REF: define NA_VALUES in libparsers (#30373)

Author: jbrockmendel

pandas/_libs/parsers.pyx

@@ -1367,7 +1367,26 @@ def _ensure_encoded(list lst):
 # common NA values
 # no longer excluding inf representations
 # '1.#INF','-1.#INF', '1.#INF000000',
-_NA_VALUES = _ensure_encoded(list(icom._NA_VALUES))
+STR_NA_VALUES = {
+    "-1.#IND",
+    "1.#QNAN",
+    "1.#IND",
+    "-1.#QNAN",
+    "#N/A N/A",
+    "#N/A",
+    "N/A",
+    "n/a",
+    "NA",
+    "#NA",
+    "NULL",
+    "null",
+    "NaN",
+    "-NaN",
+    "nan",
+    "-nan",
+    "",
+}
+_NA_VALUES = _ensure_encoded(list(STR_NA_VALUES))
 
 
 def _maybe_upcast(arr):

pandas/io/common.py

@@ -47,29 +47,6 @@
 
 lzma = _import_lzma()
 
-# common NA values
-# no longer excluding inf representations
-# '1.#INF','-1.#INF', '1.#INF000000',
-_NA_VALUES = {
-    "-1.#IND",
-    "1.#QNAN",
-    "1.#IND",
-    "-1.#QNAN",
-    "#N/A N/A",
-    "#N/A",
-    "N/A",
-    "n/a",
-    "NA",
-    "#NA",
-    "NULL",
-    "null",
-    "NaN",
-    "-NaN",
-    "nan",
-    "-nan",
-    "",
-}
-
 
 _VALID_URLS = set(uses_relative + uses_netloc + uses_params)
 _VALID_URLS.discard("")

pandas/io/excel/_base.py

@@ -6,6 +6,7 @@
 
 from pandas._config import config
 
+from pandas._libs.parsers import STR_NA_VALUES
 from pandas.errors import EmptyDataError
 from pandas.util._decorators import Appender
 
@@ -14,7 +15,6 @@
 from pandas.core.frame import DataFrame
 
 from pandas.io.common import (
-    _NA_VALUES,
     _is_url,
     _stringify_path,
     _validate_header_arg,
@@ -124,7 +124,7 @@
     Additional strings to recognize as NA/NaN. If dict passed, specific
     per-column NA values. By default the following values are interpreted
     as NaN: '"""
-    + fill("', '".join(sorted(_NA_VALUES)), 70, subsequent_indent="    ")
+    + fill("', '".join(sorted(STR_NA_VALUES)), 70, subsequent_indent="    ")
     + """'.
 keep_default_na : bool, default True
     Whether or not to include the default NaN values when parsing the data.

pandas/io/parsers.py

@@ -17,6 +17,7 @@
 import pandas._libs.lib as lib
 import pandas._libs.ops as libops
 import pandas._libs.parsers as parsers
+from pandas._libs.parsers import STR_NA_VALUES
 from pandas._libs.tslibs import parsing
 from pandas.errors import (
     AbstractMethodError,
@@ -60,7 +61,6 @@
 from pandas.core.tools import datetimes as tools
 
 from pandas.io.common import (
-    _NA_VALUES,
     BaseIterator,
     UnicodeReader,
     UTF8Recoder,
@@ -195,7 +195,7 @@
     Additional strings to recognize as NA/NaN. If dict passed, specific
     per-column NA values.  By default the following values are interpreted as
     NaN: '"""
-    + fill("', '".join(sorted(_NA_VALUES)), 70, subsequent_indent="    ")
+    + fill("', '".join(sorted(STR_NA_VALUES)), 70, subsequent_indent="    ")
     + """'.
 keep_default_na : bool, default True
     Whether or not to include the default NaN values when parsing the data.
@@ -3398,7 +3398,7 @@ def _clean_na_values(na_values, keep_default_na=True):
 
     if na_values is None:
         if keep_default_na:
-            na_values = _NA_VALUES
+            na_values = STR_NA_VALUES
         else:
             na_values = set()
         na_fvalues = set()
@@ -3415,7 +3415,7 @@ def _clean_na_values(na_values, keep_default_na=True):
                 v = [v]
 
             if keep_default_na:
-                v = set(v) | _NA_VALUES
+                v = set(v) | STR_NA_VALUES
 
             na_values[k] = v
         na_fvalues = {k: _floatify_na_values(v) for k, v in na_values.items()}
@@ -3424,7 +3424,7 @@ def _clean_na_values(na_values, keep_default_na=True):
             na_values = [na_values]
         na_values = _stringify_na_values(na_values)
         if keep_default_na:
-            na_values = na_values | _NA_VALUES
+            na_values = na_values | STR_NA_VALUES
 
         na_fvalues = _floatify_na_values(na_values)
 
@@ -3575,7 +3575,7 @@ def _get_na_values(col, na_values, na_fvalues, keep_default_na):
             return na_values[col], na_fvalues[col]
         else:
             if keep_default_na:
-                return _NA_VALUES, set()
+                return STR_NA_VALUES, set()
 
             return set(), set()
     else:

pandas/tests/io/parser/test_na_values.py

@@ -7,11 +7,11 @@
 import numpy as np
 import pytest
 
+from pandas._libs.parsers import STR_NA_VALUES
+
 from pandas import DataFrame, Index, MultiIndex
 import pandas.util.testing as tm
 
-import pandas.io.common as com
-
 
 def test_string_nas(all_parsers):
     parser = all_parsers
@@ -99,7 +99,7 @@ def test_default_na_values(all_parsers):
         "#N/A N/A",
         "",
     }
-    assert _NA_VALUES == com._NA_VALUES
+    assert _NA_VALUES == STR_NA_VALUES
 
     parser = all_parsers
     nv = len(_NA_VALUES)