laptop commit linear regression

code_regression.py

@@ -16,8 +16,8 @@ def define_vocabulary(file_to_learn_new_words):
 def tokenize_list(string_input):
     words=[]
     string=string_input.replace('\\n',' ')
-    text=re.sub(r'\w+:\/{2}[\d\w-]+(\.[\d\w-]+)*(?:(?:\/[^\s/]*))*', '', string)
-    text = re.sub(r'\\n+', " ", text)
+    #text=re.sub(r'\w+:\/{2}[\d\w-]+(\.[\d\w-]+)*(?:(?:\/[^\s/]*))*', '', string)
+    text = re.sub(r'\\n+', " ", string)
     text = re.sub(r'http\S+', " ", text)
     text = re.sub(r'\/[a-z]\/', " ", text)
     text = re.sub(r'[^a-z]', " ", text)
@@ -53,7 +53,7 @@ def read_words(input_path):
     return vocabulary
 
 def train(vocabulary,input_train,expected_train):
-    learning_rate=0.0000000000001
+    learning_rate=0.00000001
     learning_precision=0.0000001
     words_vocabulary={}
     with open(input_train,encoding='utf-8') as input_file, open(expected_train,encoding='utf-8') as expected_file: