Full Code of cbddobvyz/dijital-genc-yze for AI

main fa26926e4c89 cached
82 files
41.2 MB
10.8M tokens
38 symbols
1 requests
Copy disabled (too large) Download .txt
Showing preview only (43,205K chars total). Download the full file to get everything. 
Repository: cbddobvyz/dijital-genc-yze
Branch: main
Commit: fa26926e4c89
Files: 82
Total size: 41.2 MB

Directory structure:
gitextract_10fk8rg2/

├── README.md
├── Tematik_Egitimler/
│   ├── Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/
│   │   ├── Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/
│   │   │   ├── CNN_Giris.ipynb
│   │   │   ├── CNN_Mimarileri.ipynb
│   │   │   ├── CNN_SVM_KNN.ipynb
│   │   │   ├── Confusion_Matrix.ipynb
│   │   │   ├── Model_Mimarileri_3.ipynb
│   │   │   └── YSA_Giris.ipynb
│   │   ├── Nesne_Tespiti/
│   │   │   ├── Faster_RCNN.ipynb
│   │   │   ├── OD_1.ipynb
│   │   │   ├── OD_2.ipynb
│   │   │   ├── OD_3.ipynb
│   │   │   └── OD_Yolol.ipynb
│   │   └── Uygulamalar/
│   │       ├── T_Uyg_1_Overfitting.ipynb
│   │       ├── T_Uyg_2_Underfitting.ipynb
│   │       ├── T_Uyg_3_Model_kaydetme_ve_test.ipynb
│   │       ├── T_Uyg_4_automatic_mask_generator.ipynb
│   │       └── T_Uyg_5_predictor.ipynb
│   ├── Makine_Ogrenmesi_Mayis_2024/
│   │   ├── Kumeleme_Regresyon/
│   │   │   ├── clustering.ipynb
│   │   │   ├── data/
│   │   │   │   ├── experience_salary_dataset
│   │   │   │   └── experience_sale_dataset
│   │   │   ├── non_linear_regression.ipynb
│   │   │   └── simple_linear_regression.ipynb
│   │   ├── Siniflandirma/
│   │   │   ├── siniflandirma.ipynb
│   │   │   ├── siniflandirma_karsilastirma_1.ipynb
│   │   │   └── siniflandirma_karsilastirma_2.ipynb
│   │   ├── Uygulama_1/
│   │   │   ├── SMOTE_example.ipynb
│   │   │   ├── clus_crop_rec.ipynb
│   │   │   ├── clus_iris.ipynb
│   │   │   ├── data/
│   │   │   │   ├── Crop_Recommendation.csv
│   │   │   │   ├── ankara_hk_data.csv
│   │   │   │   ├── diamonds.csv
│   │   │   │   ├── iris.csv
│   │   │   │   └── temp_export_dir/
│   │   │   │       ├── nanned.csv
│   │   │   │       ├── org.csv
│   │   │   │       ├── station_14_nanned.csv
│   │   │   │       ├── station_14_org.csv
│   │   │   │       ├── station_15_nanned.csv
│   │   │   │       ├── station_15_org.csv
│   │   │   │       ├── station_17_nanned.csv
│   │   │   │       ├── station_17_org.csv
│   │   │   │       ├── station_1_nanned.csv
│   │   │   │       ├── station_1_org.csv
│   │   │   │       ├── station_2_nanned.csv
│   │   │   │       ├── station_2_org.csv
│   │   │   │       ├── station_9_nanned.csv
│   │   │   │       └── station_9_org.csv
│   │   │   ├── encoding_test.ipynb
│   │   │   ├── missing_data_imputation.ipynb
│   │   │   ├── reg_diamonds.ipynb
│   │   │   ├── transformations.py
│   │   │   ├── transformations_bcyj.ipynb
│   │   │   ├── utils_encoding.py
│   │   │   └── utils_missing_data.py
│   │   └── Uygulama_2/
│   │       ├── Sınıflandırma_Uygulama.ipynb
│   │       ├── data/
│   │       │   ├── car_prices.csv
│   │       │   ├── diabetes.csv
│   │       │   └── diamonds.csv
│   │       ├── reg_car_prices.ipynb
│   │       └── reg_diamonds.ipynb
│   └── Makine_Ogrenmesi_Temmuz_2024/
│       └── Regresyon/
│           ├── data/
│           │   ├── car_prices.csv
│           │   ├── diamonds.csv
│           │   ├── experience_salary_dataset
│           │   └── experience_sale_dataset
│           ├── non_linear_regression.ipynb
│           ├── reg_car_prices.ipynb
│           ├── reg_diamonds.ipynb
│           └── simple_linear_regression.ipynb
└── Webinar/
    ├── Webinar-II-VeriOnisleme/
    │   ├── data/
    │   │   └── carprices.csv
    │   ├── data_generator.py
    │   ├── discretization.ipynb
    │   ├── transformations.py
    │   ├── transformations_basic.ipynb
    │   └── transformations_bcyj.ipynb
    ├── Webinar-IV-Sağlıkta YZ Uygulamaları | Mamografi Görüntülerinden Kitle Tespiti-II/
    │   └── inbreastDataPreparing.ipynb
    ├── Webinar-V-Ozellik Muhendisligi/
    │   ├── LDA_1.ipynb
    │   ├── LDA_2.ipynb
    │   ├── PCA_1.ipynb
    │   └── PCA_2.ipynb
    └── Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/
        ├── data.yaml
        ├── dataPreparation.ipynb
        ├── utils.py
        └── yoloImplementation.ipynb

================================================
FILE CONTENTS
================================================

================================================
FILE: README.md
================================================
<div align="center" markdown="1">
<img src="docs/dijitalgencyze-icon.jpg" />

**<center><h1> Dijital Genç Yapay Zekâ Ekosistemi </h1></center>**

Cumhurbaşkanlığı Dijital Dönüşüm Ofisi Dijital Genç Yapay Zekâ Ekosistemi, üniversitelerdeki yapay zekâ ile ilgili öğrenci kulüplerinin tek bir çatı altında toplayarak bu alanlardaki potansiyel nitelikli iş gücünün uygulamaya dayalı eğitimler, yarışmalar ve eğitim sonrası kariyer ödülleri ile desteklenmesi hedefiyle kurulmuştur. İlgili kulüplere dahil olan yapay zekâ ile ilgilenen on binlerce öğrencimizin eğitim hayatı kamu-akademi iş birliğiyle desteklenerek, mezuniyet sonrası süreçte kaliteli bir kariyer yolu çizilmesi konusunda imkân sağlanacaktır.

Dijital Genç Yapay Zekâ Ekosistemi kapsamında düzenlenecek etkinlikleri ve güncel duyuruları aşağıdaki kanallardan takip edebilirsiniz:

* **Telegram:** https://t.me/dijitalgencyz.

* **Whatsapp:** https://whatsapp.com/channel/0029VaccbAfA2pL69lRYSM27

* **bip:** https://channels.bip.ai/join/dijitalgencyz

Dijital Genç Yapay Zekâ Ekosistemine dair sıkça sorulan sorulara [buradan](https://cbddo.gov.tr/sss/dijital-genc/) ulaşabilirsiniz.

Soru, görüş ve önerileriniz için Başkanlığımızla dijitalgenc@cbddo.gov.tr adresi üzerinden iletişime geçebilirsiniz.

</div>

## **[DDYM Yapay Zeka Egitimleri](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/DDYM_Yapay_Zeka_Egitimi_2024)**

## **Aylık Webinarlar**

* Webinar I - **Veri Operasyonları**
* Webinar II - **[Veri Ön İşleme](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Webinar/Webinar-II-VeriOnisleme)**
* Webinar III - **[Sağlıkta YZ Uygulamaları | Mamografi Görüntülerinden Kitle Tespiti-I](https://github.com/cbddobvyz/digitaleye-mammography)**
* Webinar IV - **[Sağlıkta YZ Uygulamaları | Mamografi Görüntülerinden Kitle Tespiti-II](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Webinar/Webinar-IV-Sa%C4%9Fl%C4%B1kta%20YZ%20Uygulamalar%C4%B1%20%7C%20Mamografi%20G%C3%B6r%C3%BCnt%C3%BClerinden%20Kitle%20Tespiti-II)**
* Webinar V - **[Ozellik Muhendisligi](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Webinar/Webinar-V-Ozellik%20Muhendisligi)**
* Webinar VII - **[YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Webinar/Webinar-VII-YOLO%20ile%20Mamografi%20G%C3%B6r%C3%BCnt%C3%BClerinden%20Kitle%20Tespit%20Uygulamas%C4%B1)**
## **Tematik Eğitimler**  

#### **[Makine Öğrenmesi (Temmuz 2024)](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024)**

- **[Regresyon](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon)**

#### **[Derin Öğrenme ile Görüntü İşleme (Temmuz 2024)](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024)**

- **[Görüntü İşleme, Yapay Sinir Ağları, Derin Öğrenme - Giriş-Sınıflandırma](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris)**
- **[Görüntü İşleme, Yapay Sinir Ağları, Derin Öğrenme - Nesne Tespiti](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Nesne_Tespiti)**
- **[Görüntü İşleme, Yapay Sinir Ağları, Derin Öğrenme - Uygulamalar](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Uygulamalar)**

#### **[Makine Öğrenmesi (Mayıs 2024)](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024)**

- **[Kumeleme - Regresyon](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Kumeleme_Regresyon)**

- **[Sınıflandırma](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Siniflandirma)**

- **[Uygulama - 1](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1)**

- **[Uygulama - 2](https://github.com/cbddobvyz/dijital-genc-yze/tree/main/Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2)**


================================================
FILE: Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/CNN_Giris.ipynb
================================================
{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KwJgZF8xSsOR"
      },
      "source": [
        "# Yapay sinir ağları CIFAR veri seti ile Uygulama"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sEBSGXoES110"
      },
      "source": [
        "## Gerekli kütüphanelerin yüklenmesi"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Kütüphaneler ve Fonksiyonlar\n",
        "\n",
        "1. **tensorflow (`import tensorflow as tf`)**:\n",
        "   - TensorFlow, Google tarafından geliştirilen açık kaynaklı bir makine öğrenimi kütüphanesidir.\n",
        "   - Derin öğrenme modelleri oluşturmak, eğitmek ve değerlendirmek için kullanılır.\n",
        "   - Keras API'sini içerir ve model oluşturma, katmanlar, optimizasyon ve metrikler gibi yüksek seviye API sağlar.\n",
        "\n",
        "2. **tensorflow.keras.datasets (`from tensorflow.keras.datasets import cifar10`)**:\n",
        "   - Keras içinde bulunan `datasets` modülü, önceden yüklü popüler veri setlerine erişim sağlar.\n",
        "   - `cifar10` modülü, CIFAR-10 veri setini yüklemek için kullanılır. CIFAR-10, 10 farklı sınıfa ait 60,000 renkli görüntüden oluşan bir veri setidir.\n",
        "\n",
        "3. **tensorflow.keras.models (`from tensorflow.keras.models import Sequential`)**:\n",
        "   - Keras içinde bulunan `models` modülü, sinir ağı modellerini oluşturmak için kullanılır.\n",
        "   - `Sequential` sınıfı, katmanları sıralı bir şekilde birleştirilmiş bir model oluşturur.\n",
        "\n",
        "4. **tensorflow.keras.layers (`from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout`)**:\n",
        "   - `layers` modülü, farklı tipteki katmanları içerir ve bu katmanları model oluştururken kullanabiliriz.\n",
        "   - `Conv2D`, `MaxPooling2D`, `Flatten`, `Dense` ve `Dropout` gibi sık kullanılan katmanlar bu modülde bulunur.\n",
        "   - Örneğin, Conv2D katmanı 2 boyutlu evrişim katmanı, Dense katmanı tam bağlı (fully connected) katman ve MaxPooling2D katmanı evrişim sonrası azaltma katmanıdır.\n",
        "\n",
        "5. **tensorflow.keras.utils (`from tensorflow.keras.utils import to_categorical`)**:\n",
        "   - `utils` modülü, yardımcı işlevleri içerir.\n",
        "   - `to_categorical` işlevi, etiketleri one-hot encode yapmak için kullanılır. Yani, çok sınıflı sınıflandırma problemlerinde etiketleri (örneğin, 0'dan 9'a kadar olan sınıflar) binary (1 ve 0'lar) vektörlerine dönüştürür.\n",
        "\n",
        "6. **matplotlib.pyplot (`import matplotlib.pyplot as plt`)**:\n",
        "   - `matplotlib.pyplot` modülü, verileri görselleştirmek için kullanılır.\n",
        "   - Grafikler, histogramlar, görüntüler ve diğer görsel temsiller oluşturmak için yaygın olarak kullanılır.\n",
        "   - Örneğin, model eğitimini görselleştirmek veya veri seti üzerinde örnek görüntüleri göstermek için kullanılabilir.\n",
        "\n",
        "7. **numpy (`import numpy as np`)**:\n",
        "   - `numpy` kütüphanesi, Python'da bilimsel hesaplama için temel bir pakettir.\n",
        "   - Diziler, matrisler ve diğer çok boyutlu veri yapıları üzerinde hızlı matematiksel işlemler yapmak için kullanılır.\n",
        "   - Örneğin, veri manipülasyonu, dizi işlemleri ve model eğitimi sırasında veri işleme için sıklıkla kullanılır."
      ],
      "metadata": {
        "id": "Tb_fTAfqdzQ9"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "c5mEI9fxSokv"
      },
      "outputs": [],
      "source": [
        "!pip install tensorflow matplotlib\n",
        "\n",
        "import tensorflow as tf\n",
        "from tensorflow.keras.datasets import cifar10\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n",
        "from tensorflow.keras.utils import to_categorical\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "C0nRkHkOS9wR"
      },
      "source": [
        "## Veri Seti"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Cq7BjoyYTEOf"
      },
      "source": [
        "### Veri seti yükleme"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LpW7ZqUNTGk1",
        "outputId": "219e1424-5671-4238-cacd-41f3b3013b06"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n",
            "170498071/170498071 [==============================] - 4s 0us/step\n"
          ]
        }
      ],
      "source": [
        "(x_train, y_train), (x_test, y_test) = cifar10.load_data()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Rastgele bir görüntü seçin\n",
        "random_index = np.random.randint(0, len(x_train))\n",
        "random_image = x_train[random_index]\n",
        "random_label = y_train[random_index][0]"
      ],
      "metadata": {
        "id": "3uJH0KhlOh8K"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Görüntüyü gösterin\n",
        "plt.imshow(random_image)\n",
        "plt.axis('off')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 406
        },
        "id": "dZtj-w8JR4qk",
        "outputId": "24e2890a-349c-4be4-a04e-a6eb9aba589a"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "random_image"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "Uzj8a_5lT-ua",
        "outputId": "48972e1c-5588-47c6-97e0-d1983e03c581"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[[157, 136, 108],\n",
              "        [152, 130, 106],\n",
              "        [139, 116,  94],\n",
              "        ...,\n",
              "        [151, 133, 114],\n",
              "        [144, 128, 109],\n",
              "        [137, 124, 107]],\n",
              "\n",
              "       [[156, 135, 107],\n",
              "        [152, 131, 106],\n",
              "        [139, 117,  95],\n",
              "        ...,\n",
              "        [155, 138, 118],\n",
              "        [151, 135, 117],\n",
              "        [142, 129, 112]],\n",
              "\n",
              "       [[156, 135, 107],\n",
              "        [153, 131, 106],\n",
              "        [140, 118,  96],\n",
              "        ...,\n",
              "        [153, 136, 116],\n",
              "        [148, 132, 114],\n",
              "        [150, 137, 120]],\n",
              "\n",
              "       ...,\n",
              "\n",
              "       [[ 84,  70,  60],\n",
              "        [ 74,  60,  51],\n",
              "        [100,  86,  77],\n",
              "        ...,\n",
              "        [ 94,  80,  67],\n",
              "        [100,  86,  72],\n",
              "        [101,  87,  74]],\n",
              "\n",
              "       [[ 89,  75,  66],\n",
              "        [ 86,  72,  63],\n",
              "        [ 93,  79,  70],\n",
              "        ...,\n",
              "        [ 96,  82,  69],\n",
              "        [104,  90,  77],\n",
              "        [109,  95,  82]],\n",
              "\n",
              "       [[ 86,  72,  63],\n",
              "        [ 91,  77,  68],\n",
              "        [ 96,  82,  73],\n",
              "        ...,\n",
              "        [ 96,  82,  69],\n",
              "        [ 91,  77,  64],\n",
              "        [ 99,  85,  72]]], dtype=uint8)"
            ],
            "text/html": [
              "<style>\n",
              "      .ndarray_repr .ndarray_raw_data {\n",
              "        display: none;\n",
              "      }\n",
              "      .ndarray_repr.show_array .ndarray_raw_data {\n",
              "        display: block;\n",
              "      }\n",
              "      .ndarray_repr.show_array .ndarray_image_preview {\n",
              "        display: none;\n",
              "      }\n",
              "      </style>\n",
              "      <div id=\"id-16ea77e5-720f-4aaf-bd44-da3b11ed9a51\" class=\"ndarray_repr\"><pre>ndarray (32, 32, 3) <button style=\"padding: 0 2px;\">show data</button></pre><img src=\"data:image/png;base64,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\" class=\"ndarray_image_preview\" /><pre class=\"ndarray_raw_data\">array([[[157, 136, 108],\n",
              "        [152, 130, 106],\n",
              "        [139, 116,  94],\n",
              "        ...,\n",
              "        [151, 133, 114],\n",
              "        [144, 128, 109],\n",
              "        [137, 124, 107]],\n",
              "\n",
              "       [[156, 135, 107],\n",
              "        [152, 131, 106],\n",
              "        [139, 117,  95],\n",
              "        ...,\n",
              "        [155, 138, 118],\n",
              "        [151, 135, 117],\n",
              "        [142, 129, 112]],\n",
              "\n",
              "       [[156, 135, 107],\n",
              "        [153, 131, 106],\n",
              "        [140, 118,  96],\n",
              "        ...,\n",
              "        [153, 136, 116],\n",
              "        [148, 132, 114],\n",
              "        [150, 137, 120]],\n",
              "\n",
              "       ...,\n",
              "\n",
              "       [[ 84,  70,  60],\n",
              "        [ 74,  60,  51],\n",
              "        [100,  86,  77],\n",
              "        ...,\n",
              "        [ 94,  80,  67],\n",
              "        [100,  86,  72],\n",
              "        [101,  87,  74]],\n",
              "\n",
              "       [[ 89,  75,  66],\n",
              "        [ 86,  72,  63],\n",
              "        [ 93,  79,  70],\n",
              "        ...,\n",
              "        [ 96,  82,  69],\n",
              "        [104,  90,  77],\n",
              "        [109,  95,  82]],\n",
              "\n",
              "       [[ 86,  72,  63],\n",
              "        [ 91,  77,  68],\n",
              "        [ 96,  82,  73],\n",
              "        ...,\n",
              "        [ 96,  82,  69],\n",
              "        [ 91,  77,  64],\n",
              "        [ 99,  85,  72]]], dtype=uint8)</pre></div><script>\n",
              "      (() => {\n",
              "      const titles = ['show data', 'hide data'];\n",
              "      let index = 0\n",
              "      document.querySelector('#id-16ea77e5-720f-4aaf-bd44-da3b11ed9a51 button').onclick = (e) => {\n",
              "        document.querySelector('#id-16ea77e5-720f-4aaf-bd44-da3b11ed9a51').classList.toggle('show_array');\n",
              "        index = (++index) % 2;\n",
              "        document.querySelector('#id-16ea77e5-720f-4aaf-bd44-da3b11ed9a51 button').textContent = titles[index];\n",
              "        e.preventDefault();\n",
              "        e.stopPropagation();\n",
              "      }\n",
              "      })();\n",
              "    </script>"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "random_image.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "22e31BSKUDBd",
        "outputId": "a2e3a9f5-3542-45fa-d97a-36f59246c014"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(32, 32, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "imbaWV6HUZVZ"
      },
      "source": [
        "### Veri Seti görselleştirme"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "CIFAR-10, görüntü tanıma ve sınıflandırma alanında yaygın olarak kullanılan bir veri setidir.\n",
        "10 farklı sınıfa ait küçük renkli görüntülerden oluşur ve makine öğrenimi algoritmalarını eğitmek ve değerlendirmek için sıklıkla kullanılır.\n",
        "\n",
        "\n",
        "**Görüntü Sayısı:**\n",
        "\n",
        "Eğitim Verisi: 50,000 görüntü\n",
        "Test Verisi: 10,000 görüntü\n",
        "Görüntü Boyutu: Her görüntü 32x32 piksel boyutunda ve renkli (RGB).\n",
        "\n",
        "**Sınıflar:**\n",
        "Veri seti, her biri 6,000 görüntüden oluşan 10 sınıfa sahiptir. Sınıflar şunlardır:\n",
        "\n",
        "* Uçak (airplane)\n",
        "\n",
        "* Otomobil (automobile)\n",
        "\n",
        "* Kuş (bird)\n",
        "\n",
        "* Kedi (cat)\n",
        "\n",
        "* Geyik (deer)\n",
        "\n",
        "* Köpek (dog)\n",
        "\n",
        "* Kurbağa (frog)\n",
        "\n",
        "* At (horse)\n",
        "\n",
        "* Gemi (ship)\n",
        "\n",
        "* Kamyon (truck)\n",
        "\n",
        "**Veri Setinin Yapısı:**\n",
        "\n",
        "Her sınıf için 5,000 eğitim görüntüsü ve 1,000 test görüntüsü bulunur."
      ],
      "metadata": {
        "id": "J1sOoYF1wVOB"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "vR-DUPkgUeCw"
      },
      "outputs": [],
      "source": [
        "# CIFAR-10 sınıf adları\n",
        "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Eğitim veri setinden rastgele 16 görüntü seçin\n",
        "num_samples = 16\n",
        "random_indices = np.random.choice(x_train.shape[0], num_samples, replace=False)\n",
        "sample_images = x_train[random_indices]\n",
        "sample_labels = y_train[random_indices]"
      ],
      "metadata": {
        "id": "-W3qI2Gc63if"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(10, 10))\n",
        "for i in range(num_samples):\n",
        "    plt.subplot(4, 4, i + 1)\n",
        "    plt.imshow(sample_images[i])\n",
        "    plt.title(class_names[int(sample_labels[i][0])])\n",
        "    plt.axis('off')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "FcdPtTEF68Cr",
        "outputId": "5ccf3dd5-bb29-4d5c-8601-63a59d2739fe"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x1000 with 16 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Normalizasyon\n",
        "x_train = x_train/255\n",
        "x_test = x_test/255"
      ],
      "metadata": {
        "id": "qcUGXq5pQyGA"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "num_samples = 16\n",
        "random_indices = np.random.choice(x_train.shape[0], num_samples, replace=False)\n",
        "sample_images = x_train[random_indices]\n",
        "sample_labels = y_train[random_indices]"
      ],
      "metadata": {
        "id": "twCKp_2aQ5Qq"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(10, 10))\n",
        "for i in range(num_samples):\n",
        "    plt.subplot(4, 4, i + 1)\n",
        "    plt.imshow(sample_images[i])\n",
        "    plt.title(class_names[int(sample_labels[i][0])])\n",
        "    plt.axis('off')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "--CbUsSqQ_hZ",
        "outputId": "0809b597-4a51-45a6-a7fb-38c330921d17"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x1000 with 16 Axes>"
            ],
            "image/png": "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
Download .txt 
gitextract_10fk8rg2/

├── README.md
├── Tematik_Egitimler/
│   ├── Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/
│   │   ├── Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/
│   │   │   ├── CNN_Giris.ipynb
│   │   │   ├── CNN_Mimarileri.ipynb
│   │   │   ├── CNN_SVM_KNN.ipynb
│   │   │   ├── Confusion_Matrix.ipynb
│   │   │   ├── Model_Mimarileri_3.ipynb
│   │   │   └── YSA_Giris.ipynb
│   │   ├── Nesne_Tespiti/
│   │   │   ├── Faster_RCNN.ipynb
│   │   │   ├── OD_1.ipynb
│   │   │   ├── OD_2.ipynb
│   │   │   ├── OD_3.ipynb
│   │   │   └── OD_Yolol.ipynb
│   │   └── Uygulamalar/
│   │       ├── T_Uyg_1_Overfitting.ipynb
│   │       ├── T_Uyg_2_Underfitting.ipynb
│   │       ├── T_Uyg_3_Model_kaydetme_ve_test.ipynb
│   │       ├── T_Uyg_4_automatic_mask_generator.ipynb
│   │       └── T_Uyg_5_predictor.ipynb
│   ├── Makine_Ogrenmesi_Mayis_2024/
│   │   ├── Kumeleme_Regresyon/
│   │   │   ├── clustering.ipynb
│   │   │   ├── data/
│   │   │   │   ├── experience_salary_dataset
│   │   │   │   └── experience_sale_dataset
│   │   │   ├── non_linear_regression.ipynb
│   │   │   └── simple_linear_regression.ipynb
│   │   ├── Siniflandirma/
│   │   │   ├── siniflandirma.ipynb
│   │   │   ├── siniflandirma_karsilastirma_1.ipynb
│   │   │   └── siniflandirma_karsilastirma_2.ipynb
│   │   ├── Uygulama_1/
│   │   │   ├── SMOTE_example.ipynb
│   │   │   ├── clus_crop_rec.ipynb
│   │   │   ├── clus_iris.ipynb
│   │   │   ├── data/
│   │   │   │   ├── Crop_Recommendation.csv
│   │   │   │   ├── ankara_hk_data.csv
│   │   │   │   ├── diamonds.csv
│   │   │   │   ├── iris.csv
│   │   │   │   └── temp_export_dir/
│   │   │   │       ├── nanned.csv
│   │   │   │       ├── org.csv
│   │   │   │       ├── station_14_nanned.csv
│   │   │   │       ├── station_14_org.csv
│   │   │   │       ├── station_15_nanned.csv
│   │   │   │       ├── station_15_org.csv
│   │   │   │       ├── station_17_nanned.csv
│   │   │   │       ├── station_17_org.csv
│   │   │   │       ├── station_1_nanned.csv
│   │   │   │       ├── station_1_org.csv
│   │   │   │       ├── station_2_nanned.csv
│   │   │   │       ├── station_2_org.csv
│   │   │   │       ├── station_9_nanned.csv
│   │   │   │       └── station_9_org.csv
│   │   │   ├── encoding_test.ipynb
│   │   │   ├── missing_data_imputation.ipynb
│   │   │   ├── reg_diamonds.ipynb
│   │   │   ├── transformations.py
│   │   │   ├── transformations_bcyj.ipynb
│   │   │   ├── utils_encoding.py
│   │   │   └── utils_missing_data.py
│   │   └── Uygulama_2/
│   │       ├── Sınıflandırma_Uygulama.ipynb
│   │       ├── data/
│   │       │   ├── car_prices.csv
│   │       │   ├── diabetes.csv
│   │       │   └── diamonds.csv
│   │       ├── reg_car_prices.ipynb
│   │       └── reg_diamonds.ipynb
│   └── Makine_Ogrenmesi_Temmuz_2024/
│       └── Regresyon/
│           ├── data/
│           │   ├── car_prices.csv
│           │   ├── diamonds.csv
│           │   ├── experience_salary_dataset
│           │   └── experience_sale_dataset
│           ├── non_linear_regression.ipynb
│           ├── reg_car_prices.ipynb
│           ├── reg_diamonds.ipynb
│           └── simple_linear_regression.ipynb
└── Webinar/
    ├── Webinar-II-VeriOnisleme/
    │   ├── data/
    │   │   └── carprices.csv
    │   ├── data_generator.py
    │   ├── discretization.ipynb
    │   ├── transformations.py
    │   ├── transformations_basic.ipynb
    │   └── transformations_bcyj.ipynb
    ├── Webinar-IV-Sağlıkta YZ Uygulamaları | Mamografi Görüntülerinden Kitle Tespiti-II/
    │   └── inbreastDataPreparing.ipynb
    ├── Webinar-V-Ozellik Muhendisligi/
    │   ├── LDA_1.ipynb
    │   ├── LDA_2.ipynb
    │   ├── PCA_1.ipynb
    │   └── PCA_2.ipynb
    └── Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/
        ├── data.yaml
        ├── dataPreparation.ipynb
        ├── utils.py
        └── yoloImplementation.ipynb
Download .txt 
SYMBOL INDEX (38 symbols across 6 files)

FILE: Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/transformations.py
  function standardize_dataset (line 7) | def standardize_dataset(df: DataFrame):
  function normalize_dataset (line 13) | def normalize_dataset(df: DataFrame,
  function box_cox (line 27) | def box_cox(data,
  function yeo_johnson (line 38) | def yeo_johnson(data,

FILE: Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/utils_encoding.py
  function encode_one_hot (line 5) | def encode_one_hot(df: DataFrame,
  function ordinal_encoding (line 19) | def ordinal_encoding(df: DataFrame,

FILE: Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/utils_missing_data.py
  function completeness_overall (line 21) | def completeness_overall(df: pandas.DataFrame):
  function completeness_feature (line 27) | def completeness_feature(df: pandas.DataFrame):
  function completeness_data_point (line 34) | def completeness_data_point(df: pandas.DataFrame):
  function remove_columns (line 38) | def remove_columns(df: pandas.DataFrame,
  function parse_date (line 49) | def parse_date(df: pandas.DataFrame,
  function introduce_nans (line 71) | def introduce_nans(df: pandas.DataFrame,
  function report_completeness (line 91) | def report_completeness(df: pandas.DataFrame,
  function sub_dataframe (line 107) | def sub_dataframe(df: pandas.DataFrame,
  function polcon2AQI (line 153) | def polcon2AQI(pol_name: str, val:float):
  function generate_class_label (line 174) | def generate_class_label(row: pandas.Series):
  function generate_class_labels (line 182) | def generate_class_labels(df: pandas.DataFrame):
  function test_data_classification (line 194) | def test_data_classification(df: pandas.DataFrame,
  function test_data_regression (line 229) | def test_data_regression(df:pandas.DataFrame, df_org:pandas.DataFrame,
  function _data_out (line 274) | def _data_out(df: pandas.DataFrame,
  function sum_results (line 282) | def sum_results(res_list: List[dict]):
  function plot_results (line 295) | def plot_results(data_in: List[dict]):

FILE: Webinar/Webinar-II-VeriOnisleme/data_generator.py
  function generate_skewed_data (line 9) | def generate_skewed_data(location: float = 1.0,
  function add_noise (line 25) | def add_noise(data_point: float,
  function generate_skewed_data_left (line 32) | def generate_skewed_data_left(size: int = 10000):
  function generate_skewed_data_right (line 39) | def generate_skewed_data_right(size: int = 10000):
  function generate_extreme_skewed_data_right (line 46) | def generate_extreme_skewed_data_right(size: int = 10000,
  function generate_uniform_dataset (line 55) | def generate_uniform_dataset(n_data_points=100,
  function generate_blobbed_dataset (line 65) | def generate_blobbed_dataset(n_data_points=100,

FILE: Webinar/Webinar-II-VeriOnisleme/transformations.py
  function standardize_dataset (line 7) | def standardize_dataset(df: DataFrame):
  function normalize_dataset (line 13) | def normalize_dataset(df: DataFrame,
  function box_cox (line 27) | def box_cox(data,
  function yeo_johnson (line 38) | def yeo_johnson(data,

FILE: Webinar/Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/utils.py
  function create_data_dir (line 19) | def create_data_dir(folderPath):
  function draw_annotation (line 23) | def draw_annotation(image, line):
  function saveImages (line 39) | def saveImages(dicomFilePath, saveFolderPath):
  function loadPoint (line 74) | def loadPoint(point_string):
  function saveMaskYOLOFormat (line 79) | def saveMaskYOLOFormat(xmlFilePath, imageFilePath, saveMaskPath, biradsS...
Copy disabled (too large) Download .json
Condensed preview — 82 files, each showing path, character count, and a content snippet. Download the .json file for the full structured content (44,938K chars). 
[
  {
    "path": "README.md",
    "chars": 4259,
    "preview": "<div align=\"center\" markdown=\"1\">\n<img src=\"docs/dijitalgencyze-icon.jpg\" />\n\n**<center><h1> Dijital Genç Yapay Zekâ Eko"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/CNN_Giris.ipynb",
    "chars": 904816,
    "preview": "{\n  \"cells\": [\n    {\n      \"cell_type\": \"markdown\",\n      \"metadata\": {\n        \"id\": \"KwJgZF8xSsOR\"\n      },\n      \"sou"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/CNN_Mimarileri.ipynb",
    "chars": 11135,
    "preview": "{\n  \"cells\": [\n    {\n      \"cell_type\": \"markdown\",\n      \"metadata\": {\n        \"id\": \"8AC6QIx_ur8-\"\n      },\n      \"sou"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/CNN_SVM_KNN.ipynb",
    "chars": 26391,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"toc_visible\": tr"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/Confusion_Matrix.ipynb",
    "chars": 1898607,
    "preview": "{\n  \"cells\": [\n    {\n      \"cell_type\": \"code\",\n      \"execution_count\": null,\n      \"metadata\": {\n        \"colab\": {\n  "
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/Model_Mimarileri_3.ipynb",
    "chars": 212481,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"gpuType\": \"T4\",\n"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Goruntu_Isleme_Yapay_Sinir_Aglari_Derin_Ogrenme_Giris/YSA_Giris.ipynb",
    "chars": 457677,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": []\n    },\n    \"kernelspec\":"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Nesne_Tespiti/Faster_RCNN.ipynb",
    "chars": 19404,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"metadata\": {\n    \"colab\": {\n     \"base_uri\": \""
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Nesne_Tespiti/OD_1.ipynb",
    "chars": 4606,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {\n    \"id\": \"wQBMQHq-0W-4\"\n   },\n   \"source\": [\n    \"# Nesn"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Nesne_Tespiti/OD_2.ipynb",
    "chars": 4395,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {\n    \"id\": \"rdQTAtcq0_Ww\"\n   },\n   \"source\": [\n    \"# coco"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Nesne_Tespiti/OD_3.ipynb",
    "chars": 6353,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {\n    \"id\": \"vqZn0ZwY1H76\"\n   },\n   \"source\": [\n    \"# Yolo"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Nesne_Tespiti/OD_Yolol.ipynb",
    "chars": 4450,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"metadata\": {\n    \"colab\": {\n     \"base_uri\": \""
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Uygulamalar/T_Uyg_1_Overfitting.ipynb",
    "chars": 365779,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"gpuType\": \"T4\",\n"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Uygulamalar/T_Uyg_2_Underfitting.ipynb",
    "chars": 722467,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": []\n    },\n    \"kernelspec\":"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Uygulamalar/T_Uyg_3_Model_kaydetme_ve_test.ipynb",
    "chars": 175627,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"gpuType\": \"T4\"\n "
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Uygulamalar/T_Uyg_4_automatic_mask_generator.ipynb",
    "chars": 17334,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"5fa21d44\",\n   \"metadata\": {\n    \"id\": \"5"
  },
  {
    "path": "Tematik_Egitimler/Derin_Ogrenme_ile_Goruntu_Isleme_Temmuz_2024/Uygulamalar/T_Uyg_5_predictor.ipynb",
    "chars": 35605,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"f400486b\",\n   \"metadata\": {\n    \"id\": \"f"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Kumeleme_Regresyon/clustering.ipynb",
    "chars": 223492,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapsed\": true,\n    \"ExecuteTim"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Kumeleme_Regresyon/data/experience_salary_dataset",
    "chars": 320,
    "preview": "YearsExperience,Salary\n1.1,39343\n1.3,46205\n1.5,37731\n2,43525\n2.2,39891\n2.9,56642\n3,60150\n3.2,54445\n3.2,64445\n3.7,57189\n3"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Kumeleme_Regresyon/data/experience_sale_dataset",
    "chars": 130,
    "preview": "YearsExperience,HouseSales\n3.2,27\n8.2,30\n5.7,31\n7.5,36\n1.5,16\n1.1,15\n6.75,36\n8.5,31\n3.2,19\n3.9,22\n0.1,9\n1.0,12\n0.4,6\n4.4"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Kumeleme_Regresyon/non_linear_regression.ipynb",
    "chars": 215561,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapsed\": true,\n    \"ExecuteTim"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Kumeleme_Regresyon/simple_linear_regression.ipynb",
    "chars": 48795,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapsed\": true,\n    \"ExecuteTim"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Siniflandirma/siniflandirma.ipynb",
    "chars": 2539738,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"toc_visible\": tr"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Siniflandirma/siniflandirma_karsilastirma_1.ipynb",
    "chars": 105430,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"toc_visible\": tr"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Siniflandirma/siniflandirma_karsilastirma_2.ipynb",
    "chars": 78453,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"toc_visible\": tr"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/SMOTE_example.ipynb",
    "chars": 168198,
    "preview": "{\n  \"cells\": [\n    {\n      \"cell_type\": \"code\",\n      \"execution_count\": 178,\n      \"id\": \"9cbcfbeb72411992\",\n      \"met"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/clus_crop_rec.ipynb",
    "chars": 140552,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"id\":\"initial_id\",\"metadata\":{\"collapsed\":true,\"ExecuteTime\":{\"end_time\":\"2024-05-29T13:18"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/clus_iris.ipynb",
    "chars": 62419,
    "preview": "{\r\n \"cells\": [\r\n  {\r\n   \"cell_type\": \"code\",\r\n   \"id\": \"initial_id\",\r\n   \"metadata\": {\r\n    \"collapsed\": true,\r\n    \"Exe"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/Crop_Recommendation.csv",
    "chars": 144866,
    "preview": "Nitrogen,Phosphorus,Potassium,Temperature,Humidity,pH_Value,Rainfall,Crop\r\n90,42,43,20.87974371,82.00274423,6.502985292,"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/ankara_hk_data.csv",
    "chars": 1268529,
    "preview": ",S1_PM10,S1_PM25,S1_SO2,S1_NO2,S1_NOX,S1_NO,S2_PM10,S2_PM25,S2_SO2,S2_CO,S2_03,S5_PM10,S5_CO,S7_PM10,S9_PM10,S9_SO2,S9_N"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/diamonds.csv",
    "chars": 3192560,
    "preview": "\"\",\"carat\",\"cut\",\"color\",\"clarity\",\"depth\",\"table\",\"price\",\"x\",\"y\",\"z\"\n\"1\",0.23,\"Ideal\",\"E\",\"SI2\",61.5,55,326,3.95,3.98,"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/iris.csv",
    "chars": 5107,
    "preview": "Id,SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Species\n1,5.1,3.5,1.4,0.2,Iris-setosa\n2,4.9,3.0,1.4,0.2,Iris-se"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/nanned.csv",
    "chars": 74018,
    "preview": ",S1_PM10,S1_PM25,S1_SO2,S1_NO2,S1_NOX,S1_NO\n0,,,,,,174.86\n1,,,12.86,,,\n2,8.58,,,,,\n3,,64.53,,,,\n4,,,,,,173.65\n5,,,,120.2"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/org.csv",
    "chars": 183167,
    "preview": ",S1_PM10,S1_PM25,S1_SO2,S1_NO2,S1_NOX,S1_NO\n0,25.78,59.82,12.86,159.93,334.79,174.86\n1,25.78,59.82,12.86,159.93,334.79,1"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_14_nanned.csv",
    "chars": 73767,
    "preview": ",S14_PM10,S14_PM25,S14_SO2,S14_NO2,S14_NOX,S14_NO\n0,,,44.23,,,\n1,,,,122.76,,\n2,,,,,,155.62\n3,,,30.38,,,\n4,,,,,365.31,\n5,"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_14_org.csv",
    "chars": 190337,
    "preview": ",S14_PM10,S14_PM25,S14_SO2,S14_NO2,S14_NOX,S14_NO,OUT\n0,85.04,39.7,44.23,122.76,227.33,104.57,3\n1,85.04,39.7,44.23,122.7"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_15_nanned.csv",
    "chars": 73750,
    "preview": ",S15_PM10,S15_SO2,S15_NO2,S15_NOX,S15_NO,S15_O3\n0,,,,237.45,,\n1,107.99,,,,,\n2,,4.41,,,,\n3,,,,212.22,,\n4,,,,,82.48,\n5,63."
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_15_org.csv",
    "chars": 190839,
    "preview": ",S15_PM10,S15_SO2,S15_NO2,S15_NOX,S15_NO,S15_O3,OUT\n0,107.99,6.18,108.15,237.45,129.3,1.24,4\n1,107.99,6.18,108.15,237.45"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_17_nanned.csv",
    "chars": 78776,
    "preview": ",S17_PM10,S17_PM25,S17_SO2,S17_NO2,S17_NOX,S17_NO,S17_O3\n0,,72.57,,,,,\n1,,,,,,,3.1\n2,,,,,,410.96,\n3,,,,,,417.82,\n4,,,9.9"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_17_org.csv",
    "chars": 218895,
    "preview": ",S17_PM10,S17_PM25,S17_SO2,S17_NO2,S17_NOX,S17_NO,S17_O3,OUT\n0,168.93,72.57,8.7,232.58,592.46,359.88,3.1,4\n1,168.93,72.5"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_1_nanned.csv",
    "chars": 74018,
    "preview": ",S1_PM10,S1_PM25,S1_SO2,S1_NO2,S1_NOX,S1_NO\n0,,,,,,174.86\n1,,,12.86,,,\n2,8.58,,,,,\n3,,64.53,,,,\n4,,,,,,173.65\n5,,,,120.2"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_1_org.csv",
    "chars": 192613,
    "preview": ",S1_PM10,S1_PM25,S1_SO2,S1_NO2,S1_NOX,S1_NO,OUT\n0,25.78,59.82,12.86,159.93,334.79,174.86,4\n1,25.78,59.82,12.86,159.93,33"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_2_nanned.csv",
    "chars": 70102,
    "preview": ",S2_PM10,S2_PM25,S2_SO2,S2_CO,S2_03\n0,,,6.73,,\n1,,,6.94,,\n2,,,,1696.22,\n3,,39.14,,,\n4,,,,,3.18\n5,,,,,3.06\n6,,,6.2,,\n7,,,"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_2_org.csv",
    "chars": 169111,
    "preview": ",S2_PM10,S2_PM25,S2_SO2,S2_CO,S2_03,OUT\n0,191.1,42.08,6.73,2132.53,4.84,4\n1,171.0,44.11,6.94,1972.46,4.57,4\n2,143.5,43.5"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_9_nanned.csv",
    "chars": 69209,
    "preview": ",S9_PM10,S9_SO2,S9_NO2,S9_NOX,S9_NO\n0,,,80.31,,\n1,,,,309.27,\n2,,5.93,,,\n3,,,,,175.36\n4,,,,,270.72\n5,93.9,,,,\n6,,6.49,,,\n"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/data/temp_export_dir/station_9_org.csv",
    "chars": 166426,
    "preview": ",S9_PM10,S9_SO2,S9_NO2,S9_NOX,S9_NO,OUT\n0,108.09,5.52,80.31,309.27,228.96,4\n1,108.09,2.52,80.31,309.27,228.96,4\n2,103.25"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/encoding_test.ipynb",
    "chars": 18219,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapsed\": true,\n    \"ExecuteTim"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/missing_data_imputation.ipynb",
    "chars": 91583,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"metadata\": {\n    \"ExecuteTime\": {\n     \"end_time\""
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/reg_diamonds.ipynb",
    "chars": 2312312,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"ExecuteT"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/transformations.py",
    "chars": 1387,
    "preview": "from typing import List\n\nfrom pandas import DataFrame\nfrom sklearn.preprocessing import PowerTransformer, StandardScaler"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/transformations_bcyj.ipynb",
    "chars": 124963,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapse"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/utils_encoding.py",
    "chars": 874,
    "preview": "from pandas import DataFrame\nfrom sklearn.preprocessing import OneHotEncoder, OrdinalEncoder\n\n\ndef encode_one_hot(df: Da"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_1/utils_missing_data.py",
    "chars": 9923,
    "preview": "import pandas, numpy, random, copy\n\nfrom sklearn.svm import SVC\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn."
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2/Sınıflandırma_Uygulama.ipynb",
    "chars": 7556154,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {\n    \"id\": \"TO8le54bUilR\"\n   },\n   \"source\": [\n    \"# Diya"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2/data/car_prices.csv",
    "chars": 26717,
    "preview": "car_ID,symboling,CarName,fueltype,aspiration,doornumber,carbody,drivewheel,enginelocation,wheelbase,carlength,carwidth,c"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2/data/diabetes.csv",
    "chars": 23875,
    "preview": "Pregnancies,Glucose,BloodPressure,SkinThickness,Insulin,BMI,DiabetesPedigreeFunction,Age,Outcome\r\n6,148,72,35,0,33.6,0.6"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2/data/diamonds.csv",
    "chars": 3192560,
    "preview": "\"\",\"carat\",\"cut\",\"color\",\"clarity\",\"depth\",\"table\",\"price\",\"x\",\"y\",\"z\"\n\"1\",0.23,\"Ideal\",\"E\",\"SI2\",61.5,55,326,3.95,3.98,"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2/reg_car_prices.ipynb",
    "chars": 2904278,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {},\n   \"source\": [\n    \"# Car Price Prediction\\n\"\n   ]\n  },"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Mayis_2024/Uygulama_2/reg_diamonds.ipynb",
    "chars": 11955,
    "preview": "{\r\n \"cells\": [\r\n  {\r\n   \"cell_type\": \"code\",\r\n   \"id\": \"initial_id\",\r\n   \"metadata\": {\r\n    \"collapsed\": true\r\n   },\r\n  "
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/data/car_prices.csv",
    "chars": 26717,
    "preview": "car_ID,symboling,CarName,fueltype,aspiration,doornumber,carbody,drivewheel,enginelocation,wheelbase,carlength,carwidth,c"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/data/diamonds.csv",
    "chars": 3192560,
    "preview": "\"\",\"carat\",\"cut\",\"color\",\"clarity\",\"depth\",\"table\",\"price\",\"x\",\"y\",\"z\"\n\"1\",0.23,\"Ideal\",\"E\",\"SI2\",61.5,55,326,3.95,3.98,"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/data/experience_salary_dataset",
    "chars": 320,
    "preview": "YearsExperience,Salary\n1.1,39343\n1.3,46205\n1.5,37731\n2,43525\n2.2,39891\n2.9,56642\n3,60150\n3.2,54445\n3.2,64445\n3.7,57189\n3"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/data/experience_sale_dataset",
    "chars": 130,
    "preview": "YearsExperience,HouseSales\n3.2,27\n8.2,30\n5.7,31\n7.5,36\n1.5,16\n1.1,15\n6.75,36\n8.5,31\n3.2,19\n3.9,22\n0.1,9\n1.0,12\n0.4,6\n4.4"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/non_linear_regression.ipynb",
    "chars": 227614,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapsed\": true,\n    \"ExecuteTim"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/reg_car_prices.ipynb",
    "chars": 2902821,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {},\n   \"source\": [\n    \"# Car Price Prediction\\n\"\n   ]\n  },"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/reg_diamonds.ipynb",
    "chars": 2325932,
    "preview": "{\r\n \"cells\": [\r\n  {\r\n   \"cell_type\": \"code\",\r\n   \"id\": \"initial_id\",\r\n   \"metadata\": {\r\n    \"collapsed\": true,\r\n    \"Exe"
  },
  {
    "path": "Tematik_Egitimler/Makine_Ogrenmesi_Temmuz_2024/Regresyon/simple_linear_regression.ipynb",
    "chars": 54989,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"collapsed\": true,\n    \"is_executi"
  },
  {
    "path": "Webinar/Webinar-II-VeriOnisleme/data/carprices.csv",
    "chars": 54228,
    "preview": ",YEAR,MIL,FCON,COND,OUTPUT\n0,2014,32761,9.41413095943381,75,832527.4374557\n1,2022,12591,9.037609379851652,68,1286958.839"
  },
  {
    "path": "Webinar/Webinar-II-VeriOnisleme/data_generator.py",
    "chars": 3415,
    "preview": "import random\nimport numpy\n\nfrom typing import List\nfrom scipy.stats import skewnorm\nfrom sklearn.datasets import make_b"
  },
  {
    "path": "Webinar/Webinar-II-VeriOnisleme/discretization.ipynb",
    "chars": 8749,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"colla"
  },
  {
    "path": "Webinar/Webinar-II-VeriOnisleme/transformations.py",
    "chars": 1387,
    "preview": "from typing import List\n\nfrom pandas import DataFrame\nfrom sklearn.preprocessing import PowerTransformer, StandardScaler"
  },
  {
    "path": "Webinar/Webinar-II-VeriOnisleme/transformations_basic.ipynb",
    "chars": 8711,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"outputs\": [],\n   \"source\": [\n    \"import numpy\\n\",\n    \"from pandas import"
  },
  {
    "path": "Webinar/Webinar-II-VeriOnisleme/transformations_bcyj.ipynb",
    "chars": 11607,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"initial_id\",\n   \"metadata\": {\n    \"colla"
  },
  {
    "path": "Webinar/Webinar-IV-Sağlıkta YZ Uygulamaları | Mamografi Görüntülerinden Kitle Tespiti-II/inbreastDataPreparing.ipynb",
    "chars": 756047,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"8869c3fe-588d-47a5-b3fb-5fd5aa23a84f\",\n   \""
  },
  {
    "path": "Webinar/Webinar-V-Ozellik Muhendisligi/LDA_1.ipynb",
    "chars": 123477,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": []\n    },\n    \"kernelspec\":"
  },
  {
    "path": "Webinar/Webinar-V-Ozellik Muhendisligi/LDA_2.ipynb",
    "chars": 106600,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": []\n    },\n    \"kernelspec\":"
  },
  {
    "path": "Webinar/Webinar-V-Ozellik Muhendisligi/PCA_1.ipynb",
    "chars": 1285842,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": [],\n      \"gpuType\": \"T4\"\n "
  },
  {
    "path": "Webinar/Webinar-V-Ozellik Muhendisligi/PCA_2.ipynb",
    "chars": 546935,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"provenance\": []\n    },\n    \"kernelspec\":"
  },
  {
    "path": "Webinar/Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/data.yaml",
    "chars": 144,
    "preview": "train: /workspace/notebooks/webinar/data/Fold0/train/images\nval: /workspace/notebooks/webinar/data/Fold0/validation/imag"
  },
  {
    "path": "Webinar/Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/dataPreparation.ipynb",
    "chars": 262698,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"a9c0df6d-c5cc-4907-b6d0-d8333fc89990\",\n   \""
  },
  {
    "path": "Webinar/Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/utils.py",
    "chars": 3833,
    "preview": "import os\nimport os\nimport glob\nimport cv2\nimport utils\nimport pydicom as dicom\nimport plistlib\nimport pandas as pd\nimpo"
  },
  {
    "path": "Webinar/Webinar-VII-YOLO ile Mamografi Görüntülerinden Kitle Tespit Uygulaması/yoloImplementation.ipynb",
    "chars": 91300,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"3f198e2e-b280-4ebe-b61f-8d7730df085d\",\n   \""
  }
]

About this extraction

This page contains the full source code of the cbddobvyz/dijital-genc-yze GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 82 files (41.2 MB), approximately 10.8M tokens, and a symbol index with 38 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.

Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.

Extract another repo
Copied to clipboard!