In [1]:

    

%matplotlib inline

import pandas as pd
import numpy as np
import seaborn as sb
import matplotlib.pyplot as plt


    

In [2]:

    

train = pd.read_csv('../data/raw/train.csv')

print train.shape


    

    




(29118021, 6)

In [3]:

    

train.info(memory_usage='deep')


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 29118021 entries, 0 to 29118020
Data columns (total 6 columns):
row_id      int64
x           float64
y           float64
accuracy    int64
time        int64
place_id    int64
dtypes: float64(2), int64(4)
memory usage: 1.3 GB

In [4]:

    

train = train.sort_values(by=['time'], ascending=True)


    

In [5]:

    

#dataset['InstallDate'] = pd.to_datetime(dataset['time'], unit='ms')


    

In [6]:

    

train.head()


    

    
Out[6]:






  

    

      

      
row_id
      
x
      
y
      
accuracy
      
time
      
place_id
    
  
  

    

      
15280869
      
15280869
      
2.9374
      
1.0010
      
433
      
1
      
7186804346
    
    

      
23020268
      
23020268
      
5.3673
      
5.6998
      
25
      
1
      
7449653826
    
    

      
3977976
      
3977976
      
3.1148
      
3.6161
      
8
      
1
      
8090429732
    
    

      
27743788
      
27743788
      
3.7725
      
6.4504
      
65
      
2
      
4115006237
    
    

      
3836334
      
3836334
      
3.5102
      
3.6296
      
8
      
3
      
8090429732
    
  

In [7]:

    

train.tail()


    

    
Out[7]:






  

    

      

      
row_id
      
x
      
y
      
accuracy
      
time
      
place_id
    
  
  

    

      
726802
      
726802
      
0.1422
      
6.1894
      
63
      
786239
      
7811482171
    
    

      
22118299
      
22118299
      
5.6199
      
1.8609
      
165
      
786239
      
5164549189
    
    

      
13764839
      
13764839
      
5.2384
      
9.6714
      
85
      
786239
      
1291702704
    
    

      
19388897
      
19388897
      
5.4300
      
1.9423
      
35
      
786239
      
5796916425
    
    

      
11015770
      
11015770
      
5.6777
      
1.1298
      
60
      
786239
      
7588817182
    
  

In [8]:

    

train.describe()


    

    
Out[8]:






  

    

      

      
row_id
      
x
      
y
      
accuracy
      
time
      
place_id
    
  
  

    

      
count
      
2.911802e+07
      
2.911802e+07
      
2.911802e+07
      
2.911802e+07
      
2.911802e+07
      
2.911802e+07
    
    

      
mean
      
1.455901e+07
      
4.999770e+00
      
5.001814e+00
      
8.284912e+01
      
4.170104e+05
      
5.493787e+09
    
    

      
std
      
8.405649e+06
      
2.857601e+00
      
2.887505e+00
      
1.147518e+02
      
2.311761e+05
      
2.611088e+09
    
    

      
min
      
0.000000e+00
      
0.000000e+00
      
0.000000e+00
      
1.000000e+00
      
1.000000e+00
      
1.000016e+09
    
    

      
25%
      
7.279505e+06
      
2.534700e+00
      
2.496700e+00
      
2.700000e+01
      
2.030570e+05
      
3.222911e+09
    
    

      
50%
      
1.455901e+07
      
5.009100e+00
      
4.988300e+00
      
6.200000e+01
      
4.339220e+05
      
5.518573e+09
    
    

      
75%
      
2.183852e+07
      
7.461400e+00
      
7.510300e+00
      
7.500000e+01
      
6.204910e+05
      
7.764307e+09
    
    

      
max
      
2.911802e+07
      
1.000000e+01
      
1.000000e+01
      
1.033000e+03
      
7.862390e+05
      
9.999932e+09
    
  

In [ ]:

    

sb.distplot(train['accuracy'])
sb.distplot(train['x'])
sb.distplot(train['y'])
sb.distplot(train['accuracy']);
sb.distplot(train['time']);
sb.distplot(train['place_id']);


    

In [ ]:

    

sb.jointplot(x="x", y="y", data=train, kind="kde")


    

In [ ]: