In [1]:

    

%reset


    

    




Once deleted, variables cannot be recovered. Proceed (y/[n])? y

In [3]:

    

from pandas import Series, DataFrame
import pandas as pd
import numpy as np
import csv
import math
import matplotlib.pyplot as plt
from scipy.signal import hilbert, chirp
import scipy


    

In [4]:

    

c_dist = ['Timestamp','vIDa', 'vIDb', 'dist_ab', 'v_a_Type', 'v_a_Vel', 'v_a_Line', 'v_a_Pred', 'v_a_Foll']

data_dist = pd.read_table('D:\\zzzLola\\PhD\\DataSet\\US101\\test\\dist_1000ts.txt', sep='\t', header=None, names=c_dist)


    

In [5]:

    

c_vehic = ['vIDa', 'count','mean_vel']

data_vehic = pd.read_table('D:\\zzzLola\\PhD\\DataSet\\US101\\test\\vehi_1000ts.txt', sep='\t', header=None, names=c_vehic)


    

In [6]:

    

dataset = pd.merge(data_dist,data_vehic, on = 'vIDa')


    

In [7]:

    

dataset['dist_ab'] = dataset.dist_ab * 0.3048
dataset['v_a_Vel'] = dataset.v_a_Vel * 0.3048
dataset['mean_vel'] = dataset.mean_vel * 0.3048
dataset[:10]


    

    
Out[7]:






  

    

      

      
Timestamp
      
vIDa
      
vIDb
      
dist_ab
      
v_a_Type
      
v_a_Vel
      
v_a_Line
      
v_a_Pred
      
v_a_Foll
      
count
      
mean_vel
    
  
  

    

      
0
      
1.118847e+12
      
1073
      
1077
      
26.760834
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
1
      
1.118847e+12
      
1073
      
1080
      
9.739521
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
2
      
1.118847e+12
      
1073
      
1081
      
19.198605
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
3
      
1.118847e+12
      
1073
      
1082
      
20.679750
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
4
      
1.118847e+12
      
1073
      
1083
      
56.396881
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
5
      
1.118847e+12
      
1073
      
1084
      
40.510313
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
6
      
1.118847e+12
      
1073
      
1086
      
56.592865
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
7
      
1.118847e+12
      
1073
      
1087
      
19.093697
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
8
      
1.118847e+12
      
1073
      
1088
      
83.171880
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
    

      
9
      
1.118847e+12
      
1073
      
1089
      
15.309671
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
    
  

In [8]:

    

dataset['delt_vel'] = dataset.v_a_Vel - dataset.mean_vel

#dataset['delt_vel'] = delta_vel


    

In [9]:

    

dataset[:10]


    

    
Out[9]:






  

    

      

      
Timestamp
      
vIDa
      
vIDb
      
dist_ab
      
v_a_Type
      
v_a_Vel
      
v_a_Line
      
v_a_Pred
      
v_a_Foll
      
count
      
mean_vel
      
delt_vel
    
  
  

    

      
0
      
1.118847e+12
      
1073
      
1077
      
26.760834
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
1
      
1.118847e+12
      
1073
      
1080
      
9.739521
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
2
      
1.118847e+12
      
1073
      
1081
      
19.198605
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
3
      
1.118847e+12
      
1073
      
1082
      
20.679750
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
4
      
1.118847e+12
      
1073
      
1083
      
56.396881
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
5
      
1.118847e+12
      
1073
      
1084
      
40.510313
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
6
      
1.118847e+12
      
1073
      
1086
      
56.592865
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
7
      
1.118847e+12
      
1073
      
1087
      
19.093697
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
8
      
1.118847e+12
      
1073
      
1088
      
83.171880
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
    

      
9
      
1.118847e+12
      
1073
      
1089
      
15.309671
      
2
      
18.263616
      
2
      
0
      
1083
      
22
      
18.18894
      
0.074676
    
  

In [10]:

    

np.savetxt('D:\\zzzLola\\PhD\\DataSet\\US101\\test\\dataset.txt',dataset, fmt='%.10e', delimiter='\t', newline='\n')


    

In [10]:

    

type(dataset)


    

    
Out[10]:





pandas.core.frame.DataFrame

In [11]:

    

del t


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-11-14ac1cb05b5a> in <module>()
----> 1 del t

NameError: name 't' is not defined

In [ ]:

    

dataset.groupby(['Timestamp', 'vIDa']).mean()


    

In [ ]:

    

v1280 = dataset.loc[dataset['vIDa'] == 1280]


    

In [ ]:

    

v1280.groupby('v_a_Line').count()


    

In [ ]:

    

for key, grp in dataset.groupby(['Timestamp']):
    plt.plot(grp['vIDa'], label=key)
    grp['mean_vel'] = pd.rolling_mean(grp['vIDa'], window=5)    
    plt.plot(grp['mean_vel'], label='rolling ({k})'.format(k=key))
plt.legend(loc='best')    
plt.show()


    

In [40]:

    




    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-40-45b2189a6a0b> in <module>()
----> 1 dataset.groupby(['vIDa']).apply(toeach_category)

C:\Anaconda2\lib\site-packages\pandas\core\groupby.pyc in apply(self, func, *args, **kwargs)
    713         # ignore SettingWithCopy here in case the user mutates
    714         with option_context('mode.chained_assignment',None):
--> 715             return self._python_apply_general(f)
    716 
    717     def _python_apply_general(self, f):

C:\Anaconda2\lib\site-packages\pandas\core\groupby.pyc in _python_apply_general(self, f)
    717     def _python_apply_general(self, f):
    718         keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 719                                                    self.axis)
    720 
    721         return self._wrap_applied_output(keys, values,

C:\Anaconda2\lib\site-packages\pandas\core\groupby.pyc in apply(self, f, data, axis)
   1404             # group might be modified
   1405             group_axes = _get_axes(group)
-> 1406             res = f(group)
   1407             if not _is_indexed_like(res, group_axes):
   1408                 mutated = True

C:\Anaconda2\lib\site-packages\pandas\core\groupby.pyc in f(g)
    709         @wraps(func)
    710         def f(g):
--> 711             return func(g, *args, **kwargs)
    712 
    713         # ignore SettingWithCopy here in case the user mutates

<ipython-input-37-3096143b616e> in toeach_category(subf)
      1 def toeach_category(subf):
----> 2     result = subf[['Timestamp']].applymap(percentage)

NameError: global name 'percentage' is not defined

In [ ]: