Adding summaries

app.py

@@ -4,6 +4,7 @@ import os
 from PIL import Image
 import plotly.graph_objects as go
 import plotly.express as px
+import operator
 
 TITLE = "Diffusion Faces Cluster Explorer"
 clusters_12 = json.load(open("clusters/id_all_blip_clusters_12.json"))
@@ -16,6 +17,17 @@ clusters_by_size = {
     48: clusters_48,
 }
 
+def describe_cluster(cl_dict, block="label"):
+    labels_values = sorted(cl_dict.items(), key=operator.itemgetter(1))
+    labels_values.reverse()
+    total = float(sum(cl_dict.values()))
+    lv_prcnt = list((item[0], round(item[1] * 100/total, 0)) for item in labels_values)
+    description_string = "The most represented %s is %s, making up about %d%% of the cluster.\n" % (block, lv_prcnt[0][0], lv_prcnt[0][1])
+    description_string += "This is followed by: "
+    for label_value_tuple in lv_prcnt[1:]:
+        description_string += "\n%s: %d%%" % label_value_tuple
+    return description_string
+
 def show_cluster(cl_id, num_clusters):
     if not cl_id:
         cl_id = 0
@@ -29,16 +41,20 @@ def show_cluster(cl_id, num_clusters):
     model_fig = go.Figure()
     model_fig.add_trace(go.Pie(labels=list(dict(cl_dct["labels_model"]).keys()), 
                                values=list(dict(cl_dct["labels_model"]).values())))
+    model_description = describe_cluster(dict(cl_dct["labels_model"]), "model")
+
     gender_fig = go.Figure()
     gender_fig.add_trace(go.Pie(labels=list(dict(cl_dct["labels_gender"]).keys()), 
                                 values=list(dict(cl_dct["labels_gender"]).values())))
+    gender_description = describe_cluster(dict(cl_dct["labels_gender"]), "gender")
+
     ethnicity_fig = go.Figure()
     ethnicity_fig.add_trace(go.Bar(x=list(dict(cl_dct["labels_ethnicity"]).keys()), 
                                    y=list(dict(cl_dct["labels_ethnicity"]).values()), 
                                    marker_color=px.colors.qualitative.G10))
     return (len(cl_dct['img_path_list']),
-            gender_fig,
-            model_fig,
+            gender_fig,gender_description,
+            model_fig, model_description,
             ethnicity_fig,
             images)
 
@@ -46,8 +62,9 @@ with gr.Blocks(title=TITLE) as demo:
     gr.Markdown(f"# {TITLE}")
     gr.Markdown("## This Space lets you explore the data generated from [DiffusionBiasExplorer](https://huggingface.co/spaces/society-ethics/DiffusionBiasExplorer).")
     gr.HTML("""<span style="color:red" font-size:smaller>⚠️ DISCLAIMER: the images displayed by this tool were generated by text-to-image models and may depict offensive stereotypes or contain explicit content.</span>""")
-    num_clusters = gr.Radio([12,24,48], value=12, label="How many clusters do you want to make from the data?")
+    num_clusters = gr.Radio([12,24,48], value=12, labels="How many clusters do you want to make from the data?")
 
+    
     with gr.Row():
         with gr.Column(scale=4):
             gallery = gr.Gallery(label="Most representative images in cluster").style(grid=(3,3))
@@ -56,14 +73,16 @@ with gr.Blocks(title=TITLE) as demo:
             a = gr.Text(label="Number of images")
     with gr.Row():
             with gr.Column(scale=1):
-                c = gr.Plot(label="Model makeup of cluster")
+                c = gr.Plot(label="Model makeup of clssuster")
+                c_desc = gr.Text(label="")
             with gr.Column(scale=1):
                 b = gr.Plot(label="Gender label makeup of cluster")
+                b_desc = gr.Text(label="")
             with gr.Column(scale=2):
                 d = gr.Plot(label="Ethnicity label makeup of cluster")
-    demo.load(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a,b,c,d, gallery])
-    num_clusters.change(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a,b,c,d, gallery])
-    cluster_id.change(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a,b,c,d, gallery])
+    demo.load(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a, b, b_desc, c, c_desc, d, gallery])
+    num_clusters.change(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a, b, b_desc, c, c_desc, d, gallery])
+    cluster_id.change(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a, b, b_desc, c, c_desc, d, gallery])
 
 if __name__ == "__main__":
     demo.queue().launch(debug=True)