MRG: make sourmash plot labels/indices arguments make sense

doc/command-line.md

@@ -259,15 +259,18 @@ sourmash plot <matrix_file>
 ```
 
 Options:
-```
---pdf -- output PDF files.
---labels -- display the signature names (by default, the filenames) on the plot
---indices -- turn off index display on the plot.
---vmax -- maximum value (default 1.0) for heatmap.
---vmin -- minimum value (default 0.0) for heatmap.
---subsample=<N> -- plot a maximum of <N> samples, randomly chosen.
---subsample-seed=<seed> -- seed for pseudorandom number generator.
-```
+* `--pdf` -- output PDF files. (defaults to PNG)
+* `--labels` -- display the signature names on the plot (default)
+* `--indices` -- turn on index display on the plot.
+* `--vmax` -- maximum value (default 1.0) for heatmap.
+* `--vmin` -- minimum value (default 0.0) for heatmap.
+* `--subsample=<N>` -- plot a maximum of <N> samples, randomly chosen.
+* `--subsample-seed=<seed>` -- seed for pseudorandom number generator.
+
+Example command lines for label and index display -
+
+* `--indices` will show only numbers;
+* `--no-labels --no-indices` will remove all labels!
 
 Example output:
 

doc/plotting-compare.ipynb

@@ -51,70 +51,22 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "\u001b[K\r\n",
-      "== This is sourmash version 4.8.2. ==\r\n",
-      "\r",
-      "\u001b[K== Please cite Brown and Irber (2016), doi:10.21105/joss.00027. ==\r\n",
-      "\r\n",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR2060939_1.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR2060939_1.sig'\r",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR2060939_2.sig'\r",
-      "\r",
-      "\u001b[K<<<igs so far. Now reading from file '../tests/test-data/demo/SRR2060939_2.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR2060939_2.sig'\r",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR2241509_1.sig'\r",
-      "\r",
-      "\u001b[K<<<igs so far. Now reading from file '../tests/test-data/demo/SRR2241509_1.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR2241509_1.sig'\r",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR2255622_1.sig'\r",
-      "\r",
-      "\u001b[K<<<igs so far. Now reading from file '../tests/test-data/demo/SRR2255622_1.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR2255622_1.sig'\r",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR453566_1.sig'\r",
-      "\r",
-      "\u001b[K<<<sigs so far. Now reading from file '../tests/test-data/demo/SRR453566_1.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR453566_1.sig'\r",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR453569_1.sig'\r",
-      "\r",
-      "\u001b[K<<<sigs so far. Now reading from file '../tests/test-data/demo/SRR453569_1.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR453569_1.sig'\r",
-      "\r",
-      "\u001b[Kloading '../tests/test-data/demo/SRR453570_1.sig'\r",
-      "\r",
-      "\u001b[K<<<sigs so far. Now reading from file '../tests/test-data/demo/SRR453570_1.sig'\r",
-      "\r",
-      "\u001b[KLoaded 1 sigs from '../tests/test-data/demo/SRR453570_1.sig'\r",
-      "\r",
-      "\u001b[K                                                                               \r",
-      "\r",
-      "\u001b[Kloaded 7 signatures total.\r\n",
-      "\r",
-      "\u001b[K\r\n",
-      "0-SRR2060939_1.fa...\t[1.    0.356 0.078 0.086 0.    0.    0.   ]\r\n",
-      "1-SRR2060939_2.fa...\t[0.356 1.    0.072 0.078 0.    0.    0.   ]\r\n",
-      "2-SRR2241509_1.fa...\t[0.078 0.072 1.    0.074 0.    0.    0.   ]\r\n",
-      "3-SRR2255622_1.fa...\t[0.086 0.078 0.074 1.    0.    0.    0.   ]\r\n",
-      "4-SRR453566_1.fas...\t[0.    0.    0.    0.    1.    0.382 0.364]\r\n",
-      "5-SRR453569_1.fas...\t[0.    0.    0.    0.    0.382 1.    0.386]\r\n",
-      "6-SRR453570_1.fas...\t[0.    0.    0.    0.    0.364 0.386 1.   ]\r\n",
-      "min similarity in matrix: 0.000\r\n",
-      "\r",
-      "\u001b[Ksaving labels to: compare-demo.labels.txt\r\n",
-      "\r",
-      "\u001b[Ksaving comparison matrix to: compare-demo\r\n"
+      "\u001b[K\n",
+      "== This is sourmash version 4.8.5.dev0. ==\n",
+      "\u001b[K== Please cite Brown and Irber (2016), doi:10.21105/joss.00027. ==\n",
+      "\n",
+      "\u001b[Kloaded 7 signatures total.                                                     \n",
+      "\u001b[K\n",
+      "0-SRR2060939_1.fa...\t[1.    0.356 0.078 0.086 0.    0.    0.   ]\n",
+      "1-SRR2060939_2.fa...\t[0.356 1.    0.072 0.078 0.    0.    0.   ]\n",
+      "2-SRR2241509_1.fa...\t[0.078 0.072 1.    0.074 0.    0.    0.   ]\n",
+      "3-SRR2255622_1.fa...\t[0.086 0.078 0.074 1.    0.    0.    0.   ]\n",
+      "4-SRR453566_1.fas...\t[0.    0.    0.    0.    1.    0.382 0.364]\n",
+      "5-SRR453569_1.fas...\t[0.    0.    0.    0.    0.382 1.    0.386]\n",
+      "6-SRR453570_1.fas...\t[0.    0.    0.    0.    0.364 0.386 1.   ]\n",
+      "min similarity in matrix: 0.000\n",
+      "\u001b[Ksaving labels to: compare-demo.labels.txt\n",
+      "\u001b[Ksaving comparison matrix to: compare-demo\n"
      ]
     }
    ],
@@ -266,10 +218,15 @@
    "source": [
     "import scipy.cluster.hierarchy as sch\n",
     "\n",
-    "def plot_composite_matrix(D, labeltext, show_labels=True, show_indices=True,\n",
+    "def plot_composite_matrix(D, labeltext, show_labels=True,\n",
     "                          vmax=1.0, vmin=0.0, force=False):\n",
     "    \"\"\"Build a composite plot showing dendrogram + distance matrix/heatmap.\n",
-    "    Returns a matplotlib figure.\"\"\"\n",
+    "\n",
+    "    Returns a matplotlib figure.\n",
+    "\n",
+    "    If show_labels is True, display labels. Otherwise, no labels are\n",
+    "    shown on the plot.\n",
+    "    \"\"\"\n",
     "    if D.max() > 1.0 or D.min() < 0.0:\n",
     "        error('This matrix doesn\\'t look like a distance matrix - min value {}, max value {}', D.min(), D.max())\n",
     "        if not force:\n",
@@ -288,12 +245,8 @@
     "    # plot dendrogram\n",
     "    Y = sch.linkage(D, method='single')  # centroid\n",
     "\n",
-    "    dendrolabels = labeltext\n",
-    "    if not show_labels:\n",
-    "        dendrolabels = [str(i) for i in range(len(labeltext))]\n",
-    "\n",
-    "    Z1 = sch.dendrogram(Y, orientation='left', labels=dendrolabels,\n",
-    "                        no_labels=not show_indices)\n",
+    "    Z1 = sch.dendrogram(Y, orientation='left', labels=labeltext,\n",
+    "                        no_labels=not show_labels, get_leaves=True)\n",
     "    ax1.set_xticks([])\n",
     "\n",
     "    xstart = 0.45\n",
@@ -302,15 +255,17 @@
     "        xstart = 0.315\n",
     "    scale_xstart = xstart + width + 0.01\n",
     "\n",
-    "    # plot matrix\n",
-    "    axmatrix = fig.add_axes([xstart, 0.1, width, 0.6])\n",
-    "\n",
-    "    # (this reorders D by the clustering in Z1)\n",
+    "    # re-order labels along rows, top to bottom\n",
     "    idx1 = Z1['leaves']\n",
+    "    reordered_labels = [ labeltext[i] for i in idx1 ]\n",
+    "\n",
+    "    # reorder D by the clustering in the dendrogram\n",
     "    D = D[idx1, :]\n",
     "    D = D[:, idx1]\n",
     "\n",
     "    # show matrix\n",
+    "    axmatrix = fig.add_axes([xstart, 0.1, width, 0.6])\n",
+    "\n",
     "    im = axmatrix.matshow(D, aspect='auto', origin='lower',\n",
     "                          cmap=pylab.cm.YlGnBu, vmin=vmin, vmax=vmax)\n",
     "    axmatrix.set_xticks([])\n",
@@ -320,7 +275,7 @@
     "    axcolor = fig.add_axes([scale_xstart, 0.1, 0.02, 0.6])\n",
     "    pylab.colorbar(im, cax=axcolor)\n",
     "\n",
-    "    return fig"
+    "    return fig, reordered_labels, D"
    ]
   },
   {
@@ -342,6 +297,13 @@
    "source": [
     "_ = plot_composite_matrix(matrix, labels)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

src/sourmash/cli/plot.py

@@ -10,16 +10,24 @@ def subparser(subparsers):
         help='output PDF; default is PNG'
     )
     subparser.add_argument(
-        '--labels', action='store_true',
+        '--labels', action='store_true', default=None,
         help='show sample labels on dendrogram/matrix'
     )
+    subparser.add_argument(
+        '--no-labels', action='store_false', dest='labels',
+        help='do not show sample labels'
+    )
     subparser.add_argument(
         '--labeltext',
-        help='filename containing list of labels (overrides signature names)'
+        help='filename containing list of labels (overrides signature names); implies --labels'
+    )
+    subparser.add_argument(
+        '--indices', action='store_true', default=None,
+        help='show sample indices but not labels; overridden by --labels'
     )
     subparser.add_argument(
-        '--indices', action='store_false',
-        help='show sample indices but not labels'
+        '--no-indices', action='store_false', dest='indices',
+        help='do not show sample indices'
     )
     subparser.add_argument(
         '--vmin', default=0.0, type=float,

src/sourmash/commands.py

@@ -246,39 +246,55 @@ def plot(args):
 
     # load files
     D_filename = args.distances
-    labelfilename = D_filename + '.labels.txt'
 
     notify(f'loading comparison matrix from {D_filename}...')
     D = numpy.load(open(D_filename, 'rb'))
     # not sure how to change this to use f-strings
     notify('...got {} x {} matrix.', *D.shape)
 
-    if args.labeltext:
-        labelfilename = args.labeltext
-    notify(f'loading labels from {labelfilename}')
-    labeltext = [ x.strip() for x in open(labelfilename) ]
-    if len(labeltext) != D.shape[0]:
-        error('{} labels != matrix size, exiting', len(labeltext))
-        sys.exit(-1)
-
-    # build filenames, decide on PDF/PNG output
-    dendrogram_out = os.path.basename(D_filename) + '.dendro'
-    if args.pdf:
-        dendrogram_out += '.pdf'
+    # see sourmash#2790 for details :)
+    if args.labeltext or args.labels:
+        display_labels = True
+        args.labels = True      # override => labels always true
+    elif args.labels is None and not args.indices:
+        # default to labels
+        args.labels = True
+        display_labels = True
+    elif args.indices or (not args.labels and args.indices is None):
+        # turn on indices only, not label names
+        args.indices = True
+        display_labels = True
     else:
-        dendrogram_out += '.png'
+        display_labels = False
 
-    matrix_out = os.path.basename(D_filename) + '.matrix'
-    if args.pdf:
-        matrix_out += '.pdf'
+    if args.labels:
+        if args.labeltext:
+            labelfilename = args.labeltext
+        else:
+            labelfilename = D_filename + '.labels.txt'
+
+        notify(f'loading labels from {labelfilename}')
+        labeltext = [ x.strip() for x in open(labelfilename) ]
+
+        if len(labeltext) != D.shape[0]:
+            error('{} labels != matrix size, exiting', len(labeltext))
+            sys.exit(-1)
+    elif args.indices:
+        # construct integer labels
+        labeltext = [str(i + 1) for i in range(D.shape[0])]
     else:
-        matrix_out += '.png'
+        assert not display_labels
+        labeltext = [""] * D.shape[0]
 
-    hist_out = os.path.basename(D_filename) + '.hist'
     if args.pdf:
-        hist_out += '.pdf'
+        ext = '.pdf'
     else:
-        hist_out += '.png'
+        ext = '.png'
+
+    # build filenames, decide on PDF/PNG output
+    dendrogram_out = os.path.basename(D_filename) + '.dendro' + ext
+    matrix_out = os.path.basename(D_filename) + '.matrix' + ext
+    hist_out = os.path.basename(D_filename) + '.hist' + ext
 
     # output to a different directory?
     if args.output_dir:
@@ -314,14 +330,14 @@ def plot(args):
 
     ### do clustering
     Y = sch.linkage(D, method='single')
-    sch.dendrogram(Y, orientation='right', labels=labeltext)
+    sch.dendrogram(Y, orientation='right', labels=labeltext,
+                   no_labels=not display_labels)
     fig.savefig(dendrogram_out)
     notify(f'wrote dendrogram to: {dendrogram_out}')
 
     ### make the dendrogram+matrix:
     (fig, rlabels, rmat) = sourmash_fig.plot_composite_matrix(D, labeltext,
-                                             show_labels=args.labels,
-                                             show_indices=args.indices,
+                                             show_labels=display_labels,
                                              vmin=args.vmin,
                                              vmax=args.vmax,
                                              force=args.force)

src/sourmash/fig.py

@@ -1,6 +1,6 @@
 #! /usr/bin/env python
 """
-Make plots using the distance matrix+labels output by ``sourmash compare``.
+Make plots using the distance matrix+labels output by `sourmash compare`.
 """
 from .logging import error, notify
 try:
@@ -20,11 +20,15 @@ def load_matrix_and_labels(basefile):
     return (D, labeltext)
 
 
-def plot_composite_matrix(D, labeltext, show_labels=True, show_indices=True,
+def plot_composite_matrix(D, labeltext, show_labels=True,
                           vmax=1.0, vmin=0.0, force=False):
     """Build a composite plot showing dendrogram + distance matrix/heatmap.
 
-    Returns a matplotlib figure."""
+    Returns a matplotlib figure.
+
+    If show_labels is True, display labels. Otherwise, no labels are
+    shown on the plot.
+    """
     if D.max() > 1.0 or D.min() < 0.0:
         error('This matrix doesn\'t look like a distance matrix - min value {}, max value {}', D.min(), D.max())
         if not force:
@@ -43,12 +47,8 @@ def plot_composite_matrix(D, labeltext, show_labels=True, show_indices=True,
     # plot dendrogram
     Y = sch.linkage(D, method='single')  # centroid
 
-    dendrolabels = labeltext
-    if not show_labels:
-        dendrolabels = [str(i) for i in range(len(labeltext))]
-
-    Z1 = sch.dendrogram(Y, orientation='left', labels=dendrolabels,
-                        no_labels=not show_indices, get_leaves=True)
+    Z1 = sch.dendrogram(Y, orientation='left', labels=labeltext,
+                        no_labels=not show_labels, get_leaves=True)
     ax1.set_xticks([])
 
     xstart = 0.45