BUG: HDFStore select for large integer (#54186)

* use decimal to prevent precision loss * added unit test * raise ValueError if given value cannot be converted to double * added bugfix in whatsnew * updated unit test * added context manager and cleaned up assert for readability * updated whatsnew * moved imports to top * reverted to float's ValueError raise * added comments for float(v)

Author: SanjithChockan

doc/source/whatsnew/v2.1.0.rst

@@ -485,7 +485,7 @@ Conversion
 - Bug in :meth:`DataFrame.__repr__` incorrectly raising a ``TypeError`` when the dtype of a column is ``np.record`` (:issue:`48526`)
 - Bug in :meth:`DataFrame.info` raising ``ValueError`` when ``use_numba`` is set (:issue:`51922`)
 - Bug in :meth:`DataFrame.insert` raising ``TypeError`` if ``loc`` is ``np.int64`` (:issue:`53193`)
--
+- Bug in :meth:`HDFStore.select` loses precision of large int when stored and retrieved (:issue:`54186`)
 
 Strings
 ^^^^^^^

pandas/core/computation/pytables.py

@@ -2,6 +2,10 @@
 from __future__ import annotations
 
 import ast
+from decimal import (
+ Decimal,
+ InvalidOperation,
+)
 from functools import partial
 from typing import (
  TYPE_CHECKING,
@@ -233,7 +237,14 @@ def stringify(value):
  result = metadata.searchsorted(v, side="left")
  return TermValue(result, result, "integer")
  elif kind == "integer":
- v = int(float(v))
+ try:
+ v_dec = Decimal(v)
+ except InvalidOperation:
+ # GH 54186
+ # convert v to float to raise float's ValueError
+ float(v)
+ else:
+ v = int(v_dec.to_integral_exact(rounding="ROUND_HALF_EVEN"))
  return TermValue(v, v, kind)
  elif kind == "float":
  v = float(v)

pandas/tests/io/pytables/test_select.py

@@ -914,7 +914,7 @@ def test_query_compare_column_type(setup_path):
  if col == "real_date":
  msg = 'Given date string "a" not likely a datetime'
  else:
- msg = "could not convert string to "
+ msg = "could not convert string to"
  with pytest.raises(ValueError, match=msg):
  store.select("test", where=query)
 
@@ -943,3 +943,22 @@ def test_select_empty_where(tmp_path, where):
  store.put("df", df, "t")
  result = read_hdf(store, "df", where=where)
  tm.assert_frame_equal(result, df)
+
+
+def test_select_large_integer(tmp_path):
+ path = tmp_path / "large_int.h5"
+
+ df = DataFrame(
+ zip(
+ ["a", "b", "c", "d"],
+ [-9223372036854775801, -9223372036854775802, -9223372036854775803, 123],
+ ),
+ columns=["x", "y"],
+ )
+ result = None
+ with HDFStore(path) as s:
+ s.append("data", df, data_columns=True, index=False)
+ result = s.select("data", where="y==-9223372036854775801").get("y").get(0)
+ expected = df["y"][0]
+
+ assert expected == result