From ead3d70c3541be9fb77192c962b6db42fc23e459 Mon Sep 17 00:00:00 2001 From: Yves Biener Date: Sat, 21 Mar 2026 21:16:18 +0100 Subject: [PATCH] WIP diff centrality scores Check whether model correction is reliable in predicting the "expected" outcome. --- diff_comparison.py | 123 ++++++++++++++++++++++++--------------------- 1 file changed, 65 insertions(+), 58 deletions(-) diff --git a/diff_comparison.py b/diff_comparison.py index f6067c5..d571c1f 100644 --- a/diff_comparison.py +++ b/diff_comparison.py @@ -79,7 +79,7 @@ def spatial_graph(adata): return g, weight -def plot_graph_diff(G, c, fig, ax, name): +def plot_graph_diff(G, c, fig, ax, name, cmap=plt.cm.plasma): pos = G.vp["pos"] x = [] y = [] @@ -89,7 +89,7 @@ def plot_graph_diff(G, c, fig, ax, name): 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 + sc = ax.scatter(x, y, s=1, cmap=cmap, c=c) # map closeness values as color mapping on the verticies ax.set_title(name) fig.colorbar(sc, ax=ax) @@ -200,7 +200,7 @@ row1, row2 = fig.subplots(2, 2) ax1, ax2 = row1 # TODO select corresponding centrality measure method vp_closeness = apply(g, seed, weight, convex_hull, ax1, closeness, "Closeness") -# vp_betweenness = apply(g, seed, weight, convex_hull, ax2, betweenness, "Betweeness") +vp_betweenness = apply(g, seed, weight, convex_hull, ax2, betweenness, "Betweeness") # calculate convex hull convex_hull = centrality.convex_hull(g_sub) @@ -214,75 +214,82 @@ fig_graph.savefig("Diff_subgraph.svg", format='svg') ax1, ax2 = row2 vp_closeness_corrected = apply_corrected(g_sub, seed, weight_sub, convex_hull, ax1, closeness, "Closeness") -# vp_betweeness_corrected = apply_corrected(g_sub, seed, weight_sub, convex_hull, ax2, betweenness, "Betweeness") +vp_betweeness_corrected = apply_corrected(g_sub, seed, weight_sub, convex_hull, ax2, betweenness, "Betweeness") fig.savefig(f"Diff_scores.svg", format='svg') -# TODO how can I match the two vp's such that I can actually create a diff? -# -print(f"Closeness: {vp_closeness}") -print(f"Closeness corrected: {vp_closeness_corrected}") +for type in ['closeness', 'betweenness']: + print(type) -sub_keys = iter(g_sub.vertices()) -keys = iter(g.vertices()) + sub_keys = iter(g_sub.vertices()) + keys = iter(g.vertices()) -scores = [] -sub_scores = [] + scores = [] + sub_scores = [] + diff_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): + for sub_key in sub_keys: 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}") + 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? + value = 0.0 + sub_value = 0.0 + if type == 'closeness': + value = vp_closeness[key] + sub_value = vp_closeness_corrected[sub_key] + else: + value = vp_betweenness[key] + sub_value = vp_betweeness_corrected[sub_key] -# 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("") + scores.append(value) + sub_scores.append(sub_value) + diff_scores.append(value - sub_value) -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("") + median_score = np.median(scores) + median_sub_score = np.median(sub_scores) + print(f"\tmedian score: {median_score}") + print(f"\tmedian sub_score: {median_sub_score}") + print(f"\tmedian delta: {(median_score - median_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)}") + max_value_score = np.max(scores) + max_value_sub_score = np.max(sub_scores) + print(f"\tmax value score: {max_value_score}") + print(f"\tmax value sub_score: {max_value_sub_score}") + print(f"\tmax 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"\tmin value score: {min_value_score}") + print(f"\tmin value sub_score: {min_value_sub_score}") + print(f"\tmin value delta: {(min_value_score - min_value_sub_score)}") + print("") -fig = plt.figure(figsize=(35, 10)) -plot_graph_ax, plot_sub_graph_ax, plot_sub_graph_before_ax = fig.subplots(1, 3) + 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") + plot_graph_diff(g, scores, fig, plot_graph_ax, "Original Graph (region of sub graph)") + plot_graph_diff(g, diff_scores, fig, plot_sub_graph_ax, "Differences after correction of sub graph compared to original graph", plt.cm.seismic) -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") + vp = None + ep = None + if type == 'closeness': + vp = closeness(g_sub, weight=weight_sub) + vp.a = np.nan_to_num(vp.a) # correct floating point values + else: + vp, ep = betweenness(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') + fig.savefig(f"Diff_graph_scatter_{type}.svg", format='svg')