1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
import cPickle
import numpy as np
import matplotlib.pyplot as plt
import data
from data.hdf5 import taxi_it
def compute_number_coordinates():
# Count the number of coordinates
n_coordinates = 0
for ride in taxi_it('train'):
n_coordinates += len(ride['latitude'])
print n_coordinates
return n_coordinates
def extract_coordinates(n_coordinates=None):
"""Extract coordinates from the dataset and store them in a numpy array"""
if n_coordinates is None:
n_coordinates = compute_number_coordinates()
coordinates = np.zeros((n_coordinates, 2), dtype="float32")
c = 0
for ride in taxi_it('train'):
for point in zip(ride['latitude'], ride['longitude']):
coordinates[c] = point
c += 1
print c
cPickle.dump(coordinates, open(data.path + "/coordinates_array.pkl", "wb"))
def draw_map(coordinates, xrg, yrg):
print "Start drawing"
plt.figure(figsize=(30, 30), dpi=100, facecolor='w', edgecolor='k')
hist, xx, yy = np.histogram2d(coordinates[:, 0], coordinates[:, 1], bins=2000, range=[xrg, yrg])
plt.imshow(np.log(hist))
plt.gca().invert_yaxis()
plt.savefig(data.path + "/analysis/xyhmap2.png")
if __name__ == "__main__":
extract_coordinates(n_coordinates=83409386)
coordinates = cPickle.load(open(data.path + "/coordinates_array.pkl", "rb"))
xrg = [41.05, 41.25]
yrg = [-8.75, -8.55]
draw_map(coordinates, xrg, yrg)
|
