From 237e17d91b8d0afe5c4a0867af7475e137788c74 Mon Sep 17 00:00:00 2001
From: Steve Schmerler <git@elcorto.com>
Date: Tue, 27 Dec 2016 02:35:54 +0100
Subject: [PATCH] ENH: use resized files by default in bin/10fingerprints.py

---
 README.rst            | 25 ++++++++++++++++---------
 bin/10fingerprints.py | 11 ++++++++---
 bin/20cluster.py      |  1 +
 3 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/README.rst b/README.rst
index cb0cc53..87a09ef 100644
--- a/README.rst
+++ b/README.rst
@@ -28,23 +28,30 @@ This will resize all images to 20% (factor 0.2) of their original size. Resized
 files are written to ``~/.imgcmp/convert/`` by default. Now, calculate the
 fingerprint database::
 
-    $ ./bin/10fingerprints.py ~/.imgcmp/convert/*
+    $ ./bin/10fingerprints.py 
 
-This creates a file ``~/.imgcmp/fingerprints.hdf`` (HDF5 file format). Last,
-cluster images by using a similarity index (``0.3`` below). A small index means
-to put only very similar images in one cluster. The extreme case 0.0 means to
-allow zero dissimilarity and thus put each image in a cluster of size 1. In
-contrast, large values imply less strict clustering and will put more but less
-similar images in a cluster. A value of 1.0 is equal to putting all images in
-one single cluster (e.g. all are treated as equal)::
+This uses all files in ``~/.imgcmp/convert/*`` by default. Alternatively,
+specify all images on the command line. It creates a file
+``~/.imgcmp/fingerprints.hdf`` (HDF5 file format, fingerprint database). 
+
+Last, we will cluster the images (actually their fingerprints) by using a
+similarity index ( ``0..1``, ``0.3`` below). The index can be thought of as the
+allowed *dissimilarity*. A small index means to put only very similar images in
+one cluster. The extreme case 0.0 means to allow zero dissimilarity and thus
+put each image in a cluster of size 1. In contrast, large values imply less
+strict clustering and will put more but less similar images in a cluster. A
+value of 1.0 is equal to putting all images in one single cluster (e.g. all
+images are treated as equal)::
 
     $ ./bin/20cluster.py 0.3
+    cluster dir: /home/user/.imgcmp/cluster
     items per cluster : number of such clusters
     2 : 41
     3 : 2
     4 : 2
 
-Have a look at the clusters (as dirs with symlinks to the relevant files)::
+By default, the database ``~/.imgcmp/fingerprints.hdf`` is used. Have a look at
+the clusters (as dirs with symlinks to the relevant files)::
 
     $ ls ~/.imgcmp/cluster/
     cluster_with_2  cluster_with_3  cluster_with_4
diff --git a/bin/10fingerprints.py b/bin/10fingerprints.py
index 09ff525..66d738f 100755
--- a/bin/10fingerprints.py
+++ b/bin/10fingerprints.py
@@ -1,9 +1,11 @@
 #!/usr/bin/python3
 
-import sys, multiprocessing, functools, argparse
+import sys, multiprocessing, functools, argparse, os
 from PIL import Image
 from imgcmp import calc, io, cli, env
 import numpy as np
+pj = os.path.join
+
 
 def _worker(tup, size_x=None, fpsdct=None):
     ii, name = tup     
@@ -19,8 +21,11 @@ def _worker(tup, size_x=None, fpsdct=None):
 Calculate fingerprint database.    
 """
     parser = argparse.ArgumentParser(description=desc) 
-    parser.add_argument('files', metavar='FILE', nargs='+',
-                        help='image file names')
+    parser.add_argument('files', metavar='FILE', nargs='*',
+                        default=[pj(cli.convert_dr, x) for x in \
+                                 os.listdir(cli.convert_dr)],
+                        help='image file names, [default: '
+                             '{}/*]'.format(cli.convert_dr))
     parser.add_argument('-x', dest='size_x',
                         default=8, type=int,
                         help='resize images to (size_x, size_x), fingerprints '
diff --git a/bin/20cluster.py b/bin/20cluster.py
index 6988636..a016780 100755
--- a/bin/20cluster.py
+++ b/bin/20cluster.py
@@ -48,6 +48,7 @@
         else:    
             cdct_multi[nn].append(x)
 
+    print("cluster dir: {}".format(cli.cluster_dr))
     print("items per cluster : number of such clusters")
     shutil.rmtree(cli.cluster_dr)
     for n_in_cluster in np.sort(list(cdct_multi.keys())):