

In [63]:

    
# -*- coding: utf-8 -*-
import pandas as pd
import numpy as np

if __name__ =='__main__':
    df = pd.read_csv('4g_gongcan.csv')
    print df.columns
    df = df[['CGI',u'lng',u'lat']]
#     print df['LAC','CI']]

    df['LAC'] = [x.split('-')[2] if type(x) is not float else '0' for x in df['CGI']]
    df['CI'] = [x.split('-')[3] if type(x) is not float else '0' for x in df['CGI']]
#     for i,x in  enumerate(df['CGI']):
#         if type(x) is float:
#             print x, i
    df = df.drop('CGI',axis=1)
#     print df.values[43462]
#     print df
    df.to_csv('4g_gongcan_tran.csv',index=False)









    



Index([u'ʱ��', u'CGI', u'����', u'����ά����', u'��������', u'����E-NODEB',
       u'С��������', u'С��Ӣ����', u'lng', u'lat', u'�豸ά��״̬', u'����״̬',
       u'��������', u'���ǳ���', u'��������֡����', u'������֡ģʽ', u'С������',
       u'����Ƶ��', u'������Ƶ���ŵ���', u'��Ƶ����', u'��������', u'����С��ʶ����',
       u'����С����ʶ', u'���������', u'��е�����', u'�������', u'��λ��',
       u'���߹Ҹ�', u'PRACH��������', u'�ο��źŹ���', u'LTEС����LTE��������',
       u'LTEС����TD��������', u'LTEС����GSM��������', u'����������', u'��ַ',
       u'��طֹ�˾'],
      dtype='object')
[nan nan '0' '0']
              lng        lat     LAC   CI
0      121.321895  31.187843  107797    3
1      121.321895  31.187843  107797    2
2      121.321895  31.187843  107797    1
3      121.512601  31.239761  114810   36
4      121.366102  31.155093  112408    1
5      121.366102  31.155093  112408    2
6             NaN        NaN  107002   43
7      121.064681  30.913801   30992   13
8      121.064681  30.913801   30992   12
9      121.064681  30.913801   30992   11
10     121.512601  31.239761  114810   33
11     121.328871  31.826981  118694   11
12     121.328871  31.826981  118694   13
13     121.328871  31.826981  118694   12
14     121.045881  30.916731   30995  140
15     121.045881  30.916731   30995  141
16     121.045881  30.916731   30995  139
17     121.512601  31.239761  114810   35
18     121.431016  30.892545  113991   11
19     121.431016  30.892545  113991   12
20     121.431016  30.892545  113991   13
21     121.512601  31.239761  114810   34
22     121.413887  31.200176  111883   11
23     121.413887  31.200176  111883   12
24     121.392805  31.268684  103847   11
25     121.392805  31.268684  103847   12
26     121.392805  31.268684  103847   13
27     121.429391  31.146781  113124   33
28     121.336561  30.746311  102126   33
29     121.314841  31.289581  109782   34
...           ...        ...     ...  ...
62229  121.397418  31.296851  101233    1
62230  121.397418  31.296851  101233    2
62231  121.397418  31.296851  101233    3
62232  121.397418  31.296851  101233    4
62233  121.397418  31.296851  101233    5
62234  121.397418  31.296851  101233    6
62235  121.447891  31.235721  111856   33
62236  121.451111  31.302181  104068    1
62237  121.451111  31.302181  104068    2
62238  121.451111  31.302181  104068    3
62239  121.161545  31.369161  109581   12
62240  121.161545  31.369161  109581   13
62241  121.161545  31.369161  109581   11
62242  121.095421  30.868561  106139   16
62243  121.095421  30.868561  106139   14
62244  121.095421  30.868561  106139   15
62245  121.095421  30.868561  106139   12
62246  121.095421  30.868561  106139   13
62247  121.095421  30.868561  106139   11
62248  121.560911  31.248951  106953   33
62249         NaN        NaN  103108   45
62250         NaN        NaN  103108   44
62251  121.896771  30.877001  103108   43
62252  121.896771  30.877001  103108   35
62253  121.896771  30.877001  103108   34
62254  121.896771  30.877001  103108   33
62255  121.412326  31.301267  101141   11
62256  121.412326  31.301267  101141   12
62257         NaN        NaN       0    0
62258         NaN        NaN       0    0

[62259 rows x 4 columns]