From 290c68795d8100cc97b8b53d80f331e536fc71b1 Mon Sep 17 00:00:00 2001
From: davidovski <david@sendula.com>
Date: Wed, 30 Nov 2022 10:06:56 +0000
Subject: Added files to repository

---
 src/neuralnetwork/generate_alphabets.py | 44 +++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 src/neuralnetwork/generate_alphabets.py

(limited to 'src/neuralnetwork/generate_alphabets.py')

diff --git a/src/neuralnetwork/generate_alphabets.py b/src/neuralnetwork/generate_alphabets.py
new file mode 100644
index 0000000..0b1e18e
--- /dev/null
+++ b/src/neuralnetwork/generate_alphabets.py
@@ -0,0 +1,44 @@
+import training
+import os
+import sys
+
+if __name__ == "__main__":
+
+    # List all the directories containing country datasets to populate the countries dictionary
+    countries = training.get_countries()
+
+    for c, country in countries.items():
+        print(f"processing {c}...", end="")
+        sys.stdout.flush()
+
+        letters = {}
+
+        # get all the names in a country's dataset
+        all_names = country.get_all()
+
+        # iterate through all letters in the all of the names
+        for name in all_names:
+
+            # preprocess the name
+            name = country.preprocess(name)
+
+            for letter in name:
+                if letter in letters:
+                    letters[letter] += 1
+                else:
+                    letters[letter] = 1
+
+        print(f" found {len(letters)} in {len(all_names)} names... ", end="")
+        sys.stdout.flush()
+
+        # sort the letters by occurrence
+        letters_sorted = [l for l in letters]
+        letters_sorted.sort()
+        # output sorted letters to a file
+        with open(os.path.join(country.path, "alphabet.txt"), "w") as file:
+            for letter in letters_sorted:
+                file.write(letter)
+                file.write("\n")
+
+        print("saved!")
+        sys.stdout.flush()
-- 
cgit v1.2.1