Linear regression first try

predict.py

@@ -2,7 +2,7 @@
 
 import sys
 import pickle
-from math import log
+from math import log, exp
 from tokenizer import tokenize
 
 #Load model
@@ -19,8 +19,7 @@ for line in sys.stdin:
     for word in terms:
         y_predicted += weights[word_to_index_mapping.get(word,0)] * (word_count.get(word,0) / len(word_count))
 
-
-    if y_predicted <= 0.63:
+    if y_predicted <= 0.5:
         print(0)
     else:
-        print(1)
+        print(1)

train.py

@@ -1,8 +1,17 @@
 #!/usr/bin/python3
 
+'''
+Linear regression for paranormal and sceptic challange 2.0.0
+In order to use train.py you need to pass two columns
+label   document
+splited by \t
+Commands used: xzcat, paste
+'''
+
 import sys
 import pickle
 import random
+from math import log, exp
 import collections
 from tokenizer import tokenize
 
@@ -76,7 +85,7 @@ def train():
         #We will stop after loss reach some value
 
         if Loss_sum_counter % 10000 == 0:
-            print(Loss_sum / 10000)
+            print(str(Loss_sum_counter) + "   " + str(Loss_sum / 10000))
             Loss_sum = 0.0
         Loss_sum_counter += 1
 
@@ -87,13 +96,13 @@ def train():
             if word in word_to_index_mapping:
                 weights[word_to_index_mapping[word]] -= ((word_count[word] / len(word_count)) * delta)
 
-        if Loss_sum_counter > 50000000:
+        if Loss_sum_counter > 10000000:
             break
         
 
 
 
-    #We save only things we need for predicion
+    #We save only things we need for prediction
     model = (weights, word_to_index_mapping, word_count)
     pickle.dump(model, open("model.pkl", "wb"))