profession visualization

app.py

@@ -17,38 +17,99 @@ clusters_by_size = {
     48: clusters_48,
 }
 
-prompts = pd.read_csv('promptsadjectives.csv')
+prompts = pd.read_csv("promptsadjectives.csv")
+# m_adjectives = prompts['Masc-adj'].tolist()[:10]
+#  f_adjectives = prompts['Fem-adj'].tolist()[:10]
+# adjectives = sorted(m_adjectives+f_adjectives)
+# adjectives.insert(0, '')
+professions = list(sorted([p.lower() for p in prompts["Occupation-Noun"].tolist()]))
+models = {
+    "All": "All Models",
+    "SD_14": "Stable Diffusion 1.4",
+    "SD_2": "Stable Diffusion 2",
+    "DallE": "Dall-E 2",
+}
+
 
-m_adjectives = prompts['Masc-adj'].tolist()[:10]
-f_adjectives = prompts['Fem-adj'].tolist()[:10]
-adjectives = sorted(m_adjectives+f_adjectives)
-adjectives.insert(0, '')
-professions = sorted([p.lower() for p in prompts['Occupation-Noun'].tolist()])
-models = ["Dall-E 2", "Stable Diffusion 1.4", "Stable Diffusion 2"]
+def make_profession_table(num_clusters, prof_name):
+    pre_pandas = dict(
+        [
+            (
+                models[mod_name],
+                dict(
+                    (
+                        f"Cluster {k}",
+                        clusters_by_size[num_clusters][mod_name][prof_name][
+                            "cluster_proportions"
+                        ][k],
+                    )
+                    for k, v in sorted(
+                        clusters_by_size[num_clusters]["All"][prof_name][
+                            "cluster_proportions"
+                        ].items(),
+                        key=lambda x: x[1],
+                        reverse=True,
+                    )
+                    if v > 0
+                ),
+            )
+            for mod_name in models
+        ]
+    )
+    df = pd.DataFrame.from_dict(pre_pandas)
+    prof_plot = df.plot(kind="bar", barmode="group")
+    return prof_plot
 
 
 with gr.Blocks() as demo:
     gr.Markdown("# 🤗 Diffusion Cluster Explorer")
     gr.Markdown("description will go here")
-    with gr.Tab("Exploring all professions together"):
+    with gr.Tab("Professions Overview"):
         gr.Markdown("TODO")
         with gr.Row():
             with gr.Column():
                 gr.Markdown("Select your settings below:")
-                num_clusters = gr.Radio([12,24,48], value=12, label="How many clusters do you want to make from the data?")
-                professions = gr.Dropdown
+                num_clusters = gr.Radio(
+                    [12, 24, 48],
+                    value=12,
+                    label="How many clusters do you want to use to represent identities?",
+                )
             with gr.Column():
                 gr.Markdown("")
-                order = gr.Dropdown(["entropy", "cluster/sum of clusters"], value="entryopy", label="Order rows by:", interactive=True)
-#        with gr.Row():
-            
-#        with gr.Accordion("Tag Frequencies", open=False):
+                order = gr.Dropdown(
+                    ["entropy", "cluster/sum of clusters"],
+                    value="entryopy",
+                    label="Order rows by:",
+                    interactive=True,
+                )
+    #        with gr.Row():
 
-    with gr.Tab("Tab 2"):
-        gr.Markdown("TODO"
-        )
-         
+    #        with gr.Accordion("Tag Frequencies", open=False):
 
+    with gr.Tab("Profession Focus"):
+        with gr.Row():
+            num_clusters = gr.Radio(
+                [12, 24, 48],
+                value=12,
+                label="How many clusters do you want to use to represent identities?",
+            )
+        with gr.Row():
+            with gr.Column():
+                profession_choice = gr.Dropdown(
+                    choices=professions, label="Select profession:"
+                )
+            with gr.Column():
+                plot = gr.Plot(
+                    label=f"Makeup of the cluster assignments for profession {profession_choice}"
+                )
+                profession_choice.change(
+                    make_profession_table,
+                    [num_clusters, profession_choice],
+                    plot,
+                    queue=False,
+                )
+        with gr.Row():
+            gr.Markdown("TODO: show examplars for cluster")
 
-demo.launch()
 
+demo.launch()