Skip to content

Fix tooltip metadata, null display, legend sort, and filter requirement #22

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
NetZissou merged 2 commits into from
Apr 1, 2026
Merged

Fix tooltip metadata, null display, legend sort, and filter requirement #22

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5fbe322
Fix tooltip metadata display, null rendering, legend sort, and filter…
NetZissou Mar 30, 2026
0c2a536
Use tableau20 color scheme for up to 20 distinct cluster colors
NetZissou Mar 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions apps/precalculated/components/sidebar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,8 +200,8 @@ def render_file_section() -> Tuple[bool, Optional[str]]:
st.session_state.parquet_file_path = file_path
st.session_state.column_info = column_info

# Reset downstream state
st.session_state.filtered_df = None
# Initialize filtered_df to full dataset (filtering is optional)
st.session_state.filtered_df = df
st.session_state.embeddings = None
st.session_state.data = None
st.session_state.labels = None
Expand Down Expand Up @@ -739,9 +739,9 @@ def create_cluster_dataframe(df: pd.DataFrame, embeddings_2d: np.ndarray, labels
"idx": range(len(df))
})

# Add available metadata columns for tooltips
# Add available metadata columns for tooltips (fill NaN for clean Altair display)
for col in df.columns:
if col not in ['uuid', 'emb', 'embedding', 'embeddings'] and col not in df_plot.columns:
df_plot[col] = df[col].values
df_plot[col] = df[col].fillna("N/A").values

return df_plot
23 changes: 19 additions & 4 deletions shared/components/visualization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,9 +82,12 @@ def _render_chart_fragment(df_plot):
tooltip_fields.append('cluster:N')
cluster_legend_title = "Cluster"

# Add other metadata columns dynamically (limit to prevent tooltip overflow)
skip_cols = {'x', 'y', 'cluster', 'cluster_name', 'idx', 'emb', 'embedding', 'embeddings', 'vector'}
metadata_cols = [c for c in df_plot.columns if c not in skip_cols][:8]
# Add other metadata columns dynamically
# Skip technical, ID, and image-URL columns (details available in Data Preview panel)
skip_cols = {'x', 'y', 'cluster', 'cluster_name', 'idx',
'emb', 'embedding', 'embeddings', 'vector',
'uuid', 'identifier', 'image_url', 'url', 'img_url', 'image'}
metadata_cols = [c for c in df_plot.columns if c not in skip_cols][:15]
tooltip_fields.extend(metadata_cols)

# Determine title based on data type
Expand All @@ -101,14 +104,26 @@ def _render_chart_fragment(df_plot):
else:
point_opacity = 0.7 # Normal opacity

# Sort legend labels: numeric sort for cluster IDs, alphabetical for strings
unique_vals = df_plot['cluster'].unique()
try:
sorted_vals = sorted(unique_vals, key=int)
except (ValueError, TypeError):
sorted_vals = sorted(unique_vals, key=str)

# Create scatter plot
scatter = (
alt.Chart(df_plot)
.mark_circle(size=60, opacity=point_opacity)
.encode(
x=alt.X('x:Q', scale=alt.Scale(zero=False)),
y=alt.Y('y:Q', scale=alt.Scale(zero=False)),
color=alt.Color('cluster:N', legend=alt.Legend(title=cluster_legend_title)),
color=alt.Color(
'cluster:N',
legend=alt.Legend(title=cluster_legend_title),
sort=sorted_vals,
scale=alt.Scale(scheme='tableau20')
),
tooltip=tooltip_fields,
fillOpacity=alt.condition(point_selector, alt.value(1), alt.value(0.3))
)
Expand Down