notebook.community

Edit and run 





In [2]:



    


import pandas as pd
import numpy as np



    











In [3]:



    


d= pd.read_csv('rec.csv')



    











In [4]:



    


d.head()



    


















    
Out[4]:










  
    

      
      medallion
      hack_license
      pickup_datetime
      dropoff_datetime
      passenger_count
      trip_time_in_secs
      trip_distance
      pickup_longitude
      dropoff_longitude
      pickup_latitude
      dropoff_latitude
      fare_amount
      surcharg
      mta_tax
      tip_amount
      tolls_amount
      total_amount
      new_total
    

  
  
    

      0
      2013003229
      2013003226
      2013-03-26 00:00:00
      2013-03-26 00:07:00
      1
      420
      2.63
      -73.977592
      -73.954391
      40.759293
      40.784023
      9.0
      0.5
      0.5
      2.85
      0.0
      12.85
      12.85
    

    

      1
      2013007090
      2013007086
      2013-03-26 00:00:00
      2013-03-26 00:02:00
      1
      120
      0.36
      -73.957893
      -73.960381
      40.811256
      40.814125
      4.0
      0.5
      0.5
      0.90
      0.0
      5.90
      5.90
    

    

      2
      2013002078
      2013002075
      2013-03-26 00:00:00
      2013-03-26 00:16:00
      1
      960
      5.38
      -73.992180
      -73.938820
      40.734428
      40.791225
      18.0
      0.5
      0.5
      5.55
      0.0
      24.55
      24.55
    

    

      3
      2013010107
      2013010107
      2013-03-26 00:00:00
      2013-03-26 00:14:00
      1
      840
      2.70
      -73.982513
      -73.975044
      40.762150
      40.735542
      13.0
      0.5
      0.5
      0.00
      0.0
      14.00
      14.00
    

    

      4
      2013009601
      2013007484
      2013-03-26 00:00:00
      2013-03-26 00:20:00
      1
      1200
      6.74
      -73.995155
      -73.943954
      40.749981
      40.711658
      22.0
      0.5
      0.5
      6.75
      0.0
      29.75
      29.75
    

  




















In [5]:



    


d['hack_license'].count()



    


















    
Out[5]:








2470654

















In [6]:



    


d['day']=d['pickup_datetime'].apply(lambda x: x.split()[0].split('-')[2])



    











In [7]:



    


d.head()



    


















    
Out[7]:










  
    

      
      medallion
      hack_license
      pickup_datetime
      dropoff_datetime
      passenger_count
      trip_time_in_secs
      trip_distance
      pickup_longitude
      dropoff_longitude
      pickup_latitude
      dropoff_latitude
      fare_amount
      surcharg
      mta_tax
      tip_amount
      tolls_amount
      total_amount
      new_total
      day
    

  
  
    

      0
      2013003229
      2013003226
      2013-03-26 00:00:00
      2013-03-26 00:07:00
      1
      420
      2.63
      -73.977592
      -73.954391
      40.759293
      40.784023
      9.0
      0.5
      0.5
      2.85
      0.0
      12.85
      12.85
      26
    

    

      1
      2013007090
      2013007086
      2013-03-26 00:00:00
      2013-03-26 00:02:00
      1
      120
      0.36
      -73.957893
      -73.960381
      40.811256
      40.814125
      4.0
      0.5
      0.5
      0.90
      0.0
      5.90
      5.90
      26
    

    

      2
      2013002078
      2013002075
      2013-03-26 00:00:00
      2013-03-26 00:16:00
      1
      960
      5.38
      -73.992180
      -73.938820
      40.734428
      40.791225
      18.0
      0.5
      0.5
      5.55
      0.0
      24.55
      24.55
      26
    

    

      3
      2013010107
      2013010107
      2013-03-26 00:00:00
      2013-03-26 00:14:00
      1
      840
      2.70
      -73.982513
      -73.975044
      40.762150
      40.735542
      13.0
      0.5
      0.5
      0.00
      0.0
      14.00
      14.00
      26
    

    

      4
      2013009601
      2013007484
      2013-03-26 00:00:00
      2013-03-26 00:20:00
      1
      1200
      6.74
      -73.995155
      -73.943954
      40.749981
      40.711658
      22.0
      0.5
      0.5
      6.75
      0.0
      29.75
      29.75
      26
    

  




















In [72]:



    


d['hour']=d['pickup_datetime'].apply(lambda x: x.split()[1].split(':')[0])



    











In [73]:



    


d.columns



    


















    
Out[73]:








Index(['medallion', 'hack_license', 'pickup_datetime', 'dropoff_datetime',
       'passenger_count', 'trip_time_in_secs', 'trip_distance',
       'pickup_longitude', 'dropoff_longitude', 'pickup_latitude',
       'dropoff_latitude', 'fare_amount', 'surcharg', 'mta_tax', 'tip_amount',
       'tolls_amount', 'total_amount', 'new_total', 'day', 'hour'],
      dtype='object')

















In [74]:



    


p=d[(d['pickup_latitude']>40.6725) & (d['pickup_latitude']<40.6925) &(d['pickup_longitude']<-73.9650) & (d['pickup_longitude']>-73.9850)]



    











In [75]:



    


p['hack_license'].count()



    


















    
Out[75]:








9704

















In [8]:



    


def sector(lat,lon):
    val=0
    if ((lat<40.8645) and (lat >40.8145) and (lon>-74.0286) and (lon<-73.9386)):
        val= 1
    elif ((lat<40.8145) and (lat >40.7645) and (lon>-74.0286) and (lon<-73.9386)):
        val=2
    elif ((lat<40.7645) and (lat >40.7145) and (lon>-74.0286) and (lon<-73.9386)):
        val=3
    elif ((lat<40.7145) and (lat >40.6645) and (lon>-74.0286) and (lon<-73.9386)):
        val=4
    elif ((lat<40.6645) and (lat >40.6145) and (lon>-74.0286) and (lon<-73.9386)):
        val=5
    elif ((lat<40.6145) and (lat >40.5645) and (lon>-74.0286) and (lon<-73.9386)):
        val=6
    elif ((lat<40.8645) and (lat >40.8145) and (lon>-73.9386) and (lon<-73.8586)):
        val=7
    elif ((lat<40.8145) and (lat >40.7645) and (lon>-73.9386) and (lon<-73.8586)):
        val=8
    elif ((lat<40.7645) and (lat >40.7145) and (lon>-73.9386) and (lon<-73.8586)):
        val=9
    elif ((lat<40.7145) and (lat >40.6645) and (lon>-73.9386) and (lon<-73.8586)):
        val=10
    elif ((lat<40.6645) and (lat >40.6145) and (lon>-73.9386) and (lon<-73.8586)):
        val=11
    elif ((lat<40.6145) and (lat >40.5645) and (lon>-73.9386) and (lon<-73.8586)):
        val=12
    return val



    











In [9]:



    


l=[]
for i in range(len(p)):
    l.append(sector(p.iloc[i]['dropoff_latitude'],p.iloc[i]['dropoff_longitude']))
p['sector']=l



    


















    






---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-9-a1de9993d373> in <module>()
      1 l=[]
----> 2 for i in range(len(p)):
      3     l.append(sector(p.iloc[i]['dropoff_latitude'],p.iloc[i]['dropoff_longitude']))
      4 p['sector']=l

NameError: name 'p' is not defined
















In [80]:



    


p26=p[p['day']=='26']
p27=p[p['day']=='27']
p28=p[p['day']=='28']
p29=p[p['day']=='29']
p30=p[p['day']=='30']
p31=p[p['day']=='31']



    











In [81]:



    


data_p=[p26,p27,p28,p29,p30,p31]



    











In [82]:



    


import pickle
pickle.dump(data_p,open('data_days.p','wb'))



    











In [83]:



    


# Sector of 'Barclays Center'
print(sector(40.6825,-73.9750))



    


















    






4

















In [ ]:

Content source: ankurlathwal/taxiridesharing

Similar notebooks:

notebook.community | gallery | about