Pandas 中文参考指南

In [1]: dtypes = [
   ...:     "int64",
   ...:     "float64",
   ...:     "datetime64[ns]",
   ...:     "timedelta64[ns]",
   ...:     "complex128",
   ...:     "object",
   ...:     "bool",
   ...: ]
   ...:

In [2]: n = 5000

In [3]: data = {t: np.random.randint(100, size=n).astype(t) for t in dtypes}

In [4]: df = pd.DataFrame(data)

In [5]: df["categorical"] = df["object"].astype("category")

In [6]: df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5000 entries, 0 to 4999
Data columns (total 8 columns):
 #   Column           Non-Null Count  Dtype
---  ------           --------------  -----
 0   int64            5000 non-null   int64
 1   float64          5000 non-null   float64
 2   datetime64[ns]   5000 non-null   datetime64[ns]
 3   timedelta64[ns]  5000 non-null   timedelta64[ns]
 4   complex128       5000 non-null   complex128
 5   object           5000 non-null   object
 6   bool             5000 non-null   bool
 7   categorical      5000 non-null   category
dtypes: bool(1), category(1), complex128(1), datetime64[ns](1), float64(1), int64(1), object(1), timedelta64[ns](1)
memory usage: 288.2+ KB

In [7]: df.info(memory_usage="deep")
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5000 entries, 0 to 4999
Data columns (total 8 columns):
 #   Column           Non-Null Count  Dtype
---  ------           --------------  -----
 0   int64            5000 non-null   int64
 1   float64          5000 non-null   float64
 2   datetime64[ns]   5000 non-null   datetime64[ns]
 3   timedelta64[ns]  5000 non-null   timedelta64[ns]
 4   complex128       5000 non-null   complex128
 5   object           5000 non-null   object
 6   bool             5000 non-null   bool
 7   categorical      5000 non-null   category
dtypes: bool(1), category(1), complex128(1), datetime64[ns](1), float64(1), int64(1), object(1), timedelta64[ns](1)
memory usage: 424.7 KB

In [8]: df.memory_usage()
Out[8]:
Index                128
int64              40000
float64            40000
datetime64[ns]     40000
timedelta64[ns]    40000
complex128         80000
object             40000
bool                5000
categorical         9968
dtype: int64

# total memory usage of dataframe
In [9]: df.memory_usage().sum()
Out[9]: 295096

In [10]: df.memory_usage(index=False)
Out[10]:
int64              40000
float64            40000
datetime64[ns]     40000
timedelta64[ns]    40000
complex128         80000
object             40000
bool                5000
categorical         9968
dtype: int64

>>> if pd.Series([False, True, False]):
...     pass

In [11]: if pd.Series([False, True, False]):
   ....:     print("I was true")
   ....:
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-11-5c782b38cd2f> in ?()
----> 1 if pd.Series([False, True, False]):
      2     print("I was true")

~/work/pandas/pandas/pandas/core/generic.py in ?(self)
   1575     @final
   1576     def __nonzero__(self) -> NoReturn:
-> 1577         raise ValueError(
   1578             f"The truth value of a {type(self).__name__} is ambiguous. "
   1579             "Use a.empty, a.bool(), a.item(), a.any() or a.all()."
   1580         )

ValueError: The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().

In [12]: if pd.Series([False, True, False]) is not None:
   ....:     print("I was not None")
   ....:
I was not None

In [13]: if pd.Series([False, True, False]).any():
   ....:     print("I am any")
   ....:
I am any

In [21]: values = [0, 1, 2, 3, 4, 5]

In [22]: n_removed = 0

In [23]: for k, value in enumerate(values):
   ....:     idx = k - n_removed
   ....:     if value % 2 == 1:
   ....:         del values[idx]
   ....:         n_removed += 1
   ....:     else:
   ....:         values[idx] = value + 1
   ....:

In [24]: values
Out[24]: [1, 4, 5]

In [25]: def f(s):
   ....:     s.pop("a")
   ....:     return s
   ....:

In [26]: df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})

In [27]: df.apply(f, axis="columns")
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
File ~/work/pandas/pandas/pandas/core/indexes/base.py:3805, in Index.get_loc(self, key)
   3804 try:
-> 3805     return self._engine.get_loc(casted_key)
   3806 except KeyError as err:

File index.pyx:167, in pandas._libs.index.IndexEngine.get_loc()

File index.pyx:196, in pandas._libs.index.IndexEngine.get_loc()

File pandas/_libs/hashtable_class_helper.pxi:7081, in pandas._libs.hashtable.PyObjectHashTable.get_item()

File pandas/_libs/hashtable_class_helper.pxi:7089, in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'a'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
Cell In[27], line 1
----> 1 df.apply(f, axis="columns")

File ~/work/pandas/pandas/pandas/core/frame.py:10374, in DataFrame.apply(self, func, axis, raw, result_type, args, by_row, engine, engine_kwargs, **kwargs)
  10360 from pandas.core.apply import frame_apply
  10362 op = frame_apply(
  10363     self,
  10364     func=func,
   (...)
  10372     kwargs=kwargs,
  10373 )
> 10374 return op.apply().__finalize__(self, method="apply")

File ~/work/pandas/pandas/pandas/core/apply.py:916, in FrameApply.apply(self)
    913 elif self.raw:
    914     return self.apply_raw(engine=self.engine, engine_kwargs=self.engine_kwargs)
--> 916 return self.apply_standard()

File ~/work/pandas/pandas/pandas/core/apply.py:1063, in FrameApply.apply_standard(self)
   1061 def apply_standard(self):
   1062     if self.engine == "python":
-> 1063         results, res_index = self.apply_series_generator()
   1064     else:
   1065         results, res_index = self.apply_series_numba()

File ~/work/pandas/pandas/pandas/core/apply.py:1081, in FrameApply.apply_series_generator(self)
   1078 with option_context("mode.chained_assignment", None):
   1079     for i, v in enumerate(series_gen):
   1080         # ignore SettingWithCopy here in case the user mutates
-> 1081         results[i] = self.func(v, *self.args, **self.kwargs)
   1082         if isinstance(results[i], ABCSeries):
   1083             # If we have a view on v, we need to make a copy because
   1084             #  series_generator will swap out the underlying data
   1085             results[i] = results[i].copy(deep=False)

Cell In[25], line 2, in f(s)
      1 def f(s):
----> 2     s.pop("a")
      3     return s

File ~/work/pandas/pandas/pandas/core/series.py:5391, in Series.pop(self, item)
   5366 def pop(self, item: Hashable) -> Any:
   5367     """
   5368     Return item and drops from series. Raise KeyError if not found.
   5369
   (...)
   5389     dtype: int64
   5390     """
-> 5391     return super().pop(item=item)

File ~/work/pandas/pandas/pandas/core/generic.py:947, in NDFrame.pop(self, item)
    946 def pop(self, item: Hashable) -> Series | Any:
--> 947     result = self[item]
    948     del self[item]
    950     return result

File ~/work/pandas/pandas/pandas/core/series.py:1121, in Series.__getitem__(self, key)
   1118     return self._values[key]
   1120 elif key_is_scalar:
-> 1121     return self._get_value(key)
   1123 # Convert generator to list before going through hashable part
   1124 # (We will iterate through the generator there to check for slices)
   1125 if is_iterator(key):

File ~/work/pandas/pandas/pandas/core/series.py:1237, in Series._get_value(self, label, takeable)
   1234     return self._values[label]
   1236 # Similar to Index.get_value, but we do not fall back to positional
-> 1237 loc = self.index.get_loc(label)
   1239 if is_integer(loc):
   1240     return self._values[loc]

File ~/work/pandas/pandas/pandas/core/indexes/base.py:3812, in Index.get_loc(self, key)
   3807     if isinstance(casted_key, slice) or (
   3808         isinstance(casted_key, abc.Iterable)
   3809         and any(isinstance(x, slice) for x in casted_key)
   3810     ):
   3811         raise InvalidIndexError(key)
-> 3812     raise KeyError(key) from err
   3813 except TypeError:
   3814     # If we have a listlike key, _check_indexing_error will raise
   3815     #  InvalidIndexError. Otherwise we fall through and re-raise
   3816     #  the TypeError.
   3817     self._check_indexing_error(key)

KeyError: 'a'

In [28]: values = [0, 1, 2, 3, 4, 5]

In [29]: n_removed = 0

In [30]: for k, value in enumerate(values.copy()):
   ....:     idx = k - n_removed
   ....:     if value % 2 == 1:
   ....:         del values[idx]
   ....:         n_removed += 1
   ....:     else:
   ....:         values[idx] = value + 1
   ....:

In [31]: values
Out[31]: [1, 3, 5]

In [32]: def f(s):
   ....:     s = s.copy()
   ....:     s.pop("a")
   ....:     return s
   ....:

In [33]: df = pd.DataFrame({"a": [1, 2, 3], 'b': [4, 5, 6]})

In [34]: df.apply(f, axis="columns")
Out[34]:
   b
0  4
1  5
2  6

Traceback
    ...
ValueError: Big-endian buffer not supported on little-endian compiler

In [49]: x = np.array(list(range(10)), ">i4")  # big endian

In [50]: newx = x.byteswap().view(x.dtype.newbyteorder())  # force native byteorder

In [51]: s = pd.Series(newx)