Changeset 608

Timestamp:

09/01/16 17:01:37 (8 years ago)

Author:

Maciej Komosinski

Message:

Displays the fraction of variance preserved after MDS

File:

• mds-and-trees/mds_plot.py (modified) (5 diffs)

mds-and-trees/mds_plot.py

@@ -78 +78 @@
                 firstsquarecolumn=distances.shape[1]-minsize
                 distances = np.array([row[firstsquarecolumn:] for row in distances]) #this can only fix matrices with more columns than rows
-                print("Making it square:",distances.shape)
+                print("Made the matrix square:",distances.shape)
 
                 #if the file has more columns than rows, assume the first extra column on the left of the square matrix has labels
@@ -93 +93 @@
 
         variances = [np.var(embed[:,i]) for i in range(len(embed[0]))]
-        percent_variances = [sum(variances[:i+1])/sum(variances) for i in range(len(variances))]
-        for i,pv in enumerate(percent_variances):
+        variances_fraction = [sum(variances[:i+1])/sum(variances) for i in range(len(variances))]
+        for i,pv in enumerate(variances_fraction):
                 print("In",i+1,"dimensions:",pv)
 
@@ -100 +100 @@
         embed = np.asarray([embed[:,i] for i in range(dim)]).T
 
-        return embed
+        return embed, variances_fraction[dim-1]
 
 
-def plot(coordinates, labels, dimensions, jitter=0, outname=""):
+def plot(coordinates, labels, dimensions, variance_fraction, jitter=0, outname=""):
         fig = plt.figure()
 
@@ -138 +138 @@
 
 
-        plt.title('Phenotypes distances') #TODO add % variance information
+        plt.title('Projection of phenotype distances, variance preserved = %.1f%%' % (variance_fraction*100))
         plt.tight_layout()
         plt.axis('tight')
@@ -151 +151 @@
 def main(filename, dimensions=3, outname="", jitter=0, separator='\t'):
         distances,labels = read_file(filename, separator)
-        embed = compute_mds(distances, dimensions)
+        embed,variance_fraction = compute_mds(distances, dimensions)
 
         if dimensions == 1:
                 embed = np.array([np.insert(e, 0, 0, axis=0) for e in embed])
         
-        plot(embed, labels, dimensions, jitter, outname)
+        plot(embed, labels, dimensions, variance_fraction, jitter, outname)