Changeset 602

Timestamp:

08/28/16 17:00:05 (8 years ago)

Author:

Maciej Komosinski

Message:

• More flexible reading of distance matrices from files
• Can also read labels for individual points and display them

File:

• mds-and-trees/mds_plot.py (modified) (6 diffs)

mds-and-trees/mds_plot.py

@@ -4 +4 @@
 import sys
 import numpy as np
-from sklearn import manifold
+#from sklearn import manifold #was needed for manifold MDS http://scikit-learn.org/stable/auto_examples/manifold/plot_compare_methods.html
 
 #to make it work in console, http://stackoverflow.com/questions/2801882/generating-a-png-with-matplotlib-when-display-is-undefined
@@ -70 +70 @@
 def read_file(fname, separator):
         distances = np.genfromtxt(fname, delimiter=separator)
-        if np.isnan(distances[0][len(distances[0])-1]):#separator after the last element in row
-                distances = np.array([row[:-1] for row in distances])
-        return distances
+        if (distances.shape[0]!=distances.shape[1]):
+                print("Matrix is not square:",distances.shape)
+                minsize = min(distances.shape[0],distances.shape[1])
+                distances = np.array([row[:minsize] for row in distances]) #this can only fix matrices with more columns than rows
+                print("Making it square:",distances.shape)
+
+        try: #maybe the file has more columns than rows, and the extra column has labels?
+                labels = np.genfromtxt(fname, delimiter=separator, usecols=distances.shape[0],dtype=[('label','S10')])
+                labels = [label[0].decode("utf-8") for label in labels] 
+        except ValueError:
+                labels = None #no labels
+        
+        return distances,labels
 
 
@@ -89 +99 @@
 
 
-def plot(coordinates, dimensions, jitter=0, outname=""):
+def plot(coordinates, labels, dimensions, jitter=0, outname=""):
         fig = plt.figure()
 
@@ -102 +112 @@
         y_dim = len(coordinates)
 
-        ax.scatter(*[add_jitter(coordinates[:, i]) for i in range(x_dim)], alpha=0.5)
+        points = [add_jitter(coordinates[:, i]) for i in range(x_dim)]
+        
+        if labels is not None and dimensions==2:
+                ax.scatter(*points, alpha=0.1) #barely visible points, because we will show labels anyway
+                labelconvert={'vel':'V','vpp':'P','vpa':'A'} #use this if you want to replace long names with short IDs
+                #for point in points:
+                #       print(point)
+                for label, x, y in zip(labels, points[0], points[1]):
+                        #if label not in knownlabels:
+                        #       knownlabels.append(label)
+                        #       colors.append('#ff0000')
+                        for key in labelconvert:
+                                if label.startswith(key):
+                                        label=labelconvert[key]
+                        plt.annotate(
+                                label, 
+                                xy = (x, y), xytext = (0, 0),
+                                textcoords = 'offset points', ha = 'center', va = 'center',
+                                #bbox = dict(boxstyle = 'round,pad=0.5', fc = 'yellow', alpha = 0.5),
+                                #arrowprops = dict(arrowstyle = '->', connectionstyle = 'arc3,rad=0')
+                                )
+        else:
+                ax.scatter(*points, alpha=0.5)
+
 
         plt.title('Phenotypes distances')
@@ -118 +151 @@
 def main(filename, dimensions=3, outname="", jitter=0, separator='\t'):
         dimensions = int(dimensions)
-        distances = read_file(filename, separator)
+        distances,labels = read_file(filename, separator)
         embed = compute_mds(distances, dimensions)
 
@@ -124 +157 @@
                 embed = np.array([np.insert(e, 0, 0, axis=0) for e in embed])
         
-        plot(embed, dimensions, jitter, outname)
+        plot(embed, labels, dimensions, jitter, outname)