Changeset 607 for mds-and-trees/mds_plot.py

Timestamp:

09/01/16 16:39:23 (8 years ago)

Author:

Maciej Komosinski

Message:

Updated for new format of dissimilarity matrix (with the optional two extra columns on the left, compatible with Framsticks CLI and GUI)

File:

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

mds-and-trees/mds_plot.py

@@ -72 +72 @@
         if (distances.shape[0]!=distances.shape[1]):
                 print("Matrix is not square:",distances.shape)
+        if (distances.shape[0]>distances.shape[1]):
+                raise ValueError('More rows than columns?')
+        if (distances.shape[0]<distances.shape[1]):
                 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
+                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)
 
-        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')])
+                #if the file has more columns than rows, assume the first extra column on the left of the square matrix has labels
+                labels = np.genfromtxt(fname, delimiter=separator, usecols=firstsquarecolumn-1,dtype=[('label','S10')])
                 labels = [label[0].decode("utf-8") for label in labels] 
-        except ValueError:
+        else:
                 labels = None #no labels
         
@@ -116 +120 @@
         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
+                labelconvert={'velland':'V','velwat':'W','vpp':'P','vpa':'A'} #use this if you want to replace long names with short IDs
                 #for point in points:
                 #       print(point)
@@ -134 +138 @@
 
 
-        plt.title('Phenotypes distances')
+        plt.title('Phenotypes distances') #TODO add % variance information
         plt.tight_layout()
         plt.axis('tight')
@@ -140 +144 @@
         if outname == "":
                 plt.show()
-
         else:
                 plt.savefig(outname+".pdf")
@@ -159 +162 @@
         parser = argparse.ArgumentParser()
         parser.add_argument('--in', dest='input', required=True, help='input file with dissimilarity matrix')
-        parser.add_argument('--out', dest='output', required=False, help='output file name without extension')
+        parser.add_argument('--out', dest='output', required=False, help='output file name (without extension)')
         parser.add_argument('--dim', required=False, help='number of dimensions of the new space')
         parser.add_argument('--sep', required=False, help='separator of the source file')