Skip to content

Commit 738a2e5

Browse files
sdpythonsdpython
authored
Uses f strings (#29)
1 parent 5cd722d commit 738a2e5

File tree

11 files changed

+39
-48
lines changed

11 files changed

+39
-48
lines changed

‎_unittests/ut_df/test_connex_split.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -110,7 +110,7 @@ def test_split_connex(self):
110110
s2 = set(test[col])
111111
if s1 & s2:
112112
raise Exception(
113-
'Non empty intersection {0} & {1}\n{2}\n{3}'.format(s1, s2, train, test))
113+
f'Non empty intersection {s1} & {s2}\n{train}\n{test}')
114114

115115
df['connex'] = 'ole'
116116
train, test = train_test_connex_split( # pylint: disable=W0632
@@ -148,7 +148,7 @@ def test_split_connex2(self):
148148
if s1 & s2:
149149
rows = []
150150
for k, v in sorted(stats[0].items()):
151-
rows.append("{0}={1}".format(k, v))
151+
rows.append(f"{k}={v}")
152152
raise Exception(
153153
'Non empty intersection {0} & {1}\n{2}\n{3}\n{4}'.format(s1, s2, train, test, "\n".join(rows)))
154154

@@ -180,7 +180,7 @@ def test_split_connex_missing(self):
180180
if s1 & s2:
181181
rows = []
182182
for k, v in sorted(stats[0].items()):
183-
rows.append("{0}={1}".format(k, v))
183+
rows.append(f"{k}={v}")
184184
raise Exception(
185185
'Non empty intersection {0} & {1}\n{2}\n{3}\n{4}'.format(s1, s2, train, test, "\n".join(rows)))
186186

‎_unittests/ut_df/test_pandas_groupbynan.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ def test_pandas_groupbynan(self):
3131
try:
3232
self.assertIsInstance(li[-1], float)
3333
except AssertionError as e:
34-
raise AssertionError("Issue with {0}".format(ty)) from e
34+
raise AssertionError(f"Issue with {ty}") from e
3535
try:
3636
self.assertTrue(numpy.isnan(li[-1]))
3737
except AssertionError as e:

‎pandas_streaming/data/dummy.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -20,10 +20,10 @@ def dummy_streaming_dataframe(n, chunksize=10, asfloat=False, **cols):
2020
"""
2121
if asfloat:
2222
df = DataFrame(dict(cfloat=[_ + 0.1 for _ in range(0, n)], cstr=[
23-
"s{0}".format(i) for i in range(0, n)]))
23+
f"s{i}" for i in range(0, n)]))
2424
else:
2525
df = DataFrame(dict(cint=list(range(0, n)), cstr=[
26-
"s{0}".format(i) for i in range(0, n)]))
26+
f"s{i}" for i in range(0, n)]))
2727
for k, v in cols.items():
2828
df[k] = v
2929
return StreamingDataFrame.read_df(df, chunksize=chunksize)

‎pandas_streaming/df/connex_split.py

Lines changed: 7 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -48,8 +48,7 @@ def train_test_split_weights(df, weights=None, test_size=0.25, train_size=None,
4848
if weights is None:
4949
if test_size == 0 or train_size == 0:
5050
raise ValueError(
51-
"test_size={0} or train_size={1} cannot be null (1)."
52-
"".format(test_size, train_size))
51+
f"test_size={test_size} or train_size={train_size} cannot be null (1).")
5352
return train_test_split(df, test_size=test_size,
5453
train_size=train_size,
5554
random_state=random_state)
@@ -69,8 +68,7 @@ def train_test_split_weights(df, weights=None, test_size=0.25, train_size=None,
6968
test_size = 1 - p
7069
if p is None or min(test_size, p) <= 0:
7170
raise ValueError(
72-
"test_size={0} or train_size={1} cannot be null (2)."
73-
"".format(test_size, train_size))
71+
f"test_size={test_size} or train_size={train_size} cannot be null (2).")
7472
ratio = test_size / p
7573

7674
if random_state is None:
@@ -330,11 +328,9 @@ def do_connex_components(dfrows, local_groups, kb, sib):
330328
grsum = dfids[[name, one]].groupby(name, as_index=False).sum()
331329
if fLOG:
332330
for g in groups:
333-
fLOG("[train_test_connex_split] #nb in '{0}': {1}".format(
334-
g, len(set(dfids[g]))))
331+
fLOG(f"[train_test_connex_split] #nb in '{g}': {len(set(dfids[g]))}")
335332
fLOG(
336-
"[train_test_connex_split] #connex {0}/{1}".format(
337-
grsum.shape[0], dfids.shape[0]))
333+
f"[train_test_connex_split] #connex {grsum.shape[0]}/{dfids.shape[0]}")
338334
if grsum.shape[0] <= 1:
339335
raise ValueError( # pragma: no cover
340336
"Every element is in the same connected components.")
@@ -358,10 +354,9 @@ def do_connex_components(dfrows, local_groups, kb, sib):
358354
"={2}/{3}".format(k, v, cum, len(elements)))
359355

360356
# Most important component
361-
fLOG('[train_test_connex_split] first row of the biggest component '
362-
'{0}'.format(maxc))
357+
fLOG(f'[train_test_connex_split] first row of the biggest component {maxc}')
363358
tdf = dfids[dfids[name] == maxc[0]]
364-
fLOG('[train_test_connex_split] \n{0}'.format(tdf.head(n=10)))
359+
fLOG(f'[train_test_connex_split] \n{tdf.head(n=10)}')
365360

366361
# Splits.
367362
train, test = train_test_split_weights(
@@ -457,8 +452,7 @@ def train_test_apart_stratify(df, group, test_size=0.25, train_size=None,
457452
test_size = 1 - p
458453
if p is None or min(test_size, p) <= 0:
459454
raise ValueError( # pragma: no cover
460-
"test_size={0} or train_size={1} cannot be null".format(
461-
test_size, train_size))
455+
f"test_size={test_size} or train_size={train_size} cannot be null")
462456

463457
couples = df[[group, stratify]].itertuples(name=None, index=False)
464458
hist = Counter(df[stratify])

‎pandas_streaming/df/dataframe.py

Lines changed: 8 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -355,14 +355,13 @@ def read_df(df, chunksize=None, check_schema=True) -> 'StreamingDataFrame':
355355
chunksize = df.shape[0]
356356
else:
357357
raise NotImplementedError(
358-
"Cannot retrieve size to infer chunksize for type={0}"
359-
".".format(type(df)))
358+
f"Cannot retrieve size to infer chunksize for type={type(df)}.")
360359

361360
if hasattr(df, 'shape'):
362361
size = df.shape[0]
363362
else:
364363
raise NotImplementedError( # pragma: no cover
365-
"Cannot retrieve size for type={0}.".format(type(df)))
364+
f"Cannot retrieve size for type={type(df)}.")
366365

367366
def local_iterator():
368367
"local iterator"
@@ -696,10 +695,10 @@ def iterator_concat(this, lothers):
696695
if check:
697696
if list(columns) != list(df.columns):
698697
raise ValueError(
699-
"Frame others[{0}] do not have the same column names or the same order.".format(i))
698+
f"Frame others[{i}] do not have the same column names or the same order.")
700699
if list(dtypes) != list(df.dtypes):
701700
raise ValueError(
702-
"Frame others[{0}] do not have the same column types.".format(i))
701+
f"Frame others[{i}] do not have the same column types.")
703702
check = False
704703
yield df
705704

@@ -896,7 +895,7 @@ def iterate_streaming():
896895
return StreamingDataFrame(lambda: iterate_streaming(), **self.get_kwargs())
897896

898897
raise ValueError( # pragma: no cover
899-
"Unknown strategy '{0}'".format(strategy))
898+
f"Unknown strategy '{strategy}'")
900899

901900
def ensure_dtype(self, df, dtypes):
902901
"""
@@ -951,7 +950,7 @@ def __setitem__(self, index, value):
951950
"""
952951
if not isinstance(index, str):
953952
raise ValueError(
954-
"Only column affected are supported but index=%r." % index)
953+
f"Only column affected are supported but index={index!r}.")
955954
if isinstance(value, (int, float, numpy.number, str)):
956955
# Is is equivalent to add_column.
957956
iter_creation = self.iter_creation
@@ -1145,7 +1144,7 @@ def sort_values(self, by, axis=0, ascending=True, kind='quicksort',
11451144
"""
11461145
if not isinstance(by, str):
11471146
raise NotImplementedError(
1148-
"Only one column can be used to sort not %r." % by)
1147+
f"Only one column can be used to sort not {by!r}.")
11491148
keys = {}
11501149
nans = []
11511150
indices = []
@@ -1224,7 +1223,7 @@ def __init__(self, iter_creation, check_schema=True, stable=True):
12241223
self, iter_creation, check_schema=check_schema, stable=stable)
12251224
if len(self.columns) != 1:
12261225
raise RuntimeError(
1227-
"A series can contain only one column not %r." % len(self.columns))
1226+
f"A series can contain only one column not {len(self.columns)!r}.")
12281227

12291228
def apply(self, *args, **kwargs) -> 'StreamingDataFrame':
12301229
"""

‎pandas_streaming/df/dataframe_helpers.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -49,7 +49,7 @@ def hash_str(c, hash_length):
4949
if isinstance(c, float):
5050
if numpy.isnan(c):
5151
return c
52-
raise ValueError("numpy.nan expected, not {0}".format(c))
52+
raise ValueError(f"numpy.nan expected, not {c}")
5353
m = hashlib.sha256()
5454
m.update(c.encode("utf-8"))
5555
r = m.hexdigest()
@@ -70,7 +70,7 @@ def hash_int(c, hash_length):
7070
if numpy.isnan(c):
7171
return c
7272
else:
73-
raise ValueError("numpy.nan expected, not {0}".format(c))
73+
raise ValueError(f"numpy.nan expected, not {c}")
7474
else:
7575
b = struct.pack("i", c)
7676
m = hashlib.sha256()
@@ -167,7 +167,7 @@ def hash_floatl(c):
167167
df[c] = df[c].apply(hash_strl)
168168
else:
169169
raise NotImplementedError(
170-
"Conversion of type {0} in column '{1}' is not implemented".format(t, c))
170+
f"Conversion of type {t} in column '{c}' is not implemented")
171171

172172
return df
173173

@@ -413,7 +413,7 @@ def pandas_groupby_nan(df, by, axis=0, as_index=False, suffix=None, nanback=True
413413
df.columns, df.dtypes)} # pylint: disable=R1721
414414
if typ[by[0]] != do:
415415
warnings.warn( # pragma: no cover
416-
"[pandas_groupby_nan] NaN value: {0}".format(rep))
416+
f"[pandas_groupby_nan] NaN value: {rep}")
417417
return res
418418
for b in by:
419419
fnan = rep[b]
@@ -468,7 +468,7 @@ def pandas_groupby_nan(df, by, axis=0, as_index=False, suffix=None, nanback=True
468468
for b in by:
469469
if typ[b] != do:
470470
warnings.warn( # pragma: no cover
471-
"[pandas_groupby_nan] NaN values: {0}".format(rep))
471+
f"[pandas_groupby_nan] NaN values: {rep}")
472472
break
473473
return res
474474
raise NotImplementedError(

‎pandas_streaming/df/dataframe_io.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -79,22 +79,22 @@ def to_zip(df, zipfilename, zname="df.csv", **kwargs):
7979
numpy.save(stb, df, **kwargs)
8080
else:
8181
raise TypeError( # pragma: no cover
82-
"Type not handled {0}".format(type(df)))
82+
f"Type not handled {type(df)}")
8383
text = stb.getvalue()
8484

8585
if isinstance(zipfilename, str):
8686
ext = os.path.splitext(zipfilename)[-1]
8787
if ext != '.zip':
8888
raise NotImplementedError( # pragma: no cover
89-
"Only zip file are implemented not '{0}'.".format(ext))
89+
f"Only zip file are implemented not '{ext}'.")
9090
zf = zipfile.ZipFile(zipfilename, 'w') # pylint: disable=R1732
9191
close = True
9292
elif isinstance(zipfilename, zipfile.ZipFile):
9393
zf = zipfilename
9494
close = False
9595
else:
9696
raise TypeError( # pragma: no cover
97-
"No implementation for type '{0}'".format(type(zipfilename)))
97+
f"No implementation for type '{type(zipfilename)}'")
9898

9999
zf.writestr(zname, text)
100100
if close:
@@ -115,15 +115,15 @@ def read_zip(zipfilename, zname=None, **kwargs):
115115
ext = os.path.splitext(zipfilename)[-1]
116116
if ext != '.zip':
117117
raise NotImplementedError( # pragma: no cover
118-
"Only zip files are supported not '{0}'.".format(ext))
118+
f"Only zip files are supported not '{ext}'.")
119119
zf = zipfile.ZipFile(zipfilename, 'r') # pylint: disable=R1732
120120
close = True
121121
elif isinstance(zipfilename, zipfile.ZipFile):
122122
zf = zipfilename
123123
close = False
124124
else:
125125
raise TypeError( # pragma: no cover
126-
"No implementation for type '{0}'".format(type(zipfilename)))
126+
f"No implementation for type '{type(zipfilename)}'")
127127

128128
if zname is None:
129129
zname = zf.namelist()[0]

‎pandas_streaming/df/dataframe_io_helpers.py

Lines changed: 5 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -131,11 +131,11 @@ def _flatten(obj, key):
131131
if not isinstance(k, str):
132132
raise TypeError(
133133
"All keys must a string.") # pragma: no cover
134-
k2 = k if key is None else "{0}{1}{2}".format(key, sep, k)
134+
k2 = k if key is None else f"{key}{sep}{k}"
135135
_flatten(v, k2)
136136
elif isinstance(obj, (list, set)):
137137
for index, item in enumerate(obj):
138-
k2 = k if key is None else "{0}{1}{2}".format(key, sep, index)
138+
k2 = k if key is None else f"{key}{sep}{index}"
139139
_flatten(item, k2)
140140
else:
141141
flattened_dict[key] = obj
@@ -266,15 +266,14 @@ def enumerate_json_items(filename, encoding=None, lines=False, flatten=False, fL
266266
for i, (_, event, value) in enumerate(parser):
267267
if i % 1000000 == 0 and fLOG is not None:
268268
fLOG( # pragma: no cover
269-
"[enumerate_json_items] i={0} yielded={1}"
270-
"".format(i, nbyield))
269+
f"[enumerate_json_items] i={i} yielded={nbyield}")
271270
if event == "start_array":
272271
if curkey is None:
273272
current = []
274273
else:
275274
if not isinstance(current, dict):
276275
raise RuntimeError( # pragma: no cover
277-
"Type issue {0}".format(type(current)))
276+
f"Type issue {type(current)}")
278277
c = []
279278
current[curkey] = c # pylint: disable=E1137
280279
current = c
@@ -324,8 +323,7 @@ def enumerate_json_items(filename, encoding=None, lines=False, flatten=False, fL
324323
current[curkey] = None # pylint: disable=E1137
325324
curkey = None
326325
else:
327-
raise ValueError("Unknown event '{0}'".format(
328-
event)) # pragma: no cover
326+
raise ValueError(f"Unknown event '{event}'") # pragma: no cover
329327

330328

331329
class JsonIterator2Stream:

‎pandas_streaming/df/dataframe_split.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -255,7 +255,7 @@ def iterator_internal(part_requested):
255255
part = cache.get(h)
256256
if part is None:
257257
raise ValueError( # pragma: no cover
258-
"Second iteration. A row was never met in the first one\n{0}".format(obs))
258+
f"Second iteration. A row was never met in the first one\n{obs}")
259259
if part == part_requested:
260260
accumul.append(obs)
261261
if len(accumul) >= static_schema[2]:

‎pandas_streaming/exc/exc_streaming.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,4 +19,4 @@ def __init__(self, meth):
1919
:param meth: inefficient method
2020
"""
2121
Exception.__init__(
22-
self, "{0} should not be done in streaming mode.".format(meth))
22+
self, f"{meth} should not be done in streaming mode.")

0 commit comments

Comments
 (0)
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy