path_img: Path to the image atlas. The labels image will be found as a corresponding, registered image, unless ``path_atlas_dir`` is given. show (bool): True if the output images should be displayed; defaults to True. atlas: True if the primary image is an atlas, which is assumed to be symmetrical. False if the image is an experimental/sample image, in which case erosion will be performed on the full images, and stats will not be performed. suffix: Modifier to append to end of ``path_img`` basename for registered image files that were output to a modified name; defaults to None. path_atlas_dir: Path to atlas directory to use labels from that directory rather than from labels image registered to ``path_img``, such as when the sample image is registered to an atlas rather than the other way around. Typically coupled with ``suffix`` to compare same sample against different labels. Defaults to None. """ # load intensity image from which to detect edges atlas_suffix = config.reg_suffixes[config.RegSuffixes.ATLAS] if not atlas_suffix: if atlas: # atlases default to using the atlas volume image print("generating edge images for atlas") atlas_suffix = config.RegNames.IMG_ATLAS.value else: # otherwise, use the experimental image print("generating edge images for experiment/sample image") atlas_suffix = config.RegNames.IMG_EXP.value # adjust image path with suffix mod_path = path_img if suffix is not None: mod_path = libmag.insert_before_ext(mod_path, suffix) labels_from_atlas_dir = path_atlas_dir and os.path.isdir(path_atlas_dir) if labels_from_atlas_dir: # load labels from atlas directory # TODO: consider applying suffix to labels dir path_atlas = path_img path_labels = os.path.join( path_atlas_dir, config.RegNames.IMG_LABELS.value) print("loading labels from", path_labels) labels_sitk = sitk.ReadImage(path_labels) else: # load labels registered to sample image path_atlas = mod_path labels_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_img_np = sitk.GetArrayFromImage(labels_sitk) # load atlas image, set resolution from it atlas_sitk = sitk_io.load_registered_img( path_atlas, atlas_suffix, get_sitk=True) config.resolutions = np.array([atlas_sitk.GetSpacing()[::-1]]) atlas_np = sitk.GetArrayFromImage(atlas_sitk) # output images atlas_sitk_log = None atlas_sitk_edge = None labels_sitk_interior = None log_sigma = config.atlas_profile["log_sigma"] if log_sigma is not None and suffix is None: # generate LoG and edge-detected images for original image print("generating LoG edge-detected images with sigma", log_sigma) thresh = (config.atlas_profile["atlas_threshold"] if config.atlas_profile["log_atlas_thresh"] else None) atlas_log = cv_nd.laplacian_of_gaussian_img( atlas_np, sigma=log_sigma, labels_img=labels_img_np, thresh=thresh) atlas_sitk_log = sitk_io.replace_sitk_with_numpy(atlas_sitk, atlas_log) atlas_edge = cv_nd.zero_crossing(atlas_log, 1).astype(np.uint8) atlas_sitk_edge = sitk_io.replace_sitk_with_numpy( atlas_sitk, atlas_edge) else: # if sigma not set or if using suffix to compare two images, # load from original image to compare against common image atlas_edge = sitk_io.load_registered_img( path_img, config.RegNames.IMG_ATLAS_EDGE.value) erode = config.atlas_profile["erode_labels"] if erode["interior"]: # make map of label interiors for interior/border comparisons print("Eroding labels to generate interior labels image") erosion = config.atlas_profile[ profiles.RegKeys.EDGE_AWARE_REANNOTATION] erosion_frac = config.atlas_profile["erosion_frac"] interior, _ = erode_labels( labels_img_np, erosion, erosion_frac, atlas and _is_profile_mirrored(), _get_mirror_mult()) labels_sitk_interior = sitk_io.replace_sitk_with_numpy( labels_sitk, interior) # make labels edge and edge distance images dist_to_orig, labels_edge = edge_distances( labels_img_np, atlas_edge, spacing=atlas_sitk.GetSpacing()[::-1]) dist_sitk = sitk_io.replace_sitk_with_numpy(atlas_sitk, dist_to_orig) labels_sitk_edge = sitk_io.replace_sitk_with_numpy(labels_sitk, labels_edge) # show all images imgs_write = { config.RegNames.IMG_ATLAS_LOG.value: atlas_sitk_log, config.RegNames.IMG_ATLAS_EDGE.value: atlas_sitk_edge, config.RegNames.IMG_LABELS_EDGE.value: labels_sitk_edge, config.RegNames.IMG_LABELS_INTERIOR.value: labels_sitk_interior, config.RegNames.IMG_LABELS_DIST.value: dist_sitk, } if show: for img in imgs_write.values(): if img: sitk.Show(img) # write images to same directory as atlas with appropriate suffix sitk_io.write_reg_images(imgs_write, mod_path)
def stack_to_img(paths, roi_offset, roi_size, series=None, subimg_offset=None, subimg_size=None, animated=False, suffix=None): """Build an image file from a stack of images in a directory or an array, exporting as an animated GIF or movie for multiple planes or extracting a single plane to a standard image file format. Writes the file to the parent directory of path. Args: paths (List[str]): Image paths, which can each be either an image directory or a base path to a single image, including volumetric images. roi_offset (Sequence[int]): Tuple of offset given in user order ``x,y,z``; defaults to None. Requires ``roi_size`` to not be None. roi_size (Sequence[int]): Size of the region of interest in user order ``x,y,z``; defaults to None. Requires ``roi_offset`` to not be None. series (int): Image series number; defaults to None. subimg_offset (List[int]): Sub-image offset as (z,y,x) to load; defaults to None. subimg_size (List[int]): Sub-image size as (z,y,x) to load; defaults to None. animated (bool): True to export as an animated image; defaults to False. suffix (str): String to append to output path before extension; defaults to None to ignore. """ # set up figure layout for collages size = config.plot_labels[config.PlotLabels.LAYOUT] ncols, nrows = size if size else (1, 1) num_paths = len(paths) collage = num_paths > 1 figs = {} for i in range(nrows): for j in range(ncols): n = i * ncols + j if n >= num_paths: break # load an image and set up its image stacker path_sub = paths[n] axs = [] # TODO: test directory of images # TODO: consider not reloading first image np_io.setup_images(path_sub, series, subimg_offset, subimg_size) stacker = setup_stack( config.image5d, path_sub, offset=roi_offset, roi_size=roi_size, slice_vals=config.slice_vals, rescale=config.transform[config.Transforms.RESCALE], labels_imgs=(config.labels_img, config.borders_img)) # add sub-plot title unless groups given as empty string title = None if config.groups: title = libmag.get_if_within(config.groups, n) elif num_paths > 1: title = os.path.basename(path_sub) if not stacker.images: continue ax = None for k in range(len(stacker.images[0])): # create or retrieve fig; animation has only 1 fig planei = 0 if animated else (stacker.img_slice.start + k * stacker.img_slice.step) fig_dict = figs.get(planei) if not fig_dict: # set up new fig fig, gs = plot_support.setup_fig( nrows, ncols, config.plot_labels[config.PlotLabels.SIZE]) fig_dict = {"fig": fig, "gs": gs, "imgs": []} figs[planei] = fig_dict if ax is None: # generate new axes for the gridspec position ax = fig_dict["fig"].add_subplot(fig_dict["gs"][i, j]) if title: ax.title.set_text(title) axs.append(ax) # export planes plotted_imgs = stacker.build_stack( axs, config.plot_labels[config.PlotLabels.SCALE_BAR], size is None or ncols * nrows == 1) if animated: # store all plotted images in single fig fig_dict = figs.get(0) if fig_dict: fig_dict["imgs"] = plotted_imgs else: # store one plotted image per fig; not used currently for fig_dict, img in zip(figs.values(), plotted_imgs): fig_dict["imgs"].append(img) path_base = paths[0] for planei, fig_dict in figs.items(): if animated: # generate animated image (eg animated GIF or movie file) animate_imgs(path_base, fig_dict["imgs"], config.delay, config.savefig, suffix) else: # generate single figure with axis and plane index in filename if collage: # output filename as a collage of images if not os.path.isdir(path_base): path_base = os.path.dirname(path_base) path_base = os.path.join(path_base, "collage") # insert mod as suffix, then add any additional suffix; # can use config.prefix_out for make_out_path prefix mod = "_plane_{}{}".format( plot_support.get_plane_axis(config.plane), planei) out_path = libmag.make_out_path(path_base, suffix=mod) if suffix: out_path = libmag.insert_before_ext(out_path, suffix) plot_support.save_fig(out_path, config.savefig, fig=fig_dict["fig"])
def edge_aware_segmentation(path_atlas, show=True, atlas=True, suffix=None, exclude_labels=None, mirror_mult=-1): """Segment an atlas using its previously generated edge map. Labels may not match their own underlying atlas image well, particularly in the orthogonal directions in which the labels were not constructed. To improve alignment between the labels and the atlas itself, register the labels to an automated, roughly segmented version of the atlas. The goal is to improve the labels' alignment so that the atlas/labels combination can be used for another form of automated segmentation by registering them to experimental brains via :func:``register``. Edge files are assumed to have been generated by :func:``make_edge_images``. Args: path_atlas (str): Path to the fixed file, typically the atlas file with stained sections. The corresponding edge and labels files will be loaded based on this path. show (bool): True if the output images should be displayed; defaults to True. atlas (bool): True if the primary image is an atlas, which is assumed to be symmetrical. False if the image is an experimental/sample image, in which case segmentation will be performed on the full images, and stats will not be performed. suffix (str): Modifier to append to end of ``path_atlas`` basename for registered image files that were output to a modified name; defaults to None. If ``atlas`` is True, ``suffix`` will only be applied to saved files, with files still loaded based on the original path. exclude_labels (List[int]): Sequence of labels to exclude from the segmentation; defaults to None. mirror_mult (int): Multiplier for mirrored labels; defaults to -1 to make mirrored labels the inverse of their source labels. """ # adjust image path with suffix load_path = path_atlas mod_path = path_atlas if suffix is not None: mod_path = libmag.insert_before_ext(mod_path, suffix) if atlas: load_path = mod_path # load corresponding files via SimpleITK atlas_sitk = sitk_io.load_registered_img( load_path, config.RegNames.IMG_ATLAS.value, get_sitk=True) atlas_sitk_edge = sitk_io.load_registered_img( load_path, config.RegNames.IMG_ATLAS_EDGE.value, get_sitk=True) labels_sitk = sitk_io.load_registered_img( load_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_sitk_markers = sitk_io.load_registered_img( load_path, config.RegNames.IMG_LABELS_MARKERS.value, get_sitk=True) # get Numpy arrays of images atlas_img_np = sitk.GetArrayFromImage(atlas_sitk) atlas_edge = sitk.GetArrayFromImage(atlas_sitk_edge) labels_img_np = sitk.GetArrayFromImage(labels_sitk) markers = sitk.GetArrayFromImage(labels_sitk_markers) # segment image from markers sym_axis = atlas_refiner.find_symmetric_axis(atlas_img_np) mirrorred = atlas and sym_axis >= 0 len_half = None seg_args = {"exclude_labels": exclude_labels} edge_prof = config.atlas_profile[profiles.RegKeys.EDGE_AWARE_REANNOTATION] if edge_prof: edge_filt = edge_prof[profiles.RegKeys.WATERSHED_MASK_FILTER] if edge_filt and len(edge_filt) > 1: # watershed mask filter settings from atlas profile seg_args["mask_filt"] = edge_filt[0] seg_args["mask_filt_size"] = edge_filt[1] if mirrorred: # segment only half of image, assuming symmetry len_half = atlas_img_np.shape[sym_axis] // 2 slices = [slice(None)] * labels_img_np.ndim slices[sym_axis] = slice(len_half) sl = tuple(slices) labels_seg = segmenter.segment_from_labels( atlas_edge[sl], markers[sl], labels_img_np[sl], **seg_args) else: # segment the full image, including excluded labels on the opposite side exclude_labels = exclude_labels.tolist().extend( (mirror_mult * exclude_labels).tolist()) seg_args["exclude_labels"] = exclude_labels labels_seg = segmenter.segment_from_labels( atlas_edge, markers, labels_img_np, **seg_args) smoothing = config.atlas_profile["smooth"] if smoothing is not None: # smoothing by opening operation based on profile setting atlas_refiner.smooth_labels( labels_seg, smoothing, config.SmoothingModes.opening) if mirrorred: # mirror back to other half labels_seg = _mirror_imported_labels( labels_seg, len_half, mirror_mult, sym_axis) # expand background to smoothed background of original labels to # roughly match background while still allowing holes to be filled crop = config.atlas_profile["crop_to_orig"] atlas_refiner.crop_to_orig( labels_img_np, labels_seg, crop) if labels_seg.dtype != labels_img_np.dtype: # watershed may give different output type, so cast back if so labels_seg = labels_seg.astype(labels_img_np.dtype) labels_sitk_seg = sitk_io.replace_sitk_with_numpy(labels_sitk, labels_seg) # show DSCs for labels print("\nMeasuring overlap of atlas and combined watershed labels:") atlas_refiner.measure_overlap_combined_labels(atlas_sitk, labels_sitk_seg) print("Measuring overlap of individual original and watershed labels:") atlas_refiner.measure_overlap_labels(labels_sitk, labels_sitk_seg) print("\nMeasuring overlap of combined original and watershed labels:") atlas_refiner.measure_overlap_labels( atlas_refiner.make_labels_fg(labels_sitk), atlas_refiner.make_labels_fg(labels_sitk_seg)) print() # show and write image to same directory as atlas with appropriate suffix sitk_io.write_reg_images( {config.RegNames.IMG_LABELS.value: labels_sitk_seg}, mod_path) if show: sitk.Show(labels_sitk_seg) return path_atlas
def make_density_image(img_path, scale=None, shape=None, suffix=None, labels_img_sitk=None, channel=None, matches=None): """Make a density image based on associated blobs. Uses the shape of the registered labels image by default to set the voxel sizes for the blobs. If ``matches`` is given, a heat map will be generated for each set of channels given in the dictionary. Otherwise, if the loaded blobs file has intensity-based colocalizations, a heat map will be generated for each combination of channels. Args: img_path: Path to image, which will be used to indentify the blobs file. scale: Rescaling factor as a scalar value to find the corresponding full-sized image. Defaults to None to use the register setting ``target_size`` instead if available, falling back to load the full size image to find its shape if necessary. shape: Final shape size; defaults to None to use the shape of the labels image. suffix: Modifier to append to end of ``img_path`` basename for registered image files that were output to a modified name; defaults to None. labels_img_sitk: Labels image as a SimpleITK ``Image`` object; defaults to None, in which case the registered labels image file corresponding to ``img_path`` with any ``suffix`` modifier will be opened. channel (List[int]): Sequence of channels to include in density image; defaults to None to combine blobs from all channels. matches (dict[tuple[int, int], :class:`magmap.cv.colocalizer`): Dictionary of channel combinations to blob matches; defaults to None. Returns: :obj:`np.ndarray`, str: The density image as a Numpy array in the same shape as the opened image and the original and ``img_path`` to track such as for multiprocessing. """ def make_heat_map(): # build heat map to store densities per label px and save to file coord_scaled = ontology.scale_coords( blobs_chl[:, :3], scaling, labels_img.shape) print("coords", coord_scaled) return cv_nd.build_heat_map(labels_img.shape, coord_scaled) # set up paths and get labels image mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(img_path, suffix) if labels_img_sitk is None: labels_img_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_img = sitk.GetArrayFromImage(labels_img_sitk) # load blobs blobs = detector.Blobs().load_blobs(np_io.img_to_blobs_path(img_path)) scaling = np_io.find_scaling(img_path, labels_img.shape, scale)[0] if shape is not None: # scale blob coordinates and heat map to an alternative final shape scaling = np.divide(shape, np.divide(labels_img.shape, scaling)) labels_spacing = np.multiply( labels_img_sitk.GetSpacing()[::-1], np.divide(labels_img.shape, shape)) labels_img = np.zeros(shape, dtype=labels_img.dtype) labels_img_sitk.SetSpacing(labels_spacing[::-1]) print("using scaling: {}".format(scaling)) # annotate blobs based on position blobs_chl = blobs.blobs if channel is not None: blobs_chl = blobs_chl[np.isin(detector.get_blobs_channel( blobs_chl), channel)] heat_map = make_heat_map() print("heat map", heat_map.shape, heat_map.dtype, labels_img.shape) imgs_write = { config.RegNames.IMG_HEAT_MAP.value: sitk_io.replace_sitk_with_numpy(labels_img_sitk, heat_map)} heat_colocs = None if matches: # create heat maps for match-based colocalization combos heat_colocs = [] for chl_combo, chl_matches in matches.items(): print("Generating match-based colocalization heat map " "for channel combo:", chl_combo) # use blobs in first channel of each channel pair for simplicity blobs_chl = chl_matches.get_blobs(1) heat_colocs.append(make_heat_map()) elif blobs.colocalizations is not None: # create heat map for each intensity-based colocalization combo # as a separate channel in output image blob_chls = range(blobs.colocalizations.shape[1]) blob_chls_len = len(blob_chls) if blob_chls_len > 1: # get all channel combos that include given channels combos = [] chls = blob_chls if channel is None else channel for r in range(2, blob_chls_len + 1): combos.extend( [tuple(c) for c in itertools.combinations(blob_chls, r) if all([h in c for h in chls])]) heat_colocs = [] for combo in combos: print("Generating intensity-based colocalization heat map " "for channel combo:", combo) blobs_chl = blobs.blobs[np.all(np.equal( blobs.colocalizations[:, combo], 1), axis=1)] heat_colocs.append(make_heat_map()) if heat_colocs is not None: # combine heat maps into single image heat_colocs = np.stack(heat_colocs, axis=3) imgs_write[config.RegNames.IMG_HEAT_COLOC.value] = \ sitk_io.replace_sitk_with_numpy( labels_img_sitk, heat_colocs) # write images to file sitk_io.write_reg_images(imgs_write, mod_path) return heat_map, img_path
def make_density_image( img_path: str, scale: Optional[float] = None, shape: Optional[Sequence[int]] = None, suffix: Optional[str] = None, labels_img_sitk: Optional[sitk.Image] = None, channel: Optional[Sequence[int]] = None, matches: Dict[Tuple[int, int], "colocalizer.BlobMatch"] = None, atlas_profile: Optional["atlas_prof.AtlasProfile"] = None ) -> Tuple[np.ndarray, str]: """Make a density image based on associated blobs. Uses the size and resolutions of the original image stores in the blobs if available to determine scaling between the blobs and the output image. Otherwise, uses the shape of the registered labels image to set the voxel sizes for the blobs. If ``matches`` is given, a heat map will be generated for each set of channels given in the dictionary. Otherwise, if the loaded blobs file has intensity-based colocalizations, a heat map will be generated for each combination of channels. Args: img_path: Path to image, which will be used to indentify the blobs file. scale: Scaling factor between the blobs' space and the output space; defaults to None to use the register. Scaling is found by :meth:`magmap.np_io.find_scaling`. shape: Output shape, used for scaling; defaults to None. suffix: Modifier to append to end of ``img_path`` basename for registered image files that were output to a modified name; defaults to None. labels_img_sitk: Labels image; defaults to None to load from a registered labels image. channel: Sequence of channels to include in density image. For multiple channels, blobs from all these channels are combined into one heatmap. Defaults to None to use all channels. matches: Dictionary of channel combinations to blob matches; defaults to None. atlas_profile: Atlas profile, used for scaling; defaults to None. Returns: Tuple of the density image as a Numpy array in the same shape as the opened image and the original and ``img_path`` to track such as for multiprocessing. """ def make_heat_map(): # build heat map to store densities per label px and save to file coord_scaled = ontology.scale_coords(blobs_chl[:, :3], scaling, labels_img.shape) _logger.debug("Scaled coords:\n%s", coord_scaled) return cv_nd.build_heat_map(labels_img.shape, coord_scaled) # set up paths and get labels image _logger.info("\n\nGenerating heat map from blobs") mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(img_path, suffix) # load blobs blobs = detector.Blobs().load_blobs(np_io.img_to_blobs_path(img_path)) is_2d = False if (shape is not None and blobs.roi_size is not None and blobs.resolutions is not None): # prepare output image and scaling factor from it to the blobs scaling = np.divide(shape, blobs.roi_size) labels_spacing = np.divide(blobs.resolutions[0], scaling) labels_img = np.zeros(shape, dtype=np.uint8) labels_img_sitk = sitk.GetImageFromArray(labels_img) labels_img_sitk.SetSpacing(labels_spacing[::-1]) else: # default to use labels image as the size of the output image if labels_img_sitk is None: labels_img_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_img = sitk.GetArrayFromImage(labels_img_sitk) is_2d = labels_img.ndim == 2 if is_2d: # temporarily convert 2D images to 3D labels_img = labels_img[None] # find the scaling between the blobs and the labels image target_size = (None if atlas_profile is None else atlas_profile["target_size"]) scaling = np_io.find_scaling(img_path, labels_img.shape, scale, target_size)[0] if shape is not None: # scale blob coordinates and heat map to an alternative final shape scaling = np.divide(shape, np.divide(labels_img.shape, scaling)) labels_spacing = np.multiply(labels_img_sitk.GetSpacing()[::-1], np.divide(labels_img.shape, shape)) labels_img = np.zeros(shape, dtype=labels_img.dtype) labels_img_sitk.SetSpacing(labels_spacing[::-1]) _logger.debug("Using image scaling: {}".format(scaling)) # annotate blobs based on position blobs_chl = blobs.blobs if channel is not None: _logger.info( "Using blobs from channel(s), combining if multiple channels: %s", channel) blobs_chl = blobs_chl[np.isin( detector.Blobs.get_blobs_channel(blobs_chl), channel)] heat_map = make_heat_map() if is_2d: # convert back to 3D heat_map = heat_map[0] imgs_write = { config.RegNames.IMG_HEAT_MAP.value: sitk_io.replace_sitk_with_numpy(labels_img_sitk, heat_map) } heat_colocs = None if matches: # create heat maps for match-based colocalization combos heat_colocs = [] for chl_combo, chl_matches in matches.items(): _logger.info( "Generating match-based colocalization heat map " "for channel combo: %s", chl_combo) # use blobs in first channel of each channel pair for simplicity blobs_chl = chl_matches.get_blobs(1) heat_colocs.append(make_heat_map()) elif blobs.colocalizations is not None: # create heat map for each intensity-based colocalization combo # as a separate channel in output image blob_chls = range(blobs.colocalizations.shape[1]) blob_chls_len = len(blob_chls) if blob_chls_len > 1: # get all channel combos that include given channels combos = [] chls = blob_chls if channel is None else channel for r in range(2, blob_chls_len + 1): combos.extend([ tuple(c) for c in itertools.combinations(blob_chls, r) if all([h in c for h in chls]) ]) heat_colocs = [] for combo in combos: _logger.info( "Generating intensity-based colocalization heat map " "for channel combo: %s", combo) blobs_chl = blobs.blobs[np.all(np.equal( blobs.colocalizations[:, combo], 1), axis=1)] heat_colocs.append(make_heat_map()) if heat_colocs is not None: # combine heat maps into single image heat_colocs = np.stack(heat_colocs, axis=3) imgs_write[config.RegNames.IMG_HEAT_COLOC.value] = \ sitk_io.replace_sitk_with_numpy( labels_img_sitk, heat_colocs) # write images to file sitk_io.write_reg_images(imgs_write, mod_path) return heat_map, img_path
def edge_aware_segmentation( path_atlas: str, atlas_profile: atlas_prof.AtlasProfile, show: bool = True, atlas: bool = True, suffix: Optional[str] = None, exclude_labels: Optional[pd.DataFrame] = None, mirror_mult: int = -1): """Segment an atlas using its previously generated edge map. Labels may not match their own underlying atlas image well, particularly in the orthogonal directions in which the labels were not constructed. To improve alignment between the labels and the atlas itself, register the labels to an automated, roughly segmented version of the atlas. The goal is to improve the labels' alignment so that the atlas/labels combination can be used for another form of automated segmentation by registering them to experimental brains via :func:``register``. Edge files are assumed to have been generated by :func:``make_edge_images``. Args: path_atlas: Path to the fixed file, typically the atlas file with stained sections. The corresponding edge and labels files will be loaded based on this path. atlas_profile: Atlas profile. show: True if the output images should be displayed; defaults to True. atlas: True if the primary image is an atlas, which is assumed to be symmetrical. False if the image is an experimental/sample image, in which case segmentation will be performed on the full images, and stats will not be performed. suffix: Modifier to append to end of ``path_atlas`` basename for registered image files that were output to a modified name; defaults to None. If ``atlas`` is True, ``suffix`` will only be applied to saved files, with files still loaded based on the original path. exclude_labels: Sequence of labels to exclude from the segmentation; defaults to None. mirror_mult: Multiplier for mirrored labels; defaults to -1 to make mirrored labels the inverse of their source labels. """ # adjust image path with suffix load_path = path_atlas mod_path = path_atlas if suffix is not None: mod_path = libmag.insert_before_ext(mod_path, suffix) if atlas: load_path = mod_path # load corresponding files via SimpleITK atlas_sitk = sitk_io.load_registered_img( load_path, config.RegNames.IMG_ATLAS.value, get_sitk=True) atlas_sitk_edge = sitk_io.load_registered_img( load_path, config.RegNames.IMG_ATLAS_EDGE.value, get_sitk=True) labels_sitk = sitk_io.load_registered_img( load_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_sitk_markers = sitk_io.load_registered_img( load_path, config.RegNames.IMG_LABELS_MARKERS.value, get_sitk=True) # get Numpy arrays of images atlas_img_np = sitk.GetArrayFromImage(atlas_sitk) atlas_edge = sitk.GetArrayFromImage(atlas_sitk_edge) labels_img_np = sitk.GetArrayFromImage(labels_sitk) markers = sitk.GetArrayFromImage(labels_sitk_markers) # segment image from markers sym_axis = atlas_refiner.find_symmetric_axis(atlas_img_np) mirrorred = atlas and sym_axis >= 0 len_half = None seg_args = {"exclude_labels": exclude_labels} edge_prof = atlas_profile[profiles.RegKeys.EDGE_AWARE_REANNOTATION] if edge_prof: edge_filt = edge_prof[profiles.RegKeys.WATERSHED_MASK_FILTER] if edge_filt and len(edge_filt) > 1: # watershed mask filter settings from atlas profile seg_args["mask_filt"] = edge_filt[0] seg_args["mask_filt_size"] = edge_filt[1] if mirrorred: # segment only half of image, assuming symmetry len_half = atlas_img_np.shape[sym_axis] // 2 slices = [slice(None)] * labels_img_np.ndim slices[sym_axis] = slice(len_half) sl = tuple(slices) labels_seg = segmenter.segment_from_labels( atlas_edge[sl], markers[sl], labels_img_np[sl], **seg_args) else: # segment the full image, including excluded labels on the opposite side exclude_labels = exclude_labels.tolist().extend( (mirror_mult * exclude_labels).tolist()) seg_args["exclude_labels"] = exclude_labels labels_seg = segmenter.segment_from_labels( atlas_edge, markers, labels_img_np, **seg_args) smoothing = atlas_profile["smooth"] smoothing_mode = atlas_profile["smoothing_mode"] cond = ["edge-aware_seg"] if smoothing is not None: # smoothing by opening operation based on profile setting meas_smoothing = atlas_profile["meas_smoothing"] cond.append("smoothing") df_aggr, df_raw = atlas_refiner.smooth_labels( labels_seg, smoothing, smoothing_mode, meas_smoothing, labels_sitk.GetSpacing()[::-1]) df_base_path = os.path.splitext(mod_path)[0] if df_raw is not None: # write raw smoothing metrics df_io.data_frames_to_csv( df_raw, f"{df_base_path}_{config.PATH_SMOOTHING_RAW_METRICS}") if df_aggr is not None: # write aggregated smoothing metrics df_io.data_frames_to_csv( df_aggr, f"{df_base_path}_{config.PATH_SMOOTHING_METRICS}") if mirrorred: # mirror back to other half labels_seg = _mirror_imported_labels( labels_seg, len_half, mirror_mult, sym_axis) # expand background to smoothed background of original labels to # roughly match background while still allowing holes to be filled crop = atlas_profile["crop_to_orig"] atlas_refiner.crop_to_orig( labels_img_np, labels_seg, crop) if labels_seg.dtype != labels_img_np.dtype: # watershed may give different output type, so cast back if so labels_seg = labels_seg.astype(labels_img_np.dtype) labels_sitk_seg = sitk_io.replace_sitk_with_numpy(labels_sitk, labels_seg) # show DSCs for labels _logger.info( "\nMeasuring overlap of individual original and watershed labels:") dsc_lbls_comb = atlas_refiner.measure_overlap_labels( labels_sitk, labels_sitk_seg) _logger.info( "\nMeasuring overlap of combined original and watershed labels:") dsc_lbls_indiv = atlas_refiner.measure_overlap_labels( atlas_refiner.make_labels_fg(labels_sitk), atlas_refiner.make_labels_fg(labels_sitk_seg)) _logger.info("") # measure and save whole atlas metrics metrics = { config.AtlasMetrics.SAMPLE: [os.path.basename(mod_path)], config.AtlasMetrics.REGION: config.REGION_ALL, config.AtlasMetrics.CONDITION: "|".join(cond), config.AtlasMetrics.DSC_LABELS_ORIG_NEW_COMBINED: dsc_lbls_comb, config.AtlasMetrics.DSC_LABELS_ORIG_NEW_INDIV: dsc_lbls_indiv, } df_metrics_path = libmag.combine_paths( mod_path, config.PATH_ATLAS_IMPORT_METRICS) atlas_refiner.measure_atlas_refinement( metrics, atlas_sitk, labels_sitk_seg, atlas_profile, df_metrics_path) # show and write image to same directory as atlas with appropriate suffix sitk_io.write_reg_images( {config.RegNames.IMG_LABELS.value: labels_sitk_seg}, mod_path) if show: sitk.Show(labels_sitk_seg) return path_atlas
def make_density_image(img_path, scale=None, shape=None, suffix=None, labels_img_sitk=None): """Make a density image based on associated blobs. Uses the shape of the registered labels image by default to set the voxel sizes for the blobs. Args: img_path: Path to image, which will be used to indentify the blobs file. scale: Rescaling factor as a scalar value to find the corresponding full-sized image. Defaults to None to use the register setting ``target_size`` instead if available, falling back to load the full size image to find its shape if necessary. shape: Final shape size; defaults to None to use the shape of the labels image. suffix: Modifier to append to end of ``img_path`` basename for registered image files that were output to a modified name; defaults to None. labels_img_sitk: Labels image as a SimpleITK ``Image`` object; defaults to None, in which case the registered labels image file corresponding to ``img_path`` with any ``suffix`` modifier will be opened. Returns: Tuple of the density image as a Numpy array in the same shape as the opened image; Numpy array of blob IDs; and the original ``img_path`` to track such as for multiprocessing. """ mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(img_path, suffix) if labels_img_sitk is None: labels_img_sitk = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value, get_sitk=True) labels_img = sitk.GetArrayFromImage(labels_img_sitk) # load blobs blobs, scaling, _ = np_io.load_blobs(img_path, True, labels_img.shape, scale) if shape is not None: # scale blob coordinates and heat map to an alternative final shape scaling = np.divide(shape, np.divide(labels_img.shape, scaling)) labels_spacing = np.multiply(labels_img_sitk.GetSpacing()[::-1], np.divide(labels_img.shape, shape)) labels_img = np.zeros(shape, dtype=labels_img.dtype) labels_img_sitk.SetSpacing(labels_spacing[::-1]) print("using scaling: {}".format(scaling)) # annotate blobs based on position blobs_ids, coord_scaled = ontology.get_label_ids_from_position( blobs[:, :3], labels_img, scaling, return_coord_scaled=True) print("blobs_ids: {}".format(blobs_ids)) # build heat map to store densities per label px and save to file heat_map = cv_nd.build_heat_map(labels_img.shape, coord_scaled) out_path = sitk_io.reg_out_path(mod_path, config.RegNames.IMG_HEAT_MAP.value) print("writing {}".format(out_path)) heat_map_sitk = sitk_io.replace_sitk_with_numpy(labels_img_sitk, heat_map) sitk.WriteImage(heat_map_sitk, out_path, False) return heat_map, blobs_ids, img_path
def stack_to_img(paths, roi_offset, roi_size, series=None, subimg_offset=None, subimg_size=None, animated=False, suffix=None): """Build an image file from a stack of images in a directory or an array, exporting as an animated GIF or movie for multiple planes or extracting a single plane to a standard image file format. Writes the file to the parent directory of path. Args: paths (List[str]): Image paths, which can each be either an image directory or a base path to a single image, including volumetric images. roi_offset (Sequence[int]): Tuple of offset given in user order ``x,y,z``; defaults to None. Requires ``roi_size`` to not be None. roi_size (Sequence[int]): Size of the region of interest in user order ``x,y,z``; defaults to None. Requires ``roi_offset`` to not be None. series (int): Image series number; defaults to None. subimg_offset (List[int]): Sub-image offset as (z,y,x) to load; defaults to None. subimg_size (List[int]): Sub-image size as (z,y,x) to load; defaults to None. animated (bool): True to export as an animated image; defaults to False. suffix (str): String to append to output path before extension; defaults to None to ignore. """ size = config.plot_labels[config.PlotLabels.LAYOUT] ncols, nrows = size if size else (1, 1) fig, gs = plot_support.setup_fig( nrows, ncols, config.plot_labels[config.PlotLabels.SIZE]) plotted_imgs = None num_paths = len(paths) for i in range(nrows): for j in range(ncols): n = i * ncols + j if n >= num_paths: break ax = fig.add_subplot(gs[i, j]) path_sub = paths[n] # TODO: test directory of images # TODO: avoid reloading first image np_io.setup_images(path_sub, series, subimg_offset, subimg_size) plotted_imgs = stack_to_ax_imgs( ax, config.image5d, path_sub, offset=roi_offset, roi_size=roi_size, slice_vals=config.slice_vals, rescale=config.transform[config.Transforms.RESCALE], labels_imgs=(config.labels_img, config.borders_img), multiplane=animated, fit=(size is None or ncols * nrows == 1)) path_base = paths[0] if animated: # generate animated image (eg animated GIF or movie file) animate_imgs(path_base, plotted_imgs, config.delay, config.savefig, suffix) else: # save image as single file if roi_offset: # get plane index from coordinate at the given axis in ROI offset planei = roi_offset[::-1][plot_support.get_plane_axis( config.plane, get_index=True)] else: # get plane index from slice start planei = config.slice_vals[0] if num_paths > 1: # output filename as a collage of images if not os.path.isdir(path_base): path_base = os.path.dirname(path_base) path_base = os.path.join(path_base, "collage") mod = "_plane_{}{}".format(plot_support.get_plane_axis(config.plane), planei) if suffix: path_base = libmag.insert_before_ext(path_base, suffix) plot_support.save_fig(path_base, config.savefig, mod)
def plot_knns(img_paths, suffix=None, show=False, names=None): """Plot k-nearest-neighbor distances for multiple sets of blobs, overlaying on a single plot. Args: img_paths (List[str]): Base paths from which registered labels and blobs files will be found and output blobs file save location will be constructed. suffix (str): Suffix for ``path``; defaults to None. show (bool): True to plot the distances; defaults to False. names (List[str]): Sequence of names corresponding to ``img_paths`` for the plot legend. """ cluster_settings = config.atlas_profile[profiles.RegKeys.METRICS_CLUSTER] knn_n = cluster_settings[profiles.RegKeys.KNN_N] if not knn_n: knn_n = cluster_settings[profiles.RegKeys.DBSCAN_MINPTS] - 1 print("Calculating k-nearest-neighbor distances and plotting distances " "for neighbor {}".format(knn_n)) # set up combined data frames for all samples at each zoom level df_keys = ("ov", "zoom") dfs_comb = {key: [] for key in df_keys} names_disp = names if names else [] for i, img_path in enumerate(img_paths): # load blobs associated with image mod_path = img_path if suffix is not None: mod_path = libmag.insert_before_ext(img_path, suffix) labels_img_np = sitk_io.load_registered_img( mod_path, config.RegNames.IMG_LABELS.value) blobs = detector.Blobs().load_blobs(np_io.img_to_blobs_path(img_path)) scaling, res = np_io.find_scaling(img_path, labels_img_np.shape) if blobs is None: libmag.warn("unable to load nuclei coordinates for", img_path) continue # convert to physical units and display k-nearest-neighbors for nuclei blobs_phys = np.multiply(blobs.blobs[:, :3], res) # TESTING: given the same blobs, simply shift #blobs = np.multiply(blobs[i*10000000:, :3], res) _, _, dfs = knn_dist(blobs_phys, knn_n, 2, 1000000, False) if names is None: # default to naming from filename names_disp.append(os.path.basename(mod_path)) for j, df in enumerate(dfs): dfs_comb[df_keys[j]].append(df) for key in dfs_comb: # combine data frames at each zoom level, save, and plot with # different colors for each image df = df_io.join_dfs(dfs_comb[key], "point") dist_cols = [col for col in df.columns if col.startswith("dist")] rename_cols = {col: name for col, name in zip(dist_cols, names_disp)} df = df.rename(rename_cols, axis=1) out_path = "knn_dist_combine_{}".format(key) df_io.data_frames_to_csv(df, out_path) plot_2d.plot_lines(out_path, "point", rename_cols.values(), df=df, show=show, title=config.plot_labels[config.PlotLabels.TITLE])
def main(): """Process stats based on command-line mode.""" # process stats based on command-line argument df_task = libmag.get_enum(config.df_task, config.DFTasks) if df_task is config.DFTasks.MERGE_CSVS: # merge multiple CSV files into single CSV file merge_csvs(config.filenames, config.prefix) elif df_task is config.DFTasks.MERGE_CSVS_COLS: # join multiple CSV files based on a given index column into single # CSV file dfs = [pd.read_csv(f) for f in config.filenames] df = join_dfs( dfs, config.plot_labels[config.PlotLabels.ID_COL], config.plot_labels[config.PlotLabels.DROP_DUPS]) out_path = config.prefix if not out_path: out_path = libmag.insert_before_ext( config.filename, "_joined") data_frames_to_csv(df, out_path) elif df_task is config.DFTasks.APPEND_CSVS_COLS: # join multiple CSV files based on a given index column into single # CSV file dfs = [pd.read_csv(f) for f in config.filenames] labels = libmag.to_seq( config.plot_labels[config.PlotLabels.X_LABEL]) extra_cols = libmag.to_seq( config.plot_labels[config.PlotLabels.X_COL]) data_cols = libmag.to_seq( config.plot_labels[config.PlotLabels.Y_COL]) df = append_cols( dfs, labels, extra_cols=extra_cols, data_cols=data_cols) out_path = config.prefix if not out_path: out_path = libmag.insert_before_ext( config.filename, "_appended") data_frames_to_csv(df, out_path) elif df_task is config.DFTasks.EXPS_BY_REGION: # convert volume stats data frame to experiments by region exps_by_regions(config.filename) elif df_task is config.DFTasks.EXTRACT_FROM_CSV: # extract rows from CSV file based on matching rows in given col, where # "X_COL" = name of column on which to filter, and # "Y_COL" = values in this column for which rows should be kept df = pd.read_csv(config.filename) df_filt, _ = filter_dfs_on_vals( [df], None, [(config.plot_labels[config.PlotLabels.X_COL], config.plot_labels[config.PlotLabels.Y_COL])]) out_path = config.prefix if not out_path: out_path = "filtered.csv" data_frames_to_csv(df_filt, out_path) elif df_task is config.DFTasks.ADD_CSV_COLS: # add columns with corresponding values for all rows, where # "X_COL" = name of column(s) to add, and # "Y_COL" = value(s) for corresponding cols df = pd.read_csv(config.filename) cols = {k: v for k, v in zip( libmag.to_seq(config.plot_labels[config.PlotLabels.X_COL]), libmag.to_seq(config.plot_labels[config.PlotLabels.Y_COL]))} df = add_cols_df(df, cols) out_path = config.prefix if not out_path: out_path = libmag.insert_before_ext( config.filename, "_appended") data_frames_to_csv(df, out_path) elif df_task is config.DFTasks.NORMALIZE: # normalize values in each group to that of a base group, where # "ID_COL" = ID column(s), # "X_COL" = condition column # "Y_COL" = base condition to which values will be normalized, # "GROUP_COL" = metric columns to normalize, # "WT_COL" = extra columns to keep df = pd.read_csv(config.filename) df = normalize_df( df, config.plot_labels[config.PlotLabels.ID_COL], config.plot_labels[config.PlotLabels.X_COL], config.plot_labels[config.PlotLabels.Y_COL], config.plot_labels[config.PlotLabels.GROUP_COL], config.plot_labels[config.PlotLabels.WT_COL]) out_path = config.prefix if not out_path: out_path = libmag.insert_before_ext(config.filename, "_norm") data_frames_to_csv(df, out_path) elif df_task is config.DFTasks.MERGE_EXCELS: # merge multiple Excel files into single Excel file, with each # original Excel file as a separate sheet in the combined file merge_excels( config.filenames, config.prefix, config.plot_labels[config.PlotLabels.LEGEND_NAMES]) elif df_task in _ARITHMETIC_TASKS: # perform arithmetic operations on pairs of columns in a data frame df = pd.read_csv(config.filename) fn = _ARITHMETIC_TASKS[df_task] for col_x, col_y, col_id in zip( libmag.to_seq(config.plot_labels[config.PlotLabels.X_COL]), libmag.to_seq(config.plot_labels[config.PlotLabels.Y_COL]), libmag.to_seq(config.plot_labels[config.PlotLabels.ID_COL])): # perform the arithmetic operation specified by the specific # task on the pair of columns, inserting the results in a new # column specified by ID func_to_paired_cols(df, col_x, col_y, fn, col_id) # output modified data frame to CSV file out_path = config.prefix if not out_path: suffix = config.suffix if config.suffix else "" out_path = libmag.insert_before_ext(config.filename, suffix) data_frames_to_csv(df, out_path)