stuff

review_svm.py

@@ -15,11 +15,14 @@
 NEGATION_WORDS = ["not", "isn't", "didn't", "doesn't"]
 PUNCTUATION = [".", "!", "?", ",", ";"]
 
+NORMAL_LENGTH = 1000
+
 # TODO Make these command-line parameters.
 USE_PRESENCE = False                       # If true, use presence rather than frequency.
-GRAM_LENGTH  = 1                           # Unigrams, bigrams, ...
+GRAM_LENGTH  = 3                           # Unigrams, bigrams, ...
 NUM_FOLDS    = 3                           # For cross-validation (Pang & Lee used 3)
-EPSILON      = 0.01                        # determines how long the algorithm runs
+EPSILON      = 0.001                       # determines how long the algorithm runs (default is 0.001)
+KERNEL_TYPE  = 0                           # 0: linear, 2: radial basis
 
 def make_bag(filename):
   f = open(filename)
@@ -48,80 +51,79 @@ def make_bag(filename):
     else:
       bag_of_words[index] = 1
       count += 1
-  # Normalize the bag of words.
-  #for k in bag_of_words.keys():
-  #  bag_of_words[k] = float(bag_of_words[k])/count
-
+  # Normalize the bag of words.  For whatever reason it didn't work very well with small decimals...
+  for k in bag_of_words.keys():
+    bag_of_words[k] = float(NORMAL_LENGTH*bag_of_words[k])/count
   return bag_of_words
 
-neg_filenames = []
 pos_filenames = []
+neg_filenames = []
 word_table = {}
 next_word_index = 0
 
-for (folder, x, filenames) in os.walk(NEG_FOLDER):
-  for filename in filenames:
-    if filename.endswith(".txt"):
-      neg_filenames.append(folder + "\\" + filename)
-
 for (folder, x, filenames) in os.walk(POS_FOLDER):
   for filename in filenames:
     if filename.endswith(".txt"):
       pos_filenames.append(folder + "\\" + filename)
 
-random.shuffle(neg_filenames)
-random.shuffle(pos_filenames)
-neg_folds = [[] for i in range(NUM_FOLDS)]
+for (folder, x, filenames) in os.walk(NEG_FOLDER):
+  for filename in filenames:
+    if filename.endswith(".txt"):
+      neg_filenames.append(folder + "\\" + filename)
+
+# Partition reviews into folds.
 pos_folds = [[] for i in range(NUM_FOLDS)]
-for i in range(len(neg_filenames)):
-  neg_folds[i % NUM_FOLDS].append(neg_filenames[i])
+neg_folds = [[] for i in range(NUM_FOLDS)]
 
 for i in range(len(pos_filenames)):
   pos_folds[i % NUM_FOLDS].append(pos_filenames[i])
 
-#TRAIN
-
-#neg_fold_bags = [[] for i in range(NUM_FOLDS)]
-#pos_fold_bags = [[] for i in range(NUM_FOLDS)]
+for i in range(len(neg_filenames)):
+  neg_folds[i % NUM_FOLDS].append(neg_filenames[i])
 
+# Construct a bag of words (or n-grams) from each file.
+pos_fold_bags = [[] for i in range(NUM_FOLDS)]
+neg_fold_bags = [[] for i in range(NUM_FOLDS)]
+
 for i in range(NUM_FOLDS):
+  for filename in pos_folds[i]:
+    pos_fold_bags[i].append(make_bag(filename))
+
+  for filename in neg_folds[i]:
+    neg_fold_bags[i].append(make_bag(filename))
 
-  neg_train_bags = []
+
+for i in range(NUM_FOLDS):
   pos_train_bags = []
+  neg_train_bags = []
 
-  neg_train_filenames = []
   pos_train_filenames = []
-  neg_test_filenames = neg_folds[i]
+  neg_train_filenames = []
+
   pos_test_filenames = pos_folds[i]
+  neg_test_filenames = neg_folds[i]
+
   for j in range(NUM_FOLDS):
     if j != i:
-      neg_train_filenames += neg_folds[j]
       pos_train_filenames += pos_folds[j]
+      neg_train_filenames += neg_folds[j]
+      pos_train_bags += pos_fold_bags[j]
+      neg_train_bags += neg_fold_bags[j]
 
-  for filename in neg_train_filenames:
-    neg_train_bags.append(make_bag(filename))
-
-  for filename in pos_train_filenames:
-    pos_train_bags.append(make_bag(filename))
-
-  train_labels = [-1] * len(neg_train_bags) + [1] * len(pos_train_bags)
-  train_bags = neg_train_bags + pos_train_bags
+  train_labels = [1] * len(pos_train_bags) + [-1] * len(neg_train_bags)
+  train_bags = pos_train_bags + neg_train_bags
 
   # TODO: Investigate LIBSVM training parameters.
-  m = svm_train(train_labels, train_bags, "-t 0 -e %d" % EPSILON)
-
-  # TEST
-  test_bags = []
-  test_filenames = neg_test_filenames + pos_test_filenames
-
-  for filename in test_filenames:
-    test_bags.append(make_bag(filename))
+  m = svm_train(train_labels, train_bags, "-t %d -e %f" % (KERNEL_TYPE, EPSILON))
 
-  test_labels = [-1] * len(neg_test_filenames) + [1] * len(pos_test_filenames)
-  (train_labels, acc, p_vals) = svm_predict(test_labels, test_bags, m)
-  #indices = random.sample(range(len(test_filenames)))
-  #for i in indices:
-  #  filename = test_filenames[i]
-  #  if filename in neg_
+  test_bags = pos_fold_bags[i] + neg_fold_bags[i]
+  test_filenames = pos_test_filenames + neg_test_filenames
+  test_labels = [1] * len(pos_test_filenames) + [-1] * len(neg_test_filenames)
 
-#sorted(bag_of_words.items(), key=lambda (k,v): -v)[:100]
+  (predicted_labels, acc, p_vals) = svm_predict(test_labels, test_bags, m)
+  indices = random.sample(range(len(test_filenames)), 10)
+  filenames_labels = {}
+  for j in indices:
+    filename = test_filenames[j]
+    predicted_label = predicted_labels[j]
+    filenames_labels[filename] = predicted_labels[j]