",
"text/html": "Sonraki: Aşama 2 kurulum. GPU seçtiyseniz aer-gpu paketini de kurun. Aşama 8 sampler AER_DEVICE bilgisini okur.
"
},
"metadata": {}
}
]
}
},
"33f06136569d45f081bae78a5c8064bd": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"b98dcf8febc54e099a1849337458265d": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"474028457ad64384b820faedcf5f5adc": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"3e11ee03afa3415a8f39ecf7bbe94777": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"9a427e09c5884c2697cc5cd069826f1e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"bc0d3a276bbb4ba1900f6453dcd2860c": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "520px"
}
},
"0106e0a52c16493b97df96395ad14954": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "80px"
}
},
"ff2514f0abfb416ba469c5f63f7b081d": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"5f442951b131498c91ae98681cb93803": {
"model_module": "@jupyter-widgets/controls",
"model_name": "SliderStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "SliderStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "100px",
"handle_color": null
}
},
"15826a7196e74899b7f2f4f2d2d18459": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"ec5916c873a1429195b89dad28fc0c49": {
"model_module": "@jupyter-widgets/controls",
"model_name": "SliderStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "SliderStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "100px",
"handle_color": null
}
},
"2d077bf93aa048dd8a33edc81e828e04": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"9c05e4407cf2485a80395bce33eb3f89": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"98bc16737704402ba9605df9907c4653": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": "40px",
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "320px"
}
},
"d0fca9b506734a5ea0802a640b55ccb0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ButtonStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ButtonStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"button_color": null,
"font_weight": ""
}
},
"3b80284183af46e3ac7541662e149913": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"88dca262feae4c99851575d9553b8999": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FileUploadModel",
"model_module_version": "1.5.0",
"state": {
"_counter": 0,
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FileUploadModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "FileUploadView",
"accept": ".csv",
"button_style": "",
"data": [],
"description": "CSV Yükle",
"description_tooltip": null,
"disabled": false,
"error": "",
"icon": "upload",
"layout": "IPY_MODEL_d4eba1fac4ba4e9c86dbe8982f351c9a",
"metadata": [],
"multiple": false,
"style": "IPY_MODEL_8b20979c08554df3a476d07355ef58e7"
}
},
"d4eba1fac4ba4e9c86dbe8982f351c9a": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"8b20979c08554df3a476d07355ef58e7": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ButtonStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ButtonStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"button_color": null,
"font_weight": ""
}
},
"d712c49777c744be86514a2f31107cbd": {
"model_module": "@jupyter-widgets/controls",
"model_name": "VBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "VBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "VBoxView",
"box_style": "",
"children": [
"IPY_MODEL_afe97e70031e48ffb96bde9d5999d43c",
"IPY_MODEL_117514629e734129a82dd14c32280e2a",
"IPY_MODEL_5b515d99a34d4fe5b770e2805d9a67ac",
"IPY_MODEL_0f9f765b703d43d9975fe3a6c6fbcfa2",
"IPY_MODEL_a15d5be8c76c47f7849a6373b599a55f",
"IPY_MODEL_47ed77dc301d47d2b51bad60f882cdcc",
"IPY_MODEL_be8698e83c1145678f12ec1b3ddc1abb",
"IPY_MODEL_1dfce3668cfb4ffa9e928993fce35ca1",
"IPY_MODEL_9cfbaa0eac394ea5acb6c1886fcca06d",
"IPY_MODEL_4a8525d27bd04de2b7afc80f89126220"
],
"layout": "IPY_MODEL_b6cbb54349e04ddc995a5af6944a4f31"
}
},
"afe97e70031e48ffb96bde9d5999d43c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_acdc08a9ee6a44aeb16d768008f4219a",
"placeholder": "",
"style": "IPY_MODEL_73c8b1fc19ab4ef7944221a624ce5312",
"value": "🎯 İlaç Etkinliği — Problem & Encoding Seçim Aracı
"
}
},
"117514629e734129a82dd14c32280e2a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_67a881470330491195b41bf9c8953444",
"placeholder": "",
"style": "IPY_MODEL_01a8a4dda1594f6dbd1f55f80e299f2a",
"value": "n_features = özellik/kübit adayı; n_samples = hasta sayısı. Ham MR boyutu burada seçilmez.
"
}
},
"5b515d99a34d4fe5b770e2805d9a67ac": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DropdownModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DropdownModel",
"_options_labels": [
"Sınıflandırma — İlaç etkili / etkisiz",
"Regresyon — Etkinlik skoru (0-1 veya %)",
"Optimizasyon — Doz / kombinasyon arama"
],
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "DropdownView",
"description": "Problem:",
"description_tooltip": null,
"disabled": false,
"index": 0,
"layout": "IPY_MODEL_13af59f7da8446de9a727e458ef78977",
"style": "IPY_MODEL_545e2ca53d0b437dab280b65447a4067"
}
},
"0f9f765b703d43d9975fe3a6c6fbcfa2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntSliderModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "IntSliderModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "IntSliderView",
"continuous_update": false,
"description": "Özellik (n_features):",
"description_tooltip": null,
"disabled": false,
"layout": "IPY_MODEL_e74944b35ad54dcc8cd7e37c03aefa09",
"max": 50,
"min": 2,
"orientation": "horizontal",
"readout": true,
"readout_format": "d",
"step": 1,
"style": "IPY_MODEL_d703a301835d4081ba977c0072b51e2d",
"value": 12
}
},
"a15d5be8c76c47f7849a6373b599a55f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntSliderModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "IntSliderModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "IntSliderView",
"continuous_update": false,
"description": "Hasta sayısı (n):",
"description_tooltip": null,
"disabled": false,
"layout": "IPY_MODEL_0c56bf122d6d4b398647fd07f68bfc82",
"max": 5000,
"min": 50,
"orientation": "horizontal",
"readout": true,
"readout_format": "d",
"step": 50,
"style": "IPY_MODEL_76fcf218d1844fab9396ba1fc7c6d6da",
"value": 300
}
},
"47ed77dc301d47d2b51bad60f882cdcc": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DropdownModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DropdownModel",
"_options_labels": [
"Sürekli (tahlil + radiomics özellikler)",
"Kategorik (cinsiyet, komorbidite, ilaç grubu)",
"Karışık (demografik + tahlil + görüntü özellikleri)"
],
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "DropdownView",
"description": "Veri Tipi:",
"description_tooltip": null,
"disabled": false,
"index": 2,
"layout": "IPY_MODEL_ba6c3940442a432e9ee0ec08d1778b96",
"style": "IPY_MODEL_219d59553e954ba7ad0ffabf66fb4d4f"
}
},
"be8698e83c1145678f12ec1b3ddc1abb": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DropdownModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DropdownModel",
"_options_labels": [
"Hızlı prototip / Eğitim (Simülatör)",
"Gerçek IBM Quantum denemesi",
"Yüksek doğruluk (simülatör + error mitigation)"
],
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "DropdownView",
"description": "Öncelik:",
"description_tooltip": null,
"disabled": false,
"index": 0,
"layout": "IPY_MODEL_74aad48683164d66b66c8be597aaed5c",
"style": "IPY_MODEL_8b1bd41bcf84444eacec4fe9ba7de1fc"
}
},
"1dfce3668cfb4ffa9e928993fce35ca1": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_f1b681a70dcb43c4a8c2032cbb7705ea",
"placeholder": "",
"style": "IPY_MODEL_6276766130e74519b1480d0280e1e6c5",
"value": "
"
}
},
"9cfbaa0eac394ea5acb6c1886fcca06d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ButtonModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ButtonModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ButtonView",
"button_style": "success",
"description": "Encoding + Qubit + Algoritma & Cihaz Öner",
"disabled": false,
"icon": "check",
"layout": "IPY_MODEL_f56ceb6b183c4645a2c66029e1123e04",
"style": "IPY_MODEL_1debb7ac70b24419b354b9b549879a29",
"tooltip": ""
}
},
"4a8525d27bd04de2b7afc80f89126220": {
"model_module": "@jupyter-widgets/output",
"model_name": "OutputModel",
"model_module_version": "1.0.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/output",
"_model_module_version": "1.0.0",
"_model_name": "OutputModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/output",
"_view_module_version": "1.0.0",
"_view_name": "OutputView",
"layout": "IPY_MODEL_1c6399173cc448068ccade5aa8c1d190",
"msg_id": "",
"outputs": []
}
},
"b6cbb54349e04ddc995a5af6944a4f31": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"acdc08a9ee6a44aeb16d768008f4219a": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"73c8b1fc19ab4ef7944221a624ce5312": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"67a881470330491195b41bf9c8953444": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"01a8a4dda1594f6dbd1f55f80e299f2a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"13af59f7da8446de9a727e458ef78977": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "520px"
}
},
"545e2ca53d0b437dab280b65447a4067": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "140px"
}
},
"e74944b35ad54dcc8cd7e37c03aefa09": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"d703a301835d4081ba977c0072b51e2d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "SliderStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "SliderStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "140px",
"handle_color": null
}
},
"0c56bf122d6d4b398647fd07f68bfc82": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"76fcf218d1844fab9396ba1fc7c6d6da": {
"model_module": "@jupyter-widgets/controls",
"model_name": "SliderStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "SliderStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "140px",
"handle_color": null
}
},
"ba6c3940442a432e9ee0ec08d1778b96": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "520px"
}
},
"219d59553e954ba7ad0ffabf66fb4d4f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "140px"
}
},
"74aad48683164d66b66c8be597aaed5c": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "520px"
}
},
"8b1bd41bcf84444eacec4fe9ba7de1fc": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": "140px"
}
},
"f1b681a70dcb43c4a8c2032cbb7705ea": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"6276766130e74519b1480d0280e1e6c5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"f56ceb6b183c4645a2c66029e1123e04": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": "40px",
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "400px"
}
},
"1debb7ac70b24419b354b9b549879a29": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ButtonStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ButtonStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"button_color": null,
"font_weight": ""
}
},
"1c6399173cc448068ccade5aa8c1d190": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
}
}
}
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "IbMu57zs9FwJ"
},
"source": "# Applied QML: Hastane Senaryosu — İlaç Etkinliği Tahmini\n## Kuantum Makine Öğrenmesi Uygulama Rehberi\n\n**Eğitmen:** Joseph Volkan Özcan\n\nBu notebook, bir hastanede hasta verilerinin (kişisel bilgiler, tahlil sonuçları, MR/görüntüleme özellik vektörleri) \nkuantum bilgisayara güvenli şekilde gönderilerek **ilaç etkinliği tahmini** yapılmasını uçtan uca gösterir.\n\n### Senaryo Özeti\n1. Hasta verileri toplanır (demografik + laboratuvar + görüntüleme özellikleri)\n2. **Anonimleştirme** (KVKK / GDPR uyumlu) uygulanır\n3. Yüksek boyutlu veriler **boyut indirgeme (PCA)** ile küçültülür\n4. Veri kuantum devresine **encoding** ile aktarılır\n5. Kuantum sınıflandırıcı / kernel ile **ilaç etkinliği** (etkili / etkisiz veya etkinlik skoru) tahmin edilir\n6. Sonuçlar ölçülür, yorumlanır ve (yetkili erişimde) de-anonimleştirilebilir\n\n> Sadece **Python + IBM Qiskit** kullanılarak tasarlanmıştır. Colab’da çalışacak şekilde hazırlanmıştır.\n"
},
{
"cell_type": "markdown",
"metadata": {
"id": "UJVQpdXw9FwU"
},
"source": "## AŞAMA 1: Proje Tanımı, Veri Büyüklüğü ve Seçim Aracı\n\n### 1.1 Problemin Tanımı\nBu projede çözülmek istenen problem:\n\n> **İlaç Etkinliği Tahmini (Drug Efficacy Prediction)** \n> Belirli bir hasta profili (yaş, cinsiyet, tahlil değerleri, MR’dan türetilmiş özellikler vb.) verildiğinde, \n> seçilen ilacın **etkili olup olmayacağını** (sınıflandırma) veya **etkinlik skorunu** (regresyon) tahmin etmek.\n\nBu bir **Sınıflandırma** (veya isteğe bağlı Regresyon) problemidir. Optimizasyon (ör. doz ayarlama) ikinci aşamada düşünülebilir.\n\n### 1.2 “Veri Büyüklüğü” Ne Anlama Gelir?\n\nKuantum makine öğrenmesinde “veri büyüklüğü” iki ayrı boyutta ele alınır. Bunları karıştırmamak kritiktir:\n\n| Kavram | Anlamı (Hastane Senaryosunda) | Kuantum Etkisi |\n|--------|-------------------------------|----------------|\n| **n_samples (kayıt / hasta sayısı)** | Kaç adet hasta kaydı var? (ör. 200, 1000, 5000) | Kernel yöntemlerinde (QSVM) maliyet ≈ O(n²). Çok büyük n → simülatörde yavaşlar, gerçek cihazda pahalılaşır. |\n| **n_features (özellik / nitelik sayısı)** | Her hasta için kaç sayısal özellik kullanılıyor? | **Doğrudan kübit sayısını belirler.** Angle Encoding’de 1 özellik ≈ 1 kübit. |\n| **Ham veri boyutu** | MR görüntüsü (MB/GB), ham tahlil tabloları | Kuantuma **gönderilmez**. Önce klasik ön-işleme + özellik çıkarımı yapılır. |\n\n#### Hastane verisinde tipik özellik kaynakları\n- **Demografik / kişisel:** yaş, cinsiyet, BMI, komorbidite sayısı → düşük boyut\n- **Laboratuvar tahlilleri:** hemogram, biyokimya, tümör belirteçleri → 10–50 özellik\n- **Görüntüleme (MR / BT / PET):** ham piksel verisi **doğrudan kullanılmaz**. \n Klasik bir CNN veya radiomics ile özellik vektörü çıkarılır (ör. 100–512 boyut). \n Bu vektör daha sonra PCA ile 4–8 boyuta indirilir.\n\n> **Özet kural (NISQ dönemi):** \n> - n_features > 8–10 ise **mutlaka PCA** uygulayın. \n> - n_samples çok büyükse (binlerce) önce alt-örnekleme veya mini-batch düşünün. \n> - Ham görüntü / kişisel kimlik bilgisi **asla** kuantum devresine ham haliyle gitmez.\n\n### 1.3 Anonimleştirme (KVKK / GDPR)\nKuantuma gönderilmeden önce:\n- Doğrudan tanımlayıcılar (TC, ad-soyad, protokol no) kaldırılır veya hash’lenir\n- Kvası-tanımlayıcılar (nadir hastalık + yaş + posta kodu kombinasyonu) genelleştirilir\n- Sadece model için gerekli sayısal özellikler ve anonim hasta ID’si tutulur\n\nSonuçlar yalnızca yetkili hekim / sistem tarafından de-anonimleştirilebilir (Aşama 10).\n\nAşağıdaki **interaktif seçim aracı** ile problem tipinizi, özellik sayısını, hasta (kayıt) sayısını ve veri tipini seçerek \nuygun **encoding**, **kübit ihtiyacı**, **algoritma** ve **cihaz** önerisini alabilirsiniz.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama1_secim",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 348,
"referenced_widgets": [
"d712c49777c744be86514a2f31107cbd",
"afe97e70031e48ffb96bde9d5999d43c",
"117514629e734129a82dd14c32280e2a",
"5b515d99a34d4fe5b770e2805d9a67ac",
"0f9f765b703d43d9975fe3a6c6fbcfa2",
"a15d5be8c76c47f7849a6373b599a55f",
"47ed77dc301d47d2b51bad60f882cdcc",
"be8698e83c1145678f12ec1b3ddc1abb",
"1dfce3668cfb4ffa9e928993fce35ca1",
"9cfbaa0eac394ea5acb6c1886fcca06d",
"4a8525d27bd04de2b7afc80f89126220",
"b6cbb54349e04ddc995a5af6944a4f31",
"acdc08a9ee6a44aeb16d768008f4219a",
"73c8b1fc19ab4ef7944221a624ce5312",
"67a881470330491195b41bf9c8953444",
"01a8a4dda1594f6dbd1f55f80e299f2a",
"13af59f7da8446de9a727e458ef78977",
"545e2ca53d0b437dab280b65447a4067",
"e74944b35ad54dcc8cd7e37c03aefa09",
"d703a301835d4081ba977c0072b51e2d",
"0c56bf122d6d4b398647fd07f68bfc82",
"76fcf218d1844fab9396ba1fc7c6d6da",
"ba6c3940442a432e9ee0ec08d1778b96",
"219d59553e954ba7ad0ffabf66fb4d4f",
"74aad48683164d66b66c8be597aaed5c",
"8b1bd41bcf84444eacec4fe9ba7de1fc",
"f1b681a70dcb43c4a8c2032cbb7705ea",
"6276766130e74519b1480d0280e1e6c5",
"f56ceb6b183c4645a2c66029e1123e04",
"1debb7ac70b24419b354b9b549879a29",
"1c6399173cc448068ccade5aa8c1d190"
]
},
"executionInfo": {
"status": "ok",
"timestamp": 1787231490914,
"user_tz": -180,
"elapsed": 354,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "2377c781-0b87-4923-c80d-838ca7d34473"
},
"source": "# ============================================================\n# AŞAMA 1 - İnteraktif Seçim Aracı\n# (Encoding + Qubit + Algoritma + Cihaz) — İlaç Etkinliği\n# ============================================================\n\nimport ipywidgets as widgets\nfrom IPython.display import display, clear_output, HTML\nimport math\n\nproblem_type = widgets.Dropdown(\n options=[\n (\"Sınıflandırma — İlaç etkili / etkisiz\", \"classification\"),\n (\"Regresyon — Etkinlik skoru (0-1 veya %)\", \"regression\"),\n (\"Optimizasyon — Doz / kombinasyon arama\", \"optimization\")\n ],\n value=\"classification\",\n description=\"Problem:\",\n style={\"description_width\": \"140px\"},\n layout=widgets.Layout(width=\"520px\")\n)\n\nn_features = widgets.IntSlider(\n value=12, min=2, max=50, step=1,\n description=\"Özellik (n_features):\",\n style={\"description_width\": \"140px\"}, continuous_update=False\n)\n\nn_samples = widgets.IntSlider(\n value=300, min=50, max=5000, step=50,\n description=\"Hasta sayısı (n):\",\n style={\"description_width\": \"140px\"}, continuous_update=False\n)\n\ndata_type = widgets.Dropdown(\n options=[\n (\"Sürekli (tahlil + radiomics özellikler)\", \"continuous\"),\n (\"Kategorik (cinsiyet, komorbidite, ilaç grubu)\", \"categorical\"),\n (\"Karışık (demografik + tahlil + görüntü özellikleri)\", \"mixed\")\n ],\n value=\"mixed\",\n description=\"Veri Tipi:\",\n style={\"description_width\": \"140px\"},\n layout=widgets.Layout(width=\"520px\")\n)\n\npriority = widgets.Dropdown(\n options=[\n (\"Hızlı prototip / Eğitim (Simülatör)\", \"prototype\"),\n (\"Gerçek IBM Quantum denemesi\", \"hardware\"),\n (\"Yüksek doğruluk (simülatör + error mitigation)\", \"accuracy\")\n ],\n value=\"prototype\",\n description=\"Öncelik:\",\n style={\"description_width\": \"140px\"},\n layout=widgets.Layout(width=\"520px\")\n)\n\nrun_button = widgets.Button(\n description=\"Encoding + Qubit + Algoritma & Cihaz Öner\",\n button_style=\"success\", icon=\"check\",\n layout=widgets.Layout(width=\"400px\", height=\"40px\")\n)\noutput_area = widgets.Output()\n\n# Aşama 1b ile paylaşılacak ölçek\nSELECTED_N_FEATURES = 12\nSELECTED_N_SAMPLES = 300\n\ndef compute_encoding_and_qubits(features, samples, dtype):\n results = {\n \"primary\": None, \"alternatives\": [],\n \"pca_recommended\": features > 8,\n \"pca_target\": min(6, max(2, features // 2)) if features > 8 else features,\n \"warnings\": []\n }\n angle_qubits = features\n amp_qubits = math.ceil(math.log2(max(features, 2)))\n amp_padded = 2 ** amp_qubits\n\n if dtype == \"continuous\":\n if features <= 8:\n results[\"primary\"] = (\n \"Angle Encoding + ZZFeatureMap\", angle_qubits,\n \"Tahlil ve radiomics sürekli değerleri dönme açılarına yazılır. NISQ için stabil.\",\n \"zz_feature_map(feature_dimension=n, reps=2, entanglement='linear')\"\n )\n results[\"alternatives\"].append((\"PauliFeatureMap\", angle_qubits, \"Daha zengin kernel için alternatif.\"))\n results[\"alternatives\"].append((\n \"Amplitude Encoding\", amp_qubits,\n f\"~{amp_qubits} kübit (2^{amp_qubits}={amp_padded} pad). State preparation pahalı.\"\n ))\n else:\n results[\"primary\"] = (\n \"PCA → Angle Encoding + ZZFeatureMap\", results[\"pca_target\"],\n f\"Özellik ({features}) yüksek. PCA → {results['pca_target']} boyut, sonra Angle/ZZ.\",\n \"PCA(n_components=k) + zz_feature_map(feature_dimension=k, reps=2)\"\n )\n results[\"alternatives\"].append((\"Amplitude Encoding\", amp_qubits, f\"Doğrudan {amp_qubits} kübit; derin hazırlama.\"))\n results[\"warnings\"].append(f\"n_features={features} > 8 → PCA uygulayın.\")\n elif dtype == \"categorical\":\n results[\"primary\"] = (\n \"One-Hot (klasik) → Angle / Basis Encoding\", angle_qubits,\n \"Kategorikler One-Hot ile sayısallaştırılır, sonra Angle Encoding.\",\n \"pd.get_dummies(...) → zz_feature_map\"\n )\n results[\"alternatives\"].append((\"Basis Encoding\", \"log2(kategori)\", \"Düşük kardinalitede daha az kübit.\"))\n results[\"warnings\"].append(\"One-Hot kübit sayısını artırabilir.\")\n else:\n results[\"primary\"] = (\n \"Hibrit: Kategorik→One-Hot + Sürekli→Angle/ZZ (+ PCA)\", angle_qubits,\n \"Hastane karışık veri için tipik yol. Yüksek boyutta PCA şart.\",\n \"One-Hot + StandardScaler + (PCA) + zz_feature_map\"\n )\n if features > 6:\n results[\"pca_recommended\"] = True\n results[\"warnings\"].append(\"Karışık klinik veri → PCA ile 4–6 boyut önerilir.\")\n\n if samples > 1000:\n results[\"warnings\"].append(f\"n_samples={samples} büyük → QSVM O(n²); alt-örnekleme düşünün.\")\n if samples < 80:\n results[\"warnings\"].append(\"Kohort küçük → overfitting riski; cross-validation kullanın.\")\n return results\n\ndef get_recommendations(prob, features, samples, dtype, prio):\n recs = {\n \"algorithms\": [], \"devices\": [], \"notes\": [],\n \"encoding_info\": compute_encoding_and_qubits(features, samples, dtype),\n \"pca_required\": features > 8\n }\n enc = recs[\"encoding_info\"]\n if prob == \"classification\":\n recs[\"algorithms\"] = [\n (\"FidelityQuantumKernel + QSVM\", \"İlaç etkili/etkisiz için ana yöntem.\"),\n (\"VQC (RealAmplitudes)\", \"Eğitilebilir varyasyonel sınıflandırıcı.\"),\n (\"SamplerQNN / EstimatorQNN\", \"Esnek kuantum sinir ağı.\")\n ]\n elif prob == \"regression\":\n recs[\"algorithms\"] = [\n (\"Variational Quantum Regressor\", \"Etkinlik skoru tahmini.\"),\n (\"Quantum Kernel Ridge\", \"Kernel regresyon.\"),\n (\"EstimatorQNN regresyon\", \"Beklenti değeri çıktısı.\")\n ]\n else:\n recs[\"algorithms\"] = [\n (\"QAOA\", \"Doz / kombinasyon arama.\"),\n (\"VQE\", \"Maliyet minimizasyonu.\"),\n (\"Grover\", \"Yapılandırılmış arama (ileri).\")\n ]\n\n effective_q = enc[\"primary\"][1]\n if isinstance(effective_q, str):\n effective_q = features\n\n if prio == \"prototype\":\n recs[\"devices\"] = [\n (\"AerSimulator / StatevectorSampler\", \"Geliştirme varsayılanı.\"),\n (\"Qiskit Runtime Simulator\", \"Bulut simülasyonu.\")\n ]\n recs[\"notes\"].append(\"Önce simülatör, sonra gerçek donanım.\")\n elif prio == \"hardware\":\n if isinstance(effective_q, int) and effective_q <= 5:\n recs[\"devices\"] = [(\"IBM Quantum küçük backend\", \"≤5 kübit.\"), (\"AerSimulator ön test\", \"Önce simülatör.\")]\n elif isinstance(effective_q, int) and effective_q <= 10:\n recs[\"devices\"] = [(\"IBM 127+ kübit + error mitigation\", \"PCA sonrası.\"), (\"Runtime SamplerV2/EstimatorV2\", \"Modern primitives.\")]\n recs[\"notes\"].append(\"reps=1–2, ResilienceLevel kullanın.\")\n else:\n recs[\"devices\"] = [(\"PCA → 4–6 özellik sonra donanım\", \"12+ pratik değil.\"), (\"Aer + noise model\", \"Gürültü taklidi.\")]\n else:\n recs[\"devices\"] = [\n (\"StatevectorSampler (exact)\", \"Gürültüsüz referans.\"),\n (\"Aer + yüksek shot\", \"İstatistiksel kararlılık.\"),\n (\"Donanım + ZNE/PEC\", \"Son aşama.\")\n ]\n\n recs[\"notes\"].append(\"Kişisel tanımlayıcılar kuantum devresine gönderilmez (KVKK).\")\n return recs\n\ndef on_button_clicked(b):\n global SELECTED_N_FEATURES, SELECTED_N_SAMPLES\n with output_area:\n clear_output()\n SELECTED_N_FEATURES = n_features.value\n SELECTED_N_SAMPLES = n_samples.value\n recs = get_recommendations(\n problem_type.value, n_features.value, n_samples.value,\n data_type.value, priority.value\n )\n enc = recs[\"encoding_info\"]\n display(HTML(\"🔍 Öneri Sonuçları — İlaç Etkinliği
\"))\n print(f\"Problem: {problem_type.label}\")\n print(f\"n_features={n_features.value} | n_samples={n_samples.value} | {data_type.label}\")\n print(\"=\" * 70)\n name, qubits, desc, hint = enc[\"primary\"]\n display(HTML(\"📐 Encoding & Qubit\"))\n print(f\"▶ {name}\\n Kübit: {qubits}\\n {desc}\\n Qiskit: {hint}\\n\")\n if enc[\"alternatives\"]:\n print(\"Alternatifler:\")\n for a, q, d in enc[\"alternatives\"]:\n print(f\" • {a} | kübit≈{q} — {d}\")\n f = n_features.value\n print(f\"\\nKarşılaştırma: Angle={f} | Amplitude={math.ceil(math.log2(max(f,2)))} kübit\")\n if enc[\"pca_recommended\"]:\n display(HTML(f\"\"\n f\"⚠️ PCA önerilir → hedef ~{enc['pca_target']} özellik
\"))\n for w in enc[\"warnings\"]:\n print(f\" ⚠ {w}\")\n print()\n display(HTML(\"🧠 Algoritmalar\"))\n for i, (n, d) in enumerate(recs[\"algorithms\"], 1):\n print(f\" {i}. {n} — {d}\")\n display(HTML(\"💻 Cihazlar\"))\n for i, (n, d) in enumerate(recs[\"devices\"], 1):\n print(f\" {i}. {n} — {d}\")\n display(HTML(\"📝 Notlar\"))\n for note in recs[\"notes\"]:\n print(f\" • {note}\")\n display(HTML(\"➡️ Sonraki: Aşama 1b (CPU/GPU/TPU), sonra Aşama 2 kurulum.
\"))\n\nrun_button.on_click(on_button_clicked)\ndisplay(widgets.VBox([\n widgets.HTML(\"🎯 İlaç Etkinliği — Problem & Encoding Seçim Aracı
\"),\n widgets.HTML(\"n_features = özellik/kübit adayı; n_samples = hasta sayısı. Ham MR boyutu burada seçilmez.
\"),\n problem_type, n_features, n_samples, data_type, priority,\n widgets.HTML(\"
\"), run_button, output_area\n]))\n",
"execution_count": 1,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"VBox(children=(HTML(value='🎯 İlaç Etkinliği — Problem & Encoding Seçim Aracı
'), HTML(value=\"= 800\n many_q = n_feat >= 12\n tiny = n_feat <= 8 and n_samp <= 500\n\n if backend == \"cpu\":\n verdict = \"CPU — bu problem ölçeği için genelde en iyi denge.\"\n notes.append(\"StatevectorSampler / Aer CPU ek paketsiz çalışır.\")\n if heavy:\n notes.append(f\"n_samples≈{n_samp} yüksek → kernel O(n²) pahalı; alt-örnekleme veya GPU deneyin.\")\n if many_q:\n notes.append(f\"n_features≈{n_feat} yüksek → PCA ile 4–6 boyuta indirin.\")\n install_cmds = [\"!pip install -q qiskit qiskit-aer qiskit-machine-learning qiskit-algorithms\"]\n code_hint = (\n \"from qiskit.primitives import StatevectorSampler\\n\"\n \"sampler = StatevectorSampler()\\n\"\n \"# veya AerSimulator(method='statevector', device='CPU')\"\n )\n elif backend == \"gpu\":\n verdict = \"GPU — Colab runtime da GPU olmalı (Runtime → Change runtime type).\"\n install_cmds = [\n \"!pip install -q qiskit qiskit-machine-learning qiskit-algorithms\",\n \"!pip install -q qiskit-aer-gpu-cu11 # CUDA 11 Colab\",\n \"# alternatif CUDA 12: !pip install -q qiskit-aer-gpu\",\n ]\n code_hint = (\n \"from qiskit_aer import AerSimulator\\n\"\n \"sim = AerSimulator(method='statevector', device='GPU')\\n\"\n \"print(AerSimulator().available_devices())\"\n )\n if tiny:\n notes.append(\"Küçük devrede GPU bazen CPU’dan yavaş kalır (transfer maliyeti).\")\n if heavy or many_q:\n notes.append(\"Büyük kernel / yüksek özellik → GPU kazanç olasılığı artar.\")\n notes.append(\"`!nvidia-smi` ile GPU’yu doğrulayın; gerekirse runtime Restart.\")\n notes.append(\"StatevectorSampler varsayılanı CPU’dur; GPU için Aer device='GPU' gerekir.\")\n else:\n verdict = \"TPU — Qiskit Aer TPU kullanmaz; simülasyon CPU’da kalır.\"\n notes.append(\"TPU/v5e-1 TF-JAX içindir; bu QML yığınını hızlandırmaz.\")\n notes.append(\"Öneri: Runtime’ı CPU veya (Aer GPU deneyecekseniz) GPU yapın.\")\n install_cmds = [\"!pip install -q qiskit qiskit-aer qiskit-machine-learning qiskit-algorithms\"]\n code_hint = \"from qiskit.primitives import StatevectorSampler\\nsampler = StatevectorSampler()\"\n\n return verdict, notes, install_cmds, code_hint\n\ndef on_click(_):\n global COMPUTE_BACKEND, USE_GPU_AER, AER_DEVICE\n with out:\n clear_output()\n COMPUTE_BACKEND = backend_dd.value\n USE_GPU_AER = COMPUTE_BACKEND == \"gpu\"\n AER_DEVICE = \"GPU\" if USE_GPU_AER else \"CPU\"\n verdict, notes, install_cmds, code_hint = _recommend(\n COMPUTE_BACKEND, feat_slider.value, samp_slider.value\n )\n display(HTML(\"
🖥️ Simülasyon Ortamı Sonucu
\"))\n print(f\"Seçim: {backend_dd.label}\")\n print(f\"COMPUTE_BACKEND={COMPUTE_BACKEND} | USE_GPU_AER={USE_GPU_AER} | AER_DEVICE={AER_DEVICE}\")\n print(f\"Ölçek: n_features≈{feat_slider.value}, n_samples≈{samp_slider.value}\")\n print(\"=\" * 70)\n print(verdict)\n display(HTML(\"📝 Notlar\"))\n for n in notes:\n print(f\" • {n}\")\n display(HTML(\"📦 Kurulum (Aşama 2 veya burada)\"))\n for c in install_cmds:\n print(c)\n display(HTML(\"💻 Kod ipucu\"))\n print(code_hint)\n display(HTML(\"🔎 Ortam kontrolü\"))\n try:\n print(subprocess.check_output([\"nvidia-smi\", \"-L\"], stderr=subprocess.STDOUT, text=True).strip())\n except Exception:\n print(\"nvidia-smi yok / GPU görünmüyor (CPU veya TPU runtime olabilir).\")\n if os.environ.get(\"COLAB_TPU_ADDR\"):\n print(\"COLAB_TPU_ADDR tanımlı → TPU runtime (Aer yine CPU kullanır).\")\n display(HTML(\n \"\"\n \"Sonraki: Aşama 2 kurulum. GPU seçtiyseniz aer-gpu paketini de kurun. \"\n \"Aşama 8 sampler AER_DEVICE bilgisini okur.\"\n \"
\"\n ))\n\nbtn.on_click(on_click)\ndisplay(widgets.VBox([\n widgets.HTML(\"⚙️ CPU / GPU / TPU Seçimi
\"),\n widgets.HTML(\"Aşama 1’deki n_features / n_samples değerleri varsa otomatik dolar; değilse elle ayarlayın.
\"),\n backend_dd, feat_slider, samp_slider, widgets.HTML(\"
\"), btn, out\n]))\n",
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"VBox(children=(HTML(value='⚙️ CPU / GPU / TPU Seçimi
'), HTML(value=\"Aşama 1’de…"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "b0a448f563a746bd9e6c88e23f32240f"
}
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9zCkzA4m9Fwj"
},
"source": "## AŞAMA 2: Kütüphane Kurulumları ve Çevresel Ayarlar\n\n- **CPU** (varsayılan / Aşama 1b): standart `qiskit-aer` yeterli.\n- **GPU** (Aşama 1b): `qiskit-aer-gpu-cu11` (veya CUDA 12 için `qiskit-aer-gpu`) kurun; Colab runtime GPU olmalı.\n- **TPU**: ek Qiskit paketi yok; Aer CPU kullanır.\n\nIBM Quantum için API anahtarı `.env` veya Colab Secrets ile verilebilir.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama2_kurulum",
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471593036,
"user_tz": -180,
"elapsed": 65863,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "5449f940-1f52-4432-9273-aeb8ce0695c7"
},
"source": "import os\nimport sys\n\n_backend = globals().get(\"COMPUTE_BACKEND\", \"cpu\")\n_use_gpu = bool(globals().get(\"USE_GPU_AER\", False))\n\nprint(f\"Kurulum modu: COMPUTE_BACKEND={_backend}, USE_GPU_AER={_use_gpu}\")\n\n# Temel paketler (her zaman)\n!pip install -q qiskit qiskit-machine-learning qiskit-ibm-runtime qiskit-algorithms\n!pip install -q scikit-learn numpy pandas python-dotenv matplotlib seaborn\n\n# Aer: GPU veya CPU\nif _use_gpu:\n print(\"GPU Aer paketi kuruluyor (qiskit-aer-gpu-cu11)...\")\n !pip install -q qiskit-aer-gpu-cu11\n print(\"Sorun olursa Runtime Restart sonrası tekrar deneyin; CUDA 12 için: qiskit-aer-gpu\")\nelse:\n print(\"CPU Aer kuruluyor...\")\n !pip install -q qiskit-aer\n\nimport numpy as np\nimport pandas as pd\nfrom dotenv import load_dotenv\n\nload_dotenv()\nibm_api_key = os.getenv(\"IBM_QUANTUM_TOKEN\")\n\nprint(\"Kütüphaneler yüklendi.\")\nprint(f\"IBM API anahtarı {'tanımlı' if ibm_api_key else 'tanımlı değil (simülatör)'}.\")\n",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Kurulum modu: COMPUTE_BACKEND=gpu, USE_GPU_AER=True\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.7/9.7 MB\u001b[0m \u001b[31m75.8 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[31m24.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m49.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m327.8/327.8 kB\u001b[0m \u001b[31m21.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m412.6/412.6 kB\u001b[0m \u001b[31m29.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m120.7/120.7 kB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.7/94.7 kB\u001b[0m \u001b[31m7.2 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[31m66.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m224.2/224.2 kB\u001b[0m \u001b[31m16.5 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[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.6/76.6 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m8.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m541.5/541.5 kB\u001b[0m \u001b[31m32.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hGPU Aer paketi kuruluyor (qiskit-aer-gpu-cu11)...\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.1/18.1 MB\u001b[0m \u001b[31m67.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.6/38.6 MB\u001b[0m \u001b[31m17.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m53.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m417.9/417.9 MB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m875.6/875.6 kB\u001b[0m \u001b[31m49.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m128.2/128.2 MB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m204.1/204.1 MB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m139.1/139.1 MB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hSorun olursa Runtime Restart sonrası tekrar deneyin; CUDA 12 için: qiskit-aer-gpu\n",
"Kütüphaneler yüklendi.\n",
"IBM API anahtarı tanımlı değil (simülatör).\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6acwkgtz9Fwl"
},
"source": "## AŞAMA 3: Veri Tipi, Nitelikler ve Boyut İndirgeme (PCA)\n\n### Hastane verisinde tipik nitelikler\n- **Demografik (kategorik / sürekli):** yaş, cinsiyet, BMI, sigara, komorbidite sayısı \n- **Laboratuvar (sürekli):** WBC, CRP, kreatinin, tümör belirteçleri, karaciğer enzimleri… \n- **Görüntüleme türevi (sürekli, yüksek boyut):** Radiomics veya CNN embedding (50–512 boyut)\n\nHam MR/BT **doğrudan** kuantum devresine verilmez. Klasik özellik çıkarımı sonrası \nyüksek boyutlu vektör **PCA** ile 4–8 boyuta indirilir (NISQ kübit sınırı).\n\nAşağıdaki fonksiyon, standardizasyon + PCA uygular.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama3_pca",
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471807693,
"user_tz": -180,
"elapsed": 1619,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "2adc4aff-8efd-4493-d879-e7ebe586e6a1"
},
"source": "from sklearn.decomposition import PCA\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.pipeline import make_pipeline\n\ndef boyut_indirgeme_uygula(X_veri, n_components=4):\n \"\"\"\n Kuantum devresine uygun boyut için StandardScaler + PCA.\n X_veri: (n_samples, n_features) numpy array veya DataFrame\n \"\"\"\n pipeline = make_pipeline(\n StandardScaler(),\n PCA(n_components=n_components)\n )\n X_kucultulmus = pipeline.fit_transform(X_veri)\n print(f\"Orijinal boyut : {X_veri.shape}\")\n print(f\"İndirgenmiş : {X_kucultulmus.shape}\")\n print(f\"Açıklanan varyans oranı (kümülatif): {pipeline.named_steps['pca'].explained_variance_ratio_.sum():.3f}\")\n return X_kucultulmus, pipeline\n\n# Örnek (rastgele yüksek boyutlu özellik → 4 boyuta)\nnp.random.seed(42)\nX_ornek = np.random.randn(100, 30) # 100 hasta, 30 radiomics/tahlil özelliği\nX_4d, pca_pipe = boyut_indirgeme_uygula(X_ornek, n_components=4)\n",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Orijinal boyut : (100, 30)\n",
"İndirgenmiş : (100, 4)\n",
"Açıklanan varyans oranı (kümülatif): 0.262\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Xpwn04l39Fwo"
},
"source": "### Kategorik alanların hazırlanması\nCinsiyet, ilaç grubu, komorbidite kodu gibi alanlar One-Hot Encoding ile sayısallaştırılmalıdır.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama3_onehot",
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471814354,
"user_tz": -180,
"elapsed": 278,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "b166d594-22bb-4036-9823-7130e25d2968"
},
"source": "# Kategorik → One-Hot örneği (hastane bağlamı)\nornek_df = pd.DataFrame({\n \"Yas\": [45, 62, 38],\n \"Cinsiyet\": [\"K\", \"E\", \"K\"],\n \"Komorbidite\": [\"Diyabet\", \"Yok\", \"Hipertansiyon\"]\n})\ndf_one_hot = pd.get_dummies(ornek_df, columns=[\"Cinsiyet\", \"Komorbidite\"], dtype=float)\nprint(\"One-Hot sonrası:\")\nprint(df_one_hot)\n",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"One-Hot sonrası:\n",
" Yas Cinsiyet_E Cinsiyet_K Komorbidite_Diyabet \\\n",
"0 45 0.0 1.0 1.0 \n",
"1 62 1.0 0.0 0.0 \n",
"2 38 0.0 1.0 0.0 \n",
"\n",
" Komorbidite_Hipertansiyon Komorbidite_Yok \n",
"0 0.0 0.0 \n",
"1 0.0 1.0 \n",
"2 1.0 0.0 \n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hbR0vcC_9Fwq"
},
"source": "## AŞAMA 4: Sentetik Hasta Verisi Üretimi ve Anonimleştirme (KVKK)\n\nGerçek hasta verisi paylaşmadan modeli geliştirebilmek için **sentetik kohort** üretiriz. \nArdından KVKK/GDPR uyumlu anonimleştirme adımları uygulanır:\n\n1. Doğrudan tanımlayıcılar (ad, TC, protokol) → hash veya tamamen kaldırılır \n2. Sadece model özellikleri + anonim ID tutulur \n3. Kuantum devresine **yalnızca anonim sayısal vektör** gider \n\nAşağıda iki seçenek vardır:\n- **Sentetik veri üret** (önerilen başlangıç)\n- Kendi CSV’nizi yükleyin (Aşama 5)\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama4_sentetik_anon",
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471821448,
"user_tz": -180,
"elapsed": 345,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "7185c7b4-cc9f-4b8b-bbcc-b5a2cb55032d"
},
"source": "import hashlib\nimport uuid\nfrom sklearn.datasets import make_classification\n\ndef sentetik_hasta_verisi_uret(n_samples=300, n_features=12, random_state=42):\n \"\"\"\n İlaç etkinliği sınıflandırması için sentetik hasta kohortu.\n Özellikler: tahlil + radiomics benzeri sürekli değerler.\n Hedef: 0 = ilaç etkisiz, 1 = ilaç etkili\n \"\"\"\n X, y = make_classification(\n n_samples=n_samples,\n n_features=n_features,\n n_informative=max(2, n_features // 2),\n n_redundant=max(0, n_features // 4),\n n_clusters_per_class=2,\n class_sep=1.2,\n random_state=random_state\n )\n # Klinik isimlendirme (örnek)\n feature_names = [f\"Ozellik_{i+1}\" for i in range(n_features)]\n # İlk birkaçına anlamlı isim verelim\n klinik_isimler = [\n \"Yas_norm\", \"BMI_norm\", \"CRP\", \"WBC\", \"Kreatinin\",\n \"Tumor_marker\", \"Radiomics_1\", \"Radiomics_2\",\n \"Radiomics_3\", \"Radiomics_4\", \"Karaciger_ALT\", \"Hgb\"\n ]\n for i, isim in enumerate(klinik_isimler):\n if i < n_features:\n feature_names[i] = isim\n\n df = pd.DataFrame(X, columns=feature_names)\n df[\"Ilac_Etkin\"] = y # 0/1\n\n # Sahte doğrudan tanımlayıcılar (anonimleştirme demosu için)\n df[\"Hasta_Ad\"] = [f\"Hasta_{i}\" for i in range(n_samples)]\n df[\"Protokol_No\"] = [f\"PR-{10000+i}\" for i in range(n_samples)]\n df[\"TC_Kimlik\"] = [f\"{10000000000+i}\" for i in range(n_samples)]\n\n return df\n\ndef anonimlestir(df, id_col=\"Anonim_ID\"):\n \"\"\"\n Doğrudan tanımlayıcıları kaldırır / hash’ler.\n Geri dönüşüm için sadece yetkili tarafta tutulacak mapping üretir.\n \"\"\"\n mapping = {}\n anon_ids = []\n for idx, row in df.iterrows():\n ham = f\"{row.get('TC_Kimlik','')}-{row.get('Protokol_No','')}-{row.get('Hasta_Ad','')}\"\n anon = hashlib.sha256(ham.encode()).hexdigest()[:16]\n anon_ids.append(anon)\n mapping[anon] = {\n \"Hasta_Ad\": row.get(\"Hasta_Ad\"),\n \"Protokol_No\": row.get(\"Protokol_No\"),\n \"TC_Kimlik\": row.get(\"TC_Kimlik\")\n }\n\n # Tanımlayıcı sütunları düşür\n drop_cols = [c for c in [\"Hasta_Ad\", \"Protokol_No\", \"TC_Kimlik\"] if c in df.columns]\n df_anon = df.drop(columns=drop_cols).copy()\n df_anon.insert(0, id_col, anon_ids)\n\n print(f\"Anonimleştirme tamamlandı. {len(df_anon)} kayıt.\")\n print(f\"Kaldırılan sütunlar: {drop_cols}\")\n print(f\"Mapping sözlüğü {len(mapping)} girdi içeriyor (sadece yetkili tarafta saklanmalı).\")\n return df_anon, mapping\n\n# --- Sentetik kohort üret ve anonimleştir ---\ndf_ham = sentetik_hasta_verisi_uret(n_samples=300, n_features=12)\nprint(\"Ham sentetik veri (ilk 3 satır, tanımlayıcılar görünür):\")\nprint(df_ham[[\"Hasta_Ad\", \"Protokol_No\", \"Yas_norm\", \"CRP\", \"Ilac_Etkin\"]].head(3))\nprint()\n\ndf_anon, deanon_mapping = anonimlestir(df_ham)\nprint(\"\\nAnonim veri (ilk 3 satır):\")\nprint(df_anon.head(3))\n",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Ham sentetik veri (ilk 3 satır, tanımlayıcılar görünür):\n",
" Hasta_Ad Protokol_No Yas_norm CRP Ilac_Etkin\n",
"0 Hasta_0 PR-10000 0.327880 -3.429009 0\n",
"1 Hasta_1 PR-10001 1.096469 -5.153065 0\n",
"2 Hasta_2 PR-10002 -1.643189 5.067190 0\n",
"\n",
"Anonimleştirme tamamlandı. 300 kayıt.\n",
"Kaldırılan sütunlar: ['Hasta_Ad', 'Protokol_No', 'TC_Kimlik']\n",
"Mapping sözlüğü 300 girdi içeriyor (sadece yetkili tarafta saklanmalı).\n",
"\n",
"Anonim veri (ilk 3 satır):\n",
" Anonim_ID Yas_norm BMI_norm CRP WBC Kreatinin \\\n",
"0 ba65e1d607189a7d 0.327880 -0.125454 -3.429009 -0.966273 0.622677 \n",
"1 693471c5ba2d6aa9 1.096469 1.223569 -5.153065 0.123042 -2.753199 \n",
"2 baf585ace757c3cc -1.643189 -0.103255 5.067190 0.676039 4.462769 \n",
"\n",
" Tumor_marker Radiomics_1 Radiomics_2 Radiomics_3 Radiomics_4 \\\n",
"0 1.057780 -0.633576 -2.640361 -1.195982 1.127387 \n",
"1 -2.309980 0.784641 -1.693481 -2.583432 0.700140 \n",
"2 1.021881 -2.666907 4.191878 3.264531 -0.658737 \n",
"\n",
" Karaciger_ALT Hgb Ilac_Etkin \n",
"0 -2.404128 0.085893 0 \n",
"1 -1.881216 -0.625677 0 \n",
"2 3.296044 -0.175854 0 \n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hR3l5Nay9Fwu"
},
"source": "## AŞAMA 5: (Opsiyonel) Kendi CSV Dosyanızı Yükleme\n\nSentetik veri yerine gerçek (anonimleştirilmiş) hasta CSV’si kullanmak isterseniz \naşağıdaki yükleyiciyi kullanın. CSV’de hedef sütun adı tercihen `Ilac_Etkin` olsun.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama5_upload",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 49,
"referenced_widgets": [
"88dca262feae4c99851575d9553b8999",
"d4eba1fac4ba4e9c86dbe8982f351c9a",
"8b20979c08554df3a476d07355ef58e7"
]
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471828728,
"user_tz": -180,
"elapsed": 474,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "4f12a8aa-34a8-4bf0-cd43-8b69c45cf163"
},
"source": "import ipywidgets as widgets\nfrom IPython.display import display\nimport io\n\nuploader = widgets.FileUpload(accept=\".csv\", multiple=False, description=\"CSV Yükle\")\ndisplay(uploader)\n\ndef yuklenen_csv_oku(uploader_widget):\n if not uploader_widget.value:\n print(\"Henüz dosya yüklenmedi. Sentetik veri (df_anon) kullanılmaya devam eder.\")\n return None\n # Colab / Jupyter farkı için esnek okuma\n uploaded = uploader_widget.value\n if isinstance(uploaded, dict):\n file_info = list(uploaded.values())[0]\n content = file_info[\"content\"]\n else:\n file_info = uploaded[0]\n content = file_info[\"content\"]\n df = pd.read_csv(io.BytesIO(content))\n print(f\"Yüklendi: {df.shape[0]} satır, {df.shape[1]} sütun\")\n print(df.head(3))\n return df\n\n# Kullanım: df_yuklenen = yuklenen_csv_oku(uploader)\n",
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"FileUpload(value={}, accept='.csv', description='CSV Yükle')"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "88dca262feae4c99851575d9553b8999"
}
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VJ6zQweO9Fww"
},
"source": "## AŞAMA 5b: Model İçin Özellik Matrisinin Hazırlanması\n\nAnonim veri üzerinden:\n1. Hedef sütunu ayır \n2. (Gerekirse) PCA uygula \n3. Eğitim / test bölünmesi yap\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama5b_hazirlik",
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471834272,
"user_tz": -180,
"elapsed": 95,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "49ef5118-bb92-453f-89dc-9811f9843243"
},
"source": "from sklearn.model_selection import train_test_split\n\n# Hedef ve özellikler\nTARGET = \"Ilac_Etkin\"\nfeature_cols = [c for c in df_anon.columns if c not in (TARGET, \"Anonim_ID\")]\n\nX = df_anon[feature_cols].values\ny = df_anon[TARGET].values\n\nprint(f\"Özellik matrisi: {X.shape} | Hedef dağılımı: {np.bincount(y)}\")\n\n# Boyut yüksekse PCA (seçim aracındaki öneriye göre ayarlayın)\nN_COMPONENTS = 4 # Seçim aracından gelen pca_target değerini buraya yazabilirsiniz\nif X.shape[1] > N_COMPONENTS:\n X_red, pca_model = boyut_indirgeme_uygula(X, n_components=N_COMPONENTS)\nelse:\n X_red = StandardScaler().fit_transform(X)\n print(\"PCA gerekmedi, sadece standardizasyon uygulandı.\")\n\nX_train, X_test, y_train, y_test = train_test_split(\n X_red, y, test_size=0.25, random_state=42, stratify=y\n)\nprint(f\"Eğitim: {X_train.shape[0]} | Test: {X_test.shape[0]}\")\n",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Özellik matrisi: (300, 12) | Hedef dağılımı: [151 149]\n",
"Orijinal boyut : (300, 12)\n",
"İndirgenmiş : (300, 4)\n",
"Açıklanan varyans oranı (kümülatif): 0.651\n",
"Eğitim: 225 | Test: 75\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yUUK-Dch9Fwx"
},
"source": "## AŞAMA 6–7: Feature Map ve Ansatz (Kuantum Devresi)\n\n- **Feature Map:** Klasik özellikleri kuantum durumuna kodlar (ZZFeatureMap) \n- **Ansatz:** Eğitilebilir parametreli devre (RealAmplitudes) — VQC kullanıldığında \n\nKernel tabanlı QSVM için yalnızca feature map yeterlidir.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama6_7_circuit",
"colab": {
"base_uri": "https://localhost:8080/"
},
"executionInfo": {
"status": "ok",
"timestamp": 1786471842545,
"user_tz": -180,
"elapsed": 910,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "26c6d9e0-6243-424c-a521-fbb8f1e103f6"
},
"source": "from qiskit import QuantumCircuit\nfrom qiskit.circuit.library import zz_feature_map, real_amplitudes\n\nnum_features = X_train.shape[1]\nprint(f\"Kullanılacak kübit / özellik sayısı: {num_features}\")\n\nfeature_map = zz_feature_map(\n feature_dimension=num_features,\n reps=2,\n entanglement=\"linear\"\n)\n\nansatz = real_amplitudes(num_qubits=num_features, reps=3)\n\n# Birleşik devre örneği (VQC için)\nqc = QuantumCircuit(num_features)\nqc.compose(feature_map, inplace=True)\nqc.compose(ansatz, inplace=True)\nqc.measure_all()\n\nprint(\"Feature map + Ansatz hazır.\")\nprint(f\"Feature map derinliği (approx): {feature_map.depth()}\")\n",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Kullanılacak kübit / özellik sayısı: 4\n",
"Feature map + Ansatz hazır.\n",
"Feature map derinliği (approx): 19\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NID-KldK9Fw0"
},
"source": "## AŞAMA 8: Kuantum Kernel Oluşturma\n\nFidelityQuantumKernel, veri noktalarının kuantum durumlarındaki benzerliğini hesaplar. \n`shots` değeri istatistiksel kararlılığı etkiler (1024 iyi bir başlangıçtır).\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama8_kernel",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 378
},
"executionInfo": {
"status": "error",
"timestamp": 1786472042027,
"user_tz": -180,
"elapsed": 18,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
},
"outputId": "333d9b3b-2830-4cea-b91f-b47f4d5c99bd"
},
"source": "from qiskit_machine_learning.kernels import FidelityQuantumKernel\nfrom qiskit_algorithms.state_fidelities import ComputeUncompute\nfrom qiskit.primitives import StatevectorSampler\n\nshots = 1024\n_device = globals().get(\"AER_DEVICE\", \"CPU\")\n_use_gpu = globals().get(\"USE_GPU_AER\", False)\n\nif _use_gpu:\n try:\n from qiskit_aer import AerSimulator\n sim = AerSimulator(method=\"statevector\", device=\"GPU\")\n print(\"Aer GPU denemesi OK. available_devices:\", AerSimulator().available_devices())\n except Exception as e:\n print(\"GPU Aer kullanılamadı:\", e)\n # Fidelity kernel için exact sampler (küçük devrede stabil)\n sampler = StatevectorSampler()\n print(\"FidelityQuantumKernel: StatevectorSampler (exact). Büyük devrede AerSampler+GPU özelleştirilebilir.\")\nelse:\n sampler = StatevectorSampler()\n print(f\"Sampler: StatevectorSampler (AER_DEVICE={_device})\")\n\nfidelity = ComputeUncompute(sampler=sampler)\nqkernel = FidelityQuantumKernel(fidelity=fidelity, feature_map=feature_map)\nprint(f\"Kuantum Kernel hazır. Shot referans: {shots}\")\n",
"execution_count": null,
"outputs": [
{
"output_type": "error",
"ename": "ModuleNotFoundError",
"evalue": "No module named 'qiskit_machine_learning'",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/tmp/ipykernel_1029/4017765636.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mqiskit_machine_learning\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkernels\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mFidelityQuantumKernel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mqiskit_algorithms\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate_fidelities\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mComputeUncompute\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mqiskit\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprimitives\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mStatevectorSampler\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mshots\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1024\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'qiskit_machine_learning'",
"",
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0;32m\nNOTE: If your import is failing due to a missing package, you can\nmanually install dependencies using either !pip or !apt.\n\nTo view examples of installing some common dependencies, click the\n\"Open Examples\" button below.\n\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n"
],
"errorDetails": {
"actions": [
{
"action": "open_url",
"actionText": "Open Examples",
"url": "/notebooks/snippets/importing_libraries.ipynb"
}
]
}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CSn5JfAQ9Fw2"
},
"source": "## AŞAMA 9: Modelin Eğitilmesi (QSVM) — Simülatör\n\nQiskit Machine Learning içindeki QSVC (Quantum Support Vector Classifier) kullanılır. \nÖnce simülatörde eğitip test skoruna bakıyoruz.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama9_qsvc",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 378
},
"outputId": "5026274f-1a0e-415e-9312-3e27381c6e25",
"executionInfo": {
"status": "error",
"timestamp": 1786471994600,
"user_tz": -180,
"elapsed": 363,
"user": {
"displayName": "Joseph Volkan ÖZCAN",
"userId": "11389530967736397480"
}
}
},
"source": "from qiskit_machine_learning.algorithms import QSVC\nfrom sklearn.metrics import classification_report, accuracy_score, confusion_matrix\n\n# QSVC — quantum kernel ile SVM\nqsvc = QSVC(quantum_kernel=qkernel)\n\nprint(\"Eğitim başlıyor (simülatör)...\")\nqsvc.fit(X_train, y_train)\n\ny_pred = qsvc.predict(X_test)\nacc = accuracy_score(y_test, y_pred)\nprint(f\"\\nTest doğruluğu: {acc:.3f}\")\nprint(\"\\nSınıflandırma raporu:\")\nprint(classification_report(y_test, y_pred, target_names=[\"Etkisiz\", \"Etkili\"]))\nprint(\"Karmaşıklık matrisi:\")\nprint(confusion_matrix(y_test, y_pred))\n",
"execution_count": null,
"outputs": [
{
"output_type": "error",
"ename": "ModuleNotFoundError",
"evalue": "No module named 'qiskit_machine_learning'",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/tmp/ipykernel_570/295129105.py\u001b[0m in \u001b[0;36m| \u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mqiskit_machine_learning\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0malgorithms\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mQSVC\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mclassification_report\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccuracy_score\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconfusion_matrix\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m# QSVC — quantum kernel ile SVM\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mqsvc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mQSVC\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquantum_kernel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mqkernel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'qiskit_machine_learning'",
"",
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0;32m\nNOTE: If your import is failing due to a missing package, you can\nmanually install dependencies using either !pip or !apt.\n\nTo view examples of installing some common dependencies, click the\n\"Open Examples\" button below.\n\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n"
],
"errorDetails": {
"actions": [
{
"action": "open_url",
"actionText": "Open Examples",
"url": "/notebooks/snippets/importing_libraries.ipynb"
}
]
}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "aUWqQe6e9Fw4"
},
"source": "## AŞAMA 10: Sonuçların Yorumlanması ve De-Anonimleştirme\n\nKuantum / model çıktısı anonim ID’ler üzerinden gelir. \nSadece yetkili sistem, saklanan mapping ile gerçek kimliğe dönebilir.\n\n> Üretim ortamında mapping **ayrı, erişim kontrollü** bir serviste tutulmalıdır. \n> Bu notebook yalnızca eğitim amaçlı demo yapar.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama10_deanon"
},
"source": "# Örnek: test setinden birkaç anonim ID için tahmin + de-anonimleştirme\n# (Gerçek pipeline'da X_test satırları ile Anonim_ID eşleştirilir)\n\n# Demo: rastgele 3 anonim ID al\nornek_anon_ids = df_anon[\"Anonim_ID\"].sample(3, random_state=1).tolist()\n\nprint(\"Örnek de-anonimleştirme (sadece yetkili erişim):\")\nfor aid in ornek_anon_ids:\n gercek = deanon_mapping.get(aid, {})\n print(f\" Anonim ID : {aid}\")\n print(f\" → Gerçek : {gercek.get('Hasta_Ad')} | Protokol: {gercek.get('Protokol_No')}\")\n print()\n",
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "lz5kLSYx9Fw5"
},
"source": "## AŞAMA 11: Sonuçların Dışa Aktarılması (CSV & SQL)\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama11_export"
},
"source": "import sqlite3\nimport os\n\n# Tahmin sonuçlarını tabloya dök (demo: test seti)\nsonuc_df = pd.DataFrame({\n \"y_true\": y_test,\n \"y_pred\": y_pred\n})\nsonuc_df[\"Dogru_Mu\"] = (sonuc_df[\"y_true\"] == sonuc_df[\"y_pred\"]).astype(int)\n\noutput_dir = \"./sonuclar\"\nos.makedirs(output_dir, exist_ok=True)\ncsv_path = os.path.join(output_dir, \"ilac_etkinligi_tahminleri.csv\")\nsonuc_df.to_csv(csv_path, index=False)\nprint(f\"CSV kaydedildi: {csv_path}\")\n\nconn = sqlite3.connect(\"qml_hastane.db\")\nsonuc_df.to_sql(\"Ilac_Etkinlik_Tahminleri\", conn, if_exists=\"replace\", index=False)\nconn.close()\nprint(\"SQL tablosuna yazıldı: Ilac_Etkinlik_Tahminleri\")\nprint(sonuc_df.head())\n",
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "tQQ7VbZ89Fw7"
},
"source": "## AŞAMA 12: Görselleştirme\n\nSınıf dağılımı ve (varsa) kuantum ölçüm histogramı.\n"
},
{
"cell_type": "code",
"metadata": {
"id": "asama12_viz"
},
"source": "%matplotlib inline\nimport matplotlib.pyplot as plt\nfrom qiskit.visualization import plot_histogram\n\n# 1) Gerçek vs tahmin sınıf dağılımı\nfig, axes = plt.subplots(1, 2, figsize=(10, 4))\naxes[0].hist(y_test, bins=[-0.5, 0.5, 1.5], rwidth=0.6, color=\"steelblue\")\naxes[0].set_xticks([0, 1])\naxes[0].set_xticklabels([\"Etkisiz\", \"Etkili\"])\naxes[0].set_title(\"Gerçek (y_test)\")\naxes[1].hist(y_pred, bins=[-0.5, 0.5, 1.5], rwidth=0.6, color=\"teal\")\naxes[1].set_xticks([0, 1])\naxes[1].set_xticklabels([\"Etkisiz\", \"Etkili\"])\naxes[1].set_title(\"Tahmin (y_pred)\")\nplt.tight_layout()\nplt.show()\n\n# 2) Örnek kuantum ölçüm histogramı (demo counts)\ndemo_counts = {\"00\": 480, \"01\": 120, \"10\": 95, \"11\": 329}\nfig2 = plot_histogram(demo_counts, title=\"Örnek Kuantum Ölçüm Histogramı\", figsize=(8, 5), color=\"teal\")\ndisplay(fig2)\n",
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "hn2BQtAy9Fw8"
},
"source": "## Özet ve Sonraki Adımlar\n\nBu notebook’ta yapılanlar:\n\n1. **Problem tanımı** — Hastane ilaç etkinliği tahmini (sınıflandırma)\n2. **Aşama 1b** — CPU / GPU / TPU seçimi ve Qiskit Aer’e etkisi \n2. **Veri büyüklüğü ayrımı** — `n_samples` (hasta sayısı) vs `n_features` (özellik / kübit) netleştirildi \n3. **Seçim aracı** — Encoding, kübit hesabı, algoritma ve cihaz önerisi \n4. **Sentetik kohort** + **KVKK anonimleştirme** \n5. **PCA** ile boyut indirgeme \n6. **ZZFeatureMap + FidelityQuantumKernel + QSVC** ile eğitim ve test \n7. **De-anonimleştirme demosu**, CSV/SQL export, görselleştirme \n\n### Gerçek ortama geçerken\n- Mapping tablosunu kuantum pipeline’ından **ayırın** (ayrı yetkili servis) \n- Ham görüntüleri yalnızca klasik özellik çıkarımı için kullanın \n- Gerçek IBM Quantum backend’ine geçmeden önce noise model ile test edin \n- Klinik validasyon ve etik kurul onayı olmadan üretim kararı vermeyin \n\n**Colab’da çalıştırma sırası:** Yukarıdan aşağıya hücreleri sırayla Run edin. \nSeçim aracındaki `n_features` / PCA hedefini Aşama 5b’deki `N_COMPONENTS` ile uyumlu tutun.\n"
}
]
} | |