Change regexes

predict.py

@@ -30,14 +30,14 @@ def calc_post_prob(post, paranormal_class_logprob, sceptic_class_logprob, word_l
         for token in tokens:
             token = clear_tokens(token, False)
             try:
-                product += word_logprobs[class_][token]
+                product *= word_logprobs[class_][token]
             except KeyError:
-                product += 0
+                product *= 1
             # tu wzoru uzyj
         if class_ == 'sceptic':
-            product +=  sceptic_class_logprob
+            product *=  sceptic_class_logprob
         elif class_ == 'paranormal':
-            product += paranormal_class_logprob
+            product *= paranormal_class_logprob
         probs[abs(product)] = class_
         #print(probs)
 # mozna jeszcze zrobic aby bralo kluczowe slowa i wtedy decydowalo ze paranormal
@@ -46,7 +46,7 @@ def calc_post_prob(post, paranormal_class_logprob, sceptic_class_logprob, word_l
     return probs[max(probs.keys())]
 
 def search_for_keywords(text):
-    keywords = ['paranormal', 'ufo', 'aliens', 'conspiracy', 'aliens']
+    keywords = ['paranormal', 'ufo', 'aliens', 'conspiracy', 'aliens', 'atlantis']
     return any(keyword in text for keyword in keywords)
 
 def main():
@@ -55,10 +55,10 @@ def main():
     paranormal_class_logprob = pickle_list[0]
     sceptic_class_logprob = pickle_list[1]
     word_logprobs = pickle_list[2]
-    #in_file = "test-A/in.tsv"
-    in_file = "dev-0/in.tsv"
-    #out_file = "test-A/out.tsv"
-    out_file = "dev-0/out.tsv"
+    in_file = "test-A/in.tsv"
+    #in_file = "dev-0/in.tsv"
+    out_file = "test-A/out.tsv"
+    #out_file = "dev-0/out.tsv"
     print (f"in {in_file}")
     print (f"out {out_file}")
     with open(in_file) as in_f, open(out_file, 'w') as out_f:

train.py

@@ -74,10 +74,10 @@ def calc_word_logprobs(word_counts):
     return word_logprobs
 
 def main():
-    #expected = './train/expected.tsv'
-    expected = './dev-0/expected.tsv'
-    #in_f = './train/in.tsv'
-    in_f = './dev-0/in.tsv'
+    expected = './train/expected.tsv'
+    #expected = './dev-0/expected.tsv'
+    in_f = './train/in.tsv'
+    #in_f = './dev-0/in.tsv'
     print (f"expected {expected}")
     print (f"in {in_f}")
     paranormal_class_lgprob, skeptic_class_logprob = calc_class_logprob(expected)