WIP: diff graph with sub graph, before and after model correction

diff_comparison.py

@@ -78,6 +78,22 @@ def spatial_graph(adata):
         weight[e] = math.sqrt(sum(map(abs, pos[e.source()].a - pos[e.target()].a)))**2
     return g, weight
 
+
+def plot_graph_diff(G, c, fig, ax, name):
+    pos = G.vp["pos"]
+    x = []
+    y = []
+    for v in G.vertices():
+        ver = pos[v]
+        if ver[0] > 0.33 and ver[0] <= 0.66 and ver[1] > 0.33 and ver[1] <= 0.66:
+            x.append(ver[0])
+            y.append(ver[1])
+
+    sc = ax.scatter(x, y, s=1, cmap=plt.cm.plasma, c=c) # map closeness values as color mapping on the verticies
+    ax.set_title(name)
+    fig.colorbar(sc, ax=ax)
+
+
 def apply(g, seed, weight, convex_hull, ax, method, method_name):
     # calculate centrality values
     vp = None
@@ -207,9 +223,66 @@ fig.savefig(f"Diff_scores.svg", format='svg')
 print(f"Closeness: {vp_closeness}")
 print(f"Closeness corrected: {vp_closeness_corrected}")
 
-keys = iter(vp_closeness_corrected.a)
+sub_keys = iter(g_sub.vertices())
+keys = iter(g.vertices())
 
-for key in keys:
-    # NOTE I think that the key's are not referencing the exact same point between the two centrality values!
-    delta = vp_closeness[key] - vp_closeness_corrected[key]
-    print(f"original: {vp_closeness[key]} | corrected: {vp_closeness_corrected[key]} | delta: {delta}")
+scores = []
+sub_scores = []
+
+for sub_key in sub_keys:
+    key = next(keys)
+    position = g.vp["pos"][key]
+    while not (position[0] > 0.33 and position[0] <= 0.66 and position[1] > 0.33 and position[1] <= 0.66):
+        key = next(keys)
+        position = g.vp["pos"][key]
+    # NOTE print corresponding position (which are identical)
+    # position = g.vp["pos"][key]
+    # sub_position = g_sub.vp["pos"][sub_key]
+    # print(f"position: {position} | sub_position: {sub_position}")
+
+    value = vp_closeness[key]
+    sub_value = vp_closeness_corrected[sub_key]
+    scores.append(value)
+    sub_scores.append(sub_value)
+    # print(f"value: {value} | sub_value: {sub_value}")
+    # TODO what do I want to know?
+    # - median score comparison?
+    # - max delta's between scores
+    # - improvement compared to with and without correction?
+
+# TODO can I create the scatter graph with the points with their corresponding values?
+median_score = np.median(scores)
+median_sub_score = np.median(sub_scores)
+print(f"median score: {median_score}")
+print(f"median sub_score: {median_sub_score}")
+print(f"median delta: {(median_score - median_sub_score)}")
+print("")
+
+max_value_score = np.max(scores)
+max_value_sub_score = np.max(sub_scores)
+print(f"max value score: {max_value_score}")
+print(f"max value sub_score: {max_value_sub_score}")
+print(f"max value delta: {(max_value_score - max_value_sub_score)}")
+print("")
+
+min_value_score = np.min(scores)
+min_value_sub_score = np.min(sub_scores)
+print(f"min value score: {min_value_score}")
+print(f"min value sub_score: {min_value_sub_score}")
+print(f"min value delta: {(min_value_score - min_value_sub_score)}")
+
+
+fig = plt.figure(figsize=(35, 10))
+plot_graph_ax, plot_sub_graph_ax, plot_sub_graph_before_ax = fig.subplots(1, 3)
+
+plot_graph_diff(g, scores, fig, plot_graph_ax, "Original Graph (region of sub graph)")
+plot_graph_diff(g, sub_scores, fig, plot_sub_graph_ax, "Sub Graph (extracted region of original graph) with correction")
+
+vp = closeness(g_sub, weight=weight_sub)
+vp.a = np.nan_to_num(vp.a) # correct floating point values
+# normalization
+min_val, max_val = vp.a.min(), vp.a.max()
+vp.a = (vp.a - min_val) / (max_val - min_val)
+plot_graph_diff(g, vp.a, fig, plot_sub_graph_before_ax, "Sub Graph (extracted region of original graph) without correction")
+
+fig.savefig(f"Diff_graph_scatter.svg", format='svg')