In [15]:

    

import pandas as pd 
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt 
np.random.seed(seed=42)


    

In [43]:

    

a = np.random.random_integers(1, 100, 100)
s = np.random.dirichlet(a, 1000)
print s.shape
z = np.linspace(0,2.0,100)
pdf_names = ['pdf_' + str(i) for i in range(100)]
df = pd.DataFrame(s, columns= pdf_names)
df['z_spec'] = np.random.uniform(0,2,1000)
df['weight'] = np.random.dirichlet(a, 1000)[0,:]


    

    




(1000, 100)






    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-43-821e7d57e4d7> in <module>()
      6 df = pd.DataFrame(s, columns= pdf_names)
      7 df['z_spec'] = np.random.uniform(0,2,1000)
----> 8 df['weight'] = np.random.dirichlet(a, 1000)[0,:]

/Users/Christopher_old/anaconda/lib/python2.7/site-packages/pandas/core/frame.pyc in __setitem__(self, key, value)
   2125         else:
   2126             # set column
-> 2127             self._set_item(key, value)
   2128 
   2129     def _setitem_slice(self, key, value):

/Users/Christopher_old/anaconda/lib/python2.7/site-packages/pandas/core/frame.pyc in _set_item(self, key, value)
   2202 
   2203         self._ensure_valid_index(value)
-> 2204         value = self._sanitize_column(key, value)
   2205         NDFrame._set_item(self, key, value)
   2206 

/Users/Christopher_old/anaconda/lib/python2.7/site-packages/pandas/core/frame.pyc in _sanitize_column(self, key, value)
   2360 
   2361             # turn me into an ndarray
-> 2362             value = _sanitize_index(value, self.index, copy=False)
   2363             if not isinstance(value, (np.ndarray, Index)):
   2364                 if isinstance(value, list) and len(value) > 0:

/Users/Christopher_old/anaconda/lib/python2.7/site-packages/pandas/core/series.pyc in _sanitize_index(data, index, copy)
   2577 
   2578     if len(data) != len(index):
-> 2579         raise ValueError('Length of values does not match length of '
   2580                          'index')
   2581 

ValueError: Length of values does not match length of index

In [17]:

    

df.head()


    

    
Out[17]:






  

    

      

      
pdf_0
      
pdf_1
      
pdf_2
      
pdf_3
      
pdf_4
      
pdf_5
      
pdf_6
      
pdf_7
      
pdf_8
      
pdf_9
      
...
      
pdf_92
      
pdf_93
      
pdf_94
      
pdf_95
      
pdf_96
      
pdf_97
      
pdf_98
      
pdf_99
      
z_spec
      
weight
    
  
  

    

      
0
      
0.008092
      
0.016048
      
0.003233
      
0.015099
      
0.011225
      
0.003413
      
0.013246
      
0.018494
      
0.016217
      
0.012765
      
...
      
0.019147
      
0.011730
      
0.007820
      
0.016400
      
0.015422
      
0.014096
      
0.007739
      
0.004836
      
1.797772
      
0.009466
    
    

      
1
      
0.008682
      
0.017071
      
0.003219
      
0.011721
      
0.015499
      
0.005767
      
0.015797
      
0.017332
      
0.013524
      
0.011667
      
...
      
0.017028
      
0.012187
      
0.007438
      
0.016055
      
0.017929
      
0.016125
      
0.009620
      
0.003188
      
0.136269
      
0.016747
    
    

      
2
      
0.008310
      
0.019172
      
0.002295
      
0.013534
      
0.012054
      
0.005590
      
0.018083
      
0.017274
      
0.017286
      
0.016156
      
...
      
0.014249
      
0.012099
      
0.008920
      
0.016750
      
0.015889
      
0.017018
      
0.011053
      
0.005926
      
0.604158
      
0.003455
    
    

      
3
      
0.009450
      
0.018925
      
0.004161
      
0.014716
      
0.013958
      
0.003665
      
0.017972
      
0.018815
      
0.012034
      
0.015107
      
...
      
0.014079
      
0.013663
      
0.007994
      
0.015989
      
0.013037
      
0.015299
      
0.008846
      
0.005579
      
0.640460
      
0.015489
    
    

      
4
      
0.008485
      
0.017963
      
0.003577
      
0.015289
      
0.011353
      
0.004700
      
0.017929
      
0.017450
      
0.015599
      
0.014457
      
...
      
0.019358
      
0.014398
      
0.007598
      
0.014795
      
0.013736
      
0.019372
      
0.011800
      
0.004501
      
0.868892
      
0.011147
    
  

5 rows × 102 columns

In [8]:

    

df.to_csv('test_df.csv',index=False)


    

In [29]:

    

a =  type(df)


    

In [19]:

    

type(z)


    

    
Out[19]:





numpy.ndarray

In [27]:

    

print  type(df) == 'pandas.core.frame.DataFrame'>"


    

    




False

In [34]:

    

isinstance(z, np.ndarray)


    

    
Out[34]:





True

In [ ]: