taxi

commit 71bb4d90da2bad933fdca48d1879886fe7aa9bc8
parent de76aae44b6c0cbe9ab42c7ae215c3ae9e4e4055
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date:   Mon,  4 May 2015 13:15:33 -0400

Add make_valid_cut

Diffstat:
A
make_valid_cut.py
 | 
40
++++++++++++++++++++++++++++++++++++++++

1 file changed, 40 insertions(+), 0 deletions(-)
diff --git a/make_valid_cut.py b/make_valid_cut.py
@@ -0,0 +1,40 @@
+# Cuts the training dataset at the following timestamps :
+
+cuts = [
+    1376503200,
+    1380616200,
+    1381167900,
+    1383364800,
+    1387722600,
+]
+
+import random
+import csv
+import ast
+
+f = open("train.csv")
+fr = csv.reader(f)
+_skip_header = fr.next()
+g = open("cutvalid.csv", "w")
+gw = csv.writer(g)
+
+for l in fr:
+    polyline = ast.literal_eval(l[-1])
+    if len(polyline) == 0: continue
+    time = int(l[5])
+    for ts in cuts:
+        if time <= ts and time + 15 * (len(polyline) - 1) >= ts:
+            # keep it
+            n = (ts - time) / 15 + 1
+            cut = polyline[:n]
+            row = l[:-1] + [
+                        cut.__str__(),
+                        polyline[-1][0],
+                        polyline[-1][1],
+                        15 * (len(polyline)-1)
+                    ]
+            print row
+            gw.writerow(row)
+
+f.close()
+g.close()