def test_info_max_cols(self):
df = DataFrame(np.random.randn(10, 5))
for len_, verbose in [(5, None), (5, False), (10, True)]:
# For verbose always ^ setting ^ summarize ^ full output
with option_context('max_info_columns', 4):
buf = StringIO()
df.info(buf=buf, verbose=verbose)
res = buf.getvalue()
self.assertEqual(len(res.strip().split('\n')), len_)
for len_, verbose in [(10, None), (5, False), (10, True)]:
# max_cols no exceeded
with option_context('max_info_columns', 5):
buf = StringIO()
df.info(buf=buf, verbose=verbose)
res = buf.getvalue()
self.assertEqual(len(res.strip().split('\n')), len_)
for len_, max_cols in [(10, 5), (5, 4)]:
# setting truncates
with option_context('max_info_columns', 4):
buf = StringIO()
df.info(buf=buf, max_cols=max_cols)
res = buf.getvalue()
self.assertEqual(len(res.strip().split('\n')), len_)
# setting wouldn't truncate
with option_context('max_info_columns', 5):
buf = StringIO()
df.info(buf=buf, max_cols=max_cols)
res = buf.getvalue()
self.assertEqual(len(res.strip().split('\n')), len_)
def test_info_memory_usage_qualified(self):
buf = StringIO()
df = DataFrame(1, columns=list('ab'),
index=[1, 2, 3])
df.info(buf=buf)
assert '+' not in buf.getvalue()
buf = StringIO()
df = DataFrame(1, columns=list('ab'),
index=list('ABC'))
df.info(buf=buf)
assert '+' in buf.getvalue()
buf = StringIO()
df = DataFrame(1, columns=list('ab'),
index=pd.MultiIndex.from_product(
[range(3), range(3)]))
df.info(buf=buf)
assert '+' not in buf.getvalue()
buf = StringIO()
df = DataFrame(1, columns=list('ab'),
index=pd.MultiIndex.from_product(
[range(3), ['foo', 'bar']]))
df.info(buf=buf)
assert '+' in buf.getvalue()
def test_to_csv_quoting(self):
df = DataFrame({'A': [1, 2, 3], 'B': ['foo', 'bar', 'baz']})
buf = StringIO()
df.to_csv(buf, index=False, quoting=csv.QUOTE_NONNUMERIC)
result = buf.getvalue()
expected = ('"A","B"\n'
'1,"foo"\n'
'2,"bar"\n'
'3,"baz"\n')
self.assertEqual(result, expected)
# quoting windows line terminators, presents with encoding?
# #3503
text = 'a,b,c\n1,"test \r\n",3\n'
df = pd.read_csv(StringIO(text))
buf = StringIO()
df.to_csv(buf, encoding='utf-8', index=False)
self.assertEqual(buf.getvalue(), text)
# testing if quoting parameter is passed through with multi-indexes
# related to issue #7791
df = pd.DataFrame({'a': [1, 2], 'b': [3, 4], 'c': [5, 6]})
df = df.set_index(['a', 'b'])
expected = '"a","b","c"\n"1","3","5"\n"2","4","6"\n'
self.assertEqual(df.to_csv(quoting=csv.QUOTE_ALL), expected)
class UnicodeWriter(object):
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
self.quoting = kwds.get("quoting", None)
def writerow(self, row):
def _check_as_is(x):
return (self.quoting == csv.QUOTE_NONNUMERIC and
is_number(x)) or isinstance(x, str)
row = [x if _check_as_is(x)
else pprint_thing(x).encode("utf-8") for x in row]
self.writer.writerow([s for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and re-encode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
def _check_as_is(x):
return (self.quoting == csv.QUOTE_NONNUMERIC and
is_number(x)) or isinstance(x, str)
for i, row in enumerate(rows):
rows[i] = [x if _check_as_is(x)
else pprint_thing(x).encode("utf-8") for x in row]
self.writer.writerows([[s for s in row] for row in rows])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and re-encode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def test_to_html(self):
# big mixed
biggie = DataFrame({'A': np.random.randn(200),
'B': tm.makeStringIndex(200)},
index=lrange(200))
biggie.loc[:20, 'A'] = np.nan
biggie.loc[:20, 'B'] = np.nan
s = biggie.to_html()
buf = StringIO()
retval = biggie.to_html(buf=buf)
self.assertIsNone(retval)
self.assertEqual(buf.getvalue(), s)
tm.assertIsInstance(s, compat.string_types)
biggie.to_html(columns=['B', 'A'], col_space=17)
biggie.to_html(columns=['B', 'A'],
formatters={'A': lambda x: '%.1f' % x})
biggie.to_html(columns=['B', 'A'], float_format=str)
biggie.to_html(columns=['B', 'A'], col_space=12, float_format=str)
frame = DataFrame(index=np.arange(200))
frame.to_html()
def _coef_table(self):
buf = StringIO()
buf.write('%14s %10s %10s %10s %10s %10s %10s\n' %
('Variable', 'Coef', 'Std Err', 't-stat',
'p-value', 'CI 2.5%', 'CI 97.5%'))
buf.write(scom.banner(''))
coef_template = '\n%14s %10.4f %10.4f %10.2f %10.4f %10.4f %10.4f'
results = self._results
beta = results['beta']
for i, name in enumerate(beta.index):
if i and not (i % 5):
buf.write('\n' + scom.banner(''))
std_err = results['std_err'][name]
CI1 = beta[name] - 1.96 * std_err
CI2 = beta[name] + 1.96 * std_err
t_stat = results['t_stat'][name]
p_value = results['p_value'][name]
line = coef_template % (name,
beta[name], std_err, t_stat, p_value, CI1, CI2)
buf.write(line)
if self.nw_lags is not None:
buf.write('\n')
buf.write('*** The calculations are Newey-West '
'adjusted with lags %5d\n' % self.nw_lags)
return buf.getvalue()
def _coef_table(self):
buffer = StringIO()
buffer.write(
"%13s %13s %13s %13s %13s %13s\n" % ("Variable", "Beta", "Std Err", "t-stat", "CI 2.5%", "CI 97.5%")
)
template = "%13s %13.4f %13.4f %13.2f %13.4f %13.4f\n"
for i, name in enumerate(self._cols):
if i and not (i % 5):
buffer.write("\n" + common.banner(""))
mean_beta = self._results["mean_beta"][i]
std_beta = self._results["std_beta"][i]
t_stat = self._results["t_stat"][i]
ci1 = mean_beta - 1.96 * std_beta
ci2 = mean_beta + 1.96 * std_beta
values = "(%s)" % name, mean_beta, std_beta, t_stat, ci1, ci2
buffer.write(template % values)
if self._nw_lags_beta is not None:
buffer.write("\n")
buffer.write("*** The Std Err, t-stat are Newey-West " "adjusted with Lags %5d\n" % self._nw_lags_beta)
return buffer.getvalue()
def save(self):
"""
Create the writer & save
"""
# GH21227 internal compression is not used when file-like passed.
if self.compression and hasattr(self.path_or_buf, 'write'):
msg = ("compression has no effect when passing file-like "
"object as input.")
warnings.warn(msg, RuntimeWarning, stacklevel=2)
# when zip compression is called.
is_zip = isinstance(self.path_or_buf, ZipFile) or (
not hasattr(self.path_or_buf, 'write')
and self.compression == 'zip')
if is_zip:
# zipfile doesn't support writing string to archive. uses string
# buffer to receive csv writing and dump into zip compression
# file handle. GH21241, GH21118
f = StringIO()
close = False
elif hasattr(self.path_or_buf, 'write'):
f = self.path_or_buf
close = False
else:
f, handles = _get_handle(self.path_or_buf, self.mode,
encoding=self.encoding,
compression=self.compression)
close = True
try:
writer_kwargs = dict(lineterminator=self.line_terminator,
delimiter=self.sep, quoting=self.quoting,
doublequote=self.doublequote,
escapechar=self.escapechar,
quotechar=self.quotechar)
if self.encoding == 'ascii':
self.writer = csvlib.writer(f, **writer_kwargs)
else:
writer_kwargs['encoding'] = self.encoding
self.writer = UnicodeWriter(f, **writer_kwargs)
self._save()
finally:
if is_zip:
# GH17778 handles zip compression separately.
buf = f.getvalue()
if hasattr(self.path_or_buf, 'write'):
self.path_or_buf.write(buf)
else:
f, handles = _get_handle(self.path_or_buf, self.mode,
encoding=self.encoding,
compression=self.compression)
f.write(buf)
close = True
if close:
f.close()
for _fh in handles:
_fh.close()
def test_to_html(self):
# big mixed
biggie = DataFrame({'A': np.random.randn(200),
'B': tm.makeStringIndex(200)},
index=lrange(200))
biggie.loc[:20, 'A'] = np.nan
biggie.loc[:20, 'B'] = np.nan
s = biggie.to_html()
buf = StringIO()
retval = biggie.to_html(buf=buf)
assert retval is None
assert buf.getvalue() == s
assert isinstance(s, compat.string_types)
biggie.to_html(columns=['B', 'A'], col_space=17)
biggie.to_html(columns=['B', 'A'],
formatters={'A': lambda x: '{x:.1f}'.format(x=x)})
biggie.to_html(columns=['B', 'A'], float_format=str)
biggie.to_html(columns=['B', 'A'], col_space=12, float_format=str)
frame = DataFrame(index=np.arange(200))
frame.to_html()
def _coef_table(self):
buf = StringIO()
buf.write(
"%14s %10s %10s %10s %10s %10s %10s\n"
% ("Variable", "Coef", "Std Err", "t-stat", "p-value", "CI 2.5%", "CI 97.5%")
)
buf.write(scom.banner(""))
coef_template = "\n%14s %10.4f %10.4f %10.2f %10.4f %10.4f %10.4f"
results = self._results
beta = results["beta"]
for i, name in enumerate(beta.index):
if i and not (i % 5):
buf.write("\n" + scom.banner(""))
std_err = results["std_err"][name]
CI1 = beta[name] - 1.96 * std_err
CI2 = beta[name] + 1.96 * std_err
t_stat = results["t_stat"][name]
p_value = results["p_value"][name]
line = coef_template % (name, beta[name], std_err, t_stat, p_value, CI1, CI2)
buf.write(line)
if self.nw_lags is not None:
buf.write("\n")
buf.write("*** The calculations are Newey-West " "adjusted with lags %5d\n" % self.nw_lags)
return buf.getvalue()
def _coef_table(self):
buffer = StringIO()
buffer.write('%13s %13s %13s %13s %13s %13s\n' %
('Variable', 'Beta', 'Std Err', 't-stat', 'CI 2.5%', 'CI 97.5%'))
template = '%13s %13.4f %13.4f %13.2f %13.4f %13.4f\n'
for i, name in enumerate(self._cols):
if i and not (i % 5):
buffer.write('\n' + common.banner(''))
mean_beta = self._results['mean_beta'][i]
std_beta = self._results['std_beta'][i]
t_stat = self._results['t_stat'][i]
ci1 = mean_beta - 1.96 * std_beta
ci2 = mean_beta + 1.96 * std_beta
values = '(%s)' % name, mean_beta, std_beta, t_stat, ci1, ci2
buffer.write(template % values)
if self._nw_lags_beta is not None:
buffer.write('\n')
buffer.write('*** The Std Err, t-stat are Newey-West '
'adjusted with Lags %5d\n' % self._nw_lags_beta)
return buffer.getvalue()
def test_to_csv_numpy_16_bug(self):
frame = DataFrame({'a': date_range('1/1/2000', periods=10)})
buf = StringIO()
frame.to_csv(buf)
result = buf.getvalue()
self.assertIn('2000-01-01', result)
def to_clipboard(obj, excel=True, sep=None, **kwargs): # pragma: no cover
"""
Attempt to write text representation of object to the system clipboard
The clipboard can be then pasted into Excel for example.
Parameters
----------
obj : the object to write to the clipboard
excel : boolean, defaults to True
if True, use the provided separator, writing in a csv
format for allowing easy pasting into excel.
if False, write a string representation of the object
to the clipboard
sep : optional, defaults to tab
other keywords are passed to to_csv
Notes
-----
Requirements for your platform
- Linux: xclip, or xsel (with gtk or PyQt4 modules)
- Windows:
- OS X:
"""
encoding = kwargs.pop('encoding', 'utf-8')
# testing if an invalid encoding is passed to clipboard
if encoding is not None and encoding.lower().replace('-', '') != 'utf8':
raise ValueError('clipboard only supports utf-8 encoding')
from pandas.io.clipboard import clipboard_set
if excel is None:
excel = True
if excel:
try:
if sep is None:
sep = '\t'
buf = StringIO()
# clipboard_set (pyperclip) expects unicode
obj.to_csv(buf, sep=sep, encoding='utf-8', **kwargs)
text = buf.getvalue()
if PY2:
text = text.decode('utf-8')
clipboard_set(text)
return
except TypeError:
warnings.warn('to_clipboard in excel mode requires a single '
'character separator.')
elif sep is not None:
warnings.warn('to_clipboard with excel=False ignores the sep argument')
if isinstance(obj, ABCDataFrame):
# str(df) has various unhelpful defaults, like truncation
with option_context('display.max_colwidth', 999999):
objstr = obj.to_string(**kwargs)
else:
objstr = str(obj)
clipboard_set(objstr)
def test_to_csv_quote_none(self):
# GH4328
df = DataFrame({'A': ['hello', '{"hello"}']})
for encoding in (None, 'utf-8'):
buf = StringIO()
df.to_csv(buf, quoting=csv.QUOTE_NONE,
encoding=encoding, index=False)
result = buf.getvalue()
expected = 'A\nhello\n{"hello"}\n'
self.assertEqual(result, expected)
def test_to_csv_line_terminators(self):
df = DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]},
index=['one', 'two', 'three'])
buf = StringIO()
df.to_csv(buf, line_terminator='\r\n')
expected = (',A,B\r\n'
'one,1,4\r\n'
'two,2,5\r\n'
'three,3,6\r\n')
self.assertEqual(buf.getvalue(), expected)
buf = StringIO()
df.to_csv(buf) # The default line terminator remains \n
expected = (',A,B\n'
'one,1,4\n'
'two,2,5\n'
'three,3,6\n')
self.assertEqual(buf.getvalue(), expected)
def test_to_csv_from_csv_categorical(self):
# CSV with categoricals should result in the same output as when one
# would add a "normal" Series/DataFrame.
s = Series(pd.Categorical(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c']))
s2 = Series(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
res = StringIO()
s.to_csv(res)
exp = StringIO()
s2.to_csv(exp)
self.assertEqual(res.getvalue(), exp.getvalue())
df = DataFrame({"s": s})
df2 = DataFrame({"s": s2})
res = StringIO()
df.to_csv(res)
exp = StringIO()
df2.to_csv(exp)
self.assertEqual(res.getvalue(), exp.getvalue())
def test_to_csv_index_no_leading_comma(self):
df = DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]},
index=['one', 'two', 'three'])
buf = StringIO()
df.to_csv(buf, index_label=False)
expected = ('A,B\n'
'one,1,4\n'
'two,2,5\n'
'three,3,6\n')
self.assertEqual(buf.getvalue(), expected)
def profiled():
pr = cProfile.Profile()
pr.enable()
yield
pr.disable()
s = StringIO()
ps = pstats.Stats(pr, stream=s).sort_stats('cumulative')
ps.print_stats()
# uncomment this to see who's calling what
# ps.print_callers()
print(s.getvalue())
def test_to_csv_index_no_leading_comma(self):
df = DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]},
index=['one', 'two', 'three'])
buf = StringIO()
df.to_csv(buf, index_label=False)
expected = ('A,B\n'
'one,1,4\n'
'two,2,5\n'
'three,3,6\n')
assert buf.getvalue() == expected
def test_to_csv_quote_none(self):
# GH4328
df = DataFrame({'A': ['hello', '{"hello"}']})
for encoding in (None, 'utf-8'):
buf = StringIO()
df.to_csv(buf,
quoting=csv.QUOTE_NONE,
encoding=encoding,
index=False)
result = buf.getvalue()
expected = 'A\nhello\n{"hello"}\n'
self.assertEqual(result, expected)
def test_to_csv_gcs(mock):
df1 = DataFrame({'int': [1, 3], 'float': [2.0, np.nan], 'str': ['t', 's'],
'dt': date_range('2018-06-18', periods=2)})
with mock.patch('gcsfs.GCSFileSystem') as MockFileSystem:
s = StringIO()
instance = MockFileSystem.return_value
instance.open.return_value = s
df1.to_csv('gs://test/test.csv', index=True)
df2 = read_csv(StringIO(s.getvalue()), parse_dates=['dt'], index_col=0)
assert_frame_equal(df1, df2)
def test_to_csv_index_no_leading_comma(self):
df = DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]},
index=['one', 'two', 'three'])
buf = StringIO()
df.to_csv(buf, index_label=False)
expected_rows = ['A,B',
'one,1,4',
'two,2,5',
'three,3,6']
expected = tm.convert_rows_list_to_csv_str(expected_rows)
assert buf.getvalue() == expected
def test_to_csv_index_no_leading_comma(self):
df = DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]},
index=['one', 'two', 'three'])
buf = StringIO()
df.to_csv(buf, index_label=False)
expected_rows = ['A,B',
'one,1,4',
'two,2,5',
'three,3,6']
expected = tm.convert_rows_list_to_csv_str(expected_rows)
assert buf.getvalue() == expected
def test_to_csv_unicodewriter_quoting(self):
df = DataFrame({'A': [1, 2, 3], 'B': ['foo', 'bar', 'baz']})
buf = StringIO()
df.to_csv(buf,
index=False,
quoting=csv.QUOTE_NONNUMERIC,
encoding='utf-8')
result = buf.getvalue()
expected_rows = ['"A","B"', '1,"foo"', '2,"bar"', '3,"baz"']
expected = tm.convert_rows_list_to_csv_str(expected_rows)
assert result == expected
def test_to_csv_unicodewriter_quoting(self):
df = DataFrame({'A': [1, 2, 3], 'B': ['foo', 'bar', 'baz']})
buf = StringIO()
df.to_csv(buf,
index=False,
quoting=csv.QUOTE_NONNUMERIC,
encoding='utf-8')
result = buf.getvalue()
expected = ('"A","B"\n' '1,"foo"\n' '2,"bar"\n' '3,"baz"\n')
self.assertEqual(result, expected)
def test_info_shows_column_dtypes(self):
dtypes = ["int64", "float64", "datetime64[ns]", "timedelta64[ns]", "complex128", "object", "bool"]
data = {}
n = 10
for i, dtype in enumerate(dtypes):
data[i] = np.random.randint(2, size=n).astype(dtype)
df = DataFrame(data)
buf = StringIO()
df.info(buf=buf)
res = buf.getvalue()
for i, dtype in enumerate(dtypes):
name = "%d %d non-null %s" % (i, n, dtype)
assert name in res
def save(self):
# create the writer & save
if self.encoding is None:
if compat.PY2:
encoding = 'ascii'
else:
encoding = 'utf-8'
else:
encoding = self.encoding
# PR 21300 uses string buffer to receive csv writing and dump into
# file-like output with compression as option. GH 21241, 21118
f = StringIO()
if not is_file_like(self.path_or_buf):
# path_or_buf is path
path_or_buf = self.path_or_buf
elif hasattr(self.path_or_buf, 'name'):
# path_or_buf is file handle
path_or_buf = self.path_or_buf.name
else:
# path_or_buf is file-like IO objects.
f = self.path_or_buf
path_or_buf = None
try:
writer_kwargs = dict(lineterminator=self.line_terminator,
delimiter=self.sep,
quoting=self.quoting,
doublequote=self.doublequote,
escapechar=self.escapechar,
quotechar=self.quotechar)
if encoding == 'ascii':
self.writer = csvlib.writer(f, **writer_kwargs)
else:
writer_kwargs['encoding'] = encoding
self.writer = UnicodeWriter(f, **writer_kwargs)
self._save()
finally:
# GH 17778 handles zip compression for byte strings separately.
buf = f.getvalue()
if path_or_buf:
f, handles = _get_handle(path_or_buf,
self.mode,
encoding=encoding,
compression=self.compression)
f.write(buf)
f.close()
for _fh in handles:
_fh.close()
def test_to_csv_unicodewriter_quoting(self):
df = DataFrame({'A': [1, 2, 3], 'B': ['foo', 'bar', 'baz']})
buf = StringIO()
df.to_csv(buf, index=False, quoting=csv.QUOTE_NONNUMERIC,
encoding='utf-8')
result = buf.getvalue()
expected_rows = ['"A","B"',
'1,"foo"',
'2,"bar"',
'3,"baz"']
expected = tm.convert_rows_list_to_csv_str(expected_rows)
assert result == expected
def test_to_csv_quote_none(self):
# GH4328
df = DataFrame({'A': ['hello', '{"hello"}']})
for encoding in (None, 'utf-8'):
buf = StringIO()
df.to_csv(buf, quoting=csv.QUOTE_NONE,
encoding=encoding, index=False)
result = buf.getvalue()
expected_rows = ['A',
'hello',
'{"hello"}']
expected = tm.convert_rows_list_to_csv_str(expected_rows)
assert result == expected
def test_to_csv_quote_none(self):
# GH4328
df = DataFrame({'A': ['hello', '{"hello"}']})
for encoding in (None, 'utf-8'):
buf = StringIO()
df.to_csv(buf, quoting=csv.QUOTE_NONE,
encoding=encoding, index=False)
result = buf.getvalue()
expected_rows = ['A',
'hello',
'{"hello"}']
expected = tm.convert_rows_list_to_csv_str(expected_rows)
assert result == expected
def test_to_csv_gcs(monkeypatch):
df1 = DataFrame({'int': [1, 3], 'float': [2.0, np.nan], 'str': ['t', 's'],
'dt': date_range('2018-06-18', periods=2)})
s = StringIO()
class MockGCSFileSystem():
def open(*args):
return s
monkeypatch.setattr('gcsfs.GCSFileSystem', MockGCSFileSystem)
df1.to_csv('gs://test/example.csv', index=True)
df2 = read_csv(StringIO(s.getvalue()), parse_dates=['dt'], index_col=0)
assert_frame_equal(df1, df2)
def test_to_csv_unicodewriter_quoting(self):
df = DataFrame({'A': [1, 2, 3], 'B': ['foo', 'bar', 'baz']})
buf = StringIO()
df.to_csv(buf, index=False, quoting=csv.QUOTE_NONNUMERIC,
encoding='utf-8')
result = buf.getvalue()
expected = ('"A","B"\n'
'1,"foo"\n'
'2,"bar"\n'
'3,"baz"\n')
self.assertEqual(result, expected)
def test_info_shows_column_dtypes(self):
dtypes = ['int64', 'float64', 'datetime64[ns]', 'timedelta64[ns]',
'complex128', 'object', 'bool']
data = {}
n = 10
for i, dtype in enumerate(dtypes):
data[i] = np.random.randint(2, size=n).astype(dtype)
df = DataFrame(data)
buf = StringIO()
df.info(buf=buf)
res = buf.getvalue()
for i, dtype in enumerate(dtypes):
name = '%d %d non-null %s' % (i, n, dtype)
assert name in res
def test_to_csv_gcs(monkeypatch):
df1 = DataFrame({'int': [1, 3], 'float': [2.0, np.nan], 'str': ['t', 's'],
'dt': date_range('2018-06-18', periods=2)})
s = StringIO()
class MockGCSFileSystem():
def open(*args):
return s
monkeypatch.setattr('gcsfs.GCSFileSystem', MockGCSFileSystem)
df1.to_csv('gs://test/test.csv', index=True)
df2 = read_csv(StringIO(s.getvalue()), parse_dates=['dt'], index_col=0)
assert_frame_equal(df1, df2)
def test_repr_bool_fails(self):
s = Series([DataFrame(np.random.randn(2, 2)) for i in range(5)])
import sys
buf = StringIO()
tmp = sys.stderr
sys.stderr = buf
try:
# it works (with no Cython exception barf)!
repr(s)
finally:
sys.stderr = tmp
self.assertEqual(buf.getvalue(), '')
def save(self):
# create the writer & save
if self.encoding is None:
if compat.PY2:
encoding = 'ascii'
else:
encoding = 'utf-8'
else:
encoding = self.encoding
# PR 21300 uses string buffer to receive csv writing and dump into
# file-like output with compression as option. GH 21241, 21118
f = StringIO()
if not is_file_like(self.path_or_buf):
# path_or_buf is path
path_or_buf = self.path_or_buf
elif hasattr(self.path_or_buf, 'name'):
# path_or_buf is file handle
path_or_buf = self.path_or_buf.name
else:
# path_or_buf is file-like IO objects.
f = self.path_or_buf
path_or_buf = None
try:
writer_kwargs = dict(lineterminator=self.line_terminator,
delimiter=self.sep, quoting=self.quoting,
doublequote=self.doublequote,
escapechar=self.escapechar,
quotechar=self.quotechar)
if encoding == 'ascii':
self.writer = csvlib.writer(f, **writer_kwargs)
else:
writer_kwargs['encoding'] = encoding
self.writer = UnicodeWriter(f, **writer_kwargs)
self._save()
finally:
# GH 17778 handles zip compression for byte strings separately.
buf = f.getvalue()
if path_or_buf:
f, handles = _get_handle(path_or_buf, self.mode,
encoding=encoding,
compression=self.compression)
f.write(buf)
f.close()
for _fh in handles:
_fh.close()
def test_to_csv_from_csv_categorical(self):
# CSV with categoricals should result in the same output
# as when one would add a "normal" Series/DataFrame.
s = Series(pd.Categorical(["a", "b", "b", "a", "a", "c", "c", "c"]))
s2 = Series(["a", "b", "b", "a", "a", "c", "c", "c"])
res = StringIO()
s.to_csv(res, header=False)
exp = StringIO()
s2.to_csv(exp, header=False)
assert res.getvalue() == exp.getvalue()
df = DataFrame({"s": s})
df2 = DataFrame({"s": s2})
res = StringIO()
df.to_csv(res)
exp = StringIO()
df2.to_csv(exp)
assert res.getvalue() == exp.getvalue()
def test_to_csv_from_csv_categorical(self):
# CSV with categoricals should result in the same output
# as when one would add a "normal" Series/DataFrame.
s = Series(pd.Categorical(["a", "b", "b", "a", "a", "c", "c", "c"]))
s2 = Series(["a", "b", "b", "a", "a", "c", "c", "c"])
res = StringIO()
s.to_csv(res, header=False)
exp = StringIO()
s2.to_csv(exp, header=False)
assert res.getvalue() == exp.getvalue()
df = DataFrame({"s": s})
df2 = DataFrame({"s": s2})
res = StringIO()
df.to_csv(res)
exp = StringIO()
df2.to_csv(exp)
assert res.getvalue() == exp.getvalue()
def _get_pretty_string(obj):
"""Return a prettier version of obj
Parameters
----------
obj : object
Object to pretty print
Returns
-------
s : str
Pretty print object repr
"""
sio = StringIO()
pprint.pprint(obj, stream=sio)
return sio.getvalue()
def _get_pretty_string(obj):
"""Return a prettier version of obj
Parameters
----------
obj : object
Object to pretty print
Returns
-------
s : str
Pretty print object repr
"""
sio = StringIO()
pprint.pprint(obj, stream=sio)
return sio.getvalue()
def test_to_csv_gcs(mock):
df1 = DataFrame({
'int': [1, 3],
'float': [2.0, np.nan],
'str': ['t', 's'],
'dt': date_range('2018-06-18', periods=2)
})
with mock.patch('gcsfs.GCSFileSystem') as MockFileSystem:
s = StringIO()
instance = MockFileSystem.return_value
instance.open.return_value = s
df1.to_csv('gs://test/test.csv', index=True)
df2 = read_csv(StringIO(s.getvalue()), parse_dates=['dt'], index_col=0)
assert_frame_equal(df1, df2)
def test_info_wide(self):
from pandas import set_option, reset_option
io = StringIO()
df = DataFrame(np.random.randn(5, 101))
df.info(buf=io)
io = StringIO()
df.info(buf=io, max_cols=101)
rs = io.getvalue()
self.assertTrue(len(rs.splitlines()) > 100)
xp = rs
set_option('display.max_info_columns', 101)
io = StringIO()
df.info(buf=io)
self.assertEqual(rs, xp)
reset_option('display.max_info_columns')
def test_info_wide(self):
from pandas import set_option, reset_option
io = StringIO()
df = DataFrame(np.random.randn(5, 101))
df.info(buf=io)
io = StringIO()
df.info(buf=io, max_cols=101)
rs = io.getvalue()
self.assertTrue(len(rs.splitlines()) > 100)
xp = rs
set_option('display.max_info_columns', 101)
io = StringIO()
df.info(buf=io)
self.assertEqual(rs, xp)
reset_option('display.max_info_columns')
def test_read_csv_chunked_download(self, s3_resource, caplog):
# 8 MB, S3FS usees 5MB chunks
df = DataFrame(np.random.randn(100000, 4), columns=list('abcd'))
buf = BytesIO()
str_buf = StringIO()
df.to_csv(str_buf)
buf = BytesIO(str_buf.getvalue().encode('utf-8'))
s3_resource.Bucket("pandas-test").put_object(Key="large-file.csv",
Body=buf)
with caplog.at_level(logging.DEBUG, logger='s3fs.core'):
read_csv("s3://pandas-test/large-file.csv", nrows=5)
# log of fetch_range (start, stop)
assert ((0, 5505024) in set(x.args[-2:] for x in caplog.records))
def to_clipboard(obj, excel=None, sep=None, **kwargs): # pragma: no cover
"""
Attempt to write text representation of object to the system clipboard
The clipboard can be then pasted into Excel for example.
Parameters
----------
obj : the object to write to the clipboard
excel : boolean, defaults to True
if True, use the provided separator, writing in a csv
format for allowing easy pasting into excel.
if False, write a string representation of the object
to the clipboard
sep : optional, defaults to tab
other keywords are passed to to_csv
Notes
-----
Requirements for your platform
- Linux: xclip, or xsel (with gtk or PyQt4 modules)
- Windows:
- OS X:
"""
from pandas.util.clipboard import clipboard_set
if excel is None:
excel = True
if excel:
try:
if sep is None:
sep = '\t'
buf = StringIO()
obj.to_csv(buf, sep=sep, **kwargs)
clipboard_set(buf.getvalue())
return
except:
pass
if isinstance(obj, DataFrame):
# str(df) has various unhelpful defaults, like truncation
with option_context('display.max_colwidth', 999999):
objstr = obj.to_string(**kwargs)
else:
objstr = str(obj)
clipboard_set(objstr)
def test_info_memory(self):
# https://github.com/pandas-dev/pandas/issues/21056
df = pd.DataFrame({'a': pd.Series([1, 2], dtype='i8')})
buf = StringIO()
df.info(buf=buf)
result = buf.getvalue()
bytes = float(df.memory_usage().sum())
expected = textwrap.dedent("""\
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2 entries, 0 to 1
Data columns (total 1 columns):
a 2 non-null int64
dtypes: int64(1)
memory usage: {} bytes
""".format(bytes))
assert result == expected
def test_to_html(biggie_df_fixture):
# TODO: split this test
df = biggie_df_fixture
s = df.to_html()
buf = StringIO()
retval = df.to_html(buf=buf)
assert retval is None
assert buf.getvalue() == s
assert isinstance(s, str)
df.to_html(columns=['B', 'A'], col_space=17)
df.to_html(columns=['B', 'A'],
formatters={'A': lambda x: '{x:.1f}'.format(x=x)})
df.to_html(columns=['B', 'A'], float_format=str)
df.to_html(columns=['B', 'A'], col_space=12, float_format=str)
def predict(args):
predict_curl = pycurl.Curl()
storage = StringIO()
values = [(args.input_node_name, (pycurl.FORM_FILE, args.file_path))]
predict_curl.setopt(predict_curl.URL, args.server_url)
predict_curl.setopt(predict_curl.WRITEFUNCTION, storage.write)
predict_curl.setopt(predict_curl.HTTPPOST, values)
predict_curl.perform()
predict_curl.close()
content = storage.getvalue()
content = content.replace('\n', '')
res = json.loads(content)
if os.path.isfile(args.label_file_path):
labels = [
line.strip() for line in open(args.label_file_path).readlines()
]
if labels is not None:
for item in res["prediction"]:
item['class'] = labels[int(item['class'])]
print res
def test_verbose_import(self):
text = """a,b,c,d
one,1,2,3
one,1,2,3
,1,2,3
one,1,2,3
,1,2,3
,1,2,3
one,1,2,3
two,1,2,3"""
buf = StringIO()
sys.stdout = buf
try: # engines are verbose in different ways
self.read_csv(StringIO(text), verbose=True)
if self.engine == 'c':
self.assertIn('Tokenization took:', buf.getvalue())
self.assertIn('Parser memory cleanup took:', buf.getvalue())
else: # Python engine
self.assertEqual(buf.getvalue(),
'Filled 3 NA values in column a\n')
finally:
sys.stdout = sys.__stdout__
buf = StringIO()
sys.stdout = buf
text = """a,b,c,d
one,1,2,3
two,1,2,3
three,1,2,3
four,1,2,3
five,1,2,3
,1,2,3
seven,1,2,3
eight,1,2,3"""
try: # engines are verbose in different ways
self.read_csv(StringIO(text), verbose=True, index_col=0)
if self.engine == 'c':
self.assertIn('Tokenization took:', buf.getvalue())
self.assertIn('Parser memory cleanup took:', buf.getvalue())
else: # Python engine
self.assertEqual(buf.getvalue(),
'Filled 1 NA values in column a\n')
finally:
sys.stdout = sys.__stdout__
def to_clipboard(obj, excel=None, sep=None, **kwargs): # pragma: no cover
"""
Attempt to write text representation of object to the system clipboard
The clipboard can be then pasted into Excel for example.
Parameters
----------
obj : the object to write to the clipboard
excel : boolean, defaults to True
if True, use the provided separator, writing in a csv
format for allowing easy pasting into excel.
if False, write a string representation of the object
to the clipboard
sep : optional, defaults to tab
other keywords are passed to to_csv
Notes
-----
Requirements for your platform
- Linux: xclip, or xsel (with gtk or PyQt4 modules)
- Windows:
- OS X:
"""
from pandas.util.clipboard import clipboard_set
if excel is None:
excel = True
if excel:
try:
if sep is None:
sep = '\t'
buf = StringIO()
obj.to_csv(buf, sep=sep, **kwargs)
clipboard_set(buf.getvalue())
return
except:
pass
clipboard_set(str(obj))
def test_info_memory_usage(self):
# Ensure memory usage is displayed, when asserted, on the last line
dtypes = [
'int64', 'float64', 'datetime64[ns]', 'timedelta64[ns]',
'complex128', 'object', 'bool'
]
data = {}
n = 10
for i, dtype in enumerate(dtypes):
data[i] = np.random.randint(2, size=n).astype(dtype)
df = DataFrame(data)
buf = StringIO()
# display memory usage case
df.info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
assert "memory usage: " in res[-1]
# do not display memory usage case
df.info(buf=buf, memory_usage=False)
res = buf.getvalue().splitlines()
assert "memory usage: " not in res[-1]
df.info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
# memory usage is a lower bound, so print it as XYZ+ MB
assert re.match(r"memory usage: [^+]+\+", res[-1])
df.iloc[:, :5].info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
# excluded column with object dtype, so estimate is accurate
assert not re.match(r"memory usage: [^+]+\+", res[-1])
# POJO.Test a DataFrame with duplicate columns
dtypes = ['int64', 'int64', 'int64', 'float64']
data = {}
n = 100
for i, dtype in enumerate(dtypes):
data[i] = np.random.randint(2, size=n).astype(dtype)
df = DataFrame(data)
df.columns = dtypes
df_with_object_index = pd.DataFrame({'a': [1]}, index=['foo'])
df_with_object_index.info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
assert re.match(r"memory usage: [^+]+\+", res[-1])
df_with_object_index.info(buf=buf, memory_usage='deep')
res = buf.getvalue().splitlines()
assert re.match(r"memory usage: [^+]+$", res[-1])
# Ensure df size is as expected
# (cols * rows * bytes) + index size
df_size = df.memory_usage().sum()
exp_size = len(dtypes) * n * 8 + df.index.nbytes
assert df_size == exp_size
# Ensure number of cols in memory_usage is the same as df
size_df = np.size(df.columns.values) + 1 # index=True; default
assert size_df == np.size(df.memory_usage())
# assert deep works only on object
assert df.memory_usage().sum() == df.memory_usage(deep=True).sum()
# test for validity
DataFrame(1, index=['a'], columns=['A']).memory_usage(index=True)
DataFrame(1, index=['a'], columns=['A']).index.nbytes
df = DataFrame(data=1,
index=pd.MultiIndex.from_product([['a'],
range(1000)]),
columns=['A'])
df.index.nbytes
df.memory_usage(index=True)
df.index.values.nbytes
mem = df.memory_usage(deep=True).sum()
assert mem > 0
def test_to_csv_quoting(self):
df = DataFrame({
'c_bool': [True, False],
'c_float': [1.0, 3.2],
'c_int': [42, np.nan],
'c_string': ['a', 'b,c'],
})
expected = """\
,c_bool,c_float,c_int,c_string
0,True,1.0,42.0,a
1,False,3.2,,"b,c"
"""
result = df.to_csv()
assert result == expected
result = df.to_csv(quoting=None)
assert result == expected
result = df.to_csv(quoting=csv.QUOTE_MINIMAL)
assert result == expected
expected = """\
"","c_bool","c_float","c_int","c_string"
"0","True","1.0","42.0","a"
"1","False","3.2","","b,c"
"""
result = df.to_csv(quoting=csv.QUOTE_ALL)
assert result == expected
# see gh-12922, gh-13259: make sure changes to
# the formatters do not break this behaviour
expected = """\
"","c_bool","c_float","c_int","c_string"
0,True,1.0,42.0,"a"
1,False,3.2,"","b,c"
"""
result = df.to_csv(quoting=csv.QUOTE_NONNUMERIC)
assert result == expected
msg = "need to escape, but no escapechar set"
tm.assert_raises_regex(csv.Error, msg, df.to_csv,
quoting=csv.QUOTE_NONE)
tm.assert_raises_regex(csv.Error, msg, df.to_csv,
quoting=csv.QUOTE_NONE,
escapechar=None)
expected = """\
,c_bool,c_float,c_int,c_string
0,True,1.0,42.0,a
1,False,3.2,,b!,c
"""
result = df.to_csv(quoting=csv.QUOTE_NONE,
escapechar='!')
assert result == expected
expected = """\
,c_bool,c_ffloat,c_int,c_string
0,True,1.0,42.0,a
1,False,3.2,,bf,c
"""
result = df.to_csv(quoting=csv.QUOTE_NONE,
escapechar='f')
assert result == expected
# see gh-3503: quoting Windows line terminators
# presents with encoding?
text = 'a,b,c\n1,"test \r\n",3\n'
df = pd.read_csv(StringIO(text))
buf = StringIO()
df.to_csv(buf, encoding='utf-8', index=False)
assert buf.getvalue() == text
# xref gh-7791: make sure the quoting parameter is passed through
# with multi-indexes
df = pd.DataFrame({'a': [1, 2], 'b': [3, 4], 'c': [5, 6]})
df = df.set_index(['a', 'b'])
expected = '"a","b","c"\n"1","3","5"\n"2","4","6"\n'
assert df.to_csv(quoting=csv.QUOTE_ALL) == expected
def summary(self):
"""
This returns the formatted result of the OLS computation
"""
template = """
%(bannerTop)s
Formula: Y ~ %(formula)s
Number of Observations: %(nobs)d
Number of Degrees of Freedom: %(df)d
R-squared: %(r2)10.4f
Adj R-squared: %(r2_adj)10.4f
Rmse: %(rmse)10.4f
F-stat %(f_stat_shape)s: %(f_stat)10.4f, p-value: %(f_stat_p_value)10.4f
Degrees of Freedom: model %(df_model)d, resid %(df_resid)d
%(bannerCoef)s
%(coef_table)s
%(bannerEnd)s
"""
coef_table = self._coef_table
results = self._results
f_stat = results['f_stat']
bracketed = ['<%s>' % str(c) for c in results['beta'].index]
formula = StringIO()
formula.write(bracketed[0])
tot = len(bracketed[0])
line = 1
for coef in bracketed[1:]:
tot = tot + len(coef) + 3
if tot // (68 * line):
formula.write('\n' + ' ' * 12)
line += 1
formula.write(' + ' + coef)
params = {
'bannerTop': scom.banner('Summary of Regression Analysis'),
'bannerCoef': scom.banner('Summary of Estimated Coefficients'),
'bannerEnd': scom.banner('End of Summary'),
'formula': formula.getvalue(),
'r2': results['r2'],
'r2_adj': results['r2_adj'],
'nobs': results['nobs'],
'df': results['df'],
'df_model': results['df_model'],
'df_resid': results['df_resid'],
'coef_table': coef_table,
'rmse': results['rmse'],
'f_stat': f_stat['f-stat'],
'f_stat_shape': '(%d, %d)' % (f_stat['DF X'], f_stat['DF Resid']),
'f_stat_p_value': f_stat['p-value'],
}
return template % params
visualizer = PredictionError(RandomForestRegressor())
# Fit
visualizer.fit(X_train, y_train)
# Score and visualize
visualizer.score(X_test, y_test)
visualizer.poof()
from sklearn import tree
from IPython.core.display import Image
from pandas.compat import StringIO
import pydotplus
# Visualize tree
dot_data = StringIO()
tree.export_graphviz(model.estimators_[0], out_file=dot_data)
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
image = graph.write("random_network")
from sklearn.ensemble import AdaBoostRegressor
model = AdaBoostRegressor()
model.fit(X_train, y_train)
yhat = model.predict(X_test)
r2 = r2_score(y_test, yhat)
me = mse(y_test, yhat)
print("r2={:0.3f} MSE={:0.3f}".format(r2, me))
from yellowbrick.regressor import PredictionError
# Instantiate the visualizer
visualizer = PredictionError(AdaBoostRegressor())
# Fit
def test_dtype_name_in_info(self, data):
buf = StringIO()
pd.DataFrame({"A": data}).info(buf=buf)
result = buf.getvalue()
assert data.dtype.name in result
def save(self):
"""
Create the writer & save
"""
# GH21227 internal compression is not used when file-like passed.
if self.compression and hasattr(self.path_or_buf, 'write'):
msg = ("compression has no effect when passing file-like "
"object as input.")
warnings.warn(msg, RuntimeWarning, stacklevel=2)
# when zip compression is called.
is_zip = isinstance(self.path_or_buf,
ZipFile) or (not hasattr(self.path_or_buf, 'write')
and self.compression == 'zip')
if is_zip:
# zipfile doesn't support writing string to archive. uses string
# buffer to receive csv writing and dump into zip compression
# file handle. GH21241, GH21118
f = StringIO()
close = False
elif hasattr(self.path_or_buf, 'write'):
f = self.path_or_buf
close = False
else:
f, handles = _get_handle(self.path_or_buf,
self.mode,
encoding=self.encoding,
compression=self.compression)
close = True
try:
writer_kwargs = dict(lineterminator=self.line_terminator,
delimiter=self.sep,
quoting=self.quoting,
doublequote=self.doublequote,
escapechar=self.escapechar,
quotechar=self.quotechar)
if self.encoding == 'ascii':
self.writer = csvlib.writer(f, **writer_kwargs)
else:
writer_kwargs['encoding'] = self.encoding
self.writer = UnicodeWriter(f, **writer_kwargs)
self._save()
finally:
if is_zip:
# GH17778 handles zip compression separately.
buf = f.getvalue()
if hasattr(self.path_or_buf, 'write'):
self.path_or_buf.write(buf)
else:
f, handles = _get_handle(self.path_or_buf,
self.mode,
encoding=self.encoding,
compression=self.compression)
f.write(buf)
close = True
if close:
f.close()
for _fh in handles:
_fh.close()
def test_info_memory_usage(self):
# Ensure memory usage is displayed, when asserted, on the last line
dtypes = [
'int64', 'float64', 'datetime64[ns]', 'timedelta64[ns]',
'complex128', 'object', 'bool'
]
data = {}
n = 10
for i, dtype in enumerate(dtypes):
data[i] = np.random.randint(2, size=n).astype(dtype)
df = DataFrame(data)
buf = StringIO()
# display memory usage case
df.info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
self.assertTrue("memory usage: " in res[-1])
# do not display memory usage cas
df.info(buf=buf, memory_usage=False)
res = buf.getvalue().splitlines()
self.assertTrue("memory usage: " not in res[-1])
df.info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
# memory usage is a lower bound, so print it as XYZ+ MB
self.assertTrue(re.match(r"memory usage: [^+]+\+", res[-1]))
df.iloc[:, :5].info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
# excluded column with object dtype, so estimate is accurate
self.assertFalse(re.match(r"memory usage: [^+]+\+", res[-1]))
df_with_object_index = pd.DataFrame({'a': [1]}, index=['foo'])
df_with_object_index.info(buf=buf, memory_usage=True)
res = buf.getvalue().splitlines()
self.assertTrue(re.match(r"memory usage: [^+]+\+", res[-1]))
df_with_object_index.info(buf=buf, memory_usage='deep')
res = buf.getvalue().splitlines()
self.assertTrue(re.match(r"memory usage: [^+]+$", res[-1]))
self.assertGreater(
df_with_object_index.memory_usage(index=True, deep=True).sum(),
df_with_object_index.memory_usage(index=True).sum())
df_object = pd.DataFrame({'a': ['a']})
self.assertGreater(
df_object.memory_usage(deep=True).sum(),
df_object.memory_usage().sum())
# Test a DataFrame with duplicate columns
dtypes = ['int64', 'int64', 'int64', 'float64']
data = {}
n = 100
for i, dtype in enumerate(dtypes):
data[i] = np.random.randint(2, size=n).astype(dtype)
df = DataFrame(data)
df.columns = dtypes
# Ensure df size is as expected
# (cols * rows * bytes) + index size
df_size = df.memory_usage().sum()
exp_size = len(dtypes) * n * 8 + df.index.nbytes
self.assertEqual(df_size, exp_size)
# Ensure number of cols in memory_usage is the same as df
size_df = np.size(df.columns.values) + 1 # index=True; default
self.assertEqual(size_df, np.size(df.memory_usage()))
# assert deep works only on object
self.assertEqual(df.memory_usage().sum(),
df.memory_usage(deep=True).sum())
# test for validity
DataFrame(1, index=['a'], columns=['A']).memory_usage(index=True)
DataFrame(1, index=['a'], columns=['A']).index.nbytes
df = DataFrame(data=1,
index=pd.MultiIndex.from_product([['a'],
range(1000)]),
columns=['A'])
df.index.nbytes
df.memory_usage(index=True)
df.index.values.nbytes
# sys.getsizeof will call the .memory_usage with
# deep=True, and add on some GC overhead
diff = df.memory_usage(deep=True).sum() - sys.getsizeof(df)
self.assertTrue(abs(diff) < 100)
def test_dump_to_file(self):
f = StringIO()
ujson.dump([1, 2, 3], f)
assert "[1,2,3]" == f.getvalue()