Add files via upload

Author: JakeCob

EnglishTest(30%).txt

@@ -30,22 +30,22 @@ def sentence_tokenizer(sentence_list) :
 def translate() :
     tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
     f_Output = ""
-    with open("input.txt") as f:
+    with open("input.txt", encoding="utf-8") as f:
         tagalog_data = f.readlines()
 
     tagalog_lines = sentence_tokenizer(tagalog_data)
 
     tagalog_sentences = list()
-    for line in tagalog_lines :
+    for line in tagalog_lines:
         l = tokenizer.tokenize(line)
-        for sen in l :
+        for sen in l:
             tagalog_sentences.append(sen)
 
-    otp_file = open("output.txt", "w+")
-    for index in range(len(tagalog_sentences)) :
+    otp_file = open("output.txt", "w+", encoding="utf-8")
+    for index in range(len(tagalog_sentences)):
         current_sentence = tagalog_sentences[index]
         translated_sentence = ModelTester.sentence_tester1(current_sentence, 1)
         otp_file.write(translated_sentence)
-        otp_file.write(". ")
+        otp_file.write(". \n")
 
     print("Successfully translated! Translated document is 'output.txt' ")

TagalogTest(30%).txt

@@ -0,0 +1,41 @@
+Changes:
+
+File: (DutchtoEnglish.py)
+
+DutchtoEnglish.py ->TagalogtoEnglish.py
+
+final_list -> f_list
+index -> index_list
+output_sentence -> otp_sentence
+final_output -> f_output
+current_sen -> current_sentence
+curr_translated_sen -> translated_sentence
+out_file -> otp_file
+
+File: (EnglishtoTagalog.py)
+
+EnglishtoDutch.py ->EnglishtoTagalog.py
+final_list -> f_list
+index -> index_list
+l -> curr_line
+current_sen -> current_sentence
+curr_translated_sen -> translated_sentence
+out_file -> otp_file
+
+File: (utlis.py)
+
+nCr -> n_factorial_r
+f -> factorial
+
+
+
+
+
+
+
+
+
+
+
+
+

TagalogtoEnglish.py

@@ -0,0 +1,15 @@
+Program:
+• Test other data sets for training model 
+• Create an algorithm that will get the BLEU score (Cedric, Miguel, Hakob)
+• Change the variable, method, and file names of the programs (Note* yung main, model_trainer, ibm1_em, at utils ay napalitan ko na yung iba so yung mga di pa na lang ang gawin siguro) (Cedric)
+	update (nabago na ni cedric yung tagalogtoenglish at englishtotagalog) ✔
+• Disseminate the train, test, and validation of data 
+• Document the results
+• Try to improve the accuracy
+• Edit the input and output text. Make sure the system will work
+
+Document:
+• Chapter 1 - Abstract, motivation (Ruffy) ✔
+• Chapter 2 - RRL (Jessie, Miguel) ✔
+• Chapter 4 - Implementation
+• Chapter 5 - Conclusion