Merge pull request #3761 from mgsergio/booking-name-matching

[booking] Booking name matching

2 files changed, 9 insertions, 5 deletions

diff --git a/tools/python/booking_hotels.py b/tools/python/booking_hotels.py
index f684505036..8912fdebe9 100755
--- a/tools/python/booking_hotels.py
+++ b/tools/python/booking_hotels.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # coding: utf8
 from __future__ import print_function
 
@@ -126,7 +126,8 @@ def translate(source, output):
     '''
     Reads *.pkl files and produces a single list of hotels as tab separated values.
     '''
-    files = [filename for filename in os.listdir(source) if filename.endswith('.pkl')]
+    files = [os.path.join(source, filename)
+             for filename in os.listdir(source) if filename.endswith('.pkl')]
 
     data = []
     for filename in sorted(files):
@@ -207,6 +208,7 @@ def process_options():
     if not options.download and not options.translate:
         parser.print_help()
 
+    # TODO(mgsergio): implpement it with argparse facilities.
     if options.translate and not options.output:
         print("--output isn't set")
         parser.print_help()
diff --git a/tools/python/booking_hotels_quality.py b/tools/python/booking_hotels_quality.py
index 9c81dad52a..cd82adfd2d 100755
--- a/tools/python/booking_hotels_quality.py
+++ b/tools/python/booking_hotels_quality.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # coding: utf8
 from __future__ import print_function
 
@@ -14,6 +14,7 @@ import os
 import pickle
 import time
 import urllib2
+import re
 
 # init logging
 logging.basicConfig(level=logging.DEBUG, format='[%(asctime)s] %(levelname)s: %(message)s')
@@ -21,7 +22,7 @@ logging.basicConfig(level=logging.DEBUG, format='[%(asctime)s] %(levelname)s: %(
 
 def load_binary_list(path):
     """
-    Loads binary classifier output.
+    Loads reference binary classifier output.
     """
     bits = []
     with open(path, 'r') as fd:
@@ -41,11 +42,12 @@ def load_score_list(path):
         for line in fd:
             if (not line.strip()) or line[0] == '#':
                 continue
-            scores.append(float(line[line.rfind(':')+2:]))
+            scores.append(float(re.search(r'result score: (\d*\.\d+)', line).group(1)))
     return scores
 
 
 def process_options():
+    # TODO(mgsergio): Fix description.
     parser = argparse.ArgumentParser(description="Download and process booking hotels.")
     parser.add_argument("-v", "--verbose", action="store_true", dest="verbose")
     parser.add_argument("-q", "--quiet", action="store_false", dest="verbose")