Seemingly our issue doesn't contain a "larger than max" error. Out of curiosity I tried to double the maxRecordsPerBatch to 20000 and reduced it to 200 and it didn't appear to help.

```
Fatal Python error: Segmentation fault

Thread 0x0000ffff7bfff120 (most recent call first):
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/client/core.py", line 1537 in _ping_handler
File "/usr/lib/python3.10/threading.py", line 953 in run
File "/usr/lib/python3.10/threading.py", line 1016 in _bootstrap_inner
File "/usr/lib/python3.10/threading.py", line 973 in _bootstrap

Current thread 0x0000ffffb5415420 (most recent call first):
File "/usr/local/lib/python3.10/dist-packages/google/protobuf/message.py", line 126 in CopyFrom
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/plan.py", line 524 in plan
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/plan.py", line 608 in plan
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/plan.py", line 799 in plan
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/plan.py", line 702 in plan
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/plan.py", line 118 in to_proto
File "/usr/local/lib/python3.10/dist-packages/pyspark/sql/connect/dataframe.py", line 1654 in toPandas
File "/home/powerwatch-data-analysis/pwdata/analysis/clustering.py", line 138 in run
File "/home/powerwatch-data-analysis/pwdata/analysis/clustering.py", line 195 in _run_stdbscan
File "/home/powerwatch-data-analysis/pwdata/analysis/clustering.py", line 243 in process
File "/home/powerwatch-data-analysis/pwdata/pipeline/core/pipeline.py", line 184 in __new__
File "/home/powerwatch-data-analysis/pwdata/analysis/clustering.py", line 292 in process
File "/home/powerwatch-data-analysis/pwdata/pipeline/core/pipeline.py", line 184 in __new__
File "/home/powerwatch-data-analysis/pwdata/analysis/outages/outage_estimation.py", line 74 in process
File "/home/powerwatch-data-analysis/pwdata/pipeline/core/pipeline.py", line 184 in __new__
File "/home/powerwatch-data-analysis/pwdata/overrides/sierra_leone/outage_estimation.py", line 23 in process
File "/home/powerwatch-data-analysis/pwdata/pipeline/core/pipeline.py", line 184 in __new__
File "/home/powerwatch-data-analysis/pwdata/kpis/outage.py", line 551 in process
File "/home/powerwatch-data-analysis/pwdata/pipeline/core/pipeline.py", line 184 in __new__
File "/home/powerwatch-data-analysis/pwdata/kpis/outage.py", line 168 in process
File "/home/powerwatch-data-analysis/pwdata/pipeline/core/pipeline.py", line 184 in __new__
File "<stdin>", line 1 in <module>

Extension modules: numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, psutil._psutil_linux, psutil._psutil_posix, charset_normalizer.md, grpc._cython.cygrpc, pyarrow.lib, pyarrow._hdfsio, pandas._libs.tslibs.np_datetime, pandas._libs.tslibs.dtypes, pandas._libs.tslibs.base, pandas._libs.tslibs.nattype, pandas._libs.tslibs.timezones, pandas._libs.tslibs.ccalendar, pandas._libs.tslibs.fields, pandas._libs.tslibs.timedeltas, pandas._libs.tslibs.tzconversion, pandas._libs.tslibs.timestamps, pandas._libs.properties, pandas._libs.tslibs.offsets, pandas._libs.tslibs.strptime, pandas._libs.tslibs.parsing, pandas._libs.tslibs.conversion, pandas._libs.tslibs.period, pandas._libs.tslibs.vectorized, pandas._libs.ops_dispatch, pandas._libs.missing, pandas._libs.hashtable, pandas._libs.algos, pandas._libs.interval, pandas._libs.lib, pandas._libs.ops, pyarrow._compute, pandas._libs.arrays, pandas._libs.tslib, pandas._libs.sparse, pandas._libs.indexing, pandas._libs.index, pandas._libs.internals, pandas._libs.join, pandas._libs.writers, pandas._libs.window.aggregations, pandas._libs.window.indexers, pandas._libs.reshape, pandas._libs.groupby, pandas._libs.json, pandas._libs.parsers, pandas._libs.testing, google._upb._message, yaml._yaml, shapely.lib, shapely._geos, shapely._geometry_helpers, pyproj._compat, pyproj._datadir, pyproj._network, pyproj._geod, pyproj.list, pyproj._crs, pyproj.database, pyproj._transformer, pyproj._sync, scipy._lib._ccallback_c, scipy.sparse._sparsetools, _csparsetools, scipy.sparse._csparsetools, scipy.sparse.linalg._isolve._iterative, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg.cython_lapack, scipy.linalg._cythonized_array_utils, scipy.linalg._solve_toeplitz, scipy.linalg._decomp_lu_cython, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg.cython_blas, scipy.linalg._matfuncs_expm, scipy.linalg._decomp_update, scipy.linalg._flinalg, scipy.sparse.linalg._dsolve._superlu, scipy.sparse.linalg._eigen.arpack._arpack, scipy.sparse.csgraph._tools, scipy.sparse.csgraph._shortest_path, scipy.sparse.csgraph._traversal, scipy.sparse.csgraph._min_spanning_tree, scipy.sparse.csgraph._flow, scipy.sparse.csgraph._matching, scipy.sparse.csgraph._reordering, scipy.spatial._ckdtree, scipy._lib.messagestream, scipy.spatial._qhull, scipy.spatial._voronoi, scipy.spatial._distance_wrap, scipy.spatial._hausdorff, scipy.special._ufuncs_cxx, scipy.special._ufuncs, scipy.special._specfun, scipy.special._comb, scipy.special._ellip_harm_2, scipy.spatial.transform._rotation (total: 110)
/usr/local/bin/pyspark: line 60: 232 Segmentation fault $PYSPARK_DRIVER_PYTHON
```