本文整理汇总了Python中pandas._libs.parsers.TextReader.read方法的典型用法代码示例。如果您正苦于以下问题：Python TextReader.read方法的具体用法？Python TextReader.read怎么用？Python TextReader.read使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pandas._libs.parsers.TextReader的用法示例。
在下文中一共展示了TextReader.read方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_file_handle_mmap
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_file_handle_mmap(self):
try:
f = open(self.csv1, 'rb')
reader = TextReader(f, memory_map=True, header=None)
reader.read()
finally:
f.close()示例2: test_skip_bad_lines
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_skip_bad_lines(self, capsys):
# too many lines, see #2430 for why
data = ('a:b:c\n'
'd:e:f\n'
'g:h:i\n'
'j:k:l:m\n'
'l:m:n\n'
'o:p:q:r')
reader = TextReader(StringIO(data), delimiter=':',
header=None)
msg = (r"Error tokenizing data\. C error: Expected 3 fields in"
" line 4, saw 4")
with pytest.raises(parser.ParserError, match=msg):
reader.read()
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=False)
result = reader.read()
expected = {0: np.array(['a', 'd', 'g', 'l'], dtype=object),
1: np.array(['b', 'e', 'h', 'm'], dtype=object),
2: np.array(['c', 'f', 'i', 'n'], dtype=object)}
assert_array_dicts_equal(result, expected)
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=True)
reader.read()
captured = capsys.readouterr()
assert 'Skipping line 4' in captured.err
assert 'Skipping line 6' in captured.err示例3: test_skip_bad_lines
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_skip_bad_lines(self):
# too many lines, see #2430 for why
data = ('a:b:c\n'
'd:e:f\n'
'g:h:i\n'
'j:k:l:m\n'
'l:m:n\n'
'o:p:q:r')
reader = TextReader(StringIO(data), delimiter=':',
header=None)
pytest.raises(parser.ParserError, reader.read)
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=False)
result = reader.read()
expected = {0: ['a', 'd', 'g', 'l'],
1: ['b', 'e', 'h', 'm'],
2: ['c', 'f', 'i', 'n']}
assert_array_dicts_equal(result, expected)
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=True)
reader.read()
val = sys.stderr.getvalue()
assert 'Skipping line 4' in val
assert 'Skipping line 6' in val示例4: test_parse_booleans
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_parse_booleans(self):
data = 'True\nFalse\nTrue\nTrue'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
assert result[0].dtype == np.bool_示例5: test_file_handle
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_file_handle(self):
try:
f = open(self.csv1, 'rb')
reader = TextReader(f)
result = reader.read() # noqa
finally:
f.close()示例6: test_embedded_newline
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_embedded_newline(self):
data = 'a\n"hello\nthere"\nthis'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
expected = np.array(['a', 'hello\nthere', 'this'], dtype=np.object_)
tm.assert_numpy_array_equal(result[0], expected)示例7: test_euro_decimal
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_euro_decimal(self):
data = '12345,67\n345,678'
reader = TextReader(StringIO(data), delimiter=':',
decimal=',', header=None)
result = reader.read()
expected = np.array([12345.67, 345.678])
tm.assert_almost_equal(result[0], expected)示例8: test_integer_thousands
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_integer_thousands(self):
data = '123,456\n12,500'
reader = TextReader(StringIO(data), delimiter=':',
thousands=',', header=None)
result = reader.read()
expected = np.array([123456, 12500], dtype=np.int64)
tm.assert_almost_equal(result[0], expected)示例9: test_escapechar
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_escapechar(self):
data = ('\\"hello world\"\n'
'\\"hello world\"\n'
'\\"hello world\"')
reader = TextReader(StringIO(data), delimiter=',', header=None,
escapechar='\\')
result = reader.read()
expected = {0: np.array(['"hello world"'] * 3, dtype=object)}
assert_array_dicts_equal(result, expected)示例10: test_delimit_whitespace
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_delimit_whitespace(self):
data = 'a b\na\t\t "b"\n"a"\t \t b'
reader = TextReader(StringIO(data), delim_whitespace=True,
header=None)
result = reader.read()
tm.assert_numpy_array_equal(result[0], np.array(['a', 'a', 'a'],
dtype=np.object_))
tm.assert_numpy_array_equal(result[1], np.array(['b', 'b', 'b'],
dtype=np.object_))示例11: test_skipinitialspace
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_skipinitialspace(self):
data = ('a, b\n'
'a, b\n'
'a, b\n'
'a, b')
reader = TextReader(StringIO(data), skipinitialspace=True,
header=None)
result = reader.read()
tm.assert_numpy_array_equal(result[0], np.array(['a', 'a', 'a', 'a'],
dtype=np.object_))
tm.assert_numpy_array_equal(result[1], np.array(['b', 'b', 'b', 'b'],
dtype=np.object_))示例12: test_header_not_enough_lines
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_header_not_enough_lines(self):
data = ('skip this\n'
'skip this\n'
'a,b,c\n'
'1,2,3\n'
'4,5,6')
reader = TextReader(StringIO(data), delimiter=',', header=2)
header = reader.header
expected = [['a', 'b', 'c']]
assert header == expected
recs = reader.read()
expected = {0: np.array([1, 4], dtype=np.int64),
1: np.array([2, 5], dtype=np.int64),
2: np.array([3, 6], dtype=np.int64)}
assert_array_dicts_equal(recs, expected)示例13: test_header_not_enough_lines
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_header_not_enough_lines(self):
data = ('skip this\n'
'skip this\n'
'a,b,c\n'
'1,2,3\n'
'4,5,6')
reader = TextReader(StringIO(data), delimiter=',', header=2)
header = reader.header
expected = [['a', 'b', 'c']]
assert header == expected
recs = reader.read()
expected = {0: [1, 4], 1: [2, 5], 2: [3, 6]}
assert_array_dicts_equal(expected, recs)
# not enough rows
pytest.raises(parser.ParserError, TextReader, StringIO(data),
delimiter=',', header=5, as_recarray=True)示例14: test_file_handle
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_file_handle(self):
with open(self.csv1, 'rb') as f:
reader = TextReader(f)
reader.read()示例15: test_string_factorize
# 需要导入模块: from pandas._libs.parsers import TextReader [as 别名]
# 或者: from pandas._libs.parsers.TextReader import read [as 别名]
def test_string_factorize(self):
# should this be optional?
data = 'a\nb\na\nb\na'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
assert len(set(map(id, result[0]))) == 2