Skip to content

CLN: Replacing %s with .format in pandas/core/frame.py #20461

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Apr 17, 2018
Merged

CLN: Replacing %s with .format in pandas/core/frame.py #20461

Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2756fb7
Replacing %s with ,format in /core/frame.py
AaronCritchley Mar 22, 2018
2e2ddda
Using !s instead of str()
AaronCritchley Mar 22, 2018
4f877ba
Merge remote-tracking branch 'upstream/master' into AaronCritchley-cl…
TomAugspurger Mar 28, 2018
2808545
Merge branch 'master' into cln-16130-core-frame
AaronCritchley Apr 17, 2018
9931432
Changing string to unicode in _put_str
AaronCritchley Apr 17, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 49 additions & 35 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -410,7 +410,7 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
arr = np.array(data, dtype=dtype, copy=copy)
except (ValueError, TypeError) as e:
exc = TypeError('DataFrame constructor called with '
'incompatible data and dtype: %s' % e)
'incompatible data and dtype: {e}'.format(e=e))
raise_with_traceback(exc)

if arr.ndim == 0 and index is not None and columns is not None:
Expand Down Expand Up @@ -536,8 +536,9 @@ def _get_axes(N, K, index=index, columns=columns):
try:
values = values.astype(dtype)
except Exception as orig:
e = ValueError("failed to cast to '%s' (Exception was: %s)"
% (dtype, orig))
e = ValueError("failed to cast to '{dtype}' (Exception "
"was: {orig})".format(dtype=dtype,
orig=orig))
raise_with_traceback(e)

index, columns = _get_axes(*values.shape)
Expand Down Expand Up @@ -888,8 +889,9 @@ def dot(self, other):
lvals = self.values
rvals = np.asarray(other)
if lvals.shape[1] != rvals.shape[0]:
raise ValueError('Dot product shape mismatch, %s vs %s' %
(lvals.shape, rvals.shape))
raise ValueError('Dot product shape mismatch, '
'{l} vs {r}'.format(l=lvals.shape,
r=rvals.shape))

if isinstance(other, DataFrame):
return self._constructor(np.dot(lvals, rvals), index=left.index,
Expand All @@ -903,7 +905,7 @@ def dot(self, other):
else:
return Series(result, index=left.index)
else: # pragma: no cover
raise TypeError('unsupported type: %s' % type(other))
raise TypeError('unsupported type: {oth}'.format(oth=type(other)))

# ----------------------------------------------------------------------
# IO methods (to / from other formats)
Expand Down Expand Up @@ -1105,7 +1107,7 @@ def to_dict(self, orient='dict', into=dict):
return into_c((t[0], dict(zip(self.columns, t[1:])))
for t in self.itertuples())
else:
raise ValueError("orient '%s' not understood" % orient)
raise ValueError("orient '{o}' not understood".format(o=orient))

def to_gbq(self, destination_table, project_id, chunksize=10000,
verbose=True, reauth=False, if_exists='fail', private_key=None):
Expand Down Expand Up @@ -2108,7 +2110,7 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
lines.append(self.index._summary())

if len(self.columns) == 0:
lines.append('Empty %s' % type(self).__name__)
lines.append('Empty {name}'.format(name=type(self).__name__))
fmt.buffer_put_lines(buf, lines)
return

Expand All @@ -2134,13 +2136,15 @@ def _verbose_repr():
space = max(len(pprint_thing(k)) for k in self.columns) + 4
counts = None

tmpl = "%s%s"
tmpl = "{count}{dtype}"
if show_counts:
counts = self.count()
if len(cols) != len(counts): # pragma: no cover
raise AssertionError('Columns must equal counts (%d != %d)'
% (len(cols), len(counts)))
tmpl = "%s non-null %s"
raise AssertionError(
'Columns must equal counts '
'({cols:d} != {counts:d})'.format(
cols=len(cols), counts=len(counts)))
tmpl = "{count} non-null {dtype}"

dtypes = self.dtypes
for i, col in enumerate(self.columns):
Expand All @@ -2151,7 +2155,8 @@ def _verbose_repr():
if show_counts:
count = counts.iloc[i]

lines.append(_put_str(col, space) + tmpl % (count, dtype))
lines.append(_put_str(col, space) + tmpl.format(count=count,
dtype=dtype))

def _non_verbose_repr():
lines.append(self.columns._summary(name='Columns'))
Expand All @@ -2160,9 +2165,12 @@ def _sizeof_fmt(num, size_qualifier):
# returns size in human readable format
for x in ['bytes', 'KB', 'MB', 'GB', 'TB']:
if num < 1024.0:
return "%3.1f%s %s" % (num, size_qualifier, x)
return ("{num:3.1f}{size_q}"
"{x}".format(num=num, size_q=size_qualifier, x=x))
num /= 1024.0
return "%3.1f%s %s" % (num, size_qualifier, 'PB')
return "{num:3.1f}{size_q} {pb}".format(num=num,
size_q=size_qualifier,
pb='PB')

if verbose:
_verbose_repr()
Expand All @@ -2175,8 +2183,9 @@ def _sizeof_fmt(num, size_qualifier):
_verbose_repr()

counts = self.get_dtype_counts()
dtypes = ['%s(%d)' % k for k in sorted(compat.iteritems(counts))]
lines.append('dtypes: %s' % ', '.join(dtypes))
dtypes = ['{k}({kk:d})'.format(k=k[0], kk=k[1]) for k
in sorted(compat.iteritems(counts))]
lines.append('dtypes: {types}'.format(types=', '.join(dtypes)))

if memory_usage is None:
memory_usage = get_option('display.memory_usage')
Expand All @@ -2194,8 +2203,9 @@ def _sizeof_fmt(num, size_qualifier):
self.index._is_memory_usage_qualified()):
size_qualifier = '+'
mem_usage = self.memory_usage(index=True, deep=deep).sum()
lines.append("memory usage: %s\n" %
_sizeof_fmt(mem_usage, size_qualifier))
lines.append("memory usage: {mem}\n".format(
mem=_sizeof_fmt(mem_usage, size_qualifier)))

fmt.buffer_put_lines(buf, lines)

def memory_usage(self, index=True, deep=False):
Expand Down Expand Up @@ -2981,8 +2991,8 @@ def select_dtypes(self, include=None, exclude=None):

# can't both include AND exclude!
if not include.isdisjoint(exclude):
raise ValueError('include and exclude overlap on %s' %
(include & exclude))
raise ValueError('include and exclude overlap on {inc_ex}'.format(
inc_ex=(include & exclude)))

# empty include/exclude -> defaults to True
# three cases (we've already raised if both are empty)
Expand Down Expand Up @@ -3832,7 +3842,8 @@ def set_index(self, keys, drop=True, append=False, inplace=False,

if verify_integrity and not index.is_unique:
duplicates = index.get_duplicates()
raise ValueError('Index has duplicate keys: %s' % duplicates)
raise ValueError('Index has duplicate keys: {dup}'.format(
dup=duplicates))

for c in to_remove:
del frame[c]
Expand Down Expand Up @@ -4204,7 +4215,7 @@ def dropna(self, axis=0, how='any', thresh=None, subset=None,
mask = count > 0
else:
if how is not None:
raise ValueError('invalid how option: %s' % how)
raise ValueError('invalid how option: {h}'.format(h=how))
else:
raise TypeError('must specify how or thresh')

Expand Down Expand Up @@ -6738,8 +6749,8 @@ def _count_level(self, level, axis=0, numeric_only=False):
agg_axis = frame._get_agg_axis(axis)

if not isinstance(count_axis, MultiIndex):
raise TypeError("Can only count levels on hierarchical %s." %
self._get_axis_name(axis))
raise TypeError("Can only count levels on hierarchical "
"{ax}.".format(ax=self._get_axis_name(axis)))

if frame._is_mixed_type:
# Since we have mixed types, calling notna(frame.values) might
Expand Down Expand Up @@ -6817,9 +6828,9 @@ def f(x):
elif filter_type == 'bool':
data = self._get_bool_data()
else: # pragma: no cover
e = NotImplementedError("Handling exception with filter_"
"type %s not implemented." %
filter_type)
e = NotImplementedError(
"Handling exception with filter_type {f} not"
"implemented.".format(f=filter_type))
raise_with_traceback(e)
with np.errstate(all='ignore'):
result = f(data.values)
Expand All @@ -6831,8 +6842,8 @@ def f(x):
elif filter_type == 'bool':
data = self._get_bool_data()
else: # pragma: no cover
msg = ("Generating numeric_only data with filter_type %s"
"not supported." % filter_type)
msg = ("Generating numeric_only data with filter_type {f}"
"not supported.".format(f=filter_type))
raise NotImplementedError(msg)
values = data.values
labels = data._get_agg_axis(axis)
Expand Down Expand Up @@ -7107,7 +7118,8 @@ def to_timestamp(self, freq=None, how='start', axis=0, copy=True):
elif axis == 1:
new_data.set_axis(0, self.columns.to_timestamp(freq=freq, how=how))
else: # pragma: no cover
raise AssertionError('Axis must be 0 or 1. Got %s' % str(axis))
raise AssertionError('Axis must be 0 or 1. Got {ax!s}'.format(
ax=axis))

return self._constructor(new_data)

Expand Down Expand Up @@ -7138,7 +7150,8 @@ def to_period(self, freq=None, axis=0, copy=True):
elif axis == 1:
new_data.set_axis(0, self.columns.to_period(freq=freq))
else: # pragma: no cover
raise AssertionError('Axis must be 0 or 1. Got %s' % str(axis))
raise AssertionError('Axis must be 0 or 1. Got {ax!s}'.format(
ax=axis))

return self._constructor(new_data)

Expand Down Expand Up @@ -7499,8 +7512,9 @@ def _convert_object_array(content, columns, coerce_float=False, dtype=None):
else:
if len(columns) != len(content): # pragma: no cover
# caller's responsibility to check for this...
raise AssertionError('%d columns passed, passed data had %s '
'columns' % (len(columns), len(content)))
raise AssertionError('{col:d} columns passed, passed data had '
'{con} columns'.format(col=len(columns),
con=len(content)))

# provide soft conversion of object dtypes
def convert(arr):
Expand Down Expand Up @@ -7575,4 +7589,4 @@ def _from_nested_dict(data):


def _put_str(s, space):
return ('%s' % s)[:space].ljust(space)
return '{s}'.format(s=s)[:space].ljust(space)
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey @TomAugspurger, thanks for merging in master, it looks like CI is failing here when given a unicode value for s:

s = 'σ', space = 5

    def _put_str(s, space):
>       return '{s}'.format(s=s)[:space].ljust(space)
E       UnicodeEncodeError: 'ascii' codec can't encode character u'\u03c3' in position 0: ordinal not in range(128)

I'm not sure on how Pandas approaches unicode and what the preferred way of solving is, I'm happy to implement something but would rather make sure it's in the Pandas style.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

To clarify, not at my laptop atm but I have a feeling just making this:

u'{s}'.format(s=s)[:space].ljust(space)

would fix it, but it doesn't seem consistent with other .format occurrences, this could all be from a lack of understanding of how Pandas generally handles unicode though.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The u prefix is appropriate here.