Часто задаваемые вопросы (FAQ)

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

In [11]: if pd.Series([False, True, False]):
   ....:     print("I was true")
   ....: 
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In [11], line 1
----> 1 if pd.Series([False, True, False]):
      2     print("I was true")

File ~/work/pandas/pandas/pandas/core/generic.py:1526, in NDFrame.__nonzero__(self)
   1524 @final
   1525 def __nonzero__(self) -> NoReturn:
-> 1526     raise ValueError(
   1527         f"The truth value of a {type(self).__name__} is ambiguous. "
   1528         "Use a.empty, a.bool(), a.item(), a.any() or a.all()."
   1529     )

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 [14]: pd.Series([True]).bool()
Out[14]: True

In [15]: pd.Series([False]).bool()
Out[15]: False

In [16]: pd.DataFrame([[True]]).bool()
Out[16]: True

In [17]: pd.DataFrame([[False]]).bool()
Out[17]: False

In [25]: values = [0, 1, 2, 3, 4, 5]

In [26]: n_removed = 0

In [27]: 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 [28]: values
Out[28]: [1, 4, 5]

In [29]: def f(s):
   ....:     s.pop("a")
   ....:     return s
   ....: 

In [30]: df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})

In [31]: try:
   ....:     df.apply(f, axis="columns")
   ....: except Exception as err:
   ....:     print(repr(err))
   ....: 
KeyError('a')

In [32]: values = [0, 1, 2, 3, 4, 5]

In [33]: n_removed = 0

In [34]: 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 [35]: values
Out[35]: [1, 3, 5]

In [36]: def f(s):
   ....:     s = s.copy()
   ....:     s.pop("a")
   ....:     return s
   ....: 

In [37]: df = pd.DataFrame({"a": [1, 2, 3], 'b': [4, 5, 6]})

In [38]: df.apply(f, axis="columns")
Out[38]: 
   b
0  4
1  5
2  6

In [51]: x = np.array(list(range(10)), ">i4")  # big endian

In [52]: newx = x.byteswap().newbyteorder()  # force native byteorder

In [53]: s = pd.Series(newx)