megadetector 5.0.10__py3-none-any.whl → 5.0.11__py3-none-any.whl

md_utils/write_html_image_list.py

@@ -1,225 +0,0 @@
-"""
-
-write_html_image_list.py
-
-Given a list of image file names, writes an HTML file that
-shows all those images, with optional one-line headers above each.
-
-Each "filename" can also be a dict with elements 'filename','title',
-'imageStyle','textStyle', 'linkTarget'
-
-"""
-
-#%% Constants and imports
-
-import os
-import math
-import urllib
-
-from md_utils import path_utils
-
-
-#%% write_html_image_list
-
-def write_html_image_list(filename=None,images=None,options=None):
-    """
-    Given a list of image file names, writes an HTML file that shows all those images, 
-    with optional one-line headers above each.
-
-    Args:
-        filename (str, optional): the .html output file; if None, just returns a valid 
-            options dict
-        images (list, optional): the images to write to the .html file; if None, just returns 
-            a valid options dict.  This can be a flat list of image filenames, or this can
-            be a list of dictionaries with one or more of the following fields:
-                
-            - filename (image filename) (required, all other fields are optional)
-            - imageStyle (css style for this image)
-            - textStyle (css style for the title associated with this image)
-            - title (text label for this image)
-            - linkTarget (URL to which this image should link on click)
-            
-        options (dict, optional): a dict with one or more of the following fields:        
-            
-            - fHtml (file pointer to write to, used for splitting write operations over multiple calls)
-            - headerHtml (html text to include before the image list)
-            - trailerHtml (html text to include after the image list)
-            - defaultImageStyle (default css style for images)
-            - defaultTextStyle (default css style for image titles)
-            - maxFiguresPerHtmlFile (max figures for a single HTML file; overflow will be handled by creating
-              multiple files and a TOC with links)
-            - urlEncodeFilenames (default True, e.g. '#' will be replaced by '%23')
-            - urlEncodeLinkTargets (default True, e.g. '#' will be replaced by '%23')
-            
-    """
-    
-    # returns an options struct
-    if options is None:
-        options = {}
-        
-    if 'fHtml' not in options:
-        options['fHtml'] = -1
-    
-    if 'headerHtml' not in options or options['headerHtml'] is None:
-        options['headerHtml'] = ''        
-    
-    if 'trailerHtml' not in options or options['trailerHtml'] is None:
-        options['trailerHtml'] = ''    
-    
-    if 'defaultTextStyle' not in options or options['defaultTextStyle'] is None:
-        options['defaultTextStyle'] = \
-        "font-family:calibri,verdana,arial;font-weight:bold;font-size:150%;text-align:left;margin:0px;"
-
-    if 'defaultImageStyle' not in options or options['defaultImageStyle'] is None:
-        options['defaultImageStyle'] = \
-        "margin:0px;margin-top:5px;margin-bottom:5px;"
-    
-    if 'urlEncodeFilenames' not in options or options['urlEncodeFilenames'] is None:
-        options['urlEncodeFilenames'] = True
-    
-    if 'urlEncodeLinkTargets' not in options or options['urlEncodeLinkTargets'] is None:
-        options['urlEncodeLinkTargets'] = True
-    
-    # Possibly split the html output for figures into multiple files; Chrome gets sad with
-    # thousands of images in a single tab.        
-    if 'maxFiguresPerHtmlFile' not in options or options['maxFiguresPerHtmlFile'] is None:
-        options['maxFiguresPerHtmlFile'] = math.inf    
-    
-    if filename is None or images is None:
-        return options
-    
-    # images may be a list of images or a list of image/style/title dictionaries, 
-    # enforce that it's the latter to simplify downstream code
-    for iImage,imageInfo in enumerate(images):
-        if isinstance(imageInfo,str):
-            imageInfo = {'filename':imageInfo}
-        if 'filename' not in imageInfo:
-            imageInfo['filename'] = ''
-        if 'imageStyle' not in imageInfo:
-            imageInfo['imageStyle'] = options['defaultImageStyle']
-        if 'title' not in imageInfo:
-            imageInfo['title'] = ''
-        if 'linkTarget' not in imageInfo:
-            imageInfo['linkTarget'] = ''
-        if 'textStyle' not in imageInfo:
-            textStyle = options['defaultTextStyle']
-            imageInfo['textStyle'] = options['defaultTextStyle']
-        images[iImage] = imageInfo            
-    
-    nImages = len(images)
-    
-    # If we need to break this up into multiple files...
-    if nImages > options['maxFiguresPerHtmlFile']:
-    
-        # You can't supply your own file handle in this case
-        if options['fHtml'] != -1:
-            raise ValueError(
-                    'You can''t supply your own file handle if we have to page the image set')
-        
-        figureFileStartingIndices = list(range(0,nImages,options['maxFiguresPerHtmlFile']))
-
-        assert len(figureFileStartingIndices) > 1
-        
-        # Open the meta-output file
-        fMeta = open(filename,'w')
-        
-        # Write header stuff
-        fMeta.write('<html><body>\n')    
-        fMeta.write(options['headerHtml'])        
-        fMeta.write('<table border = 0 cellpadding = 2>\n')
-        
-        for startingIndex in figureFileStartingIndices:
-            
-            iStart = startingIndex
-            iEnd = startingIndex+options['maxFiguresPerHtmlFile']-1;
-            if iEnd >= nImages:
-                iEnd = nImages-1
-            
-            trailer = 'image_{:05d}_{:05d}'.format(iStart,iEnd)
-            localFiguresHtmlFilename = path_utils.insert_before_extension(filename,trailer)
-            fMeta.write('<tr><td>\n')
-            fMeta.write('<p style="padding-bottom:0px;margin-bottom:0px;text-align:left;font-family:''segoe ui'',calibri,arial;font-size:100%;text-decoration:none;font-weight:bold;">')
-            fMeta.write('<a href="{}">Figures for images {} through {}</a></p></td></tr>\n'.format(
-                os.path.basename(localFiguresHtmlFilename),iStart,iEnd))
-            
-            localImages = images[iStart:iEnd+1]
-            
-            localOptions = options.copy();
-            localOptions['headerHtml'] = '';
-            localOptions['trailerHtml'] = '';
-            
-            # Make a recursive call for this image set
-            write_html_image_list(localFiguresHtmlFilename,localImages,localOptions)
-            
-        # ...for each page of images
-        
-        fMeta.write('</table></body>\n')
-        fMeta.write(options['trailerHtml'])
-        fMeta.write('</html>\n')
-        fMeta.close()
-        
-        return options
-        
-    # ...if we have to make multiple sub-pages
-        
-    bCleanupFile = False
-    
-    if options['fHtml'] == -1:
-        bCleanupFile = True;
-        fHtml = open(filename,'w')
-    else:
-        fHtml = options['fHtml']
-        
-    fHtml.write('<html><body>\n')
-    
-    fHtml.write(options['headerHtml'])
-    
-    # Write out images
-    for iImage,image in enumerate(images):
-        
-        title = image['title']
-        imageStyle = image['imageStyle']
-        textStyle = image['textStyle']
-        filename = image['filename']
-        linkTarget = image['linkTarget']
-        
-        # Remove unicode characters
-        title = title.encode('ascii','ignore').decode('ascii')
-        filename = filename.encode('ascii','ignore').decode('ascii')
-        
-        filename = filename.replace('\\','/')
-        if options['urlEncodeFilenames']:            
-            filename = urllib.parse.quote(filename)
-        
-        if len(title) > 0:       
-            fHtml.write(
-                    '<p style="{}">{}</p>\n'\
-                    .format(textStyle,title))            
-
-        linkTarget = linkTarget.replace('\\','/')
-        if options['urlEncodeLinkTargets']:
-            # These are typically absolute paths, so we only want to mess with certain characters
-            linkTarget = urllib.parse.quote(linkTarget,safe=':/')
-            
-        if len(linkTarget) > 0:
-            fHtml.write('<a href="{}">'.format(linkTarget))
-            # imageStyle.append(';border:0px;')
-        
-        fHtml.write('<img src="{}" style="{}">\n'.format(filename,imageStyle))
-        
-        if len(linkTarget) > 0:
-            fHtml.write('</a>')
-            
-        if iImage != len(images)-1:
-            fHtml.write('<br/>')             
-            
-    # ...for each image we need to write
-    
-    fHtml.write(options['trailerHtml'])
-    
-    fHtml.write('</body></html>\n')
-    
-    if bCleanupFile:
-        fHtml.close()    
-
-# ...function

md_visualization/plot_utils.py

@@ -1,293 +0,0 @@
-"""
-
-plot_utils.py
-
-Utility functions for plotting, particularly for plotting confusion matrices
-and precision-recall curves.
-
-"""
-
-#%% Imports
-
-import numpy as np
-
-# This also imports mpl.{cm, axes, colors}
-import matplotlib.figure
-
-
-#%% Plotting functions
-
-def plot_confusion_matrix(matrix,
-                          classes,
-                          normalize=False,
-                          title='Confusion matrix',
-                          cmap=matplotlib.cm.Blues,
-                          vmax=None,
-                          use_colorbar=True,
-                          y_label=True,
-                          fmt= '{:.0f}',
-                          fig=None):
-    """
-    Plots a confusion matrix.
-
-    Args:
-        matrix (np.ndarray): shape [num_classes, num_classes], confusion matrix
-            where rows are ground-truth classes and columns are predicted classes
-        classes (list of str): class names for each row/column
-        normalize (bool, optional): whether to perform row-wise normalization; 
-            by default, assumes values in the confusion matrix are percentages
-        title (str, optional): figure title
-        cmap (matplotlib.colors.colormap): colormap for cell backgrounds
-        vmax (float, optional), value corresponding to the largest value of the colormap;
-            if None, the maximum value in [matrix] will be used
-        use_colorbar (bool, optional): whether to show colorbar
-        y_label (bool, optional): whether to show class names on the y axis
-        fmt (str): format string for rendering numeric values
-        fig (Figure): existing figure to which we should render, otherwise creates
-            a new figure
-        
-    Returns: 
-        matplotlib.figure.Figure: the figure we rendered to or created
-    """
-    
-    num_classes = matrix.shape[0]
-    assert matrix.shape[1] == num_classes
-    assert len(classes) == num_classes
-
-    normalized_matrix = matrix.astype(np.float64) / (
-        matrix.sum(axis=1, keepdims=True) + 1e-7)
-    if normalize:
-        matrix = normalized_matrix
-
-    fig_h = 3 + 0.3 * num_classes
-    fig_w = fig_h
-    if use_colorbar:
-        fig_w += 0.5
-
-    if fig is None:
-        fig = matplotlib.figure.Figure(figsize=(fig_w, fig_h), tight_layout=True)
-    ax = fig.subplots(1, 1)
-    im = ax.imshow(normalized_matrix, interpolation='nearest', cmap=cmap, vmax=vmax)
-    ax.set_title(title)
-
-    if use_colorbar:
-        cbar = fig.colorbar(im, fraction=0.046, pad=0.04,
-                            ticks=[0.0, 0.25, 0.5, 0.75, 1.0])
-        cbar.set_ticklabels(['0%', '25%', '50%', '75%', '100%'])
-
-    tick_marks = np.arange(num_classes)
-    ax.set_xticks(tick_marks)
-    ax.set_yticks(tick_marks)
-    ax.set_xticklabels(classes, rotation=90)
-    ax.set_xlabel('Predicted class')
-
-    if y_label:
-        ax.set_yticklabels(classes)
-        ax.set_ylabel('Ground-truth class')
-
-    for i, j in np.ndindex(matrix.shape):
-        v = matrix[i, j]        
-        ax.text(j, i, fmt.format(v),
-                horizontalalignment='center',
-                verticalalignment='center',
-                color='white' if normalized_matrix[i, j] > 0.5 else 'black')
-
-    return fig
-
-# ...def plot_confusion_matrix(...)
-
-
-def plot_precision_recall_curve(precisions, 
-                                recalls, 
-                                title='Precision/recall curve',
-                                xlim=(0.0,1.05),
-                                ylim=(0.0,1.05)):
-    """
-    Plots a precision/recall curve given lists of (ordered) precision
-    and recall values.
-
-    Args:
-        precisions (list of float): precision for corresponding recall values,
-            should have same length as [recalls].
-        recalls (list of float): recall for corresponding precision values,
-            should have same length as [precisions].
-        title (str, optional): plot title
-        xlim (tuple, optional): x-axis limits as a length-2 tuple
-        ylim (tuple, optional): y-axis limits as a length-2 tuple
-
-    Returns: 
-        matplotlib.figure.Figure: the (new) figure
-    """
-    
-    assert len(precisions) == len(recalls)
-
-    fig = matplotlib.figure.Figure(tight_layout=True)
-    ax = fig.subplots(1, 1)
-    ax.step(recalls, precisions, color='b', alpha=0.2, where='post')
-    ax.fill_between(recalls, precisions, alpha=0.2, color='b', step='post')
-
-    try:
-        ax.set(x_label='Recall', y_label='Precision', title=title)
-        ax.set(x_lim=xlim, y_lim=ylim)    
-    # 
-    except Exception:
-        ax.set_xlabel('Recall')
-        ax.set_ylabel('Precision')
-        ax.set_title(title)
-        ax.set_xlim(xlim[0],xlim[1])
-        ax.set_ylim(ylim[0],ylim[1])
-        
-    return fig
-
-
-def plot_stacked_bar_chart(data, series_labels=None, col_labels=None,
-                           x_label=None, y_label=None, log_scale=False):
-    """
-    Plot a stacked bar chart, for plotting e.g. species distribution across locations.
-    
-    Reference: https://stackoverflow.com/q/44309507
-
-    Args:
-        data (np.ndarray or list of list): data to plot; rows (series) are species, columns
-            are locations
-        series_labels (list of str, optional): series labels, typically species names
-        col_labels (list of str, optional): column labels, typically location names
-        x_label (str, optional): x-axis label
-        y_label (str, optional): y-axis label
-        log_scale (bool, optional) whether to plot the y axis in log-scale
-
-    Returns: 
-        matplotlib.figure.Figure: the (new) figure
-    """
-    
-    data = np.asarray(data)
-    num_series, num_columns = data.shape
-    ind = np.arange(num_columns)
-
-    fig = matplotlib.figure.Figure(tight_layout=True)
-    ax = fig.subplots(1, 1)
-    colors = matplotlib.cm.rainbow(np.linspace(0, 1, num_series))
-
-    # stacked bar charts are made with each segment starting from a y position
-    cumulative_size = np.zeros(num_columns)
-    for i, row_data in enumerate(data):
-        ax.bar(ind, row_data, bottom=cumulative_size, label=series_labels[i],
-               color=colors[i])
-        cumulative_size += row_data
-
-    if col_labels and len(col_labels) < 25:
-        ax.set_xticks(ind)
-        ax.set_xticklabels(col_labels, rotation=90)
-    elif col_labels:
-        ax.set_xticks(list(range(0, len(col_labels), 20)))
-        ax.set_xticklabels(col_labels, rotation=90)
-
-    if x_label is not None:
-        ax.set_xlabel(x_label)
-    if y_label is not None:
-        ax.set_ylabel(y_label)
-    if log_scale:
-        ax.set_yscale('log')
-
-    # To fit the legend in, shrink current axis by 20%
-    box = ax.get_position()
-    ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
-
-    # Put a legend to the right of the current axis
-    ax.legend(loc='center left', bbox_to_anchor=(0.99, 0.5), frameon=False)
-
-    return fig
-
-
-def calibration_ece(true_scores, pred_scores, num_bins):
-    r"""
-    Expected calibration error (ECE) as defined in equation (3) of
-    Guo et al. "On Calibration of Modern Neural Networks." (2017).
-
-    Implementation modified from sklearn.calibration.calibration_curve()
-    in order to implement ECE calculation. See:
-    
-    https://github.com/scikit-learn/scikit-learn/issues/18268
-
-    Args:
-        true_scores (list of int): true values, length N, binary-valued (0 = neg, 1 = pos)
-        pred_scores (list of float): predicted confidence values, length N, pred_scores[i] is the 
-            predicted confidence that example i is positive
-        num_bins (int): number of bins to use (`M` in eq. (3) of Guo 2017)
-
-    Returns:
-        tuple: a length-three tuple containing:
-            - accs: np.ndarray, shape [M], type float64, accuracy in each bin,
-              M <= num_bins because bins with no samples are not returned        
-            - confs: np.ndarray, shape [M], type float64, mean model confidence in
-              each bin
-            - ece: float, expected calibration error
-    """
-    
-    assert len(true_scores) == len(pred_scores)
-
-    bins = np.linspace(0., 1. + 1e-8, num=num_bins + 1)
-    binids = np.digitize(pred_scores, bins) - 1
-
-    bin_sums = np.bincount(binids, weights=pred_scores, minlength=len(bins))
-    bin_true = np.bincount(binids, weights=true_scores, minlength=len(bins))
-    bin_total = np.bincount(binids, minlength=len(bins))
-
-    nonzero = bin_total != 0
-    accs = bin_true[nonzero] / bin_total[nonzero]
-    confs = bin_sums[nonzero] / bin_total[nonzero]
-
-    weights = bin_total[nonzero] / len(true_scores)
-    ece = np.abs(accs - confs) @ weights
-    return accs, confs, ece
-
-
-def plot_calibration_curve(true_scores, pred_scores, num_bins,
-                           name='calibration', plot_perf=True, plot_hist=True,
-                           ax=None, **fig_kwargs):
-    """
-    Plots a calibration curve.
-
-    Args:
-        true_scores (list of int): true values, length N, binary-valued (0 = neg, 1 = pos)
-        pred_scores (list of float): predicted confidence values, length N, pred_scores[i] is the 
-            predicted confidence that example i is positive
-        num_bins (int): number of bins to use (`M` in eq. (3) of Guo 2017)
-        name (str, optional): label in legend for the calibration curve
-        plot_perf (bool, optional): whether to plot y=x line indicating perfect calibration
-        plot_hist (bool, optional): whether to plot histogram of counts
-        ax (Axes, optional): if given then no legend is drawn, and fig_kwargs are ignored
-        fig_kwargs (dict, optional): only used if [ax] is None
-
-    Returns:
-        matplotlib.figure.Figure: the (new) figure
-    """
-    
-    accs, confs, ece = calibration_ece(true_scores, pred_scores, num_bins)
-
-    created_fig = False
-    if ax is None:
-        created_fig = True
-        fig = matplotlib.figure.Figure(**fig_kwargs)
-        ax = fig.subplots(1, 1)
-    ax.plot(confs, accs, 's-', label=name)  # 's-': squares on line
-    ax.set(xlabel='Model confidence', ylabel='Actual accuracy',
-           title=f'Calibration plot (ECE: {ece:.02g})')
-    ax.set(xlim=[-0.05, 1.05], ylim=[-0.05, 1.05])
-    if plot_perf:
-        ax.plot([0, 1], [0, 1], color='black', label='perfect calibration')
-    ax.grid(True)
-
-    if plot_hist:
-        ax1 = ax.twinx()
-        bins = np.linspace(0., 1. + 1e-8, num=num_bins + 1)
-        counts = ax1.hist(pred_scores, alpha=0.5, label='histogram of examples',
-                          bins=bins, color='tab:red')[0]
-        max_count = np.max(counts)
-        ax1.set_ylim([-0.05 * max_count, 1.05 * max_count])
-        ax1.set_ylabel('Count')
-
-    if created_fig:
-        fig.legend(loc='upper left', bbox_to_anchor=(0.15, 0.85))
-
-    return ax.figure