Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+joystick_move_model.keras filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,20 +1,83 @@
----
-title: Street Fighter Move Recognizer
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
-license: mit
----
-
-# Welcome to Streamlit!
-
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
-
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+---
+tags:
+- deep-learning
+- lstm
+- game-ai
+- sequence-classification
+- streamlit-app
+---
+
+# 🎮 Street Fighter Move Recognizer
+
+Bu proje, joystick kombinasyonlarını analiz ederek oyuncunun hangi **özel hareketi** yapmak istediğini tahmin eden bir makine öğrenimi modelini içermektedir. Veri simüle edilmiştir ve Street Fighter benzeri dövüş oyunlarından esinlenilmiştir.
+
+## 🧠 Proje Hedefi
+
+Joystick sekanslarından (`["DOWN", "RIGHT", "PUNCH"]` gibi) yola çıkarak hangi **move (hareket)** yapıldığını sınıflandıran bir sekans model geliştirmek. Bu, oyun AI sistemlerinin temel yapı taşlarından biridir.
+
+---
+
+## 📊 Kullanılan Veri
+
+Veri seti manuel olarak oluşturulmuştur ve aşağıdaki gibi örnek joystick girişlerinden ve etiketli hareket isimlerinden oluşur:
+
+| Joystick Sequence           | Move           |
+|-----------------------------|----------------|
+| DOWN,RIGHT,PUNCH            | Hadouken       |
+| RIGHT,DOWN,RIGHT,KICK       | Shoryuken      |
+| LEFT,LEFT,PUNCH             | Dash Punch     |
+| DOWN,KICK                   | Low Kick       |
+| LEFT,DOWN,RIGHT,PUNCH       | Combo Strike   |
+| ...                         | ...            |
+
+---
+
+## 🔧 Kullanılan Teknolojiler
+
+- **TensorFlow / Keras** – LSTM model ile sekans sınıflandırma
+- **scikit-learn** – LabelEncoder
+- **Streamlit** – Web arayüzü
+- **Pickle** – Model nesnelerinin kaydedilmesi
+- **Hugging Face Hub** – Model paylaşımı
+- **GitHub** – Kod ve dokümantasyon paylaşımı
+
+---
+
+## 🏗️ Model Mimarisi
+
+- `Tokenizer` ile joystick girişleri tokenize edildi
+- `pad_sequences` ile sabit uzunlukta girişe dönüştürüldü
+- `LSTM` tabanlı sekans modeli eğitildi
+- `LabelEncoder` ile sınıf etiketleri dönüştürüldü
+- Model `.keras`, `tokenizer.pkl`, `label_encoder.pkl` olarak kaydedildi
+
+---
+
+## 🚀 Streamlit Uygulaması
+
+Kullanıcıdan joystick kombinasyonu alınır ve model ile eşleşen hareket tahmin edilir.
+
+### Uygulamayı Başlatmak İçin:
+```bash
+streamlit run app.py
+
+
+🔬 Örnek Tahmin
+DOWN,RIGHT,PUNCH
+Çıktı:
+Tahmin Edilen Hareket: Hadouken
+
+
+
+💡 Gelecekte Ne Yapılabilir?
+Gerçek zamanlı joystick verisi entegrasyonu
+
+Sesli komut tanıma ile komboları tetikleme
+
+Mobil uyumlu arayüz
+
+Daha fazla kombo ile veri setinin genişletilmesi
+
+
+📚 Eğitim Amaçlıdır
+Bu proje, oyun zekası ve sekans modellemeyi birleştiren bir örnek olarak eğitim amaçlı geliştirilmiştir.

Street Fighter Move Recognizer.ipynb

@@ -0,0 +1,480 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a38a8be9-9f57-4d4e-b101-704e636db4fe",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: tensorflow in c:\\programdata\\anaconda3\\lib\\site-packages (2.19.0)\n",
+      "Requirement already satisfied: scikit-learn in c:\\programdata\\anaconda3\\lib\\site-packages (1.6.1)\n",
+      "Requirement already satisfied: pandas in c:\\programdata\\anaconda3\\lib\\site-packages (2.2.3)\n",
+      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (2.1.0)\n",
+      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (1.6.3)\n",
+      "Requirement already satisfied: flatbuffers>=24.3.25 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (25.2.10)\n",
+      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (0.6.0)\n",
+      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (0.2.0)\n",
+      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (18.1.1)\n",
+      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (3.4.0)\n",
+      "Requirement already satisfied: packaging in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (24.2)\n",
+      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (5.29.3)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (2.32.3)\n",
+      "Requirement already satisfied: setuptools in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (72.1.0)\n",
+      "Requirement already satisfied: six>=1.12.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (1.17.0)\n",
+      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (2.5.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorflow) (4.12.2)\n",
+      "Requirement already satisfied: wrapt>=1.11.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (1.17.0)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (1.71.0)\n",
+      "Requirement already satisfied: tensorboard~=2.19.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (2.19.0)\n",
+      "Requirement already satisfied: keras>=3.5.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (3.10.0)\n",
+      "Requirement already satisfied: numpy<2.2.0,>=1.26.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (1.26.4)\n",
+      "Requirement already satisfied: h5py>=3.11.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (3.12.1)\n",
+      "Requirement already satisfied: ml-dtypes<1.0.0,>=0.5.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorflow) (0.5.1)\n",
+      "Requirement already satisfied: scipy>=1.6.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn) (1.13.1)\n",
+      "Requirement already satisfied: joblib>=1.2.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn) (1.4.2)\n",
+      "Requirement already satisfied: threadpoolctl>=3.1.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from scikit-learn) (3.5.0)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2024.1)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2023.3)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from astunparse>=1.6.0->tensorflow) (0.45.1)\n",
+      "Requirement already satisfied: rich in c:\\programdata\\anaconda3\\lib\\site-packages (from keras>=3.5.0->tensorflow) (13.9.4)\n",
+      "Requirement already satisfied: namex in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from keras>=3.5.0->tensorflow) (0.0.8)\n",
+      "Requirement already satisfied: optree in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from keras>=3.5.0->tensorflow) (0.14.0)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (3.3.2)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (3.7)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2.3.0)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\programdata\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow) (2025.1.31)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorboard~=2.19.0->tensorflow) (3.4.1)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\lgr\\appdata\\roaming\\python\\python312\\site-packages (from tensorboard~=2.19.0->tensorflow) (0.7.2)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from tensorboard~=2.19.0->tensorflow) (3.1.3)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard~=2.19.0->tensorflow) (3.0.2)\n",
+      "Requirement already satisfied: markdown-it-py>=2.2.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from rich->keras>=3.5.0->tensorflow) (2.2.0)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from rich->keras>=3.5.0->tensorflow) (2.15.1)\n",
+      "Requirement already satisfied: mdurl~=0.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.5.0->tensorflow) (0.1.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install tensorflow scikit-learn pandas\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0b044499-8bd6-4e40-84b9-2d7f22c180b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "data = {\n",
+    "    \"sequence\": [\n",
+    "        \"DOWN,RIGHT,PUNCH\",\n",
+    "        \"RIGHT,DOWN,RIGHT,KICK\",\n",
+    "        \"LEFT,LEFT,PUNCH\",\n",
+    "        \"DOWN,KICK\",\n",
+    "        \"UP,PUNCH\",\n",
+    "        \"RIGHT,RIGHT,KICK\",\n",
+    "        \"DOWN,DOWN,RIGHT,PUNCH\",\n",
+    "        \"LEFT,DOWN,RIGHT,PUNCH\"\n",
+    "    ],\n",
+    "    \"move\": [\n",
+    "        \"Hadouken\",\n",
+    "        \"Shoryuken\",\n",
+    "        \"Dash Punch\",\n",
+    "        \"Low Kick\",\n",
+    "        \"Jump Punch\",\n",
+    "        \"Double Kick\",\n",
+    "        \"Super Hadouken\",\n",
+    "        \"Combo Strike\"\n",
+    "    ]\n",
+    "}\n",
+    "\n",
+    "df = pd.DataFrame(data)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "606f2fd1-42b8-49f0-87b7-cc2f5c450662",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Tokenizer ve Label Encoding\n",
+    "\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
+    "from tensorflow.keras.preprocessing.text import Tokenizer\n",
+    "\n",
+    "# Joystick hareketlerini tokenize et\n",
+    "tokenizer = Tokenizer(filters='', lower=False, split=',')\n",
+    "tokenizer.fit_on_texts(df['sequence'])\n",
+    "\n",
+    "X_seq = tokenizer.texts_to_sequences(df['sequence'])\n",
+    "X_pad = pad_sequences(X_seq, padding='post')  # sekansları eşitle\n",
+    "\n",
+    "# Etiketleri sayısallaştır\n",
+    "le = LabelEncoder()\n",
+    "y_encoded = le.fit_transform(df['move'])\n",
+    "\n",
+    "# Bilgiler\n",
+    "vocab_size = len(tokenizer.word_index) + 1\n",
+    "num_classes = len(le.classes_)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e654d9b3-faea-4888-a4a3-e3cc6b762940",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\ProgramData\\anaconda3\\Lib\\site-packages\\keras\\src\\layers\\core\\embedding.py:97: UserWarning: Argument `input_length` is deprecated. Just remove it.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step - accuracy: 0.2500 - loss: 2.0767\n",
+      "Epoch 2/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - accuracy: 0.2500 - loss: 2.0758\n",
+      "Epoch 3/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - accuracy: 0.3750 - loss: 2.0749\n",
+      "Epoch 4/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - accuracy: 0.5000 - loss: 2.0739\n",
+      "Epoch 5/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - accuracy: 0.6250 - loss: 2.0730\n",
+      "Epoch 6/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.5000 - loss: 2.0720\n",
+      "Epoch 7/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.6250 - loss: 2.0710\n",
+      "Epoch 8/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - accuracy: 0.5000 - loss: 2.0699\n",
+      "Epoch 9/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.5000 - loss: 2.0689\n",
+      "Epoch 10/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - accuracy: 0.5000 - loss: 2.0677\n",
+      "Epoch 11/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 78ms/step - accuracy: 0.5000 - loss: 2.0665\n",
+      "Epoch 12/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - accuracy: 0.5000 - loss: 2.0653\n",
+      "Epoch 13/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.6250 - loss: 2.0640\n",
+      "Epoch 14/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - accuracy: 0.6250 - loss: 2.0626\n",
+      "Epoch 15/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - accuracy: 0.6250 - loss: 2.0612\n",
+      "Epoch 16/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - accuracy: 0.6250 - loss: 2.0597\n",
+      "Epoch 17/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.6250 - loss: 2.0581\n",
+      "Epoch 18/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.6250 - loss: 2.0564\n",
+      "Epoch 19/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.6250 - loss: 2.0546\n",
+      "Epoch 20/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - accuracy: 0.6250 - loss: 2.0527\n",
+      "Epoch 21/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - accuracy: 0.6250 - loss: 2.0508\n",
+      "Epoch 22/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - accuracy: 0.6250 - loss: 2.0487\n",
+      "Epoch 23/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - accuracy: 0.6250 - loss: 2.0464\n",
+      "Epoch 24/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - accuracy: 0.6250 - loss: 2.0441\n",
+      "Epoch 25/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - accuracy: 0.6250 - loss: 2.0415\n",
+      "Epoch 26/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - accuracy: 0.6250 - loss: 2.0389\n",
+      "Epoch 27/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - accuracy: 0.6250 - loss: 2.0361\n",
+      "Epoch 28/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step - accuracy: 0.6250 - loss: 2.0331\n",
+      "Epoch 29/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - accuracy: 0.6250 - loss: 2.0299\n",
+      "Epoch 30/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - accuracy: 0.6250 - loss: 2.0265\n",
+      "Epoch 31/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - accuracy: 0.6250 - loss: 2.0229\n",
+      "Epoch 32/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - accuracy: 0.6250 - loss: 2.0191\n",
+      "Epoch 33/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - accuracy: 0.6250 - loss: 2.0151\n",
+      "Epoch 34/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - accuracy: 0.6250 - loss: 2.0108\n",
+      "Epoch 35/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - accuracy: 0.6250 - loss: 2.0062\n",
+      "Epoch 36/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 0.6250 - loss: 2.0013\n",
+      "Epoch 37/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.6250 - loss: 1.9961\n",
+      "Epoch 38/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.6250 - loss: 1.9906\n",
+      "Epoch 39/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - accuracy: 0.6250 - loss: 1.9848\n",
+      "Epoch 40/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step - accuracy: 0.7500 - loss: 1.9785\n",
+      "Epoch 41/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.8750 - loss: 1.9719\n",
+      "Epoch 42/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 103ms/step - accuracy: 0.8750 - loss: 1.9649\n",
+      "Epoch 43/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 72ms/step - accuracy: 0.8750 - loss: 1.9574\n",
+      "Epoch 44/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - accuracy: 0.8750 - loss: 1.9494\n",
+      "Epoch 45/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - accuracy: 0.8750 - loss: 1.9410\n",
+      "Epoch 46/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - accuracy: 0.8750 - loss: 1.9320\n",
+      "Epoch 47/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step - accuracy: 0.8750 - loss: 1.9225\n",
+      "Epoch 48/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - accuracy: 0.8750 - loss: 1.9123\n",
+      "Epoch 49/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step - accuracy: 0.8750 - loss: 1.9016\n",
+      "Epoch 50/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 102ms/step - accuracy: 0.8750 - loss: 1.8902\n",
+      "Epoch 51/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step - accuracy: 0.8750 - loss: 1.8781\n",
+      "Epoch 52/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - accuracy: 0.8750 - loss: 1.8653\n",
+      "Epoch 53/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.8750 - loss: 1.8517\n",
+      "Epoch 54/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.8750 - loss: 1.8374\n",
+      "Epoch 55/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step - accuracy: 0.8750 - loss: 1.8223\n",
+      "Epoch 56/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.7500 - loss: 1.8063\n",
+      "Epoch 57/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - accuracy: 0.7500 - loss: 1.7895\n",
+      "Epoch 58/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.7500 - loss: 1.7718\n",
+      "Epoch 59/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.7500 - loss: 1.7532\n",
+      "Epoch 60/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - accuracy: 0.7500 - loss: 1.7338\n",
+      "Epoch 61/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - accuracy: 0.7500 - loss: 1.7134\n",
+      "Epoch 62/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.7500 - loss: 1.6922\n",
+      "Epoch 63/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.7500 - loss: 1.6701\n",
+      "Epoch 64/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.7500 - loss: 1.6471\n",
+      "Epoch 65/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 0.7500 - loss: 1.6233\n",
+      "Epoch 66/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step - accuracy: 0.7500 - loss: 1.5988\n",
+      "Epoch 67/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 69ms/step - accuracy: 0.7500 - loss: 1.5735\n",
+      "Epoch 68/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step - accuracy: 0.7500 - loss: 1.5476\n",
+      "Epoch 69/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 0.7500 - loss: 1.5211\n",
+      "Epoch 70/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - accuracy: 0.7500 - loss: 1.4941\n",
+      "Epoch 71/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 0.7500 - loss: 1.4667\n",
+      "Epoch 72/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.7500 - loss: 1.4390\n",
+      "Epoch 73/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 0.7500 - loss: 1.4110\n",
+      "Epoch 74/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.7500 - loss: 1.3829\n",
+      "Epoch 75/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - accuracy: 0.7500 - loss: 1.3547\n",
+      "Epoch 76/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.7500 - loss: 1.3266\n",
+      "Epoch 77/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 0.7500 - loss: 1.2986\n",
+      "Epoch 78/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.7500 - loss: 1.2707\n",
+      "Epoch 79/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - accuracy: 0.7500 - loss: 1.2430\n",
+      "Epoch 80/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 0.7500 - loss: 1.2157\n",
+      "Epoch 81/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 0.8750 - loss: 1.1886\n",
+      "Epoch 82/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 1.0000 - loss: 1.1618\n",
+      "Epoch 83/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 1.0000 - loss: 1.1354\n",
+      "Epoch 84/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 1.0000 - loss: 1.1093\n",
+      "Epoch 85/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 1.0000 - loss: 1.0835\n",
+      "Epoch 86/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - accuracy: 1.0000 - loss: 1.0581\n",
+      "Epoch 87/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 74ms/step - accuracy: 1.0000 - loss: 1.0330\n",
+      "Epoch 88/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step - accuracy: 1.0000 - loss: 1.0082\n",
+      "Epoch 89/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 1.0000 - loss: 0.9838\n",
+      "Epoch 90/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 1.0000 - loss: 0.9596\n",
+      "Epoch 91/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 1.0000 - loss: 0.9357\n",
+      "Epoch 92/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 1.0000 - loss: 0.9121\n",
+      "Epoch 93/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step - accuracy: 1.0000 - loss: 0.8888\n",
+      "Epoch 94/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step - accuracy: 1.0000 - loss: 0.8656\n",
+      "Epoch 95/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 1.0000 - loss: 0.8427\n",
+      "Epoch 96/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 1.0000 - loss: 0.8199\n",
+      "Epoch 97/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - accuracy: 1.0000 - loss: 0.7974\n",
+      "Epoch 98/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - accuracy: 1.0000 - loss: 0.7750\n",
+      "Epoch 99/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step - accuracy: 1.0000 - loss: 0.7527\n",
+      "Epoch 100/100\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step - accuracy: 1.0000 - loss: 0.7307\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.history.History at 0x230194c7410>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    " # LSTM Modeli Oluştur ve Eğit\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Embedding, LSTM, Dense\n",
+    "\n",
+    "model = Sequential([\n",
+    "    Embedding(input_dim=vocab_size, output_dim=16, input_length=X_pad.shape[1]),\n",
+    "    LSTM(32),\n",
+    "    Dense(num_classes, activation='softmax')\n",
+    "])\n",
+    "\n",
+    "model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
+    "model.fit(X_pad, y_encoded, epochs=100, verbose=1)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f5d9bb8c-c4da-45f9-93d6-23f083368c05",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 165ms/step\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Hadouken'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Tahmin Fonksiyonu\n",
+    "\n",
+    "import numpy as np\n",
+    "\n",
+    "def predict_move(sequence_text):\n",
+    "    seq = tokenizer.texts_to_sequences([sequence_text])\n",
+    "    pad = pad_sequences(seq, maxlen=X_pad.shape[1], padding='post')\n",
+    "    pred = model.predict(pad)\n",
+    "    label = le.inverse_transform([np.argmax(pred)])\n",
+    "    return label[0]\n",
+    "\n",
+    "# Örnek:\n",
+    "predict_move(\"DOWN,RIGHT,PUNCH\")  # Hadouken\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "89a797c1-fa12-4552-951a-4dcede799be8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save(\"joystick_move_model.keras\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "847f55ca-1b05-41f8-a0b8-57af26f1fb90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle\n",
+    "\n",
+    "# Tokenizer\n",
+    "with open(\"tokenizer.pkl\", \"wb\") as f:\n",
+    "    pickle.dump(tokenizer, f)\n",
+    "\n",
+    "# LabelEncoder\n",
+    "with open(\"label_encoder.pkl\", \"wb\") as f:\n",
+    "    pickle.dump(le, f)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a8343757-6301-49f2-894f-30ce3df0b601",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -0,0 +1,31 @@
+import streamlit as st
+import numpy as np
+import pickle
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+# Model ve yardımcı objeleri yükle
+model = load_model("joystick_move_model.keras")
+
+with open("tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
+
+with open("label_encoder.pkl", "rb") as f:
+    label_encoder = pickle.load(f)
+
+# Başlık
+st.title("🎮 Street Fighter Combo Tahmin Edici")
+st.write("Joystick sekansını girin (örn: DOWN,RIGHT,PUNCH)")
+
+# Girdi
+user_input = st.text_input("Joystick Kombinasyonu")
+
+if st.button("Tahmin Et"):
+    if user_input:
+        seq = tokenizer.texts_to_sequences([user_input])
+        pad = pad_sequences(seq, maxlen=model.input_shape[1], padding='post')
+        prediction = model.predict(pad)
+        predicted_move = label_encoder.inverse_transform([np.argmax(prediction)])
+        st.success(f"🧠 Tahmin Edilen Hareket: **{predicted_move[0]}**")
+    else:
+        st.warning("Lütfen bir joystick sekansı girin.")

joystick_move_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32b2cc79868a0382d7676868e74dc82742fc57da34d50c34b32da1165cf9ad8
+size 107552

label_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a3481a5f1602de9175c441d031624922af84c6dc641da86862f843ecfe2f78
+size 348

projeözet.txt

@@ -0,0 +1,65 @@
+✅ Proje Özeti: Street Fighter Move Recognizer
+🎯 Amaç:
+Joystick hareketlerine (örneğin: ⬇️➡️🅱️ gibi) bakarak oyuncunun hangi “özel hareketi” (Hadouken, Shoryuken vb.) yapmak istediğini tahmin eden bir model oluşturmak.
+
+💡 Neden Özel?
+Gerçek zamanlı joystick verilerini taklit ederek çalışır.
+
+Sekans verisiyle çalışmak (zaman sıralı girişler).
+
+Oyun zekâsı gibi davranmak: Oyuncu hangi hareketi yapıyor?
+
+🛠️ Teknik Yaklaşım:
+Aşama	Açıklama
+1. Veri Üretimi / Toplama	Simüle joystick sekansları (örnek: ['DOWN', 'RIGHT', 'PUNCH']) ve bunların karşılığı özel hareket etiketi (Hadouken)
+2. Veri İşleme	Her combo bir sekans (sequence), veri X = ["DOWN", "RIGHT", "PUNCH"], y = "Hadouken" gibi olur
+3. Modelleme	
+Seçenek 1: LSTM / GRU (sekans modelleme için)	
+Seçenek 2: 1D CNN (daha hızlı sonuçlar verir)	
+Seçenek 3: HMM (Hidden Markov Model, klasik çözüm)	
+4. Model Eğitimi	%80 eğitim, %20 test — sınıflandırma problemi
+5. Değerlendirme	Accuracy, confusion matrix ile
+6. Model Kaydı	model.pkl veya .keras olarak
+7. Streamlit Uygulaması	Kullanıcıdan joystick sekansı al → model tahminini göster
+8. Hugging Face	config.json, README.md, model.pkl / .keras, sample_input.json
+9. GitHub	Notebook + app + model + README ile tam repo
+
+
+
+
+
+
+
+
+
+
+
+📁 Örnek Combo Dataset (Simülasyon)
+Joystick Sequence	Move
+["DOWN", "RIGHT", "PUNCH"]	Hadouken
+["RIGHT", "DOWN", "RIGHT", "KICK"]	Shoryuken
+["LEFT", "LEFT", "PUNCH"]	Dash Punch
+["DOWN", "KICK"]	Low Kick
+
+Toplam 5–10 özel hareket tanımıyla başlamak yeterli.
+
+
+
+
+
+
+
+✅ Evet, Yapabiliriz:
+✔ Model eğitimi (LSTM / CNN)
+
+✔ Streamlit arayüz (combo tuşları seçtir → tahmini göster)
+
+✔ Hugging Face'e yükleme
+
+✔ GitHub'da paylaşım
+
+
+
+
+
+

requirements.txt

@@ -1,3 +1,5 @@
-altair
-pandas
-streamlit
+streamlit
+tensorflow
+scikit-learn
+numpy
+pandas

tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5598ce21164b613f7d520d25eeafce1c27a18f54584193aa028914381b003b6b
+size 500