In [1]:
%reset
In [2]:
%matplotlib inline
In [3]:
from pandas import Series, DataFrame
import pandas as pd
import numpy as np
import csv
import matplotlib.pyplot as plt
In [4]:
c_names = ['vID', 'frID', 'tFr','Timestamp', 'localX', 'localY', 'globalX','globalY', 'vLenght', 'vWidth', 'vType',
'veloc','accel', 'line', 'pred', 'foll', 'spac', 'headway']
data = pd.read_table('D:\\zzzLola\\PhD\\DataSet\\US101\\test\\1000ts.txt', sep='\t', header=None, names=c_names)
In [5]:
data[:10]
Out[5]:
In [6]:
data['vID'][:10]
Out[6]:
In [7]:
vID_counts = data['vID'].value_counts()
vID_counts[:10]
Out[7]:
In [8]:
plt.figure(figsize=(10, 4))
Out[8]:
In [9]:
vID_counts[:10].plot(kind='barh', rot=0)
Out[9]:
In [10]:
vID_count = DataFrame({'count' : data.groupby(['vID']).size()}).reset_index()
vID_mean = data.groupby('vID').mean()
In [11]:
vID_count[:10]
Out[11]:
In [12]:
veloc_mean = DataFrame({'mean_vel' : vID_mean['veloc']}).reset_index()
In [13]:
veloc_mean[:10]
Out[13]:
In [14]:
type(vID_count)
Out[14]:
In [15]:
type(veloc_mean)
Out[15]:
In [16]:
vehicles = pd.merge(vID_count,veloc_mean, on = 'vID')
In [17]:
vehicles[:10]
Out[17]:
In [21]:
max(vehicles['count'])
Out[21]:
In [25]:
vehicles.loc[vehicles['count'] == 600]
Out[25]:
In [27]:
v1280 = data.loc[data['vID'] == 1280]
In [33]:
v1280group = v1280.groupby('pred').count()
In [34]:
v1280group
Out[34]:
In [ ]:
In [17]:
np.savetxt('D:\\zzzLola\\PhD\\DataSet\\US101\\test\\vehi_small.txt',vehicles, fmt='%.10e', delimiter='\t', newline='\n')