{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "cc9292ee-97bb-4697-9e4b-ee8b7559b25c",
   "metadata": {
    "id": "cc9292ee-97bb-4697-9e4b-ee8b7559b25c"
   },
   "source": "# Predictive Maintenance with Quantum ML (Qiskit)\n## MES + Sensor/PLC Layer → Failure Prediction Pipeline\n\n**Hedef kitle:** QML / Quantum Computing ogrencileri  \n**Senaryo:** Fabrika hattinda motor / pompa / kompresor icin ariza tahmini  \n\n**Mimari katmanlar:**\n1. **Sensor / PLC** – titresim, sicaklik, akim, basinc (IoT / OPC-UA simulasyonu)\n2. **MES** – is emri, makine durumu, uretim sayaci, alarm gecmisi\n3. **Feature Store** – pencereme, istatistikler, etiketleme\n4. **Quantum ML** – Quantum Kernel + QSVC\n5. **Karar katmani** – bakim onerisi, OEE etkisi\n\n> Egitim amacli toy dataset. Gercek uretimde edge gateway + historian + hybrid pipeline gerekir.\n"
  },
  {
   "cell_type": "markdown",
   "id": "77789374-a4d5-4fa9-9ab6-f3f71bde7c9c",
   "metadata": {
    "id": "77789374-a4d5-4fa9-9ab6-f3f71bde7c9c"
   },
   "source": "## 0. Ortam Kurulumu"
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "fe515d41-c5a2-4c11-998b-7792ff49a4e0",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "fe515d41-c5a2-4c11-998b-7792ff49a4e0",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441619379,
     "user_tz": -180,
     "elapsed": 33512,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "9f7a153b-b8c7-4549-d4af-e753a16d4e75"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.7/9.7 MB\u001b[0m \u001b[31m52.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m263.1/263.1 kB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.4/12.4 MB\u001b[0m \u001b[31m24.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m34.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.5/54.5 kB\u001b[0m \u001b[31m1.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hKurulum tamam: 2026-08-11 09:46\n"
     ]
    }
   ],
   "source": "# Colab kurulumu\n%pip install -q \"qiskit>=1.0\" qiskit-machine-learning qiskit-aer \\\n               matplotlib seaborn pandas numpy scikit-learn\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom datetime import datetime, timedelta\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import MinMaxScaler, StandardScaler\nfrom sklearn.metrics import accuracy_score, classification_report, ConfusionMatrixDisplay\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.svm import SVC\n\nfrom qiskit.circuit.library import ZZFeatureMap\nfrom qiskit_machine_learning.kernels import FidelityQuantumKernel\nfrom qiskit_machine_learning.algorithms import QSVC\n\ntry:\n    from IPython.display import display\nexcept ImportError:\n    display = print\n\nplt.rcParams.update({\n    \"figure.figsize\": (9, 4.5),\n    \"axes.grid\": True,\n    \"grid.alpha\": 0.3,\n    \"font.size\": 11,\n})\nsns.set_palette(\"colorblind\")\nprint(\"Kurulum tamam:\", datetime.now().strftime(\"%Y-%m-%d %H:%M\"))\n"
  },
  {
   "cell_type": "markdown",
   "id": "593042fc-2fb8-48e0-a832-0991b299ed16",
   "metadata": {
    "id": "593042fc-2fb8-48e0-a832-0991b299ed16"
   },
   "source": "## 1. Endustriyel Mimari\n\n```\n[PLC / Sensorler]          [MES / SCADA]\n  titresim (mm/s)            is emri no\n  sicaklik (C)               makine durumu (RUN/IDLE/DOWN)\n  motor akimi (A)            uretim sayaci\n  basinc (bar)               alarm kodlari\n        \\                      /\n         v                    v\n     Edge / Gateway  (OPC-UA, MQTT, historian)\n              |\n              v\n     Feature engineering\n              |\n              v\n     Quantum ML (Qiskit QSVC)\n              |\n              v\n     Bakim karari + OEE etkisi\n```\n"
  },
  {
   "cell_type": "markdown",
   "id": "69db614f-fbfe-462f-a6a0-ed58bd6e7a4a",
   "metadata": {
    "id": "69db614f-fbfe-462f-a6a0-ed58bd6e7a4a"
   },
   "source": "## 2. Sensor / PLC Katmani Simulasyonu\n\nPLC analog/digital sinyalleri:\n- titresim, sicaklik, akim, basinc, rpm\n- motor_run, emergency_stop\n\nEtiket: `failure_soon = 1` → sonraki 24 saat icinde ariza riski yuksek.\n"
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b478ea4a-e8c8-4f16-96d7-83ac17033948",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 450
    },
    "id": "b478ea4a-e8c8-4f16-96d7-83ac17033948",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441619574,
     "user_tz": -180,
     "elapsed": 190,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "02d5454c-3077-47ba-95f0-ed557be479ea"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "PLC / Sensor katmani ornekleri:\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "                   ts machine_id  vibration_mms  temp_c  current_a  \\\n",
       "0 2026-03-01 00:00:00     CMP-03          2.151   56.69      12.71   \n",
       "1 2026-03-01 01:00:00     CMP-03          1.861   53.60      12.81   \n",
       "2 2026-03-01 02:00:00     MTR-01          1.260   59.15      11.62   \n",
       "3 2026-03-01 03:00:00     CMP-03          2.435   50.94      13.42   \n",
       "4 2026-03-01 04:00:00     CMP-03          2.215   47.03      12.85   \n",
       "5 2026-03-01 05:00:00     PMP-02          1.945   51.12      13.78   \n",
       "6 2026-03-01 06:00:00     CMP-03          8.127   87.90      17.31   \n",
       "7 2026-03-01 07:00:00     MTR-01          2.924   58.38      12.26   \n",
       "\n",
       "   pressure_bar     rpm  motor_run  emergency_stop  failure_soon  \n",
       "0          6.55  1422.5          1               0             0  \n",
       "1          5.81  1436.0          1               0             0  \n",
       "2          5.93  1405.7          1               0             0  \n",
       "3          6.12  1430.9          1               0             0  \n",
       "4          5.72  1408.7          1               0             0  \n",
       "5          6.31  1529.7          1               0             0  \n",
       "6          3.81  1328.2          1               0             1  \n",
       "7          6.26  1457.2          1               0             0  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-c4b56b33-9b0f-4b5c-a6a2-4895c34dc6a7\" 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>ts</th>\n",
       "      <th>machine_id</th>\n",
       "      <th>vibration_mms</th>\n",
       "      <th>temp_c</th>\n",
       "      <th>current_a</th>\n",
       "      <th>pressure_bar</th>\n",
       "      <th>rpm</th>\n",
       "      <th>motor_run</th>\n",
       "      <th>emergency_stop</th>\n",
       "      <th>failure_soon</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2026-03-01 00:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>2.151</td>\n",
       "      <td>56.69</td>\n",
       "      <td>12.71</td>\n",
       "      <td>6.55</td>\n",
       "      <td>1422.5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2026-03-01 01:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>1.861</td>\n",
       "      <td>53.60</td>\n",
       "      <td>12.81</td>\n",
       "      <td>5.81</td>\n",
       "      <td>1436.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2026-03-01 02:00:00</td>\n",
       "      <td>MTR-01</td>\n",
       "      <td>1.260</td>\n",
       "      <td>59.15</td>\n",
       "      <td>11.62</td>\n",
       "      <td>5.93</td>\n",
       "      <td>1405.7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2026-03-01 03:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>2.435</td>\n",
       "      <td>50.94</td>\n",
       "      <td>13.42</td>\n",
       "      <td>6.12</td>\n",
       "      <td>1430.9</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2026-03-01 04:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>2.215</td>\n",
       "      <td>47.03</td>\n",
       "      <td>12.85</td>\n",
       "      <td>5.72</td>\n",
       "      <td>1408.7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2026-03-01 05:00:00</td>\n",
       "      <td>PMP-02</td>\n",
       "      <td>1.945</td>\n",
       "      <td>51.12</td>\n",
       "      <td>13.78</td>\n",
       "      <td>6.31</td>\n",
       "      <td>1529.7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2026-03-01 06:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>8.127</td>\n",
       "      <td>87.90</td>\n",
       "      <td>17.31</td>\n",
       "      <td>3.81</td>\n",
       "      <td>1328.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2026-03-01 07:00:00</td>\n",
       "      <td>MTR-01</td>\n",
       "      <td>2.924</td>\n",
       "      <td>58.38</td>\n",
       "      <td>12.26</td>\n",
       "      <td>6.26</td>\n",
       "      <td>1457.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>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-c4b56b33-9b0f-4b5c-a6a2-4895c34dc6a7')\"\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-c4b56b33-9b0f-4b5c-a6a2-4895c34dc6a7 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-c4b56b33-9b0f-4b5c-a6a2-4895c34dc6a7');\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\\\"\\\\nToplam kayit: {len(plc_df)}\\\")\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"ts\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2026-03-01 00:00:00\",\n        \"max\": \"2026-03-01 07:00:00\",\n        \"num_unique_values\": 8,\n        \"samples\": [\n          \"2026-03-01 01:00:00\",\n          \"2026-03-01 05:00:00\",\n          \"2026-03-01 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"machine_id\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"CMP-03\",\n          \"MTR-01\",\n          \"PMP-02\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"vibration_mms\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.1791138926506015,\n        \"min\": 1.26,\n        \"max\": 8.127,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          1.861,\n          1.945,\n          2.151\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"temp_c\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12.727865310300189,\n        \"min\": 47.03,\n        \"max\": 87.9,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          53.6,\n          51.12,\n          56.69\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"current_a\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.7321910155308256,\n        \"min\": 11.62,\n        \"max\": 17.31,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          12.81,\n          13.78,\n          12.71\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pressure_bar\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8551179951996598,\n        \"min\": 3.81,\n        \"max\": 6.55,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          5.81,\n          6.31,\n          6.55\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rpm\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 56.21992370528949,\n        \"min\": 1328.2,\n        \"max\": 1529.7,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          1436.0,\n          1529.7,\n          1422.5\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"motor_run\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 1,\n        \"max\": 1,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"emergency_stop\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"failure_soon\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\n",
      "Sinif dagilimi (failure_soon):\n",
      "failure_soon\n",
      "0    177\n",
      "1     63\n",
      "Name: count, dtype: int64\n",
      "\n",
      "Toplam kayit: 240\n"
     ]
    }
   ],
   "source": "np.random.seed(42)\n\nMACHINES = [\"MTR-01\", \"PMP-02\", \"CMP-03\"]\nN_SAMPLES = 240\n\ndef simulate_plc_sensors(n=N_SAMPLES, failure_ratio=0.28):\n    rows = []\n    for i in range(n):\n        machine = np.random.choice(MACHINES)\n        vibration = np.random.normal(2.5, 0.6)\n        temperature = np.random.normal(55, 5)\n        current = np.random.normal(12, 1.5)\n        pressure = np.random.normal(6.0, 0.4)\n        rpm = np.random.normal(1450, 30)\n        motor_run = 1\n        emergency_stop = 0\n\n        is_fail = 1 if np.random.rand() < failure_ratio else 0\n        if is_fail:\n            vibration += np.random.uniform(3.0, 6.0)\n            temperature += np.random.uniform(15, 30)\n            current += np.random.uniform(4, 8)\n            pressure += np.random.uniform(-1.5, 1.0)\n            rpm -= np.random.uniform(50, 150)\n\n        vibration = max(0.1, vibration + np.random.normal(0, 0.15))\n        temperature = temperature + np.random.normal(0, 1.0)\n\n        rows.append({\n            \"ts\": datetime(2026, 3, 1) + timedelta(hours=i),\n            \"machine_id\": machine,\n            \"vibration_mms\": round(vibration, 3),\n            \"temp_c\": round(temperature, 2),\n            \"current_a\": round(current, 2),\n            \"pressure_bar\": round(pressure, 2),\n            \"rpm\": round(rpm, 1),\n            \"motor_run\": motor_run,\n            \"emergency_stop\": emergency_stop,\n            \"failure_soon\": is_fail,\n        })\n    return pd.DataFrame(rows)\n\nplc_df = simulate_plc_sensors()\nprint(\"PLC / Sensor katmani ornekleri:\")\ndisplay(plc_df.head(8))\nprint(\"\\nSinif dagilimi (failure_soon):\")\nprint(plc_df[\"failure_soon\"].value_counts())\nprint(f\"\\nToplam kayit: {len(plc_df)}\")\n"
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "193f4e7b-d5cb-4682-881e-4b655f0b6a9a",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 706
    },
    "id": "193f4e7b-d5cb-4682-881e-4b655f0b6a9a",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441622476,
     "user_tz": -180,
     "elapsed": 2873,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "157c9d24-3b68-4923-a1b0-3176a1eb9ea7"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1100x700 with 4 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "# Sensor dagilimlari\nfig, axes = plt.subplots(2, 2, figsize=(11, 7))\nfig.suptitle(\"PLC Sensor Dagitimlari (Normal vs Ariza Riski)\", fontweight=\"bold\")\n\nfor ax, (col, title) in zip(axes.ravel(), [\n    (\"vibration_mms\", \"Titresim (mm/s)\"),\n    (\"temp_c\", \"Sicaklik (C)\"),\n    (\"current_a\", \"Motor Akimi (A)\"),\n    (\"pressure_bar\", \"Basinc (bar)\"),\n]):\n    for label, color, name in [(0, \"#4C72B0\", \"Normal\"), (1, \"#DD8452\", \"Risk\")]:\n        subset = plc_df[plc_df[\"failure_soon\"] == label][col]\n        ax.hist(subset, bins=20, alpha=0.65, color=color, label=name)\n    ax.set_title(title)\n    ax.legend()\nplt.tight_layout()\nplt.show()\n"
  },
  {
   "cell_type": "markdown",
   "id": "789caa22-cfeb-4c25-84c4-fa0238baf78e",
   "metadata": {
    "id": "789caa22-cfeb-4c25-84c4-fa0238baf78e"
   },
   "source": "## 3. MES Katmani Simulasyonu\n\nMES baglami: is emri, makine durumu, OEE, son bakim, alarm sayisi.\n"
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f944eaa8-be20-4cae-bd54-9e32650d539a",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 612
    },
    "id": "f944eaa8-be20-4cae-bd54-9e32650d539a",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441622529,
     "user_tz": -180,
     "elapsed": 50,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "c769bc07-1a2b-4879-dd02-731ac363ef0a"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "MES + PLC birlesik tablo:\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "                   ts machine_id  vibration_mms  temp_c  current_a  \\\n",
       "0 2026-03-01 00:00:00     CMP-03          2.151   56.69      12.71   \n",
       "1 2026-03-01 01:00:00     CMP-03          1.861   53.60      12.81   \n",
       "2 2026-03-01 02:00:00     MTR-01          1.260   59.15      11.62   \n",
       "3 2026-03-01 03:00:00     CMP-03          2.435   50.94      13.42   \n",
       "4 2026-03-01 04:00:00     CMP-03          2.215   47.03      12.85   \n",
       "5 2026-03-01 05:00:00     PMP-02          1.945   51.12      13.78   \n",
       "\n",
       "   pressure_bar     rpm  motor_run  emergency_stop  failure_soon  work_order  \\\n",
       "0          6.55  1422.5          1               0             0  WO-03-2932   \n",
       "1          5.81  1436.0          1               0             0  WO-03-7474   \n",
       "2          5.93  1405.7          1               0             0  WO-01-3743   \n",
       "3          6.12  1430.9          1               0             0  WO-03-1619   \n",
       "4          5.72  1408.7          1               0             0  WO-03-9199   \n",
       "5          6.31  1529.7          1               0             0  WO-02-6973   \n",
       "\n",
       "  mes_status    oee  availability  days_since_maint  alarm_count_24h  \n",
       "0        RUN  0.810         0.879                33                0  \n",
       "1        RUN  0.794         0.946                16                0  \n",
       "2        RUN  0.832         0.976                89                1  \n",
       "3        RUN  0.931         0.959                80                2  \n",
       "4        RUN  0.662         0.821                81                0  \n",
       "5       IDLE  0.545         0.581                28                0  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-a4f37f91-f19d-4e0c-ac22-063714f06faa\" 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>ts</th>\n",
       "      <th>machine_id</th>\n",
       "      <th>vibration_mms</th>\n",
       "      <th>temp_c</th>\n",
       "      <th>current_a</th>\n",
       "      <th>pressure_bar</th>\n",
       "      <th>rpm</th>\n",
       "      <th>motor_run</th>\n",
       "      <th>emergency_stop</th>\n",
       "      <th>failure_soon</th>\n",
       "      <th>work_order</th>\n",
       "      <th>mes_status</th>\n",
       "      <th>oee</th>\n",
       "      <th>availability</th>\n",
       "      <th>days_since_maint</th>\n",
       "      <th>alarm_count_24h</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2026-03-01 00:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>2.151</td>\n",
       "      <td>56.69</td>\n",
       "      <td>12.71</td>\n",
       "      <td>6.55</td>\n",
       "      <td>1422.5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>WO-03-2932</td>\n",
       "      <td>RUN</td>\n",
       "      <td>0.810</td>\n",
       "      <td>0.879</td>\n",
       "      <td>33</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2026-03-01 01:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>1.861</td>\n",
       "      <td>53.60</td>\n",
       "      <td>12.81</td>\n",
       "      <td>5.81</td>\n",
       "      <td>1436.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>WO-03-7474</td>\n",
       "      <td>RUN</td>\n",
       "      <td>0.794</td>\n",
       "      <td>0.946</td>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2026-03-01 02:00:00</td>\n",
       "      <td>MTR-01</td>\n",
       "      <td>1.260</td>\n",
       "      <td>59.15</td>\n",
       "      <td>11.62</td>\n",
       "      <td>5.93</td>\n",
       "      <td>1405.7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>WO-01-3743</td>\n",
       "      <td>RUN</td>\n",
       "      <td>0.832</td>\n",
       "      <td>0.976</td>\n",
       "      <td>89</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2026-03-01 03:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>2.435</td>\n",
       "      <td>50.94</td>\n",
       "      <td>13.42</td>\n",
       "      <td>6.12</td>\n",
       "      <td>1430.9</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>WO-03-1619</td>\n",
       "      <td>RUN</td>\n",
       "      <td>0.931</td>\n",
       "      <td>0.959</td>\n",
       "      <td>80</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2026-03-01 04:00:00</td>\n",
       "      <td>CMP-03</td>\n",
       "      <td>2.215</td>\n",
       "      <td>47.03</td>\n",
       "      <td>12.85</td>\n",
       "      <td>5.72</td>\n",
       "      <td>1408.7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>WO-03-9199</td>\n",
       "      <td>RUN</td>\n",
       "      <td>0.662</td>\n",
       "      <td>0.821</td>\n",
       "      <td>81</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2026-03-01 05:00:00</td>\n",
       "      <td>PMP-02</td>\n",
       "      <td>1.945</td>\n",
       "      <td>51.12</td>\n",
       "      <td>13.78</td>\n",
       "      <td>6.31</td>\n",
       "      <td>1529.7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>WO-02-6973</td>\n",
       "      <td>IDLE</td>\n",
       "      <td>0.545</td>\n",
       "      <td>0.581</td>\n",
       "      <td>28</td>\n",
       "      <td>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-a4f37f91-f19d-4e0c-ac22-063714f06faa')\"\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-a4f37f91-f19d-4e0c-ac22-063714f06faa 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-a4f37f91-f19d-4e0c-ac22-063714f06faa');\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(factory_df[\\\"mes_status\\\"]\",\n  \"rows\": 6,\n  \"fields\": [\n    {\n      \"column\": \"ts\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2026-03-01 00:00:00\",\n        \"max\": \"2026-03-01 05:00:00\",\n        \"num_unique_values\": 6,\n        \"samples\": [\n          \"2026-03-01 00:00:00\",\n          \"2026-03-01 01:00:00\",\n          \"2026-03-01 05:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"machine_id\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"CMP-03\",\n          \"MTR-01\",\n          \"PMP-02\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"vibration_mms\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.4062631741453644,\n        \"min\": 1.26,\n        \"max\": 2.435,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          2.151,\n          1.861,\n          1.945\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"temp_c\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4.362812930514745,\n        \"min\": 47.03,\n        \"max\": 59.15,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          56.69,\n          53.6,\n          51.12\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"current_a\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.7379092085073882,\n        \"min\": 11.62,\n        \"max\": 13.78,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          12.71,\n          12.81,\n          13.78\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pressure_bar\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3162699269084348,\n        \"min\": 5.72,\n        \"max\": 6.55,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          6.55,\n          5.81,\n          6.31\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rpm\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 46.044083948610236,\n        \"min\": 1405.7,\n        \"max\": 1529.7,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          1422.5,\n          1436.0,\n          1529.7\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"motor_run\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 1,\n        \"max\": 1,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"emergency_stop\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"failure_soon\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"work_order\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 6,\n        \"samples\": [\n          \"WO-03-2932\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mes_status\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"IDLE\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"oee\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.13702359894071775,\n        \"min\": 0.545,\n        \"max\": 0.931,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          0.81\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"availability\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1485768039320629,\n        \"min\": 0.581,\n        \"max\": 0.976,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          0.879\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"days_since_maint\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 32,\n        \"min\": 16,\n        \"max\": 89,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          33\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"alarm_count_24h\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 2,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "\n",
      "MES status dagilimi:\n",
      "mes_status\n",
      "RUN      194\n",
      "IDLE      29\n",
      "MAINT      9\n",
      "DOWN       8\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": "def simulate_mes_context(plc_df):\n    mes_rows = []\n    for _, row in plc_df.iterrows():\n        machine = row[\"machine_id\"]\n        wo = f\"WO-{machine[-2:]}-{np.random.randint(1000, 9999)}\"\n        if row[\"failure_soon\"] == 1 and np.random.rand() < 0.35:\n            status = np.random.choice([\"DOWN\", \"MAINT\"], p=[0.6, 0.4])\n        else:\n            status = np.random.choice([\"RUN\", \"IDLE\"], p=[0.85, 0.15])\n        availability = np.random.uniform(0.75, 0.98) if status == \"RUN\" else np.random.uniform(0.4, 0.7)\n        performance = np.random.uniform(0.80, 0.99)\n        quality = np.random.uniform(0.92, 0.995)\n        oee = availability * performance * quality\n        days_since_maint = np.random.randint(1, 90)\n        alarm_count_24h = int(np.random.poisson(3 if row[\"failure_soon\"] else 0.4))\n        mes_rows.append({\n            \"work_order\": wo,\n            \"mes_status\": status,\n            \"oee\": round(oee, 3),\n            \"availability\": round(availability, 3),\n            \"days_since_maint\": days_since_maint,\n            \"alarm_count_24h\": alarm_count_24h,\n        })\n    mes_df = pd.DataFrame(mes_rows)\n    return pd.concat([plc_df.reset_index(drop=True), mes_df], axis=1)\n\nfactory_df = simulate_mes_context(plc_df)\nprint(\"MES + PLC birlesik tablo:\")\ndisplay(factory_df.head(6))\nprint(\"\\nMES status dagilimi:\")\nprint(factory_df[\"mes_status\"].value_counts())\n"
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4dd0323e-e4c9-4cb8-abe0-8d90c7d18da1",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 404
    },
    "id": "4dd0323e-e4c9-4cb8-abe0-8d90c7d18da1",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441623017,
     "user_tz": -180,
     "elapsed": 485,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "323efe24-e685-4085-b9b4-7e22eb355f8d"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1100x400 with 2 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "fig, axes = plt.subplots(1, 2, figsize=(11, 4))\nsns.boxplot(data=factory_df, x=\"failure_soon\", y=\"oee\", ax=axes[0])\naxes[0].set_xticklabels([\"Normal\", \"Ariza riski\"])\naxes[0].set_title(\"OEE vs Ariza Riski\")\nsns.boxplot(data=factory_df, x=\"failure_soon\", y=\"alarm_count_24h\", ax=axes[1])\naxes[1].set_xticklabels([\"Normal\", \"Ariza riski\"])\naxes[1].set_title(\"24s Alarm Sayisi vs Ariza Riski\")\nplt.tight_layout()\nplt.show()\n"
  },
  {
   "cell_type": "markdown",
   "id": "926c99e5-69dc-4284-9bab-2584f4fb382a",
   "metadata": {
    "id": "926c99e5-69dc-4284-9bab-2584f4fb382a"
   },
   "source": "## 4. Feature Engineering\n\nModel girdisi (6 feature – quantum encoding icin uygun):\n1. vibration_mms\n2. temp_c\n3. current_a\n4. pressure_bar\n5. days_since_maint\n6. alarm_count_24h\n"
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2600484e-597e-4ec8-b95d-0a5d70f6b355",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "2600484e-597e-4ec8-b95d-0a5d70f6b355",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441623033,
     "user_tz": -180,
     "elapsed": 13,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "5114ef3d-4e54-4353-a64c-7cfb724f412e"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Train: 168 | Test: 72\n",
      "Feature boyutu: 6\n",
      "Pozitif sinif orani (train): 26.19%\n"
     ]
    }
   ],
   "source": "FEATURE_COLS = [\n    \"vibration_mms\", \"temp_c\", \"current_a\",\n    \"pressure_bar\", \"days_since_maint\", \"alarm_count_24h\",\n]\nTARGET = \"failure_soon\"\n\nX = factory_df[FEATURE_COLS].values.astype(float)\ny = factory_df[TARGET].values.astype(int)\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, test_size=0.30, random_state=42, stratify=y\n)\n\nscaler = MinMaxScaler(feature_range=(0, np.pi))\nX_train_q = scaler.fit_transform(X_train)\nX_test_q = scaler.transform(X_test)\n\nscaler_c = StandardScaler()\nX_train_c = scaler_c.fit_transform(X_train)\nX_test_c = scaler_c.transform(X_test)\n\nprint(f\"Train: {X_train.shape[0]} | Test: {X_test.shape[0]}\")\nprint(f\"Feature boyutu: {X_train.shape[1]}\")\nprint(f\"Pozitif sinif orani (train): {y_train.mean():.2%}\")\n"
  },
  {
   "cell_type": "markdown",
   "id": "ee1c72ee-743d-401f-b0b8-c15e88d46404",
   "metadata": {
    "id": "ee1c72ee-743d-401f-b0b8-c15e88d46404"
   },
   "source": "## 5. Klasik Baseline"
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a647c1e3-7a70-41a7-abf7-db6bb9637d03",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 592
    },
    "id": "a647c1e3-7a70-41a7-abf7-db6bb9637d03",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441623623,
     "user_tz": -180,
     "elapsed": 554,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "4139ac52-2203-4540-d2f8-5091291f7def"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "=== Klasik Baseline ===\n",
      "Random Forest accuracy: 1.000\n",
      "RBF-SVM accuracy      : 1.000\n",
      "\n",
      "Random Forest report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0      1.000     1.000     1.000        53\n",
      "           1      1.000     1.000     1.000        19\n",
      "\n",
      "    accuracy                          1.000        72\n",
      "   macro avg      1.000     1.000     1.000        72\n",
      "weighted avg      1.000     1.000     1.000        72\n",
      "\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 800x350 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "rf = RandomForestClassifier(n_estimators=100, random_state=42, class_weight=\"balanced\")\nrf.fit(X_train_c, y_train)\ny_rf = rf.predict(X_test_c)\nacc_rf = accuracy_score(y_test, y_rf)\n\nsvc_c = SVC(kernel=\"rbf\", class_weight=\"balanced\", probability=True, random_state=42)\nsvc_c.fit(X_train_c, y_train)\ny_svc = svc_c.predict(X_test_c)\nacc_svc = accuracy_score(y_test, y_svc)\n\nprint(\"=== Klasik Baseline ===\")\nprint(f\"Random Forest accuracy: {acc_rf:.3f}\")\nprint(f\"RBF-SVM accuracy      : {acc_svc:.3f}\")\nprint(\"\\nRandom Forest report:\")\nprint(classification_report(y_test, y_rf, digits=3))\n\nimp = pd.Series(rf.feature_importances_, index=FEATURE_COLS).sort_values(ascending=True)\nfig, ax = plt.subplots(figsize=(8, 3.5))\nimp.plot(kind=\"barh\", ax=ax, color=\"#4C72B0\")\nax.set_title(\"Random Forest Feature Importance (MES + PLC)\")\nplt.tight_layout()\nplt.show()\n"
  },
  {
   "cell_type": "markdown",
   "id": "24f3280e-e2b3-48a6-9a10-e1de7839ae49",
   "metadata": {
    "id": "24f3280e-e2b3-48a6-9a10-e1de7839ae49"
   },
   "source": "## 6. Quantum Kernel + QSVC (Qiskit)\n\nZZFeatureMap ile encoding, FidelityQuantumKernel, QSVC.\n\nColab hizi icin reps=1, linear entanglement, sinirli ornek sayisi.\n"
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "0a702f7c-f140-4df0-b614-2591272cac5f",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0a702f7c-f140-4df0-b614-2591272cac5f",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441672959,
     "user_tz": -180,
     "elapsed": 49337,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "b1ca874f-a148-4db9-9589-09d6444e2ef5"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Quantum train: 50 | test: 25\n",
      "Feature map devresi...\n",
      "MPL drawer atlandi: MissingOptionalLibraryError\n",
      "     ┌───┐┌───────────┐                                   »\n",
      "q_0: ┤ H ├┤ P(2*x[0]) ├──■────────────────────────────────»\n",
      "     ├───┤├───────────┤┌─┴─┐┌────────────────────────────┐»\n",
      "q_1: ┤ H ├┤ P(2*x[1]) ├┤ X ├┤ P(2*(π - x[0])*(π - x[1])) ├»\n",
      "     ├───┤├───────────┤└───┘└────────────────────────────┘»\n",
      "q_2: ┤ H ├┤ P(2*x[2]) ├───────────────────────────────────»\n",
      "     ├───┤├───────────┤                                   »\n",
      "q_3: ┤ H ├┤ P(2*x[3]) ├───────────────────────────────────»\n",
      "     ├───┤├───────────┤                                   »\n",
      "q_4: ┤ H ├┤ P(2*x[4]) ├───────────────────────────────────»\n",
      "     ├───┤├───────────┤                                   »\n",
      "q_5: ┤ H ├┤ P(2*x[5]) ├───────────────────────────────────»\n",
      "     └───┘└───────────┘                                   »\n",
      "«                                                       »\n",
      "«q_0: ──■───────────────────────────────────────────────»\n",
      "«     ┌─┴─┐                                             »\n",
      "«q_1: ┤ X ├──■──────────────────────────────────■───────»\n",
      "«     └───┘┌─┴─┐┌────────────────────────────┐┌─┴─┐     »\n",
      "«q_2: ─────┤ X ├┤ P(2*(π - x[1])*(π - x[2])) ├┤ X ├──■──»\n",
      "«          └───┘└────────────────────────────┘└───┘┌─┴─┐»\n",
      "«q_3: ─────────────────────────────────────────────┤ X ├»\n",
      "«                                                  └───┘»\n",
      "«q_4: ──────────────────────────────────────────────────»\n",
      "«                                                       »\n",
      "«q_5: ──────────────────────────────────────────────────»\n",
      "«                                                       »\n",
      "«                                             »\n",
      "«q_0: ────────────────────────────────────────»\n",
      "«                                             »\n",
      "«q_1: ────────────────────────────────────────»\n",
      "«                                             »\n",
      "«q_2: ────────────────────────────────■───────»\n",
      "«     ┌────────────────────────────┐┌─┴─┐     »\n",
      "«q_3: ┤ P(2*(π - x[2])*(π - x[3])) ├┤ X ├──■──»\n",
      "«     └────────────────────────────┘└───┘┌─┴─┐»\n",
      "«q_4: ───────────────────────────────────┤ X ├»\n",
      "«                                        └───┘»\n",
      "«q_5: ────────────────────────────────────────»\n",
      "«                                             »\n",
      "«                                             »\n",
      "«q_0: ────────────────────────────────────────»\n",
      "«                                             »\n",
      "«q_1: ────────────────────────────────────────»\n",
      "«                                             »\n",
      "«q_2: ────────────────────────────────────────»\n",
      "«                                             »\n",
      "«q_3: ────────────────────────────────■───────»\n",
      "«     ┌────────────────────────────┐┌─┴─┐     »\n",
      "«q_4: ┤ P(2*(π - x[3])*(π - x[4])) ├┤ X ├──■──»\n",
      "«     └────────────────────────────┘└───┘┌─┴─┐»\n",
      "«q_5: ───────────────────────────────────┤ X ├»\n",
      "«                                        └───┘»\n",
      "«                                        \n",
      "«q_0: ───────────────────────────────────\n",
      "«                                        \n",
      "«q_1: ───────────────────────────────────\n",
      "«                                        \n",
      "«q_2: ───────────────────────────────────\n",
      "«                                        \n",
      "«q_3: ───────────────────────────────────\n",
      "«                                        \n",
      "«q_4: ────────────────────────────────■──\n",
      "«     ┌────────────────────────────┐┌─┴─┐\n",
      "«q_5: ┤ P(2*(π - x[4])*(π - x[5])) ├┤ X ├\n",
      "«     └────────────────────────────┘└───┘\n",
      "QSVC egitiliyor (genelde 1-2 dk)...\n",
      "==================================================\n",
      "QSVC accuracy: 0.760\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0      0.760     1.000     0.864        19\n",
      "           1      0.000     0.000     0.000         6\n",
      "\n",
      "    accuracy                          0.760        25\n",
      "   macro avg      0.380     0.500     0.432        25\n",
      "weighted avg      0.578     0.760     0.656        25\n",
      "\n"
     ]
    }
   ],
   "source": "MAX_TRAIN = 50\nMAX_TEST = 25\nXtr = X_train_q[:MAX_TRAIN]\nytr = y_train[:MAX_TRAIN]\nXte = X_test_q[:MAX_TEST]\nyte = y_test[:MAX_TEST]\n\nprint(f\"Quantum train: {len(Xtr)} | test: {len(Xte)}\", flush=True)\n\nfeature_map = ZZFeatureMap(\n    feature_dimension=len(FEATURE_COLS),\n    reps=1,\n    entanglement=\"linear\",\n)\n\nprint(\"Feature map devresi...\", flush=True)\ntry:\n    feature_map.decompose().draw(output=\"mpl\", style=\"iqp\", fold=50)\n    plt.suptitle(\"ZZFeatureMap – Predictive Maintenance Encoding\", fontweight=\"bold\", y=1.02)\n    plt.tight_layout()\n    plt.show()\nexcept Exception as e:\n    print(\"MPL drawer atlandi:\", type(e).__name__)\n    print(feature_map.decompose().draw(output=\"text\", fold=60))\n\nquantum_kernel = FidelityQuantumKernel(feature_map=feature_map)\n\nprint(\"QSVC egitiliyor (genelde 1-2 dk)...\", flush=True)\nqsvc = QSVC(quantum_kernel=quantum_kernel)\nqsvc.fit(Xtr, ytr)\ny_q = qsvc.predict(Xte)\nacc_q = accuracy_score(yte, y_q)\n\nprint(\"=\" * 50)\nprint(f\"QSVC accuracy: {acc_q:.3f}\")\nprint(classification_report(yte, y_q, digits=3))\n"
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "17710700-0d96-4781-8f0e-022c5f2e11b1",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 440
    },
    "id": "17710700-0d96-4781-8f0e-022c5f2e11b1",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441674799,
     "user_tz": -180,
     "elapsed": 1836,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "a4e6785f-b6da-4ea3-9630-7cb91ad9dde4"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Kernel matrisi hesaplaniyor...\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1100x420 with 3 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "print(\"Kernel matrisi hesaplaniyor...\", flush=True)\nK = quantum_kernel.evaluate(x_vec=Xtr[:16])\n\nfig, axes = plt.subplots(1, 2, figsize=(11, 4.2))\nsns.heatmap(K, ax=axes[0], cmap=\"viridis\", cbar_kws={\"label\": \"Fidelity\"})\naxes[0].set_title(\"Quantum Kernel Matrix (16x16)\")\naxes[0].set_xlabel(\"Sample\")\naxes[0].set_ylabel(\"Sample\")\n\nConfusionMatrixDisplay.from_predictions(yte, y_q, ax=axes[1], cmap=\"Blues\", colorbar=False)\naxes[1].set_title(f\"QSVC Confusion Matrix (acc={acc_q:.2f})\")\nplt.tight_layout()\nplt.show()\n"
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "be678496-596c-4cca-afe4-e93513ce9798",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 404
    },
    "id": "be678496-596c-4cca-afe4-e93513ce9798",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441674986,
     "user_tz": -180,
     "elapsed": 182,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "a31aa8e7-95c1-4b6a-f1c1-3eab58e75e23"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 700x400 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": "Xte_c = X_test_c[:MAX_TEST]\nyte_c = y_test[:MAX_TEST]\nacc_rf_s = accuracy_score(yte_c, rf.predict(Xte_c))\nacc_svc_s = accuracy_score(yte_c, svc_c.predict(Xte_c))\n\nlabels = [\"Random Forest\", \"RBF-SVM\", \"Quantum QSVC\"]\nscores = [acc_rf_s, acc_svc_s, acc_q]\ncolors = [\"#4C72B0\", \"#DD8452\", \"#55A868\"]\n\nfig, ax = plt.subplots(figsize=(7, 4))\nbars = ax.bar(labels, scores, color=colors, edgecolor=\"k\", width=0.55)\nax.set_ylim(0, 1.05)\nax.set_ylabel(\"Test accuracy\")\nax.set_title(\"Predictive Maintenance – Klasik vs Quantum\", fontweight=\"bold\")\nfor b, s in zip(bars, scores):\n    ax.text(b.get_x() + b.get_width() / 2, s + 0.02, f\"{s:.3f}\", ha=\"center\", fontweight=\"bold\")\nplt.tight_layout()\nplt.show()\n"
  },
  {
   "cell_type": "markdown",
   "id": "67cd5c84-ac8b-47b6-b5ad-6b6aacdaa9a3",
   "metadata": {
    "id": "67cd5c84-ac8b-47b6-b5ad-6b6aacdaa9a3"
   },
   "source": "## 7. Karar Katmani – Bakim Onerisi\n\n| Risk | Aksiyon |\n|------|---------|\n| Dusuk | Normal operasyon |\n| Orta | Planli bakim penceresi |\n| Yuksek | Acil inceleme |\n"
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "502d5209-2857-49c8-b657-9a80a516e000",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "502d5209-2857-49c8-b657-9a80a516e000",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1786441678763,
     "user_tz": -180,
     "elapsed": 3774,
     "user": {
      "displayName": "Joseph Volkan ÖZCAN",
      "userId": "11389530967736397480"
     }
    },
    "outputId": "78b0df66-52fd-439d-bf69-393d331b95a0"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Canli karar ornekleri (son kayitlar):\n",
      "\n",
      "CMP-03 | vib=2.6 temp=57 | true=0 pred=0 | LOW: DUSUK RISK -> Normal operasyon\n",
      "CMP-03 | vib=2.4 temp=54 | true=0 pred=0 | LOW: DUSUK RISK -> Normal operasyon\n",
      "PMP-02 | vib=3.7 temp=50 | true=0 pred=0 | LOW: DUSUK RISK -> Normal operasyon\n",
      "CMP-03 | vib=2.6 temp=56 | true=0 pred=0 | LOW: DUSUK RISK -> Normal operasyon\n",
      "PMP-02 | vib=7.4 temp=73 | true=1 pred=1 | HIGH: YUKSEK RISK -> Acil inceleme / planli durus\n"
     ]
    }
   ],
   "source": "def maintenance_decision(sample_features):\n    x_q = scaler.transform(sample_features.reshape(1, -1))\n    x_c = scaler_c.transform(sample_features.reshape(1, -1))\n    pred = int(qsvc.predict(x_q)[0])\n    try:\n        proba = float(rf.predict_proba(x_c)[0, 1])\n    except Exception:\n        proba = float(pred)\n\n    if proba >= 0.65 or pred == 1:\n        action = \"YUKSEK RISK -> Acil inceleme / planli durus\"\n        level = \"HIGH\"\n    elif proba >= 0.40:\n        action = \"ORTA RISK -> 48s icinde bakim penceresi\"\n        level = \"MEDIUM\"\n    else:\n        action = \"DUSUK RISK -> Normal operasyon\"\n        level = \"LOW\"\n    return {\"pred\": pred, \"proba_rf\": proba, \"level\": level, \"action\": action}\n\nprint(\"Canli karar ornekleri (son kayitlar):\\n\")\nfor idx in factory_df.tail(5).index:\n    row = factory_df.loc[idx]\n    feats = row[FEATURE_COLS].values.astype(float)\n    dec = maintenance_decision(feats)\n    print(\n        f\"{row['machine_id']} | vib={row['vibration_mms']:.1f} temp={row['temp_c']:.0f} \"\n        f\"| true={row['failure_soon']} pred={dec['pred']} | {dec['level']}: {dec['action']}\"\n    )\n"
  },
  {
   "cell_type": "markdown",
   "id": "a5c7a54e-35d1-435a-8eb2-1d6141903fa2",
   "metadata": {
    "id": "a5c7a54e-35d1-435a-8eb2-1d6141903fa2"
   },
   "source": "## 8. Uretim Entegrasyon Semasi\n\n```\nPLC (S7 / ControlLogix) --OPC-UA/MQTT--> Edge Gateway\n                                              |\nMES (SAP ME / Opcenter) ----------------------+\n                                              v\n                                    Feature service\n                                              |\n                         +--------------------+--------------------+\n                         v                                         v\n                Classical models (RF)                     Quantum kernel (Qiskit)\n                         |                                         |\n                         +--------------------+--------------------+\n                                              v\n                                    Risk score + work order\n                                              v\n                                    CMMS / bakim planlama\n```\n"
  },
  {
   "cell_type": "markdown",
   "id": "2fa4af0d-1ea7-435a-b3f8-32ef06cda7f4",
   "metadata": {
    "id": "2fa4af0d-1ea7-435a-b3f8-32ef06cda7f4"
   },
   "source": "## 9. Ogrenci Alistirmalari\n\n1. `failure_ratio` degerini degistirip sinif dengesinin QSVC performansina etkisini olcun.\n2. Feature setine `rpm` ve `oee` ekleyip accuracy degisimini kaydedin.\n3. `ZZFeatureMap` yerine `PauliFeatureMap` deneyin.\n4. `reps=2` yapip devre derinligi vs dogruluk trade-off unu tartisin.\n5. Sadece bir makine (`MTR-01`) icin model egitin.\n6. (Ileri) IBM Quantum Runtime ile ayni QSVC yi gercek backend de calistirin.\n7. False Negative maliyeti yuksekse threshold u dusurun; precision-recall tartisin.\n"
  },
  {
   "cell_type": "markdown",
   "id": "7cafe244-d179-4a94-809d-b016c0fa506e",
   "metadata": {
    "id": "7cafe244-d179-4a94-809d-b016c0fa506e"
   },
   "source": "## 10. Ozet\n\nBu notebook ta ogrenciler:\n- **PLC/sensor** telemetrisini simule etti\n- **MES** uretim baglamini ekledi\n- Klasik baseline (RF, SVM) kurdu\n- **Qiskit Quantum Kernel + QSVC** ile ariza tahmini yapti\n- Operasyonel bakim kararina map ledi\n\n### Kaynaklar\n- Qiskit Machine Learning – Quantum Kernel / QSVC\n- ISO 13374 (Condition monitoring)\n- ISA-95 / MES katman modeli\n\n---\n**QML dersi – Predictive Maintenance (MES + PLC + Qiskit)**\n"
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "name": "python3"
  },
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}