From 9ec62bc7bb161d6549db94b58849665a76d612d5 Mon Sep 17 00:00:00 2001
From: SzamanFL <karolgrzyski@gmail.com>
Date: Sun, 17 Jan 2021 01:36:24 +0100
Subject: [PATCH] Start translator

---
 src/train.py | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)
 create mode 100644 src/train.py

diff --git a/src/train.py b/src/train.py
new file mode 100644
index 0000000..799e85f
--- /dev/null
+++ b/src/train.py
@@ -0,0 +1,37 @@
+#!/usr/bin/env python3
+
+# an LSTM language model trained on sentence pairs 
+
+import argparse
+from collection import Counter
+
+def clear_line(string, target):
+    return re.sub("[^a-z ]", "", string.lower()), re.sub("[^a-z ]", "", target.lower())
+
+def read_clear_data(in_file_path, exptected_file_path):
+    print("Reading data")
+    source_data = []
+    target_data = []
+    with open(in_file_path) as in_file, open(exptected_file_path) as exp_file:
+        for string, target in zip(in_file, exp_file):
+            string, target = clear_line(string, target)
+            source_data.appen(string)
+            target_data.appen(target)
+    return source_data, target_data
+
+def create_dict(data):
+    counter = Counter()
+    
+    for line in data:
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--in_f')
+    parser.add_argument('--exp')
+    parser.add_argument("--vocab")
+    args = parser.parse_args()
+
+    source_data, target_data = read_clear_data(args.in_f, args.exp)
+
+
+main()