{
 "nbformat": 4,
 "nbformat_minor": 5,
 "metadata": {
  "colab": {
   "provenance": [],
   "gpuType": "T4"
  },
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3"
  },
  "language_info": {
   "name": "python"
  }
 },
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "title"
   },
   "source": "# 🏭 SAP S/4HANA Public Cloud → Quantum Sales Forecast\n## OData API + Qiskit Quantum Kernel Regression (QML Şablonu)\n\n**Hedef kitle:** Öğrenciler (ERP + Quantum Machine Learning kesişimi)  \n**Ortam:** Google Colab  \n**Bileşenler:** SAP OData API • Qiskit • IBM Quantum Runtime • scikit-learn • XGBoost\n\n---\n\n### Pipeline Özeti\n\n| Aşama | Konu |\n|-------|------|\n| 1 | Ortam kurulumu (Qiskit + IBM Quantum) |\n| 2 | SAP S/4HANA Public Cloud OData bağlantısı |\n| 3 | Satış verisinin çekilmesi / sentetik fallback |\n| 4 | Zaman serisi özellik mühendisliği (lag + takvim) |\n| 5 | Klasik baseline (Ridge + XGBoost) |\n| 6 | **Quantum Kernel Ridge Regression** (QML çekirdeği) |\n| 7 | IBM Quantum gerçek backend (opsiyonel iskelet) |\n| 8 | Performans karşılaştırması + 3 aylık forecast |\n| 9 | Akademik tartışma ve geliştirme önerileri |\n\n> **Önemli:** Gerçek SAP erişimi için Communication User + Basic Auth / OAuth gerekir.  \n> Bu notebook **gerçek API kodu** + **sentetik fallback** birlikte sunar.  \n> SAP kimlik bilgileriniz yoksa sentetik veri ile tüm QML pipeline’ı kesintisiz çalışır.\n",
   "id": "title"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section1"
   },
   "source": "## 1. Ortam Kurulumu\n\nAşağıdaki hücreyi çalıştırın. Ardından IBM Quantum hesabınızı bağlayacağız.\n",
   "id": "section1"
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "setup",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407010732,
     "user_tz": -180,
     "elapsed": 49866,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "36f7bff6-4227-4957-cdb4-c4300870bbf4"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Python: 3.13.15\n",
      "Mounted at /content/drive\n",
      "✅ Google Drive bağlandı\n",
      "\n",
      "📦 Paketler kuruluyor...\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25h\n",
      "✅ Kurulum tamamlandı.\n"
     ]
    }
   ],
   "source": "# ============================================================\n# COLAB KURULUM\n# ============================================================\nimport sys\nprint(f\"Python: {sys.version.split()[0]}\")\n\ntry:\n    from google.colab import drive\n    drive.mount('/content/drive')\n    print(\"✅ Google Drive bağlandı\")\nexcept Exception as e:\n    print(f\"⚠️ Drive mount atlandı: {e}\")\n\nprint(\"\\n📦 Paketler kuruluyor...\")\n!pip install -q --upgrade pip\n!pip install -q qiskit qiskit-aer qiskit-machine-learning qiskit-ibm-runtime\n!pip install -q scikit-learn pandas numpy matplotlib seaborn xgboost requests tqdm\n\nprint(\"\\n✅ Kurulum tamamlandı.\")\n",
   "id": "setup"
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "imports",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407014384,
     "user_tz": -180,
     "elapsed": 3632,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "efe71f44-f54f-409f-e4b5-18b8f23d8693"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "✅ Temel kütüphaneler yüklendi.\n"
     ]
    }
   ],
   "source": "import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport requests\nfrom datetime import datetime, timedelta\nimport warnings\nwarnings.filterwarnings('ignore')\n\nfrom sklearn.preprocessing import StandardScaler, MinMaxScaler\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import Ridge\nfrom sklearn.kernel_ridge import KernelRidge\nfrom sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score\nfrom xgboost import XGBRegressor\n\nsns.set_style('whitegrid')\nplt.rcParams['figure.figsize'] = (12, 5)\nprint(\"✅ Temel kütüphaneler yüklendi.\")\n",
   "id": "imports"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section2"
   },
   "source": "## 2. IBM Quantum Hesabı Bağlantısı\n\n1. [IBM Quantum Platform](https://quantum.ibm.com/) üzerinden ücretsiz hesap açın.\n2. **API Token** alın (Account → API Token).\n3. Aşağıdaki hücrede token’ınızı girin **veya** Colab Secrets kullanın.\n\n> Token’ı Colab Secrets ile saklamak daha güvenlidir:  \n> Sol menü → 🔑 Secrets → `IBM_QUANTUM_TOKEN` ekleyin.\n",
   "id": "section2"
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "ibm_token",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407016380,
     "user_tz": -180,
     "elapsed": 1988,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "4a5686a0-6176-4c8d-a9b3-d03363a21fc4"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "✅ Token Colab Secrets'tan alındı.\n",
      "ℹ️ Simülatör modu aktif (Aer / Statevector).\n",
      "   Gerçek backend için USE_REAL_BACKEND=True ve token girin.\n"
     ]
    }
   ],
   "source": "# ============================================================\n# IBM QUANTUM TOKEN\n# ============================================================\ntry:\n    from google.colab import userdata\n    IBM_TOKEN = userdata.get('IBM_QUANTUM_TOKEN')\n    print(\"✅ Token Colab Secrets'tan alındı.\")\nexcept Exception:\n    IBM_TOKEN = \"\"  # ← Buraya IBM Quantum API Token yazabilirsiniz\n    if not IBM_TOKEN:\n        print(\"⚠️ Token girilmedi. Simülatör ile devam edilecek.\")\n    else:\n        print(\"✅ Token manuel olarak alındı.\")\n\nfrom qiskit_ibm_runtime import QiskitRuntimeService\n\nUSE_REAL_BACKEND = False  # True yaparsanız gerçek IBM Quantum backend kullanılır\n\nif IBM_TOKEN and USE_REAL_BACKEND:\n    try:\n        QiskitRuntimeService.save_account(\n            channel=\"ibm_quantum\", token=IBM_TOKEN, overwrite=True\n        )\n        service = QiskitRuntimeService(channel=\"ibm_quantum\")\n        print(\"✅ IBM Quantum hesabı bağlandı.\")\n        print(\"Kullanılabilir backend'ler (ilk 5):\")\n        for b in service.backends()[:5]:\n            print(f\"  - {b.name}\")\n    except Exception as e:\n        print(f\"⚠️ IBM Quantum bağlantı hatası: {e}\")\n        print(\"   Simülatör ile devam edilecek.\")\n        USE_REAL_BACKEND = False\nelse:\n    print(\"ℹ️ Simülatör modu aktif (Aer / Statevector).\")\n    print(\"   Gerçek backend için USE_REAL_BACKEND=True ve token girin.\")\n",
   "id": "ibm_token"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section3"
   },
   "source": "## 3. SAP S/4HANA Public Cloud – OData API ile Satış Verisi\n\n### Gerçek Sistem İçin Gerekenler\n\n| Parametre | Açıklama |\n|-----------|----------|\n| `SAP_BASE_URL` | Örn: `https://myXXXXXX-api.s4hana.cloud.sap` |\n| `SAP_USER` / `SAP_PASSWORD` | Communication User (Basic Auth) |\n| OData Servisi | `API_SALES_ORDER_SRV` veya `API_BILLING_DOCUMENT_SRV` |\n\n**Örnek endpoint:**  \n`/sap/opu/odata/sap/API_SALES_ORDER_SRV/A_SalesOrder?$top=500&$select=SalesOrder,SoldToParty,TotalNetAmount,SalesOrderDate`\n\n> Kimlik bilgileriniz yoksa otomatik olarak **sentetik satış verisi** üretilir.\n",
   "id": "section3"
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "sap_api",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407016442,
     "user_tz": -180,
     "elapsed": 56,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "a904f6da-ef89-495f-c067-9ebc865d4acf"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "→ Sentetik veri moduna geçiliyor...\n"
     ]
    }
   ],
   "source": "# ============================================================\n# SAP S/4HANA PUBLIC CLOUD BAĞLANTI AYARLARI\n# ============================================================\nSAP_BASE_URL = \"\"          # Örn: https://my123456-api.s4hana.cloud.sap\nSAP_USER     = \"\"          # Communication User\nSAP_PASSWORD = \"\"          # Şifre\n\nODATA_PATH = \"/sap/opu/odata/sap/API_SALES_ORDER_SRV/A_SalesOrder\"\n\ndef fetch_sap_sales_orders(base_url, user, password, top=500):\n    \"\"\"\n    SAP S/4HANA Public Cloud'dan Sales Order verisi çeker.\n    OData V2 / V4 Basic Auth.\n    \"\"\"\n    if not base_url or not user:\n        return None\n\n    url = f\"{base_url.rstrip('/')}{ODATA_PATH}\"\n    params = {\n        \"$top\": top,\n        \"$select\": \"SalesOrder,SoldToParty,TotalNetAmount,SalesOrderDate,\"\n                   \"SalesOrganization,TransactionCurrency\",\n        \"$orderby\": \"SalesOrderDate desc\",\n        \"$format\": \"json\"\n    }\n    headers = {\n        \"Accept\": \"application/json\",\n        \"x-csrf-token\": \"Fetch\"\n    }\n\n    try:\n        resp = requests.get(\n            url, params=params, auth=(user, password),\n            headers=headers, timeout=30\n        )\n        resp.raise_for_status()\n        data = resp.json()\n\n        # OData V2 → d.results | OData V4 → value\n        results = data.get(\"d\", {}).get(\"results\") or data.get(\"value\") or []\n        if not results:\n            print(\"⚠️ API yanıtı boş döndü.\")\n            return None\n\n        df = pd.DataFrame(results)\n        print(f\"✅ SAP'den {len(df)} satış kaydı çekildi.\")\n        return df\n\n    except Exception as e:\n        print(f\"⚠️ SAP API hatası: {e}\")\n        return None\n\n\ndf_sap = fetch_sap_sales_orders(SAP_BASE_URL, SAP_USER, SAP_PASSWORD)\n\nif df_sap is not None:\n    display(df_sap.head())\nelse:\n    print(\"→ Sentetik veri moduna geçiliyor...\")\n",
   "id": "sap_api"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section4"
   },
   "source": "## 4. Satış Verisinin Hazırlanması\n\nSAP’den veri gelmezse, gerçekçi **sentetik aylık satış zaman serisi** üretilir  \n(trend + mevsimsellik + kampanya etkisi + gürültü).  \nBu sayede tüm pipeline (ön işleme → klasik → kuantum) kesintisiz çalışır.\n",
   "id": "section4"
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "data_prep",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 451
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407016507,
     "user_tz": -180,
     "elapsed": 62,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "f17ebf06-61e2-4b45-eedf-eeb0bc5cfb93"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Sentetik satış verisi üretiliyor...\n",
      "\n",
      "Veri şekli: (48, 4)\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "        date  sales_amount  orders_count  avg_order_value\n",
       "0 2022-01-01     103973.71           127            850.0\n",
       "1 2022-02-01     113096.01           106            850.0\n",
       "2 2022-03-01     130236.40           158            850.0\n",
       "3 2022-04-01     142290.62           161            850.0\n",
       "4 2022-05-01     126585.92           138            850.0\n",
       "5 2022-06-01     119137.54           149            850.0\n",
       "6 2022-07-01     122846.47           159            850.0\n",
       "7 2022-08-01     105554.37           138            850.0\n",
       "8 2022-09-01      88210.59            91            850.0\n",
       "9 2022-10-01      94659.63           106            850.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-2da9f735-92c5-47ba-bed1-c0d5caec0034\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>sales_amount</th>\n",
       "      <th>orders_count</th>\n",
       "      <th>avg_order_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2022-01-01</td>\n",
       "      <td>103973.71</td>\n",
       "      <td>127</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2022-02-01</td>\n",
       "      <td>113096.01</td>\n",
       "      <td>106</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2022-03-01</td>\n",
       "      <td>130236.40</td>\n",
       "      <td>158</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2022-04-01</td>\n",
       "      <td>142290.62</td>\n",
       "      <td>161</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2022-05-01</td>\n",
       "      <td>126585.92</td>\n",
       "      <td>138</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2022-06-01</td>\n",
       "      <td>119137.54</td>\n",
       "      <td>149</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2022-07-01</td>\n",
       "      <td>122846.47</td>\n",
       "      <td>159</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2022-08-01</td>\n",
       "      <td>105554.37</td>\n",
       "      <td>138</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2022-09-01</td>\n",
       "      <td>88210.59</td>\n",
       "      <td>91</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2022-10-01</td>\n",
       "      <td>94659.63</td>\n",
       "      <td>106</td>\n",
       "      <td>850.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2da9f735-92c5-47ba-bed1-c0d5caec0034')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-2da9f735-92c5-47ba-bed1-c0d5caec0034 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-2da9f735-92c5-47ba-bed1-c0d5caec0034');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"print(f\\\"Toplam sat\\u0131\\u015f: {df['sales_amount']\",\n  \"rows\": 10,\n  \"fields\": [\n    {\n      \"column\": \"date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2022-01-01 00:00:00\",\n        \"max\": \"2022-10-01 00:00:00\",\n        \"num_unique_values\": 10,\n        \"samples\": [\n          \"2022-09-01 00:00:00\",\n          \"2022-02-01 00:00:00\",\n          \"2022-06-01 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"sales_amount\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 16781.309246137964,\n        \"min\": 88210.59,\n        \"max\": 142290.62,\n        \"num_unique_values\": 10,\n        \"samples\": [\n          88210.59,\n          113096.01,\n          119137.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"orders_count\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 25,\n        \"min\": 91,\n        \"max\": 161,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          106,\n          149,\n          127\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"avg_order_value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0,\n        \"min\": 850.0,\n        \"max\": 850.0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          850.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\n",
      "Tarih aralığı: 2022-01-01 → 2025-12-01\n",
      "Toplam satış: 6,761,166\n"
     ]
    }
   ],
   "source": "def generate_synthetic_sales(n_months=48, seed=42):\n    \"\"\"\n    Gerçekçi aylık satış verisi üretir:\n    - Trend + mevsimsellik + gürültü\n    - Tatil / kampanya etkileri (Kasım-Aralık)\n    \"\"\"\n    np.random.seed(seed)\n    dates = pd.date_range(start='2022-01-01', periods=n_months, freq='MS')\n\n    trend = np.linspace(100_000, 180_000, n_months)\n    seasonality = 25_000 * np.sin(2 * np.pi * np.arange(n_months) / 12)\n    campaign = np.array([15_000 if d.month in [11, 12] else 0 for d in dates])\n    noise = np.random.normal(0, 8_000, n_months)\n\n    sales = trend + seasonality + campaign + noise\n    sales = np.maximum(sales, 20_000)\n\n    df = pd.DataFrame({\n        'date': dates,\n        'sales_amount': sales.round(2),\n        'orders_count': (sales / 850 + np.random.normal(0, 15, n_months))\n                         .astype(int).clip(min=20),\n        'avg_order_value': 850.0\n    })\n    return df\n\n\nif df_sap is not None and len(df_sap) > 10:\n    print(\"SAP verisi işleniyor...\")\n    df = df_sap.copy()\n\n    date_col = next(\n        (c for c in df.columns if 'date' in c.lower() or 'Date' in c), None\n    )\n    amount_col = next(\n        (c for c in df.columns\n         if 'amount' in c.lower() or 'Amount' in c or 'Net' in c), None\n    )\n\n    if date_col and amount_col:\n        df['date'] = pd.to_datetime(df[date_col], errors='coerce')\n        df['sales_amount'] = pd.to_numeric(df[amount_col], errors='coerce')\n        df = df.dropna(subset=['date', 'sales_amount'])\n        df = (df.set_index('date')\n                .resample('MS')['sales_amount']\n                .sum()\n                .reset_index())\n        df.columns = ['date', 'sales_amount']\n        print(f\"✅ SAP verisi aylık seriye dönüştürüldü: {len(df)} ay\")\n    else:\n        print(\"⚠️ Tarih/tutar sütunu bulunamadı → sentetik veri\")\n        df = generate_synthetic_sales()\nelse:\n    print(\"Sentetik satış verisi üretiliyor...\")\n    df = generate_synthetic_sales()\n\nprint(f\"\\nVeri şekli: {df.shape}\")\ndisplay(df.head(10))\nprint(f\"\\nTarih aralığı: {df['date'].min().date()} → {df['date'].max().date()}\")\nprint(f\"Toplam satış: {df['sales_amount'].sum():,.0f}\")\n",
   "id": "data_prep"
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "viz_raw",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 707
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407017804,
     "user_tz": -180,
     "elapsed": 1293,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "e5bd6b34-5df9-46e4-ee24-d2906fb8c703"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1200x700 with 2 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "# Görselleştirme\nfig, axes = plt.subplots(2, 1, figsize=(12, 7), sharex=True)\n\naxes[0].plot(df['date'], df['sales_amount'], marker='o', color='#2980b9', linewidth=1.5)\naxes[0].set_ylabel('Satış Tutarı')\naxes[0].set_title('Aylık Satış Tutarı')\naxes[0].grid(True, alpha=0.3)\n\nif 'orders_count' in df.columns:\n    axes[1].bar(df['date'], df['orders_count'], width=20, color='#27ae60', alpha=0.7)\n    axes[1].set_ylabel('Sipariş Adedi')\n    axes[1].set_title('Aylık Sipariş Adedi')\n    axes[1].grid(True, alpha=0.3)\n\nplt.xlabel('Tarih')\nplt.tight_layout()\nplt.show()\n",
   "id": "viz_raw"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section5"
   },
   "source": "## 5. Zaman Serisi Özellik Mühendisliği\n\nForecast için **lag features** (geçmiş değerler) ve takvim özellikleri oluşturuyoruz.\n\n- `lag_1` … `lag_6` → önceki 1–6 ayın satış tutarı  \n- `month`, `quarter` → mevsimsel etki  \n\nSonuç: Supervised learning problemine dönüşmüş tablo.\n",
   "id": "section5"
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "lag_features",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 234
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407017867,
     "user_tz": -180,
     "elapsed": 58,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "fed0befd-2759-4447-d12a-36980af9c626"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Özellikler: ['lag_1', 'lag_2', 'lag_3', 'lag_4', 'lag_5', 'lag_6', 'month', 'quarter']\n",
      "X şekli: (42, 8)  |  y şekli: (42,)\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "        date  sales_amount  orders_count  avg_order_value      lag_1  \\\n",
       "0 2022-07-01     122846.47           159            850.0  119137.54   \n",
       "1 2022-08-01     105554.37           138            850.0  122846.47   \n",
       "2 2022-09-01      88210.59            91            850.0  105554.37   \n",
       "3 2022-10-01      94659.63           106            850.0   88210.59   \n",
       "4 2022-11-01     106663.30           130            850.0   94659.63   \n",
       "\n",
       "       lag_2      lag_3      lag_4      lag_5      lag_6  month  quarter  \n",
       "0  126585.92  142290.62  130236.40  113096.01  103973.71      7        3  \n",
       "1  119137.54  126585.92  142290.62  130236.40  113096.01      8        3  \n",
       "2  122846.47  119137.54  126585.92  142290.62  130236.40      9        3  \n",
       "3  105554.37  122846.47  119137.54  126585.92  142290.62     10        4  \n",
       "4   88210.59  105554.37  122846.47  119137.54  126585.92     11        4  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-62ee243d-7000-4b78-ac1a-e1c99506cbcd\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>sales_amount</th>\n",
       "      <th>orders_count</th>\n",
       "      <th>avg_order_value</th>\n",
       "      <th>lag_1</th>\n",
       "      <th>lag_2</th>\n",
       "      <th>lag_3</th>\n",
       "      <th>lag_4</th>\n",
       "      <th>lag_5</th>\n",
       "      <th>lag_6</th>\n",
       "      <th>month</th>\n",
       "      <th>quarter</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2022-07-01</td>\n",
       "      <td>122846.47</td>\n",
       "      <td>159</td>\n",
       "      <td>850.0</td>\n",
       "      <td>119137.54</td>\n",
       "      <td>126585.92</td>\n",
       "      <td>142290.62</td>\n",
       "      <td>130236.40</td>\n",
       "      <td>113096.01</td>\n",
       "      <td>103973.71</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2022-08-01</td>\n",
       "      <td>105554.37</td>\n",
       "      <td>138</td>\n",
       "      <td>850.0</td>\n",
       "      <td>122846.47</td>\n",
       "      <td>119137.54</td>\n",
       "      <td>126585.92</td>\n",
       "      <td>142290.62</td>\n",
       "      <td>130236.40</td>\n",
       "      <td>113096.01</td>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2022-09-01</td>\n",
       "      <td>88210.59</td>\n",
       "      <td>91</td>\n",
       "      <td>850.0</td>\n",
       "      <td>105554.37</td>\n",
       "      <td>122846.47</td>\n",
       "      <td>119137.54</td>\n",
       "      <td>126585.92</td>\n",
       "      <td>142290.62</td>\n",
       "      <td>130236.40</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2022-10-01</td>\n",
       "      <td>94659.63</td>\n",
       "      <td>106</td>\n",
       "      <td>850.0</td>\n",
       "      <td>88210.59</td>\n",
       "      <td>105554.37</td>\n",
       "      <td>122846.47</td>\n",
       "      <td>119137.54</td>\n",
       "      <td>126585.92</td>\n",
       "      <td>142290.62</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2022-11-01</td>\n",
       "      <td>106663.30</td>\n",
       "      <td>130</td>\n",
       "      <td>850.0</td>\n",
       "      <td>94659.63</td>\n",
       "      <td>88210.59</td>\n",
       "      <td>105554.37</td>\n",
       "      <td>122846.47</td>\n",
       "      <td>119137.54</td>\n",
       "      <td>126585.92</td>\n",
       "      <td>11</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-62ee243d-7000-4b78-ac1a-e1c99506cbcd')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-62ee243d-7000-4b78-ac1a-e1c99506cbcd button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-62ee243d-7000-4b78-ac1a-e1c99506cbcd');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"display(df_feat\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2022-07-01 00:00:00\",\n        \"max\": \"2022-11-01 00:00:00\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"2022-08-01 00:00:00\",\n          \"2022-11-01 00:00:00\",\n          \"2022-09-01 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"sales_amount\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13232.472091514874,\n        \"min\": 88210.59,\n        \"max\": 122846.47,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          105554.37,\n          106663.3,\n          88210.59\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"orders_count\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 26,\n        \"min\": 91,\n        \"max\": 159,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          138,\n          130,\n          91\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"avg_order_value\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0,\n        \"min\": 850.0,\n        \"max\": 850.0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          850.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"lag_1\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15013.583881791848,\n        \"min\": 88210.59,\n        \"max\": 122846.47,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          122846.47\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"lag_2\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15714.096243035106,\n        \"min\": 88210.59,\n        \"max\": 126585.92,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          119137.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"lag_3\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13265.35541663811,\n        \"min\": 105554.37,\n        \"max\": 142290.62,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          126585.92\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"lag_4\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 8889.380406456909,\n        \"min\": 119137.54,\n        \"max\": 142290.62,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          142290.62\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"lag_5\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 11145.833249453359,\n        \"min\": 113096.01,\n        \"max\": 142290.62,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          130236.4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"lag_6\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14976.32564533003,\n        \"min\": 103973.71,\n        \"max\": 142290.62,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          113096.01\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"month\",\n      \"properties\": {\n        \"dtype\": \"int32\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          8\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"quarter\",\n      \"properties\": {\n        \"dtype\": \"int32\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    }
   ],
   "source": "def create_lag_features(data, target='sales_amount', lags=6):\n    df_feat = data.copy()\n    for lag in range(1, lags + 1):\n        df_feat[f'lag_{lag}'] = df_feat[target].shift(lag)\n    df_feat['month'] = df_feat['date'].dt.month\n    df_feat['quarter'] = df_feat['date'].dt.quarter\n    df_feat = df_feat.dropna().reset_index(drop=True)\n    return df_feat\n\n\ndf_feat = create_lag_features(df, lags=6)\nfeature_cols = [c for c in df_feat.columns\n                if c.startswith('lag_') or c in ('month', 'quarter')]\ntarget_col = 'sales_amount'\n\nX = df_feat[feature_cols].values\ny = df_feat[target_col].values\ndates = df_feat['date'].values\n\nprint(f\"Özellikler: {feature_cols}\")\nprint(f\"X şekli: {X.shape}  |  y şekli: {y.shape}\")\ndisplay(df_feat.head())\n",
   "id": "lag_features"
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "split_scale",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407017951,
     "user_tz": -180,
     "elapsed": 80,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "ebe391e0-42cf-43a3-c4db-192588b22c7e"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Train: (31, 8)  |  Test: (11, 8)\n"
     ]
    }
   ],
   "source": "# Train / Test split (zaman sırası korunarak – shuffle=False)\nsplit_idx = int(len(X) * 0.75)\nX_train, X_test = X[:split_idx], X[split_idx:]\ny_train, y_test = y[:split_idx], y[split_idx:]\ndates_train, dates_test = dates[:split_idx], dates[split_idx:]\n\nscaler = StandardScaler()\nX_train_s = scaler.fit_transform(X_train)\nX_test_s  = scaler.transform(X_test)\n\nprint(f\"Train: {X_train_s.shape}  |  Test: {X_test_s.shape}\")\n",
   "id": "split_scale"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section6"
   },
   "source": "## 6. Klasik Baseline Modeller\n\nKuantum modeli karşılaştırmak için iki güçlü klasik regressor eğitiyoruz:\n- **Ridge Regression** (L2 regularized linear)\n- **XGBoost** (gradient boosting)\n",
   "id": "section6"
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "classical_models",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407018163,
     "user_tz": -180,
     "elapsed": 207,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "ae6a6d0e-388d-4c5f-c8b7-dd840ebcf7b5"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Ridge                      MAE=13,807  RMSE=17,249  R²=0.0581\n",
      "XGBoost                    MAE=21,980  RMSE=26,757  R²=-1.2663\n"
     ]
    }
   ],
   "source": "def regression_metrics(y_true, y_pred, name=\"Model\"):\n    mae  = mean_absolute_error(y_true, y_pred)\n    rmse = np.sqrt(mean_squared_error(y_true, y_pred))\n    r2   = r2_score(y_true, y_pred)\n    print(f\"{name:25s}  MAE={mae:,.0f}  RMSE={rmse:,.0f}  R²={r2:.4f}\")\n    return {\"MAE\": mae, \"RMSE\": rmse, \"R2\": r2}\n\n\n# Ridge\nridge = Ridge(alpha=1.0)\nridge.fit(X_train_s, y_train)\nridge_pred = ridge.predict(X_test_s)\nridge_scores = regression_metrics(y_test, ridge_pred, \"Ridge\")\n\n# XGBoost\nxgb = XGBRegressor(\n    n_estimators=100, max_depth=3, learning_rate=0.1,\n    subsample=0.8, colsample_bytree=0.8, random_state=42, verbosity=0\n)\nxgb.fit(X_train_s, y_train)\nxgb_pred = xgb.predict(X_test_s)\nxgb_scores = regression_metrics(y_test, xgb_pred, \"XGBoost\")\n",
   "id": "classical_models"
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "viz_classical",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 507
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407019139,
     "user_tz": -180,
     "elapsed": 971,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "17f3623b-7f2f-47d7-84f8-ec8e5c796564"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1200x500 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "plt.figure(figsize=(12, 5))\nplt.plot(dates_test, y_test, 'o-', label='Gerçek', color='#2c3e50', linewidth=2)\nplt.plot(dates_test, ridge_pred, 's--', label='Ridge', color='#3498db', alpha=0.8)\nplt.plot(dates_test, xgb_pred, '^--', label='XGBoost', color='#e74c3c', alpha=0.8)\nplt.title('Klasik Baseline – Test Seti')\nplt.ylabel('Satış Tutarı')\nplt.legend()\nplt.grid(True, alpha=0.3)\nplt.tight_layout()\nplt.show()\n",
   "id": "viz_classical"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section7"
   },
   "source": "## 7. Quantum Kernel Regression (QML Çekirdeği)\n\n**Yöntem (Quantum Kernel Ridge):**\n\n1. Klasik özellikleri `zz_feature_map` ile Hilbert uzayına göm  \n2. Fidelity tabanlı quantum kernel matrisi hesapla  \n   $$K(x,y) = \\bigl|\\langle\\phi(x)\\,|\\,\\phi(y)\\rangle\\bigr|^2$$\n3. Kernel matrisini klasik **Kernel Ridge Regression**’a ver\n\nBu yaklaşım NISQ döneminde en stabil quantum regression yöntemlerinden biridir.\n\n> Qubit sayısı = özellik sayısı. Bu yüzden XGBoost importance ile en önemli **4 özelliği** seçiyoruz (hız + kararlılık).\n",
   "id": "section7"
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "q_features",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407019445,
     "user_tz": -180,
     "elapsed": 301,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "7585451b-7d14-481b-9181-702efb456e62"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Kuantum için seçilen özellikler: ['lag_1', 'lag_5', 'month', 'lag_2']\n",
      "lag_1      0.226086\n",
      "lag_5      0.188105\n",
      "month      0.174473\n",
      "lag_2      0.157896\n",
      "lag_3      0.095144\n",
      "quarter    0.075512\n",
      "\n",
      "Quantum veri şekli → Train: (31, 4), Test: (11, 4)\n"
     ]
    }
   ],
   "source": "from qiskit.circuit.library import zz_feature_map\nfrom qiskit_machine_learning.kernels import FidelityStatevectorKernel\n\n# En önemli 4 özelliği seç (XGBoost importance)\nimp = pd.Series(xgb.feature_importances_, index=feature_cols).sort_values(ascending=False)\ntop_features = imp.head(4).index.tolist()\nprint(f\"Kuantum için seçilen özellikler: {top_features}\")\nprint(imp.head(6).to_string())\n\nfeat_idx = [feature_cols.index(f) for f in top_features]\nX_train_q = X_train_s[:, feat_idx]\nX_test_q  = X_test_s[:, feat_idx]\n\n# Açı aralığına ölçekle [0, π]  →  feature map için doğal aralık\nq_scaler = MinMaxScaler(feature_range=(0, np.pi))\nX_train_q = q_scaler.fit_transform(X_train_q)\nX_test_q  = q_scaler.transform(X_test_q)\n\nprint(f\"\\nQuantum veri şekli → Train: {X_train_q.shape}, Test: {X_test_q.shape}\")\n",
   "id": "q_features"
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "q_train",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407032176,
     "user_tz": -180,
     "elapsed": 12725,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "47e7c1e4-a7b2-4751-97b9-f3ad24e42d48"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "⏳ Quantum Kernel matrisi hesaplanıyor (Statevector)...\n",
      "✅ Quantum Kernel Ridge eğitildi.\n",
      "\n",
      "=== Quantum Kernel Regression Performansı ===\n",
      "Quantum KR                 MAE=88,575  RMSE=90,159  R²=-24.7320\n"
     ]
    }
   ],
   "source": "# ============================================================\n# QUANTUM FEATURE MAP + FIDELITY KERNEL\n# ============================================================\nn_qubits = 4\nfeature_map = zz_feature_map(\n    feature_dimension=n_qubits,\n    reps=2,\n    entanglement='circular'\n)\n\n# Statevector tabanlı, hızlı simülasyon (eğitim için ideal)\nquantum_kernel = FidelityStatevectorKernel(feature_map=feature_map)\n\nprint(\"⏳ Quantum Kernel matrisi hesaplanıyor (Statevector)...\")\n\n# sklearn uyumlu callable: quantum_kernel.evaluate\nq_model = KernelRidge(alpha=0.5, kernel=quantum_kernel.evaluate)\nq_model.fit(X_train_q, y_train)\nprint(\"✅ Quantum Kernel Ridge eğitildi.\")\n\nq_pred = q_model.predict(X_test_q)\n\nprint(\"\\n=== Quantum Kernel Regression Performansı ===\")\nq_scores = regression_metrics(y_test, q_pred, \"Quantum KR\")\n",
   "id": "q_train"
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "viz_quantum",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 507
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407033004,
     "user_tz": -180,
     "elapsed": 821,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "b4e8bd1a-8ca6-4e55-bff2-17d4dda87d8e"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1200x500 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "plt.figure(figsize=(12, 5))\nplt.plot(dates_test, y_test, 'o-', label='Gerçek', color='#2c3e50', linewidth=2)\nplt.plot(dates_test, xgb_pred, '^--', label='XGBoost', color='#e74c3c', alpha=0.8)\nplt.plot(dates_test, q_pred, 'D--', label='Quantum Kernel', color='#9b59b6', linewidth=2)\nplt.title('Klasik vs Quantum Forecast – Test Seti')\nplt.ylabel('Satış Tutarı')\nplt.legend()\nplt.grid(True, alpha=0.3)\nplt.tight_layout()\nplt.show()\n",
   "id": "viz_quantum"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section8"
   },
   "source": "## 8. IBM Quantum Gerçek Backend (Opsiyonel İskelet)\n\nAşağıdaki hücre **sadece** `USE_REAL_BACKEND = True` ve geçerli token varsa anlamlıdır.\n\nGerçek donanımda:\n- Gürültü vardır → sonuçlar simülatörden farklı olabilir\n- Kuyruk süresi uzayabilir\n- Ücretsiz tier’da aylık job hakkı sınırlıdır\n\n> Eğitim amaçlı olarak önce simülatörle çalışmanız önerilir.  \n> Production için: Session + SamplerV2 + transpilation + error mitigation.\n",
   "id": "section8"
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "real_backend",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407033163,
     "user_tz": -180,
     "elapsed": 154,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "cf1cb1d7-8ef4-4422-f1bd-056375591d6c"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "ℹ️ Gerçek backend atlandı (USE_REAL_BACKEND=False veya token yok).\n",
      "   Simülatör (FidelityStatevectorKernel) sonuçları geçerli.\n"
     ]
    }
   ],
   "source": "# ============================================================\n# GERÇEK IBM QUANTUM BACKEND (OPSİYONEL İSKELET)\n# ============================================================\nif USE_REAL_BACKEND and IBM_TOKEN:\n    from qiskit_ibm_runtime import SamplerV2 as Sampler, Session\n    from qiskit.transpiler.preset_passmanagers import generate_preset_pass_manager\n    from qiskit_machine_learning.kernels import FidelityQuantumKernel\n    from qiskit_machine_learning.state_fidelities import ComputeUncompute\n\n    try:\n        service = QiskitRuntimeService(channel=\"ibm_quantum\")\n        backend = service.least_busy(\n            operational=True, simulator=False, min_num_qubits=n_qubits\n        )\n        print(f\"Seçilen backend: {backend.name}\")\n\n        # --- İskelet (eğitim amaçlı) ---\n        # pm = generate_preset_pass_manager(backend=backend, optimization_level=1)\n        # with Session(backend=backend) as session:\n        #     sampler = Sampler(mode=session)\n        #     fidelity = ComputeUncompute(sampler=sampler)\n        #     qk = FidelityQuantumKernel(feature_map=feature_map, fidelity=fidelity)\n        #     # ... KernelRidge veya QSVR ile devam\n        print(\"\"\"\n        ⚠️ Gerçek donanım kodu iskelet olarak bırakıldı.\n        Tam production kodu için:\n          - Session içinde SamplerV2 kullanın\n          - Transpilation (pass manager) uygulayın\n          - Error mitigation (TREX / ZNE) ekleyin\n          - Job sonuçlarını asenkron takip edin\n        \"\"\")\n    except Exception as e:\n        print(f\"Gerçek backend hatası: {e}\")\n        print(\"Simülatör sonuçları ile devam ediliyor.\")\nelse:\n    print(\"ℹ️ Gerçek backend atlandı (USE_REAL_BACKEND=False veya token yok).\")\n    print(\"   Simülatör (FidelityStatevectorKernel) sonuçları geçerli.\")\n",
   "id": "real_backend"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "section9"
   },
   "source": "## 9. Performans Karşılaştırması ve İleriye Dönük Tahmin\n",
   "id": "section9"
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "comparison",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 189
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407033349,
     "user_tz": -180,
     "elapsed": 180,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "b8b25b81-3e9e-4456-a333-13d20c8a49a2"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "=== Model Karşılaştırması ===\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "                  Model      MAE     RMSE       R²\n",
       "0                 Ridge  13807.0  17249.0   0.0581\n",
       "1               XGBoost  21980.0  26757.0  -1.2663\n",
       "2  Quantum Kernel Ridge  88575.0  90159.0 -24.7320"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-4e87eb4c-42fa-4611-85fa-59659195870b\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Model</th>\n",
       "      <th>MAE</th>\n",
       "      <th>RMSE</th>\n",
       "      <th>R²</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Ridge</td>\n",
       "      <td>13807.0</td>\n",
       "      <td>17249.0</td>\n",
       "      <td>0.0581</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>XGBoost</td>\n",
       "      <td>21980.0</td>\n",
       "      <td>26757.0</td>\n",
       "      <td>-1.2663</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Quantum Kernel Ridge</td>\n",
       "      <td>88575.0</td>\n",
       "      <td>90159.0</td>\n",
       "      <td>-24.7320</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4e87eb4c-42fa-4611-85fa-59659195870b')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-4e87eb4c-42fa-4611-85fa-59659195870b button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-4e87eb4c-42fa-4611-85fa-59659195870b');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "  <div id=\"id_7effa039-f29b-480e-b4d7-dd316b2b1283\">\n",
       "    <style>\n",
       "      .colab-df-generate {\n",
       "        background-color: #E8F0FE;\n",
       "        border: none;\n",
       "        border-radius: 50%;\n",
       "        cursor: pointer;\n",
       "        display: none;\n",
       "        fill: #1967D2;\n",
       "        height: 32px;\n",
       "        padding: 0 0 0 0;\n",
       "        width: 32px;\n",
       "      }\n",
       "\n",
       "      .colab-df-generate:hover {\n",
       "        background-color: #E2EBFA;\n",
       "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "        fill: #174EA6;\n",
       "      }\n",
       "\n",
       "      [theme=dark] .colab-df-generate {\n",
       "        background-color: #3B4455;\n",
       "        fill: #D2E3FC;\n",
       "      }\n",
       "\n",
       "      [theme=dark] .colab-df-generate:hover {\n",
       "        background-color: #434B5C;\n",
       "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "        fill: #FFFFFF;\n",
       "      }\n",
       "    </style>\n",
       "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('comparison')\"\n",
       "            title=\"Generate code using this dataframe.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "       width=\"24px\">\n",
       "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "    <script>\n",
       "      (() => {\n",
       "      const buttonEl =\n",
       "        document.querySelector('#id_7effa039-f29b-480e-b4d7-dd316b2b1283 button.colab-df-generate');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      buttonEl.onclick = () => {\n",
       "        google.colab.notebook.generateWithVariable('comparison');\n",
       "      }\n",
       "      })();\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "comparison",
       "summary": "{\n  \"name\": \"comparison\",\n  \"rows\": 3,\n  \"fields\": [\n    {\n      \"column\": \"Model\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"Ridge\",\n          \"XGBoost\",\n          \"Quantum Kernel Ridge\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MAE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 41012.08313412037,\n        \"min\": 13807.0,\n        \"max\": 88575.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          13807.0,\n          21980.0,\n          88575.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"RMSE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 39636.01848487476,\n        \"min\": 17249.0,\n        \"max\": 90159.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          17249.0,\n          26757.0,\n          90159.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"R\\u00b2\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13.945980124872305,\n        \"min\": -24.732,\n        \"max\": 0.0581,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0581,\n          -1.2663,\n          -24.732\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\n",
      "En düşük MAE: Ridge\n"
     ]
    }
   ],
   "source": "comparison = pd.DataFrame({\n    'Model': ['Ridge', 'XGBoost', 'Quantum Kernel Ridge'],\n    'MAE':  [ridge_scores['MAE'], xgb_scores['MAE'], q_scores['MAE']],\n    'RMSE': [ridge_scores['RMSE'], xgb_scores['RMSE'], q_scores['RMSE']],\n    'R²':   [ridge_scores['R2'], xgb_scores['R2'], q_scores['R2']],\n})\ncomparison = comparison.round({'MAE': 0, 'RMSE': 0, 'R²': 4})\nprint(\"=== Model Karşılaştırması ===\")\ndisplay(comparison)\n\n# En iyi modeli (düşük MAE) seç\nbest_idx = comparison['MAE'].idxmin()\nprint(f\"\\nEn düşük MAE: {comparison.loc[best_idx, 'Model']}\")\n",
   "id": "comparison"
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "id": "future_forecast",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 678
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1789407034173,
     "user_tz": -180,
     "elapsed": 820,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "23e2168d-9b9e-4c41-dbd6-45cdc923a8da"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Gelecek 3 ay için forecast üretiliyor (XGBoost + son lag'ler)...\n",
      "\n",
      "=== 3 Aylık Satış Tahmini ===\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "        date  forecast_sales\n",
       "0 2026-01-01        143515.0\n",
       "1 2026-02-01        161647.0\n",
       "2 2026-03-01        156769.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-7a6713b2-d411-42fb-a238-68340b860e3f\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>forecast_sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2026-01-01</td>\n",
       "      <td>143515.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2026-02-01</td>\n",
       "      <td>161647.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2026-03-01</td>\n",
       "      <td>156769.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7a6713b2-d411-42fb-a238-68340b860e3f')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-7a6713b2-d411-42fb-a238-68340b860e3f button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-7a6713b2-d411-42fb-a238-68340b860e3f');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "  <div id=\"id_9b9110b7-fc5a-4ecd-82a3-512ec6d04353\">\n",
       "    <style>\n",
       "      .colab-df-generate {\n",
       "        background-color: #E8F0FE;\n",
       "        border: none;\n",
       "        border-radius: 50%;\n",
       "        cursor: pointer;\n",
       "        display: none;\n",
       "        fill: #1967D2;\n",
       "        height: 32px;\n",
       "        padding: 0 0 0 0;\n",
       "        width: 32px;\n",
       "      }\n",
       "\n",
       "      .colab-df-generate:hover {\n",
       "        background-color: #E2EBFA;\n",
       "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "        fill: #174EA6;\n",
       "      }\n",
       "\n",
       "      [theme=dark] .colab-df-generate {\n",
       "        background-color: #3B4455;\n",
       "        fill: #D2E3FC;\n",
       "      }\n",
       "\n",
       "      [theme=dark] .colab-df-generate:hover {\n",
       "        background-color: #434B5C;\n",
       "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "        fill: #FFFFFF;\n",
       "      }\n",
       "    </style>\n",
       "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('forecast_df')\"\n",
       "            title=\"Generate code using this dataframe.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "       width=\"24px\">\n",
       "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "    <script>\n",
       "      (() => {\n",
       "      const buttonEl =\n",
       "        document.querySelector('#id_9b9110b7-fc5a-4ecd-82a3-512ec6d04353 button.colab-df-generate');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      buttonEl.onclick = () => {\n",
       "        google.colab.notebook.generateWithVariable('forecast_df');\n",
       "      }\n",
       "      })();\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "forecast_df",
       "summary": "{\n  \"name\": \"forecast_df\",\n  \"rows\": 3,\n  \"fields\": [\n    {\n      \"column\": \"date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2026-01-01 00:00:00\",\n        \"max\": \"2026-03-01 00:00:00\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"2026-01-01 00:00:00\",\n          \"2026-02-01 00:00:00\",\n          \"2026-03-01 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"forecast_sales\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          143515.0,\n          161647.0,\n          156769.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1200x500 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "# ============================================================\n# SONRAKİ 3 AY İÇİN FORECAST (XGBoost + recursive lag)\n# ============================================================\nprint(\"Gelecek 3 ay için forecast üretiliyor (XGBoost + son lag'ler)...\\n\")\n\nlast_row = df_feat.iloc[-1:].copy()\nfuture_preds = []\nfuture_dates = []\n\ncurrent_features = last_row[feature_cols].values.copy()\nlast_date = df_feat['date'].iloc[-1]\n\nfor i in range(1, 4):\n    next_date = last_date + pd.DateOffset(months=i)\n    future_dates.append(next_date)\n\n    curr_s = scaler.transform(current_features)\n    pred = xgb.predict(curr_s)[0]\n    future_preds.append(pred)\n\n    # Lag kaydır (recursive)\n    new_feats = current_features.copy()\n    lag_cols = [c for c in feature_cols if c.startswith('lag_')]\n    if lag_cols:\n        lag_idx = [feature_cols.index(c) for c in lag_cols]\n        for j in range(len(lag_idx) - 1, 0, -1):\n            new_feats[0, lag_idx[j]] = new_feats[0, lag_idx[j - 1]]\n        new_feats[0, lag_idx[0]] = pred\n\n    if 'month' in feature_cols:\n        new_feats[0, feature_cols.index('month')] = next_date.month\n    if 'quarter' in feature_cols:\n        new_feats[0, feature_cols.index('quarter')] = next_date.quarter\n\n    current_features = new_feats\n\nforecast_df = pd.DataFrame({\n    'date': future_dates,\n    'forecast_sales': np.round(future_preds, 0)\n})\nprint(\"=== 3 Aylık Satış Tahmini ===\")\ndisplay(forecast_df)\n\nplt.figure(figsize=(12, 5))\nplt.plot(df_feat['date'], df_feat['sales_amount'], 'o-',\n         label='Geçmiş', color='#2c3e50')\nplt.plot(forecast_df['date'], forecast_df['forecast_sales'], 'D--',\n         label='Forecast (3 ay)', color='#e67e22', markersize=10)\nplt.axvline(df_feat['date'].iloc[-1], color='gray', linestyle=':', label='Bugün')\nplt.title('Satış Forecast – Sonraki 3 Ay')\nplt.ylabel('Satış Tutarı')\nplt.legend()\nplt.grid(True, alpha=0.3)\nplt.tight_layout()\nplt.show()\n",
   "id": "future_forecast"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "discussion"
   },
   "source": "## 10. Akademik Tartışma ve Öğrenci Notları\n\n### 10.1 Neden Quantum Forecast Klasik Modelleri Her Zaman Geçmez?\n\n| Faktör | Açıklama |\n|--------|----------|\n| **Veri boyutu** | Quantum kernel \\(O(n^2)\\) maliyetlidir. 40–50 aylık seri küçük kalır. |\n| **Özellik sayısı** | 4 qubit ile sınırlıyız → bilgi kaybı olabilir. |\n| **Problem tipi** | Tabular zaman serisi, kuantum avantajı için en zor problem sınıflarındandır. |\n| **NISQ gürültüsü** | Gerçek donanımda ek hata katmanı oluşur. |\n\n### 10.2 Farklı Kuantum Mimarilerinde Satış Tahmini (Kavramsal)\n\n| Mimari | Framework | Satış Problemine Yaklaşım | En İyi Olduğu Aşama |\n|--------|-----------|---------------------------|---------------------|\n| **IBM (Süperiletken)** | Qiskit | Feature Map + Quantum Kernel / VQC | Direkt regresyon |\n| **D-Wave (Annealing)** | Ocean SDK | QUBO → stok / tedarik optimizasyonu | Tahmin sonrası planlama |\n| **Fotonik (CV)** | Strawberry Fields | Continuous-Variable QNN | Yüksek boyutlu matrisler |\n| **Soğuk Atom (Rydberg)** | Pulser / Bloqade | Graph / network dinamikleri | Müşteri ilişki ağları |\n\n> Bu notebook **IBM gate-based + Quantum Kernel** yolunu uygulamalı gösterir.  \n> Diğer mimariler için problem formülasyonu (QUBO, CV, graph) tamamen değişir.\n\n### 10.3 Bu Pipeline’ın Değeri\n\n- **SAP ↔ Quantum** köprüsünü kurmayı öğrendiniz.\n- OData API → zaman serisi feature engineering → quantum kernel zincirini uçtan uca gördünüz.\n- Gerçek enterprise sistemden (S/4HANA) veri alıp quantum modele besleme mimarisini anladınız.\n\n### 10.4 Geliştirme Önerileri (Ödev / Proje)\n\n1. SAP’den **Billing Document** veya **Outbound Delivery** verisi de çekip çok değişkenli forecast yapın.\n2. PCA yerine klasik feature importance ile qubit seçimini optimize edin (zaten yaptık; farklı metrikler deneyin).\n3. `qiskit-ibm-runtime` ile gerçek backend’de küçük bir job çalıştırıp simülatörle karşılaştırın.\n4. Prophet / NeuralProphet gibi güçlü klasik modelleri de baseline’a ekleyin.\n5. Forecast sonuçlarını tekrar SAP’ye (custom CDS view veya side-by-side extension) yazacak bir mimari tasarlayın.\n6. Trainable quantum kernel (`TrainableFidelityStatevectorKernel` + `QuantumKernelTrainer`) deneyin.\n",
   "id": "discussion"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "closing"
   },
   "source": "---\n\n## 11. Özet\n\nBu notebook’ta:\n\n1. SAP S/4HANA Public Cloud OData API bağlantı iskeletini kurduk  \n2. Satış verisini (gerçek veya sentetik) zaman serisine dönüştürdük  \n3. Lag features ile supervised forecasting problemi oluşturduk  \n4. Ridge + XGBoost baseline eğittik  \n5. **Qiskit Quantum Kernel Ridge** ile tahmin yaptık  \n6. IBM Quantum gerçek backend için hazırlık kodu bıraktık  \n7. 3 aylık ileri forecast ürettik  \n\n**Ana mesaj:**  \n> Enterprise sistemlerden (SAP) veri alıp quantum modellere beslemek mümkündür.  \n> Ancak günümüz NISQ cihazlarında tabular forecast’te klasik yöntemler hâlâ baskındır.  \n> Değer, mimariyi kurabilmekte ve doğru problem seçiminde yatar.\n\n---\n\n**Hazırlayan:** Joseph Volkan Özcan – Öğrenci odaklı eğitim materyali  \n**Teknolojiler:** SAP S/4HANA OData • Qiskit • IBM Quantum Runtime • scikit-learn • XGBoost  \n**Ortam:** Google Colab  \n**Tarih:** 2026  \n**QML Şablon Versiyonu:** Quantum Kernel Ridge (FidelityStatevectorKernel + zz_feature_map)\n",
   "id": "closing"
  }
 ]
}