In [1]:

    

import pandas as pd


    

In [2]:

    

import numpy as np


    

In [3]:

    

print pd.__version__
print np.__version__


    

    




0.17.1
1.10.4

In [4]:

    

fname = 'sample.txt'


    

In [5]:

    

!head sample.txt


    

    




SourceID Photons AvgX AvgY
6144039378640938.000000 71 1457.802817 2692.802817
6144053114071082.000000 8 1498.125000 2696.375000
6145000614093866.000000 0 nan nan
6145000614092842.000000 0 nan nan
6144137763642410.000000 0 nan nan

In [6]:

    

df = pd.read_csv('sample.txt', sep='\s+')


    

In [7]:

    

df.head()


    

    
Out[7]:






  

    

      

      
SourceID
      
Photons
      
AvgX
      
AvgY
    
  
  

    

      
0
      
6.144039e+15
      
71
      
1457.802817
      
2692.802817
    
    

      
1
      
6.144053e+15
      
8
      
1498.125000
      
2696.375000
    
    

      
2
      
6.145001e+15
      
0
      
NaN
      
NaN
    
    

      
3
      
6.145001e+15
      
0
      
NaN
      
NaN
    
    

      
4
      
6.144138e+15
      
0
      
NaN
      
NaN
    
  

In [8]:

    

df.ix[0,0]


    

    
Out[8]:





6144039378640936.0

In [9]:

    

df.dtypes


    

    
Out[9]:





SourceID    float64
Photons       int64
AvgX        float64
AvgY        float64
dtype: object

In [10]:

    

df = pd.read_csv('sample.txt', sep='\s+', dtype={'SourceID': np.int64})


    

In [11]:

    

df.ix[0,0]


    

    
Out[11]:





6144039378640936.0

In [12]:

    

arr = np.loadtxt('sample.txt', skiprows=1)


    

In [13]:

    

arr[0,0]


    

    
Out[13]:





6144039378640938.0

In [14]:

    

arr.dtype


    

    
Out[14]:





dtype('float64')