From 1cafed32e87d95847d8d100f06124e7f312a7b9b Mon Sep 17 00:00:00 2001
From: Steve Schmerler <git@elcorto.com>
Date: Mon, 18 Feb 2019 01:04:27 +0100
Subject: [PATCH] ENH: Add optional PCA before clustering in main

---
 examples/example_main.py |  2 +-
 imagecluster/main.py     | 17 ++++++++++++++++-
 requirements.txt         |  1 +
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/examples/example_main.py b/examples/example_main.py
index 7a98755..7b0783c 100644
--- a/examples/example_main.py
+++ b/examples/example_main.py
@@ -1,3 +1,3 @@
 from imagecluster import main
 
-main.main('pics/', sim=0.65, vis=True, maxelem=30)
+main.main('pics/', sim=0.65, vis=True, maxelem=10, pca=True)
diff --git a/imagecluster/main.py b/imagecluster/main.py
index 3a7a72e..271fadb 100644
--- a/imagecluster/main.py
+++ b/imagecluster/main.py
@@ -1,4 +1,8 @@
 import os
+from collections import OrderedDict
+
+import numpy as np
+from sklearn.decomposition import PCA
 
 from imagecluster import calc as ic
 from imagecluster import common as co
@@ -11,7 +15,7 @@
 
 
 def main(imagedir, sim=0.5, layer='fc2', size=(224,224), links=True, vis=False,
-         maxelem=None):
+         maxelem=None, pca=False, pca_params=dict(n_components=0.9)):
     """Example main app using this library.
 
     Upon first invocation, the image and fingerprint databases are built and
@@ -40,6 +44,10 @@ def main(imagedir, sim=0.5, layer='fc2', size=(224,224), links=True, vis=False,
         plot images in clusters
     maxelem : max number of images per cluster for visualization (see
         :mod:`~postproc`)
+    pca : bool
+        Perform PCA on fingerprints before clustering, using `pca_params`.
+    pca_params : dict
+        kwargs to sklearn's PCA
 
     Notes
     -----
@@ -67,6 +75,13 @@ def main(imagedir, sim=0.5, layer='fc2', size=(224,224), links=True, vis=False,
     else:
         print(f"loading fingerprints database {fps_fn} ...")
         fps = co.read_pk(fps_fn)
+    if pca:
+        # Yes in recent Pythons, dicts are ordered in CPython, but still.
+        _fps = OrderedDict(fps)
+        X = np.array(list(_fps.values()))
+        Xp = PCA(**pca_params).fit(X).transform(X)
+        fps = {k:v for k,v in zip(_fps.keys(), Xp)}
+        print("pca dims:", Xp.shape[1])
     print("clustering ...")
     clusters = ic.cluster(fps, sim)
     if links:
diff --git a/requirements.txt b/requirements.txt
index 0c2b6d4..613413b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,3 +2,4 @@ numpy
 tensorflow
 keras
 Pillow
+scikit-learn