HDBSCAN运行报错：'float'对象无法解析为整数，求解决方案

我用HDBSCAN处理基因表达数据集已经几周了，之前运行完全正常，但最近突然执行失败，代码如下：

clusterer = hdbscan.HDBSCAN(min_cluster_size=10, min_samples=1).fit(df)

报错信息：

TypeError: 'float' object cannot be interpreted as an integer

这明显不合理，因为我的数据集从一开始就只有float类型数据，而且之前一直正常运行。另外把数据转成整数完全没意义，会丢失所有数据含义。

完整错误栈如下：

TypeError                                 Traceback (most recent call last)
Cell In[18], line 1
----> 1 clusterer = hdbscan.HDBSCAN(min_cluster_size=10, min_samples=1).fit(df.select_dtypes(include='number'))
      2 df_cluster = pd.DataFrame({'samples':df['SAMPLES'],'labels': df['labels'], 'clusters': clusterer.labels_,'probabilities': clusterer.probabilities_})
      3 df_cluster

File ~/opt/anaconda3/envs/env_test/lib/python3.8/site-packages/hdbscan/hdbscan_.py:1205, in HDBSCAN.fit(self, X, y)
   1195 kwargs.pop("prediction_data", None)
   1196 kwargs.update(self._metric_kwargs)
   1198 (
   1199     self.labels_,
   1200     self.probabilities_,
   1201     self.cluster_persistence_,
   1202     self._condensed_tree,
   1203     self._single_linkage_tree,
   1204     self._min_spanning_tree,
-> 1205 ) = hdbscan(clean_data, **kwargs)
   1207 if self.metric != "precomputed" and not self._all_finite:
   1208     # remap indices to align with original data in the case of non-finite entries.
   1209     self._condensed_tree = remap_condensed_tree(
   1210         self._condensed_tree, internal_to_raw, outliers
   1211     )

File ~/opt/anaconda3/envs/env_test/lib/python3.8/site-packages/hdbscan/hdbscan_.py:824, in hdbscan(X, min_cluster_size, min_samples, alpha, cluster_selection_epsilon, max_cluster_size, metric, p, leaf_size, algorithm, memory, approx_min_span_tree, gen_min_span_tree, core_dist_n_jobs, cluster_selection_method, allow_single_cluster, match_reference_implementation, **kwargs)
    820 elif metric in KDTREE_VALID_METRICS:
    821     # TO DO: Need heuristic to decide when to go to boruvka;
    822     # still debugging for now
    823     if X.shape[1] > 60:
--> 824         (single_linkage_tree, result_min_span_tree) = memory.cache(
    825             _hdbscan_prims_kdtree
    826         )(
    827             X,
    828             min_samples,
    829             alpha,
    830             metric,
    831             p,
    832             leaf_size,
    833             gen_min_span_tree,
    834             **kwargs
    835         )
    836     else:
    837         (single_linkage_tree, result_min_span_tree) = memory.cache(
    838             _hdbscan_boruvka_kdtree
    839         )(
   (...)
    849             **kwargs
    850         )

File ~/opt/anaconda3/envs/env_test/lib/python3.8/site-packages/joblib/memory.py:349, in NotMemorizedFunc.__call__(self, *args, **kwargs)
    348 def __call__(self, *args, **kwargs):
--> 349     return self.func(*args, **kwargs)

File ~/opt/anaconda3/envs/env_test/lib/python3.8/site-packages/hdbscan/hdbscan_.py:265, in _hdbscan_prims_kdtree(X, min_samples, alpha, metric, p, leaf_size, gen_min_span_tree, **kwargs)
    260 core_distances = tree.query(
    261     X, k=min_samples + 1, dualtree=True, breadth_first=True
    262 )[0][:, -1].copy(order="C")
    264 # Mutual reachability distance is implicit in mst_linkage_core_vector
--> 265 min_spanning_tree = mst_linkage_core_vector(X, core_distances, dist_metric, alpha)
    267 # Sort edges of the min_spanning_tree by weight
    268 min_spanning_tree = min_spanning_tree[np.argsort(min_spanning_tree.T[2]), :]

File hdbscan/_hdbscan_linkage.pyx:55, in hdbscan._hdbscan_linkage.mst_linkage_core_vector()

File hdbscan/_hdbscan_linkage.pyx:144, in hdbscan._hdbscan_linkage.mst_linkage_core_vector()

TypeError: 'float' object cannot be interpreted as an integer

可能的原因及解决办法 #

• HDBSCAN版本兼容性：近期若更新过HDBSCAN，新版本的Cython底层代码可能对参数或数据类型校验更严格。可以回退到之前能正常运行的版本：

  pip install hdbscan==[你之前使用的版本号]
  

• 数据维度异常：检查数据集的列数是否为整数类型。报错路径显示当列数>60时会调用_hdbscan_prims_kdtree，如果列数被意外转为float类型，会触发该错误。执行以下代码确认维度：

  print(df.select_dtypes(include='number').shape)
  

  若维度是float，需排查数据处理流程中是否不小心修改了维度属性，确保行列数为整数。
• 参数类型错误：确认所有需要整数的参数（如min_cluster_size、min_samples、leaf_size等）均为整数类型，避免传递float值。
• 数组类型适配：尝试将数据集转换为numpy.float64类型后再传入模型：

  import numpy as np
  X = df.select_dtypes(include='number').values.astype(np.float64)
  clusterer = hdbscan.HDBSCAN(min_cluster_size=10, min_samples=1).fit(X)
  

内容的提问来源于stack exchange，提问作者Nozelar