ups

scripts/lpls/plots_lpls.py

@@ -1,6 +1,7 @@
 import pylab
 import matplotlib
 import networkx as nx
+import scipy
 
 def plot_corrloads(R, pc1=0,pc2=1,s=20, c='b', zorder=5,expvar=None,ax=None,drawback=True, labels=None):
     """ Correlation loading plot."""
@@ -56,3 +57,31 @@ def plot_dag(edge_dict, node_color='b', node_size=30,labels=None,nodelist=None,p
         
     nx.draw_networkx(G,pos, with_labels=with_labels, node_size=node_size, node_color=node_color, nodelist=nodelist)
     
+
+def plot_ZXcorr(gene_ids, term_ids, gene2go, X, D, scale=True):
+    """ Plot correlation/covariance between genes as a function of
+    semantic difference.
+
+    input: X (n, p) data matrix
+           D (p, p) gene-gene sematic similarity matrix
+    """
+    D = scipy.corrcoef(X)
+    term2ind = dict(enumerate(term_ids))
+    for i, gene_i in enumerate(gene_ids):
+        for j, gene_j in enumerate(gene_ids):
+            if j<i:
+                r2 = D[i,j]
+                terms_i = gene2go[gene_i]
+                terms_j = gene2go[gene_j]
+                for ti, term in enumerate(term_ids):
+                    if term in terms_i:
+                        pass
+
+
+def clustering_index(T, Yg):
+    pass
+                
+                
+                
+                
+