taxi

commit b6566c010be7c871a5b6c199feaf1dfda0910ade
parent 97e9ac0e15b890076af0cf469efbead89f8eb804
Author: AdeB <adbrebs@gmail.com>
Date:   Thu, 16 Jul 2015 18:59:50 -0400

Fix a bug in the heatmap generation

Diffstat:
M
data_analysis/maps.py
 | 
28
++++++++++------------------

1 file changed, 10 insertions(+), 18 deletions(-)
diff --git a/data_analysis/maps.py b/data_analysis/maps.py
@@ -2,22 +2,16 @@ import cPickle
 import numpy as np
 import matplotlib.pyplot as plt
 
-from fuel.schemes import ConstantScheme
-from fuel.streams import DataStream
-
 import data
-from data.hdf5 import TaxiDataset, TaxiStream
+from data.hdf5 import taxi_it
 
 
 def compute_number_coordinates():
-    dataset = TaxiDataset('train')
-    stream = DataStream(dataset, iteration_scheme=ConstantScheme(1, dataset.num_examples))
-    train_it = stream.get_epoch_iterator()
 
     # Count the number of coordinates
     n_coordinates = 0
-    for ride in train_it:
-        n_coordinates += len(ride[2])
+    for ride in taxi_it('train'):
+        n_coordinates += len(ride['latitude'])
     print n_coordinates
 
     return n_coordinates
@@ -29,17 +23,14 @@ def extract_coordinates(n_coordinates=None):
     if n_coordinates is None:
         n_coordinates = compute_number_coordinates()
 
-    dataset = TaxiDataset('train')
-    stream = DataStream(dataset, iteration_scheme=ConstantScheme(1, dataset.num_examples))
-
     coordinates = np.zeros((n_coordinates, 2), dtype="float32")
-    train_it = stream.get_epoch_iterator()
 
     c = 0
-    for ride in train_it:
-        for point in zip(ride[2], ride[3]):
+    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"))
@@ -52,13 +43,14 @@ def draw_map(coordinates, xrg, yrg):
     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=32502730)
+    extract_coordinates(n_coordinates=83409386)
 
     coordinates = cPickle.load(open(data.path + "/coordinates_array.pkl", "rb"))
-    xrg = [-8.75, -8.55]
-    yrg = [41.05, 41.25]
+    xrg = [41.05, 41.25]
+    yrg = [-8.75, -8.55]
     draw_map(coordinates, xrg, yrg)