[
https://issues.apache.org/jira/browse/ARROW-2145?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16377634#comment-16377634
]
ASF GitHub Bot commented on ARROW-2145:
---------------------------------------
wesm commented on a change in pull request #1651:
ARROW-2145/ARROW-2153/ARROW-2157/ARROW-2160/ARROW-2177: [Python] Decimal
conversion not working for NaN values
URL: https://github.com/apache/arrow/pull/1651#discussion_r170739037
##########
File path: cpp/src/arrow/python/helpers.cc
##########
@@ -193,6 +218,63 @@ Status UInt64FromPythonInt(PyObject* obj, uint64_t* out) {
return Status::OK();
}
+bool PyFloat_isnan(PyObject* obj) {
+ return PyFloat_Check(obj) && std::isnan(PyFloat_AS_DOUBLE(obj));
+}
+
+bool PyDecimal_Check(PyObject* obj) {
+ // TODO(phillipc): Is this expensive?
+ OwnedRef Decimal;
+ OwnedRef decimal;
+ Status status = ImportModule("decimal", &decimal);
+ DCHECK(status.ok()) << "Error during import of the decimal module";
+ status = ImportFromModule(decimal, "Decimal", &Decimal);
+ DCHECK(status.ok())
+ << "Error during import of the Decimal object from the decimal module";
+ const int32_t result = PyObject_IsInstance(obj, Decimal.obj());
+ DCHECK_NE(result, -1) << " error during PyObject_IsInstance check";
+ return result == 1;
+}
+
+bool PyDecimal_ISNAN(PyObject* obj) {
+ DCHECK(PyDecimal_Check(obj)) << "obj is not an instance of decimal.Decimal";
+ OwnedRef is_nan(PyObject_CallMethod(obj, "is_nan", ""));
+ return PyObject_IsTrue(is_nan.obj()) == 1;
+}
+
+DecimalMetadata::DecimalMetadata()
+ : DecimalMetadata(std::numeric_limits<int32_t>::min(),
+ std::numeric_limits<int32_t>::min()) {}
+
+DecimalMetadata::DecimalMetadata(int32_t precision, int32_t scale)
+ : precision_(precision), scale_(scale) {}
+
+Status DecimalMetadata::Update(int32_t suggested_precision, int32_t
suggested_scale) {
+ const int32_t current_precision = precision_;
+ precision_ = std::max(current_precision, suggested_precision);
+
+ const int32_t current_scale = scale_;
+ scale_ = std::max(current_scale, suggested_scale);
+
+ // if our suggested scale is zero and we don't yet have enough precision
then we need to
+ // add whatever the current scale is to the precision
+ if (suggested_scale == 0 && suggested_precision > current_precision) {
+ precision_ += scale_;
+ }
+
+ return Status::OK();
+}
+
+Status DecimalMetadata::Update(PyObject* object) {
+ DCHECK(PyDecimal_Check(object)) << "Object is not a Python Decimal";
+ DCHECK(!PyDecimal_ISNAN(object))
+ << "Decimal object cannot be NAN when inferring precision and scale";
Review comment:
This should never happen by design, right?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
> [Python] Decimal conversion not working for NaN values
> ------------------------------------------------------
>
> Key: ARROW-2145
> URL: https://issues.apache.org/jira/browse/ARROW-2145
> Project: Apache Arrow
> Issue Type: Bug
> Components: C++, Python
> Affects Versions: 0.8.0
> Reporter: Antony Mayi
> Assignee: Phillip Cloud
> Priority: Major
> Labels: pull-request-available
>
> {code:python}
> import pyarrow as pa
> import pandas as pd
> import decimal
> pa.Table.from_pandas(pd.DataFrame({'a': [decimal.Decimal('1.1'),
> decimal.Decimal('NaN')]}))
> {code}
> throws following exception:
> {code}
> Traceback (most recent call last):
> File "<stdin>", line 1, in <module>
> File "pyarrow/table.pxi", line 875, in pyarrow.lib.Table.from_pandas
> (/arrow/python/build/temp.linux-x86_64-3.6/lib.cxx:44927)
> File "/lib/python3.6/site-packages/pyarrow/pandas_compat.py", line 350, in
> dataframe_to_arrays
> convert_types)]
> File "/lib/python3.6/site-packages/pyarrow/pandas_compat.py", line 349, in
> <listcomp>
> for c, t in zip(columns_to_convert,
> File "/lib/python3.6/site-packages/pyarrow/pandas_compat.py", line 345, in
> convert_column
> return pa.array(col, from_pandas=True, type=ty)
> File "pyarrow/array.pxi", line 170, in pyarrow.lib.array
> (/arrow/python/build/temp.linux-x86_64-3.6/lib.cxx:29224)
> File "pyarrow/array.pxi", line 70, in pyarrow.lib._ndarray_to_array
> (/arrow/python/build/temp.linux-x86_64-3.6/lib.cxx:28465)
> File "pyarrow/error.pxi", line 98, in pyarrow.lib.check_status
> (/arrow/python/build/temp.linux-x86_64-3.6/lib.cxx:9068)
> pyarrow.lib.ArrowException: Unknown error: an integer is required (got type
> str)
> {code}
> Same problem with other special decimal values like {{infinity}}.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
