HJQ/tianxuan
2
1
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

fix(umap): LazyFrame.sample not available in Polars 1.42, use DataFrame.sample after collect

Browse Source
This commit is contained in:
PM-pinou
2026-07-24 11:39:00 +08:00
parent e2c64fd068
commit 5280ce5819
1 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
analysis/views/clustering.py
+5 -6
View File
@@ -1,4 +1,4 @@
"""Cluster views: overview, detail, globe flows, and the clustering pipeline.""" """Cluster views: overview, detail, globe flows, and the clustering pipeline."""
import asyncio import asyncio
import json import json
import traceback import traceback
@@ -382,12 +382,11 @@ def _run_clustering_pipeline(run, store, ds_id, feature_columns, algorithm,
if len(num_cols) >= 2: if len(num_cols) >= 2:
if n_total > MAX_UMAP_TRAIN: if n_total > MAX_UMAP_TRAIN:
run.progress_msg = f'UMAP 采样 {MAX_UMAP_TRAIN}/{n_total} 实体训练...' run.progress_msg = f'UMAP 采样 {MAX_UMAP_TRAIN}/{n_total} 行训练...'
run.save(update_fields=['progress_msg']) run.save(update_fields=['progress_msg'])
df_sample = lf.sample(n=MAX_UMAP_TRAIN, seed=RANDOM_SEED).collect(streaming=True) # LazyFrame.sample() is unavailable in Polars 1.42 — collect then sample
df_umap = lf.collect(streaming=True) df_sample = df_umap.sample(n=MAX_UMAP_TRAIN, seed=RANDOM_SEED)
else: df_sample = df_umap
df_umap = lf.collect(streaming=True)
umap_components = 3 # try 3D first umap_components = 3 # try 3D first
coords = None coords = None