From 54bd6ae220dae77ff4ca2001949d5627e533e63e Mon Sep 17 00:00:00 2001 From: gfyoung Date: Tue, 5 Nov 2019 23:07:52 +0000 Subject: [PATCH] TST: consistent result in dropping NA from CSV Closes https://github.com/pandas-dev/pandas/issues/21131 --- pandas/tests/io/parser/test_na_values.py | 28 ++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/pandas/tests/io/parser/test_na_values.py b/pandas/tests/io/parser/test_na_values.py index f154d09358dc1..f52c6b8858fd3 100644 --- a/pandas/tests/io/parser/test_na_values.py +++ b/pandas/tests/io/parser/test_na_values.py @@ -536,3 +536,31 @@ def test_cast_NA_to_bool_raises_error(all_parsers, data, na_values): dtype={"a": "bool"}, na_values=na_values, ) + + +def test_str_nan_dropped(all_parsers): + # see gh-21131 + parser = all_parsers + + data = """File: small.csv,, +10010010233,0123,654 +foo,,bar +01001000155,4530,898""" + + result = parser.read_csv( + StringIO(data), + header=None, + names=["col1", "col2", "col3"], + dtype={"col1": str, "col2": str, "col3": str}, + ).dropna() + + expected = DataFrame( + { + "col1": ["10010010233", "01001000155"], + "col2": ["0123", "4530"], + "col3": ["654", "898"], + }, + index=[1, 3], + ) + + tm.assert_frame_equal(result, expected)