update bar chart

app.py

@@ -20,16 +20,38 @@ SCORE_NAME_MAPPING = {'clip': 'clip_score', 'rank': 'avg_rank', 'pop': 'model_do
 
 # hist_data = pd.DataFrame(np.random.normal(42, 10, (200, 1)), columns=["x"])
 @st.cache_resource
-def altair_histogram(hist_data, sort_by):
+def altair_histogram(hist_data, sort_by, mini, maxi):
     brushed = alt.selection_interval(encodings=['x'], name="brushed")
-    return (
+
+    chart = (
         alt.Chart(hist_data)
-        .mark_bar()
-        .encode(alt.X(f"{sort_by}:Q", bin=True), y="count()")
-        .add_selection(brushed)
-        .properties(width=600, height=300)
+        .mark_bar(opacity=0.7, cornerRadius=2)
+        .encode(alt.X(f"{sort_by}:Q", bin=alt.Bin(maxbins=20)), y="count()")
+        # .add_selection(brushed)
+        # .properties(width=800, height=300)
+    )
+
+    # Create a transparent rectangle for highlighting the range
+    highlight = (
+        alt.Chart(pd.DataFrame({'x1': [mini], 'x2': [maxi]}))
+        .mark_rect(opacity=0.3)
+        .encode(x='x1', x2='x2')
+        # .properties(width=800, height=300)
     )
 
+    # Layer the chart and the highlight rectangle
+    layered_chart = alt.layer(chart, highlight)
+
+    return layered_chart
+
+    # return (
+    #     alt.Chart(hist_data)
+    #     .mark_bar()
+    #     .encode(alt.X(f"{sort_by}:Q", bin=alt.Bin(maxbins=20)), y="count()")
+    #     .add_selection(brushed)
+    #     .properties(width=600, height=300)
+    # )
+
 class GalleryApp:
     def __init__(self, promptBook, images_ds):
         self.promptBook = promptBook
@@ -169,7 +191,6 @@ class GalleryApp:
 
         return items, info, col_num
 
-
     def selection_panel_2(self, items):
         selecters = st.columns([1, 5])
 
@@ -226,14 +247,25 @@ class GalleryApp:
                     items = items[items['checked'] == True].reset_index(drop=True)
                     print(items)
 
+        # draw a distribution histogram
         if sort_type == 'Scores':
-            st.write('Select the range of scores to show')
-            hist_data = pd.DataFrame(items[sort_by])
-            event_dict = altair_component(altair_chart=altair_histogram(hist_data, sort_by))
-            r = event_dict.get(sort_by)
-            if r:
-                items = items[(items[sort_by] >= r[0]) & (items[sort_by] <= r[1])].reset_index(drop=True)
-                st.write(r)
+            with st.expander('Show score distribution histogram and select score range'):
+                st.write('**Score distribution histogram**')
+                chart_space = st.container()
+                # st.write('Select the range of scores to show')
+                hist_data = pd.DataFrame(items[sort_by])
+                mini = hist_data[sort_by].min().item()
+                maxi = hist_data[sort_by].max().item()
+                st.write('**Select the range of scores to show**')
+                r = st.slider('Select the range of scores to show', min_value=mini, max_value=maxi, value=(mini, maxi), label_visibility='collapsed')
+                with chart_space:
+                    st.altair_chart(altair_histogram(hist_data, sort_by, r[0], r[1]), use_container_width=True)
+                # event_dict = altair_component(altair_chart=altair_histogram(hist_data, sort_by))
+                # r = event_dict.get(sort_by)
+                if r:
+                    items = items[(items[sort_by] >= r[0]) & (items[sort_by] <= r[1])].reset_index(drop=True)
+                    # st.write(r)
+
 
         info = st.multiselect('Show Info',
                               ['model_download_count', 'clip_score', 'avg_rank', 'model_name', 'model_id',
@@ -308,7 +340,6 @@ class GalleryApp:
                 except:
                     pass
 
-
         # add safety check for some prompts
         safety_check = True
         unsafe_prompts = {}
@@ -398,44 +429,7 @@ if __name__ == '__main__':
     login(token=os.environ.get("HF_TOKEN"))
     st.set_page_config(layout="wide")
 
-    # if 'roster' not in st.session_state:
-    #     print('loading roster')
-    #     # st.session_state.roster = pd.DataFrame(load_dataset('NYUSHPRP/ModelCofferRoster', split='train'))
-    #     st.session_state.roster = pd.DataFrame(load_from_disk(os.path.join(os.getcwd(), 'data', 'roster')))
-    #     st.session_state.roster = st.session_state.roster[['model_id', 'model_name', 'modelVersion_id', 'modelVersion_name',
-    #                                       'model_download_count']].drop_duplicates().reset_index(drop=True)
-    # # add model download count from roster to promptbook dataframe
-    # if 'promptBook' not in st.session_state:
-    #     print('loading promptBook')
-    #
-    #     st.session_state.promptBook = pd.DataFrame(load_dataset('NYUSHPRP/ModelCofferMetadata', split='train'))
-    #     # add 'checked' column to promptBook if not exist
-    #     if 'checked' not in st.session_state.promptBook.columns:
-    #         st.session_state.promptBook.loc[:, 'checked'] = False
-    #
-    #     # add 'custom_score_weights' column to promptBook if not exist
-    #     if 'weighted_score_sum' not in st.session_state.promptBook.columns:
-    #         st.session_state.promptBook.loc[:, 'weighted_score_sum'] = 0
-    #
-    #     st.session_state.images = load_from_disk(os.path.join(os.getcwd(), 'data', 'promptbook'))
-    #     # st.session_state.images = load_dataset('NYUSHPRP/ModelCofferPromptBook', split='train', streaming=True)
-    #     print(st.session_state.images)
-    #     print('images loaded')
-    #     # st.session_state.promptBook = pd.DataFrame(load_dataset('NYUSHPRP/ModelCofferPromptBook', split='train'))
-    #     st.session_state.promptBook = st.session_state.promptBook.merge(st.session_state.roster[['model_id', 'model_name', 'modelVersion_id', 'modelVersion_name', 'model_download_count']], on=['model_id', 'modelVersion_id'], how='left')
-    #
-    #     # add column to record current row index
-    #     st.session_state.promptBook['row_idx'] = st.session_state.promptBook.index
-    #     print('promptBook loaded')
-    # # print(st.session_state.promptBook)
-    #
-    # check_roster_error = False
-    # if check_roster_error:
-    #     # print all rows with the same model_id and modelVersion_id but different model_download_count in roster
-    #     print(st.session_state.roster[st.session_state.roster.duplicated(subset=['model_id', 'modelVersion_id'], keep=False)].sort_values(by=['model_id', 'modelVersion_id']))
     roster, promptBook, images_ds = load_hf_dataset()
-    # if 'images' not in st.session_state:
-    #     st.session_state.images = load_from_disk(os.path.join(os.getcwd(), 'data', 'promptbook'))
 
     app = GalleryApp(promptBook=promptBook, images_ds=images_ds)
     app.app()

test_altair.py

@@ -1,50 +1,25 @@
-import altair as alt
 import streamlit as st
+import altair as alt
 import pandas as pd
-import numpy as np
-
-from streamlit_vega_lite import vega_lite_component, altair_component, _component_func
-
-hist_data = pd.DataFrame(np.random.normal(42, 10, (200, 1)), columns=["abc"])
-print(hist_data)
-
-@st.cache_resource
-def altair_histogram():
-    brushed = alt.selection_interval(encodings=["x"], name="brushed")
-
-    return (
-        alt.Chart(hist_data)
-        .mark_bar()
-        .encode(alt.X("abc:Q", bin=True), y="count()")
-        .add_selection(brushed)
-    )
-
-chart = altair_histogram()
-res = st.altair_chart(chart, use_container_width=True)
-# print(res)
-event_dict = altair_component(altair_chart=altair_histogram())
-chart_dict = chart.to_dict()
-print(chart_dict)
-altair_chart = chart.copy()
-datasets = {}
-
-def id_transform(data):
-    """Altair data transformer that returns a fake named dataset with the
-    object id."""
-    name = f"d{id(data)}"
-    datasets[name] = data
-    return {"name": name}
-
-alt.data_transformers.register("id", id_transform)
-
-with alt.data_transformers.enable("id"):
-    chart_dict = altair_chart.to_dict()
-# st.write(event_dict)
-
-event_dict = _component_func(spec=chart_dict, **datasets, key=None, default={})
-# print(chart_dict)
 
-r = event_dict.get("abc")
-if r:
-    filtered = hist_data[(hist_data.abc >= r[0]) & (hist_data.abc < r[1])]
-    st.write(filtered)
+# Generate random data for the chart
+data = pd.DataFrame({
+    'Category': ['A', 'B', 'C', 'D', 'E'],
+    'Value': [0.2, 0.5, 0.8, 1.2, 1.5]
+})
+
+# Define the color scale for the bars
+color_scale = alt.Scale(
+    domain=[0, 1],  # Values between 0 and 1 will be blue
+    range=['steelblue', 'lightgray']
+)
+
+# Create the bar chart using Altair
+chart = alt.Chart(data).mark_bar().encode(
+    x='Category',
+    y='Value',
+    color=alt.Color('Value', scale=color_scale)
+)
+
+# Render the chart using Streamlit
+st.altair_chart(chart, use_container_width=True)