决策树-dataframe (1)

DataFrame 的用法

#创建Dataframe
import pandas as pd
import numpy as np

f1=pd.DataFrame(np.random.randn(4,4),index=list('ABCD'),columns=list('ABCD'))

print(f1)

          A         B         C         D
A -0.883017 -0.026927  1.262445 -0.751374
B -0.207952 -0.187403 -0.527665  0.641382
C  0.485144 -0.987394  0.010190  2.035886
D -2.764454 -0.905228  0.179511  0.118676

f1=pd.DataFrame(np.random.randn(1,3),index=list('ABCD'),columns=list('ABCD')) # 报错原因：生成对的数字和表格不匹配

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in create_block_manager_from_blocks(blocks, axes)
   1677                 blocks = [
-> 1678                     make_block(values=blocks[0], placement=slice(0, len(axes[0])))
   1679                 ]


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\blocks.py in make_block(values, placement, klass, ndim, dtype, fastpath)
   3283 
-> 3284     return klass(values, ndim=ndim, placement=placement)
   3285 


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\blocks.py in __init__(self, values, placement, ndim)
    127                 "Wrong number of items passed {val}, placement implies "
--> 128                 "{mgr}".format(val=len(self.values), mgr=len(self.mgr_locs))
    129             )


ValueError: Wrong number of items passed 3, placement implies 4


During handling of the above exception, another exception occurred:


ValueError                                Traceback (most recent call last)

<ipython-input-6-7f52b87cad5f> in <module>
----> 1 f1=pd.DataFrame(np.random.randn(1,3),index=list('ABCD'),columns=list('ABCD')) # 报错原因：生成对的数字和表格不匹配


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in __init__(self, data, index, columns, dtype, copy)
    438                 mgr = init_dict({data.name: data}, index, columns, dtype=dtype)
    439             else:
--> 440                 mgr = init_ndarray(data, index, columns, dtype=dtype, copy=copy)
    441 
    442         # For data is list-like, or Iterable (will consume into list)


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\construction.py in init_ndarray(values, index, columns, dtype, copy)
    211         block_values = [values]
    212 
--> 213     return create_block_manager_from_blocks(block_values, [columns, index])
    214 
    215 


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in create_block_manager_from_blocks(blocks, axes)
   1686         blocks = [getattr(b, "values", b) for b in blocks]
   1687         tot_items = sum(b.shape[0] for b in blocks)
-> 1688         construction_error(tot_items, blocks[0].shape[1:], axes, e)
   1689 
   1690 


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in construction_error(tot_items, block_shape, axes, e)
   1717         raise ValueError("Empty data passed with indices specified.")
   1718     raise ValueError(
-> 1719         "Shape of passed values is {0}, indices imply {1}".format(passed, implied)
   1720     )
   1721 


ValueError: Shape of passed values is (1, 3), indices imply (4, 4)

np.random.rand(4,2) #随机生成4， 行两列的数字 ，但是没有指定范围

array([[0.6289186 , 0.39523553],
       [0.83934118, 0.20554643],
       [0.76923949, 0.85221097],
       [0.46651911, 0.10604422]])