In [1]:

    

import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

plt.rcParams["figure.figsize"] = (10,10)


    

In [2]:

    

import random
import matplotlib.patches as mpatches


    

In [3]:

    

taxi_full_pd = pd.read_csv('../data/taxi_short_2.csv')


    

In [4]:

    

center_lat = 40.76
center_lng = -73.925
dlat = 0.1
dlng = 0.1
min_lat = center_lat - dlat
max_lat = center_lat + dlat
min_lng = center_lng - dlng
max_lng = center_lng + dlng


    

In [5]:

    

taxi_pd = pd.DataFrame(taxi_full_pd[(taxi_full_pd.trip_distance <= 50) & 
                                    (taxi_full_pd.trip_distance > 0.1) &
                                    (taxi_full_pd.trip_time_in_secs > 1) &
                                    (taxi_full_pd.fare_amount < 50) &
                                    (taxi_full_pd.fare_amount*2 % 1 == 0) &
                                    (taxi_full_pd.pickup_latitude > center_lat - dlat) &
                                    (taxi_full_pd.pickup_latitude < center_lat + dlat) &
                                    (taxi_full_pd.pickup_longitude > center_lng - dlng) &
                                    (taxi_full_pd.pickup_longitude < center_lng + dlng)])

del taxi_full_pd


    

In [8]:

    

# drop garbage columns 
taxi_pd.drop(taxi_pd.columns[:2],axis=1, inplace=True)

taxi_pd.head()


    

    
Out[8]:






  

    

      

      
medallion
      
hack_license
      
pickup_datetime
      
payment_type
      
fare_amount
      
tip_amount
      
total_amount
      
dropoff_datetime
      
passenger_count
      
trip_time_in_secs
      
trip_distance
      
pickup_longitude
      
pickup_latitude
      
dropoff_longitude
      
dropoff_latitude
    
  
  

    

      
0
      
1B5C0970
      
D9613323
      
2013-02-08 23:35:14
      
CRD
      
6.0
      
0.0
      
7.0
      
2013-02-08 23:42:58
      
1
      
463
      
0.8
      
-73.992439
      
40.724487
      
-73.984421
      
40.718903
    
    

      
1
      
B42249AE
      
D4BB308D
      
2013-02-07 12:20:16
      
CRD
      
20.0
      
3.0
      
23.5
      
2013-02-07 12:50:27
      
4
      
1810
      
3.1
      
-73.989494
      
40.769588
      
-73.990303
      
40.737347
    
    

      
2
      
89069922
      
6318C3AE
      
2013-02-08 08:56:54
      
CRD
      
5.0
      
1.1
      
6.6
      
2013-02-08 08:59:43
      
1
      
168
      
1.0
      
-73.963036
      
40.799141
      
-73.972168
      
40.786446
    
    

      
3
      
74B7D835
      
D5E278C9
      
2013-02-08 09:37:02
      
CRD
      
11.0
      
2.3
      
13.8
      
2013-02-08 09:50:50
      
1
      
828
      
2.1
      
-73.987953
      
40.728764
      
-74.007118
      
40.705399
    
    

      
4
      
4003B847
      
0B766F10
      
2013-02-08 19:31:25
      
CRD
      
13.0
      
1.5
      
16.0
      
2013-02-08 19:46:23
      
1
      
897
      
3.3
      
-73.987282
      
40.743042
      
-74.010284
      
40.703964
    
  

In [9]:

    

num_lat_bins = 40
num_lng_bins = 40

lat_bins = np.linspace(min_lat, max_lat, num_lat_bins+1)
lng_bins = np.linspace(min_lng, max_lng, num_lng_bins+1)


    

In [10]:

    

print lat_bins[:5]
print lng_bins[:5]


    

    




[ 40.66   40.665  40.67   40.675  40.68 ]
[-74.025 -74.02  -74.015 -74.01  -74.005]

In [18]:

    

pick_clat = pd.cut(taxi_pd.pickup_latitude.values, lat_bins)
print pick_clat


    

    




[(40.72, 40.725], (40.765, 40.77], (40.795, 40.8], (40.725, 40.73], (40.74, 40.745], ..., (40.75, 40.755], (40.735, 40.74], (40.75, 40.755], (40.755, 40.76], (40.77, 40.775]]
Length: 13295988
Categories (40, object): [(40.66, 40.665] < (40.665, 40.67] < (40.67, 40.675] < (40.675, 40.68] ... (40.84, 40.845] < (40.845, 40.85] < (40.85, 40.855] < (40.855, 40.86]]

In [21]:

    

print pick_clat[:5]


    

    




[(40.72, 40.725], (40.765, 40.77], (40.795, 40.8], (40.725, 40.73], (40.74, 40.745]]
Categories (40, object): [(40.66, 40.665] < (40.665, 40.67] < (40.67, 40.675] < (40.675, 40.68] ... (40.84, 40.845] < (40.845, 40.85] < (40.85, 40.855] < (40.855, 40.86]]

In [22]:

    

print pick_clat.codes[:5]


    

    




[12 21 27 13 16]

In [25]:

    

print pick_clat.codes[:50]


    

    




[12 21 27 13 16 12 24 19 18 16 15 21 23 18 20 18 14 19 13 16 18 11 23 18 25
 18 25 23 20 24 16 11 24 23 15  9 17 12 20 17 13 21 12 17 16 24 18 18 14 16]

In [26]:

    

pick_clng = pd.cut(taxi_pd.pickup_longitude.values, lng_bins)
drop_clat = pd.cut(taxi_pd.dropoff_latitude.values, lat_bins)
drop_clng = pd.cut(taxi_pd.dropoff_longitude.values, lng_bins)


    

In [31]:

    

pick_s = pd.Series(taxi_pd.pickup_longitude)
drop_s = pd.Series(taxi_pd.dropoff_longitude)

print pick_s[:5]


    

    




0   -73.992439
1   -73.989494
2   -73.963036
3   -73.987953
4   -73.987282
Name: pickup_longitude, dtype: float64

In [35]:

    

pick_s.groupby([pick_clat.codes, pick_clng.codes]).count()


    

    
Out[35]:





0   0       2
    1       1
    4      15
    5     475
    6     571
    7     252
    8     489
    9     115
    10      2
    12    502
    13     58
    14     56
    15     16
    16     22
    17     15
    18     93
    19     62
    20      8
    21      6
    22      1
    23      7
    24      3
    25     21
    26      8
    27      5
    28      4
    30      1
    31      3
    33      4
    34      2
         ... 
39  8       2
    9       3
    10      2
    11      6
    12      2
    14      3
    15      1
    16      1
    17    139
    18    316
    19     31
    20     15
    21      8
    22      5
    23     24
    24     33
    25     51
    26     13
    27     24
    28      6
    29      1
    30      2
    31     27
    32      3
    33      6
    34      2
    35      5
    36      3
    37      1
    39      2
Name: pickup_longitude, dtype: int64

In [11]:

    

#bin stops (pickup or dropoff) in uniform lng/lat bins
lat_lng_mi = pd.MultiIndex.from_product([range(0, num_lat_bins), 
                                         range(0, num_lng_bins)], 
                                        names=['lat', 'lng'])
print lat_lng_mi
print lat_lng_mi.labels


    

In [27]:

    

#total number of stops (pickup or dropoff) in each lng/lat bin
stop_binned_cnts = pick_s.groupby([pick_clat.codes, pick_clng.codes]).count()


    

In [36]:

    

pick_s.groupby([pick_clat.codes, pick_clng.codes]).count().reindex(lat_lng_mi).fillna(0)


    

    
Out[36]:





lat  lng
0    0        2.0
     1        1.0
     2        0.0
     3        0.0
     4       15.0
     5      475.0
     6      571.0
     7      252.0
     8      489.0
     9      115.0
     10       2.0
     11       0.0
     12     502.0
     13      58.0
     14      56.0
     15      16.0
     16      22.0
     17      15.0
     18      93.0
     19      62.0
     20       8.0
     21       6.0
     22       1.0
     23       7.0
     24       3.0
     25      21.0
     26       8.0
     27       5.0
     28       4.0
     29       0.0
            ...  
39   10       2.0
     11       6.0
     12       2.0
     13       0.0
     14       3.0
     15       1.0
     16       1.0
     17     139.0
     18     316.0
     19      31.0
     20      15.0
     21       8.0
     22       5.0
     23      24.0
     24      33.0
     25      51.0
     26      13.0
     27      24.0
     28       6.0
     29       1.0
     30       2.0
     31      27.0
     32       3.0
     33       6.0
     34       2.0
     35       5.0
     36       3.0
     37       1.0
     38       0.0
     39       2.0
Name: pickup_longitude, dtype: float64

In [37]:

    

stop_binned_cnts_ri = stop_binned_cnts.reindex(lat_lng_mi).fillna(0)


    

In [38]:

    

stop_binned_cnts_ri.values[:5]


    

    
Out[38]:





array([  2.,   1.,   0.,   0.,  15.])

In [40]:

    

stop_binned_cnts_ri[:5]


    

    
Out[40]:





lat  lng
0    0       2.0
     1       1.0
     2       0.0
     3       0.0
     4      15.0
Name: pickup_longitude, dtype: float64

In [ ]: