{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "version_major": 2, "version_minor": 0, "state": { "5a8b8c2fe93f4864a1c6c3eecd1b154e": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_2a60552d9ca24ebb8bde706caffb288b", "IPY_MODEL_1435bd36758d4edcbb4e3c8a85200330", "IPY_MODEL_ba3fe51b37f04a90bb61716515cc18cd" ], "layout": "IPY_MODEL_4d144546b6f545a496aaf49246b264a6" } }, "2a60552d9ca24ebb8bde706caffb288b": { "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_d1bff2cc36d342ad95d7048fc1712737", "placeholder": "​", "style": "IPY_MODEL_bab0258e9beb47449b68e08756e88a0a", "value": "Descargando ASOS: 100%" } }, "1435bd36758d4edcbb4e3c8a85200330": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ce5c4b346b124a93aa6e3ad7d2cbfb1c", "max": 16, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_01e0918b453b4f2992b8186f2ecd2db3", "value": 16 } }, "ba3fe51b37f04a90bb61716515cc18cd": { "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_3b4da1d71dba45d99550a0ff6d2d8947", "placeholder": "​", "style": "IPY_MODEL_1ad9b04b2db6464898c59e7f2987ada9", "value": " 16/16 [04:08<00:00, 15.51s/it]" } }, "4d144546b6f545a496aaf49246b264a6": { "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 } }, "d1bff2cc36d342ad95d7048fc1712737": { "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 } }, "bab0258e9beb47449b68e08756e88a0a": { "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": "" } }, "ce5c4b346b124a93aa6e3ad7d2cbfb1c": { "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 } }, "01e0918b453b4f2992b8186f2ecd2db3": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "3b4da1d71dba45d99550a0ff6d2d8947": { "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 } }, "1ad9b04b2db6464898c59e7f2987ada9": { "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": "" } }, "d32fd123693540e482c737441ba1df14": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_e0c110fee938460c96fa70c838ec41d8", "IPY_MODEL_b4351a5aab914373ae3d328f081e7494", "IPY_MODEL_5f5838184c494963bbec7e176628e1d6" ], "layout": "IPY_MODEL_20996146f0794c019dd1b40a5e080393" } }, "e0c110fee938460c96fa70c838ec41d8": { "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_90a1118af8a041218ed7196e949f9f4b", "placeholder": "​", "style": "IPY_MODEL_9daff681a7ca4be4892a4f1d9201a264", "value": "Procesando: 100%" } }, "b4351a5aab914373ae3d328f081e7494": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a726158af3e54d458b3aed03f1df5cbe", "max": 104, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_df4ab8be122b454f8d4147a6dc5fd9e4", "value": 104 } }, "5f5838184c494963bbec7e176628e1d6": { "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_406a24fc92be42a49743e4c6c79cf8ed", "placeholder": "​", "style": "IPY_MODEL_661c9f05f3ae472ba0cc1096b41cce2f", "value": " 104/104 [00:01<00:00, 66.48it/s]" } }, "20996146f0794c019dd1b40a5e080393": { "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 } }, "90a1118af8a041218ed7196e949f9f4b": { "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 } }, "9daff681a7ca4be4892a4f1d9201a264": { "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": "" } }, "a726158af3e54d458b3aed03f1df5cbe": { "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 } }, "df4ab8be122b454f8d4147a6dc5fd9e4": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "406a24fc92be42a49743e4c6c79cf8ed": { "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 } }, "661c9f05f3ae472ba0cc1096b41cce2f": { "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": "" } }, "2303adb59f8343e4bf7ba7e0bfec18b0": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b8fb929fd45e4eed85a60b7b7aed8170", "IPY_MODEL_89fff66d849f43b9b37c3e9f2388a8b4", "IPY_MODEL_391048ad027a4e2ab1e9f7abc916b59e" ], "layout": "IPY_MODEL_503bbe389cd0481cbcadc4ccfdb06418" } }, "b8fb929fd45e4eed85a60b7b7aed8170": { "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_2f85c358cb7d477b9dd28112c710fa6a", "placeholder": "​", "style": "IPY_MODEL_9033eec2233f4a8baa99fe4917626266", "value": "Radiación ERA5: 100%" } }, "89fff66d849f43b9b37c3e9f2388a8b4": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_dc0f41f027df4fdd9d57bb30a8b817a8", "max": 16, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d00ba11cedc34305aa42f7fc55f94ea1", "value": 16 } }, "391048ad027a4e2ab1e9f7abc916b59e": { "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_a9ff0704d67a456d9960a9f89b1613f4", "placeholder": "​", "style": "IPY_MODEL_553cecb9b6e943b3a31d2b10174019cc", "value": " 16/16 [00:04<00:00,  3.26it/s]" } }, "503bbe389cd0481cbcadc4ccfdb06418": { "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 } }, "2f85c358cb7d477b9dd28112c710fa6a": { "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 } }, "9033eec2233f4a8baa99fe4917626266": { "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": "" } }, "dc0f41f027df4fdd9d57bb30a8b817a8": { "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 } }, "d00ba11cedc34305aa42f7fc55f94ea1": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a9ff0704d67a456d9960a9f89b1613f4": { "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 } }, "553cecb9b6e943b3a31d2b10174019cc": { "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": "" } }, "4a68404920cb48c099155bf3c233fafb": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_c1488996287d429495db8fda2fc92946", "IPY_MODEL_e827aebbb971422b9e24c324e7052805", "IPY_MODEL_ef89e7faaa22420a974ff1965b2bfc5c" ], "layout": "IPY_MODEL_156a1f501dc8464ba44d1da8416ec5d9" } }, "c1488996287d429495db8fda2fc92946": { "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_7588c70956fe48c2b6d4ec7f18837097", "placeholder": "​", "style": "IPY_MODEL_7c7ab54c68e642deac402aff098e32c7", "value": "Recalculando con rad ERA5: 100%" } }, "e827aebbb971422b9e24c324e7052805": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_59ca34068ce845d29d8d0de02871e81e", "max": 104, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_6dd9a828863844baba24a44db749fbbd", "value": 104 } }, "ef89e7faaa22420a974ff1965b2bfc5c": { "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_6d1f0cba076c4356996c16bf7ffcfe5a", "placeholder": "​", "style": "IPY_MODEL_8c0d2011e7754ff4a45c4ca3e2cc3d44", "value": " 104/104 [00:01<00:00, 63.41it/s]" } }, "156a1f501dc8464ba44d1da8416ec5d9": { "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 } }, "7588c70956fe48c2b6d4ec7f18837097": { "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 } }, "7c7ab54c68e642deac402aff098e32c7": { "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": "" } }, "59ca34068ce845d29d8d0de02871e81e": { "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 } }, "6dd9a828863844baba24a44db749fbbd": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "6d1f0cba076c4356996c16bf7ffcfe5a": { "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 } }, "8c0d2011e7754ff4a45c4ca3e2cc3d44": { "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": "" } } } } } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "282P1qbnhEtV" }, "source": [ "# Mundial 2026 — WBGT NOAA Observacional (15 sedes + KPHL)\n", "## Notebook DEFINITIVO para el artículo IJBM\n", "\n", "**Cambios respecto a la versión anterior:**\n", "1. Filadelfia: KTTN (30 km) → KPHL/PHL (7 km)\n", "2. Delays de 15s entre peticiones IEM para evitar HTTP 429\n", "3. Re-descarga de KC, SF, Toronto con reintentos\n", "4. sdh₂₈ corregido: usa integración horaria (B7_grados_hora × asistencia)\n", "5. Bland-Altman añadido\n", "6. Leave-one-venue-out ICC añadido\n", "7. Bootstrap de disparidad corregido (Houston − sede más fría disponible)\n", "8. Todas las celdas de análisis operan sobre el dataset completo post-pipeline\n" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "8JUeiLaYhEti", "outputId": "b0e09397-8c8b-4911-926e-83e7193f3ea0" }, "source": [ "# Celda 1 — Instalación e imports\n", "!pip install openpyxl pysolar tqdm statsmodels -q\n", "\n", "import pandas as pd\n", "import numpy as np\n", "from datetime import datetime, timedelta, timezone\n", "import pysolar.solar as solar\n", "import requests, io, time, warnings\n", "from tqdm.notebook import tqdm\n", "import statsmodels.api as sm\n", "import statsmodels.formula.api as smf\n", "from scipy import stats as sp_stats\n", "import matplotlib\n", "matplotlib.use('Agg')\n", "import matplotlib.pyplot as plt\n", "warnings.filterwarnings('ignore')\n", "print('✅ Imports OK')\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/46.9 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.9/46.9 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h✅ Imports OK\n" ] } ], "execution_count": null }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-nwIBinChEtn", "outputId": "19b215a5-d5cd-44f3-ae32-15ffe9acbd33" }, "source": [ "# Celda 2 — 16 sedes con ICAO CORREGIDOS (Filadelfia = KPHL)\n", "sedes = {\n", " 1: {'ciudad':'Ciudad de Mexico','icao':'MMMX','iem':'MMMX','lat':19.3029,'lon':-99.1505,'utc_offset':-6,'dist_km':10,'alt_m':2195},\n", " 2: {'ciudad':'Guadalajara','icao':'MMGL','iem':'MMGL','lat':20.6810,'lon':-103.4625,'utc_offset':-6,'dist_km':25,'alt_m':1560},\n", " 3: {'ciudad':'Monterrey','icao':'MMMY','iem':'MMMY','lat':25.6700,'lon':-100.2440,'utc_offset':-6,'dist_km':25,'alt_m':540},\n", " 4: {'ciudad':'Atlanta','icao':'KATL','iem':'KATL','lat':33.7553,'lon':-84.4006,'utc_offset':-5,'dist_km':15,'alt_m':320},\n", " 5: {'ciudad':'Dallas','icao':'KDFW','iem':'KDFW','lat':32.7473,'lon':-97.0945,'utc_offset':-6,'dist_km':20,'alt_m':180},\n", " 6: {'ciudad':'Houston','icao':'KHOU','iem':'KHOU','lat':29.6847,'lon':-95.4107,'utc_offset':-6,'dist_km':15,'alt_m':15},\n", " 7: {'ciudad':'Los Angeles','icao':'KLAX','iem':'KLAX','lat':33.9534,'lon':-118.3387,'utc_offset':-8,'dist_km':10,'alt_m':30},\n", " 8: {'ciudad':'Kansas City','icao':'KMCI','iem':'KMCI','lat':39.0489,'lon':-94.4839,'utc_offset':-6,'dist_km':20,'alt_m':270},\n", " 9: {'ciudad':'Miami','icao':'KMIA','iem':'KMIA','lat':25.9580,'lon':-80.2389,'utc_offset':-5,'dist_km':25,'alt_m':3},\n", " 10: {'ciudad':'Filadelfia','icao':'KPHL','iem':'PHL','lat':39.8744,'lon':-75.2424,'utc_offset':-5,'dist_km':7,'alt_m':10},\n", " 11: {'ciudad':'Boston','icao':'KBOS','iem':'KBOS','lat':42.0909,'lon':-71.2643,'utc_offset':-5,'dist_km':40,'alt_m':90},\n", " 12: {'ciudad':'Nueva York/NJ','icao':'KEWR','iem':'KEWR','lat':40.8128,'lon':-74.0742,'utc_offset':-5,'dist_km':10,'alt_m':5},\n", " 13: {'ciudad':'San Francisco','icao':'KSJC','iem':'KSJC','lat':37.4033,'lon':-121.9694,'utc_offset':-8,'dist_km':8,'alt_m':5},\n", " 14: {'ciudad':'Seattle','icao':'KSEA','iem':'KSEA','lat':47.5952,'lon':-122.3316,'utc_offset':-8,'dist_km':18,'alt_m':5},\n", " 15: {'ciudad':'Toronto','icao':'CYTZ','iem':'CYTZ','lat':43.6332,'lon':-79.4186,'utc_offset':-5,'dist_km':2,'alt_m':76},\n", " 16: {'ciudad':'Vancouver','icao':'CYVR','iem':'CYVR','lat':49.2768,'lon':-123.1118,'utc_offset':-8,'dist_km':15,'alt_m':0},\n", "}\n", "\n", "# Mapeo estadio → sede_id\n", "est_map = {\n", " 'Estadio Azteca':1,'Estadio Akron':2,'Estadio BBVA':3,'Mercedes-Benz Stadium':4,\n", " 'AT&T Stadium':5,'NRG Stadium':6,'SoFi Stadium':7,'Arrowhead Stadium':8,\n", " 'Hard Rock Stadium':9,'Lincoln Financial Field':10,'Gillette Stadium':11,\n", " 'MetLife Stadium':12,'Levis Stadium':13,'Lumen Field':14,'BMO Field':15,'BC Place':16\n", "}\n", "\n", "print(f'{len(sedes)} sedes definidas:')\n", "for eid, s in sedes.items():\n", " print(f' {s[\"ciudad\"]:20s}: {s[\"icao\"]} (IEM: {s[\"iem\"]}, {s[\"dist_km\"]} km, {s[\"alt_m\"]}m)')\n", "print(f'\\n⚠ Filadelfia ahora usa KPHL (PHL en IEM) a 7 km, no KTTN (30 km)')\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "16 sedes definidas:\n", " Ciudad de Mexico : MMMX (IEM: MMMX, 10 km, 2195m)\n", " Guadalajara : MMGL (IEM: MMGL, 25 km, 1560m)\n", " Monterrey : MMMY (IEM: MMMY, 25 km, 540m)\n", " Atlanta : KATL (IEM: KATL, 15 km, 320m)\n", " Dallas : KDFW (IEM: KDFW, 20 km, 180m)\n", " Houston : KHOU (IEM: KHOU, 15 km, 15m)\n", " Los Angeles : KLAX (IEM: KLAX, 10 km, 30m)\n", " Kansas City : KMCI (IEM: KMCI, 20 km, 270m)\n", " Miami : KMIA (IEM: KMIA, 25 km, 3m)\n", " Filadelfia : KPHL (IEM: PHL, 7 km, 10m)\n", " Boston : KBOS (IEM: KBOS, 40 km, 90m)\n", " Nueva York/NJ : KEWR (IEM: KEWR, 10 km, 5m)\n", " San Francisco : KSJC (IEM: KSJC, 8 km, 5m)\n", " Seattle : KSEA (IEM: KSEA, 18 km, 5m)\n", " Toronto : CYTZ (IEM: CYTZ, 2 km, 76m)\n", " Vancouver : CYVR (IEM: CYVR, 15 km, 0m)\n", "\n", "⚠ Filadelfia ahora usa KPHL (PHL en IEM) a 7 km, no KTTN (30 km)\n" ] } ], "execution_count": null }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 413, "referenced_widgets": [ "5a8b8c2fe93f4864a1c6c3eecd1b154e", "2a60552d9ca24ebb8bde706caffb288b", "1435bd36758d4edcbb4e3c8a85200330", "ba3fe51b37f04a90bb61716515cc18cd", "4d144546b6f545a496aaf49246b264a6", "d1bff2cc36d342ad95d7048fc1712737", "bab0258e9beb47449b68e08756e88a0a", "ce5c4b346b124a93aa6e3ad7d2cbfb1c", "01e0918b453b4f2992b8186f2ecd2db3", "3b4da1d71dba45d99550a0ff6d2d8947", "1ad9b04b2db6464898c59e7f2987ada9" ] }, "id": "DnnnsJXFhEtq", "outputId": "21629dd5-4e05-4937-b3d9-60f1fee5fe12" }, "source": [ "# Celda 3 — Descarga ASOS de las 16 sedes (con delays para evitar HTTP 429)\n", "BASE_URL = 'https://mesonet.agron.iastate.edu/cgi-bin/request/asos.py'\n", "datos_obs = {}\n", "info_estaciones = {}\n", "DELAY = 15 # segundos entre peticiones\n", "\n", "for eid, s in tqdm(sedes.items(), desc='Descargando ASOS'):\n", " try:\n", " station_code = s['iem']\n", " url = f'{BASE_URL}?station={station_code}'\n", " for d in ['tmpf','dwpf','relh','sknt']:\n", " url += f'&data={d}'\n", " url += '&year1=2026&month1=6&day1=1&year2=2026&month2=7&day2=22'\n", " url += '&tz=Etc/UTC&format=comma&latlon=yes&missing=M&direct=yes&report_type=3'\n", "\n", " resp = requests.get(url, timeout=30)\n", "\n", " # Reintento si rate limited\n", " if resp.status_code == 429:\n", " print(f' ⏳ Rate limited {s[\"ciudad\"]}, esperando 60s...')\n", " time.sleep(60)\n", " resp = requests.get(url, timeout=30)\n", "\n", " if resp.status_code != 200:\n", " print(f' ❌ {s[\"ciudad\"]} ({station_code}): HTTP {resp.status_code}')\n", " datos_obs[eid] = pd.DataFrame()\n", " time.sleep(DELAY)\n", " continue\n", "\n", " lines = resp.text.strip().split('\\n')\n", " header_idx = next(i for i, line in enumerate(lines) if not line.startswith('#'))\n", " csv_text = '\\n'.join(lines[header_idx:])\n", " df = pd.read_csv(io.StringIO(csv_text), low_memory=False)\n", "\n", " if df.empty or len(df) < 10:\n", " print(f' ❌ SIN DATOS {s[\"ciudad\"]} ({station_code}): {len(df)} registros')\n", " datos_obs[eid] = pd.DataFrame()\n", " time.sleep(DELAY)\n", " continue\n", "\n", " time_col = [c for c in df.columns if 'valid' in c.lower()]\n", " if not time_col:\n", " print(f' ❌ {s[\"ciudad\"]}: sin columna de tiempo')\n", " datos_obs[eid] = pd.DataFrame()\n", " time.sleep(DELAY)\n", " continue\n", "\n", " df['time'] = pd.to_datetime(df[time_col[0]], utc=True)\n", " df = df.set_index('time').sort_index()\n", "\n", " for col in ['tmpf','dwpf','relh','sknt']:\n", " if col in df.columns:\n", " df[col] = pd.to_numeric(df[col], errors='coerce')\n", "\n", " df['temp'] = (df['tmpf'] - 32) * 5/9\n", " df['rhum'] = df['relh']\n", " df['wspd'] = df['sknt'] * 0.5144\n", "\n", " df_h = df[['temp','rhum','wspd']].resample('1h').mean()\n", " datos_obs[eid] = df_h\n", " cob = df_h['temp'].notna().mean() * 100\n", " info_estaciones[eid] = {\n", " 'icao': s['icao'], 'iem': s['iem'], 'dist_km': s['dist_km'],\n", " 'registros': len(df_h), 'cobertura': f'{cob:.0f}%',\n", " 'temp_range': f\"{df_h['temp'].min():.1f} - {df_h['temp'].max():.1f} C\"\n", " }\n", " print(f' ✅ {s[\"ciudad\"]} ({station_code}): {len(df_h)} h, cob {cob:.0f}%, T {df_h[\"temp\"].min():.1f}-{df_h[\"temp\"].max():.1f}°C')\n", "\n", " except Exception as e:\n", " print(f' ❌ {s[\"ciudad\"]}: {e}')\n", " datos_obs[eid] = pd.DataFrame()\n", "\n", " time.sleep(DELAY)\n", "\n", "ok = sum(1 for v in datos_obs.values() if not v.empty)\n", "sin = [sedes[k]['ciudad'] for k, v in datos_obs.items() if v.empty]\n", "print(f'\\n{\"=\"*60}')\n", "print(f'Sedes con datos: {ok}/16')\n", "print(f'Sin datos: {sin}')\n", "if 'Guadalajara' in sin and len(sin) == 1:\n", " print('✅ Solo falta Guadalajara (esperado: ASOS mexicanos no en IEM)')\n", "elif len(sin) > 1:\n", " print('⚠ Faltan sedes además de Guadalajara. Re-ejecutar con más delay.')\n" ], "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "Descargando ASOS: 0%| | 0/16 [00:00= 32: return 'Extreme'\n", " if wbgt >= 30: return 'High'\n", " if wbgt >= 28: return 'Moderate'\n", " return 'Low'\n", "\n", "# Test\n", "print(f'Test Liljegren (33°C, 70%, 2.5 m/s, 500 W/m²): {calc_wbgt_liljegren(33,70,2.5,500):.1f}°C')\n", "print(f'Test sWBGT (33°C, 70%): {calc_swbgt(33,70):.1f}°C')\n", "print('✅ Funciones OK')\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Test Liljegren (33°C, 70%, 2.5 m/s, 500 W/m²): 30.5°C\n", "Test sWBGT (33°C, 70%): 29.8°C\n", "✅ Funciones OK\n" ] } ], "execution_count": null }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 105 }, "id": "sf1-UC6ShEt3", "outputId": "d134f58f-a56a-4f29-fbce-cdf8e3e2f436" }, "source": [ "# Celda 5 — Cargar calendario + datos ERA5 previos\n", "from google.colab import files\n", "print('Sube tu Excel (Mundial2026_Datos_Termicos_v6_FINAL.xlsx):')\n", "uploaded = files.upload()\n", "fname = list(uploaded.keys())[0]\n", "df_era5 = pd.read_excel(fname)\n", "df_era5['estadio_id'] = df_era5['A6_Estadio'].map(est_map)\n", "print(f'✅ Cargados {len(df_era5)} partidos, IDs mapeados: {df_era5[\"estadio_id\"].notna().sum()}/104')\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Sube tu Excel (Mundial2026_Datos_Termicos_v6_FINAL.xlsx):\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " \n", " Upload widget is only available when the cell has been executed in the\n", " current browser session. Please rerun this cell to enable.\n", " \n", " " ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Saving Mundial2026_Datos_Termicos_v6_FINAL (1).xlsx to Mundial2026_Datos_Termicos_v6_FINAL (1) (1).xlsx\n", "✅ Cargados 104 partidos, IDs mapeados: 104/104\n" ] } ], "execution_count": null }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 552, "referenced_widgets": [ "d32fd123693540e482c737441ba1df14", "e0c110fee938460c96fa70c838ec41d8", "b4351a5aab914373ae3d328f081e7494", "5f5838184c494963bbec7e176628e1d6", "20996146f0794c019dd1b40a5e080393", "90a1118af8a041218ed7196e949f9f4b", "9daff681a7ca4be4892a4f1d9201a264", "a726158af3e54d458b3aed03f1df5cbe", "df4ab8be122b454f8d4147a6dc5fd9e4", "406a24fc92be42a49743e4c6c79cf8ed", "661c9f05f3ae472ba0cc1096b41cce2f" ] }, "id": "2lqAWBZ5hEt6", "outputId": "30d9bca2-d683-4205-a909-0470182a7879" }, "source": [ "# Celda 6 — Pipeline: WBGT NOAA + sWBGT para los 104 partidos\n", "\n", "era5_col = 'B1_WBGT_max' if 'B1_WBGT_max' in df_era5.columns else 'B1_WBGT_OBS'\n", "era5_cat = 'B11_cat_riesgo' if 'B11_cat_riesgo' in df_era5.columns else 'B11_cat_riesgo_OBS'\n", "\n", "resultados = []\n", "\n", "for idx, p in tqdm(df_era5.iterrows(), total=len(df_era5), desc='Procesando'):\n", " eid = p.get('estadio_id')\n", " if pd.isna(eid):\n", " continue\n", " eid = int(eid)\n", " s = sedes[eid]\n", "\n", " df_obs = datos_obs.get(eid, pd.DataFrame())\n", " if df_obs.empty:\n", " resultados.append({\n", " 'A1_ID': int(p['A1_ID']), 'A2_Fecha': str(p['A2_Fecha'])[:10],\n", " 'A3_Hora_local': str(p['A3_Hora_local'])[:5],\n", " 'A5_Sede': s['ciudad'], 'A7_Equipos': p.get('A7_Equipos',''),\n", " 'B1_WBGT_NOAA': None, 'B1_sWBGT_NOAA': None,\n", " 'B1_WBGT_ERA5': p.get(era5_col),\n", " 'B1_WBGT_diff': None,\n", " 'B3_T_max_NOAA': None, 'B6_HR_media_NOAA': None,\n", " 'B7_grados_hora_28': None, 'B7_grados_hora_26': None, 'B7_grados_hora_30': None,\n", " 'B11_cat_NOAA': None, 'B11_cat_ERA5': p.get(era5_cat,''),\n", " 'Estacion': s['icao'], 'Dist_km': s['dist_km'],\n", " 'Horas': 0, 'C5_Pct_sombra': p.get('C5_Pct_sombra'),\n", " 'C7_Ocupacion': p.get('C7_Ocupacion'), 'Fuente': 'ERA5',\n", " })\n", " continue\n", "\n", " # Ventana de exposición: kickoff -2h a +4h\n", " try:\n", " fecha_str = str(p['A2_Fecha'])[:10]\n", " hora_str = str(p['A3_Hora_local'])[:5]\n", " if ':' not in hora_str: hora_str += ':00'\n", " hora_local = datetime.strptime(f'{fecha_str} {hora_str}', '%Y-%m-%d %H:%M')\n", " except:\n", " continue\n", "\n", " inicio = (hora_local - timedelta(hours=2) - timedelta(hours=s['utc_offset'])).replace(tzinfo=timezone.utc)\n", " fin = (hora_local + timedelta(hours=4) - timedelta(hours=s['utc_offset'])).replace(tzinfo=timezone.utc)\n", " ventana = df_obs.loc[(df_obs.index >= inicio) & (df_obs.index <= fin)].copy()\n", "\n", " if ventana.empty or ventana['temp'].isna().all():\n", " continue\n", "\n", " wbgt_vals = []; swbgt_vals = []; ta_vals = []; rh_vals = []\n", "\n", " for ts, row in ventana.iterrows():\n", " ta = row.get('temp', np.nan)\n", " rh = row.get('rhum', np.nan)\n", " ws = row.get('wspd', np.nan)\n", " if pd.isna(ta) or pd.isna(rh): continue\n", " if pd.isna(ws): ws = 1.0\n", "\n", " # Radiación pysolar (clear-sky)\n", " try:\n", " elev = solar.get_altitude(s['lat'], s['lon'], ts.to_pydatetime())\n", " rad = max(0, 1361 * np.sin(np.radians(elev)) * 0.70) if elev > 0 else 0.0\n", " except:\n", " rad = 0.0\n", "\n", " # Wind speed 10m → 2m (log profile, z0=0.01m)\n", " ws_2m = ws * (np.log(2/0.01) / np.log(10/0.01)) # factor ≈ 0.75\n", "\n", " w = calc_wbgt_liljegren(ta, rh, ws_2m, rad)\n", " sw = calc_swbgt(ta, rh)\n", " if not pd.isna(w):\n", " wbgt_vals.append(w)\n", " ta_vals.append(ta)\n", " rh_vals.append(rh)\n", " if not pd.isna(sw):\n", " swbgt_vals.append(sw)\n", "\n", " if not wbgt_vals:\n", " continue\n", "\n", " wbgt_arr = np.array(wbgt_vals)\n", " wbgt_max = float(np.max(wbgt_arr))\n", " swbgt_max = float(np.max(swbgt_vals)) if swbgt_vals else np.nan\n", " era5_val = p.get(era5_col, np.nan)\n", "\n", " resultados.append({\n", " 'A1_ID': int(p['A1_ID']),\n", " 'A2_Fecha': fecha_str,\n", " 'A3_Hora_local': hora_str,\n", " 'A5_Sede': s['ciudad'],\n", " 'A7_Equipos': p.get('A7_Equipos', ''),\n", " 'B1_WBGT_NOAA': round(wbgt_max, 2),\n", " 'B1_sWBGT_NOAA': round(swbgt_max, 2) if not pd.isna(swbgt_max) else None,\n", " 'B1_WBGT_ERA5': round(era5_val, 2) if pd.notna(era5_val) else None,\n", " 'B1_WBGT_diff': round(wbgt_max - era5_val, 2) if pd.notna(era5_val) else None,\n", " 'B3_T_max_NOAA': round(max(ta_vals), 1),\n", " 'B6_HR_media_NOAA': round(np.mean(rh_vals), 1),\n", " 'B7_grados_hora_28': round(sum(max(w - 28, 0) for w in wbgt_arr), 2),\n", " 'B7_grados_hora_26': round(sum(max(w - 26, 0) for w in wbgt_arr), 2),\n", " 'B7_grados_hora_30': round(sum(max(w - 30, 0) for w in wbgt_arr), 2),\n", " 'B11_cat_NOAA': cat_riesgo(wbgt_max),\n", " 'B11_cat_ERA5': p.get(era5_cat, ''),\n", " 'Estacion': s['icao'],\n", " 'Dist_km': s['dist_km'],\n", " 'Horas': len(wbgt_arr),\n", " 'C5_Pct_sombra': p.get('C5_Pct_sombra'),\n", " 'C7_Ocupacion': p.get('C7_Ocupacion'),\n", " 'Fuente': 'NOAA',\n", " })\n", "\n", "df_noaa = pd.DataFrame(resultados)\n", "dn = df_noaa[df_noaa['B1_WBGT_NOAA'].notna()].copy()\n", "\n", "print(f'\\n{\"=\"*60}')\n", "print(f'NOAA: {len(dn)} partidos en {dn[\"A5_Sede\"].nunique()} sedes')\n", "print(f'ERA5-only: {len(df_noaa) - len(dn)} partidos')\n", "print(f'\\nCategorías NOAA:')\n", "print(dn['B11_cat_NOAA'].value_counts().to_string())\n", "print(f'\\nRESUMEN POR SEDE:')\n", "sede = dn.groupby('A5_Sede').agg(\n", " WBGT_mean=('B1_WBGT_NOAA','mean'), WBGT_max=('B1_WBGT_NOAA','max'),\n", " n=('A1_ID','count'),\n", " n_mod=('B11_cat_NOAA', lambda x: (x=='Moderate').sum()),\n", " n_high=('B11_cat_NOAA', lambda x: (x=='High').sum()),\n", " bias=('B1_WBGT_diff','mean'),\n", ").sort_values('WBGT_mean', ascending=False)\n", "print(sede.round(2).to_string())\n" ], "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "Procesando: 0%| | 0/104 [00:00= inicio) & (df_obs.index <= fin)]\n", " ventana_rad = df_rad.loc[(df_rad.index >= inicio) & (df_rad.index <= fin)]\n", " if ventana_obs.empty or ventana_obs['temp'].isna().all(): continue\n", " wbgt_cs = []; wbgt_e5r = []\n", " for ts, row in ventana_obs.iterrows():\n", " ta = row.get('temp', np.nan); rh = row.get('rhum', np.nan); ws = row.get('wspd', np.nan)\n", " if pd.isna(ta) or pd.isna(rh): continue\n", " if pd.isna(ws): ws = 1.0\n", " ws_2m = ws * (np.log(2/0.01) / np.log(10/0.01))\n", " try:\n", " elev = solar.get_altitude(s['lat'], s['lon'], ts.to_pydatetime())\n", " rad_cs = max(0, 1361 * np.sin(np.radians(elev)) * 0.70) if elev > 0 else 0.0\n", " except: rad_cs = 0.0\n", " rad_e5 = 0.0\n", " if not ventana_rad.empty:\n", " idx_closest = ventana_rad.index.get_indexer([ts], method='nearest')[0]\n", " if idx_closest >= 0 and idx_closest < len(ventana_rad):\n", " rad_e5 = max(0, ventana_rad.iloc[idx_closest]['rad_era5'])\n", " wbgt_cs.append(calc_wbgt_liljegren(ta, rh, ws_2m, rad_cs))\n", " wbgt_e5r.append(calc_wbgt_liljegren(ta, rh, ws_2m, rad_e5))\n", " cs_arr = [x for x in wbgt_cs if not pd.isna(x)]\n", " e5_arr = [x for x in wbgt_e5r if not pd.isna(x)]\n", " if not cs_arr or not e5_arr: continue\n", " era5_val = p.get(era5_col, np.nan)\n", " resultados_corr.append({\n", " 'A1_ID': int(p['A1_ID']), 'A5_Sede': s['ciudad'],\n", " 'WBGT_clearsky': round(max(cs_arr), 2), 'WBGT_ERA5rad': round(max(e5_arr), 2),\n", " 'WBGT_ERA5': round(era5_val, 2) if pd.notna(era5_val) else None,\n", " 'cat_cs': cat_riesgo(max(cs_arr)), 'cat_e5r': cat_riesgo(max(e5_arr)),\n", " 'cat_era5': cat_riesgo(era5_val) if pd.notna(era5_val) else None,\n", " })\n", "df_corr = pd.DataFrame(resultados_corr)\n", "\n", "# Results\n", "bias_cs = (df_corr['WBGT_clearsky'] - df_corr['WBGT_ERA5']).mean()\n", "bias_e5r = (df_corr['WBGT_ERA5rad'] - df_corr['WBGT_ERA5']).mean()\n", "efecto_rad = (df_corr['WBGT_clearsky'] - df_corr['WBGT_ERA5rad']).mean()\n", "print(f'\\n{\"=\"*60}')\n", "print(f'SENSIBILIDAD A LA RADIACIÓN (n={len(df_corr)})')\n", "print(f'{\"=\"*60}')\n", "print(f' Bias total (clearsky vs ERA5): {bias_cs:+.2f}°C')\n", "print(f' Componente radiación: {efecto_rad:+.2f}°C ({abs(efecto_rad/bias_cs)*100:.0f}%)')\n", "print(f' Componente genuino (datos): {bias_e5r:+.2f}°C ({abs(bias_e5r/bias_cs)*100:.0f}%)')\n", "print(f'\\n Categorías clearsky: {df_corr[\"cat_cs\"].value_counts().to_dict()}')\n", "print(f' Categorías ERA5rad: {df_corr[\"cat_e5r\"].value_counts().to_dict()}')\n", "print(f' Categorías ERA5: {df_corr[\"cat_era5\"].value_counts().to_dict()}')\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Descargando radiación ERA5 para las 16 sedes...\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Radiación ERA5: 0%| | 0/16 [00:00 uloa) | (diff < lloa)).sum()\n", "\n", "print(f'\\nBLAND-ALTMAN:')\n", "print(f' Mean bias: {md:+.3f}°C')\n", "print(f' SD: {sd:.3f}°C')\n", "print(f' 95% LoA: [{lloa:.2f}, {uloa:.2f}]°C')\n", "print(f' 95% CI of bias: [{md-1.96*se_mean:.2f}, {md+1.96*se_mean:.2f}]')\n", "print(f' Proportional bias: r={r_pb:.3f}, p={p_pb:.4f}')\n", "print(f' Outside LoA: {outside}/{len(diff)} ({100*outside/len(diff):.1f}%)')\n", "\n", "# Gráficos\n", "fig, axes = plt.subplots(1, 4, figsize=(24, 5))\n", "\n", "# 1. Scatter\n", "ax = axes[0]\n", "colors_map = {'Low':'steelblue','Moderate':'orange','High':'red'}\n", "for cat in ['Low','Moderate','High']:\n", " mask = dn['B11_cat_NOAA']==cat\n", " if mask.sum()>0:\n", " ax.scatter(dn.loc[mask,'B1_WBGT_ERA5'], dn.loc[mask,'B1_WBGT_NOAA'],\n", " c=colors_map[cat], alpha=0.7, edgecolors='k', lw=0.5, s=50, label=f'{cat} ({mask.sum()})')\n", "ax.plot([12,33],[12,33],'k--',lw=1,alpha=0.5)\n", "ax.axhline(28,color='orange',ls=':',lw=1); ax.axhline(30,color='red',ls=':',lw=1)\n", "ax.set_xlabel('WBGT ERA5 (°C)'); ax.set_ylabel('WBGT NOAA (°C)')\n", "ax.set_title(f'NOAA vs ERA5 — R²={r**2:.3f}, RMSE={rmse:.1f}°C'); ax.legend(fontsize=8)\n", "ax.set_aspect('equal'); ax.set_xlim(12,33); ax.set_ylim(12,33)\n", "\n", "# 2. Bland-Altman\n", "ax = axes[1]\n", "for cat in ['Low','Moderate','High']:\n", " mask = dn['B11_cat_NOAA']==cat\n", " if mask.sum()>0:\n", " idx_mask = dn.index[mask]\n", " m_sub = (dn.loc[idx_mask,'B1_WBGT_NOAA'].values + dn.loc[idx_mask,'B1_WBGT_ERA5'].values)/2\n", " d_sub = dn.loc[idx_mask,'B1_WBGT_NOAA'].values - dn.loc[idx_mask,'B1_WBGT_ERA5'].values\n", " ax.scatter(m_sub, d_sub, c=colors_map[cat], alpha=0.7, edgecolors='k', lw=0.3, s=50, label=cat)\n", "ax.axhline(md, color='black', lw=1.5, label=f'Bias: {md:+.2f}°C')\n", "ax.axhline(uloa, color='gray', ls='--', lw=1, label=f'LoA: [{lloa:.1f}, {uloa:.1f}]')\n", "ax.axhline(lloa, color='gray', ls='--', lw=1)\n", "ax.axhline(0, color='lightgray', lw=0.5)\n", "ax.set_xlabel('Mean of NOAA and ERA5 WBGT (°C)'); ax.set_ylabel('NOAA − ERA5 (°C)')\n", "ax.set_title('Bland–Altman'); ax.legend(fontsize=7)\n", "\n", "# 3. Bias by venue\n", "ax = axes[2]\n", "sesgo = dn.groupby('A5_Sede')['B1_WBGT_diff'].mean().sort_values()\n", "colors_bar = ['crimson' if x>0 else 'steelblue' for x in sesgo.values]\n", "ax.barh(range(len(sesgo)), sesgo.values, color=colors_bar, edgecolor='black', lw=0.5)\n", "ax.set_yticks(range(len(sesgo))); ax.set_yticklabels(sesgo.index, fontsize=8)\n", "ax.axvline(0, color='k', lw=0.5); ax.set_xlabel('Bias NOAA − ERA5 (°C)'); ax.set_title('Bias by venue')\n", "\n", "# 4. Categories\n", "ax = axes[3]\n", "cats = ['Low','Moderate','High']\n", "e_c = [(dn['B11_cat_ERA5'].isin(['Bajo','Low']) if c=='Low' else dn['B11_cat_ERA5']==c).sum() for c in cats]\n", "n_c = [(dn['B11_cat_NOAA']==c).sum() for c in cats]\n", "x = np.arange(len(cats))\n", "ax.bar(x-0.2, e_c, 0.35, label='ERA5', color='lightblue', edgecolor='black', lw=0.5)\n", "ax.bar(x+0.2, n_c, 0.35, label='NOAA', color='salmon', edgecolor='black', lw=0.5)\n", "ax.set_xticks(x); ax.set_xticklabels(cats); ax.legend(); ax.set_title('Risk categories')\n", "\n", "plt.tight_layout()\n", "plt.savefig('NOAA_vs_ERA5_validation.png', dpi=200, bbox_inches='tight')\n", "plt.savefig('Bland_Altman.png', dpi=300, bbox_inches='tight')\n", "plt.show()\n", "print('✅ Figuras guardadas')\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "NOAA vs ERA5 (n=100)\n", " R² = 0.933, RMSE = 1.35°C, bias = +0.52°C\n", "\n", "BLAND-ALTMAN:\n", " Mean bias: +0.523°C\n", " SD: 1.253°C\n", " 95% LoA: [-1.93, 2.98]°C\n", " 95% CI of bias: [0.28, 0.77]\n", " Proportional bias: r=0.286, p=0.0039\n", " Outside LoA: 6/100 (6.0%)\n", "✅ Figuras guardadas\n" ] } ], "execution_count": null }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "wFKKtWcwhEuF", "outputId": "533ffd30-81e5-4488-e997-d98ea9f9a385" }, "source": [ "# Celda 9 — M5/M6: Todas las métricas para el artículo\n", "# ICC, Mixed model, sdh (INTEGRACIÓN HORARIA), Gini, Bootstrap, Leave-one-out\n", "\n", "dn = df_noaa[df_noaa['B1_WBGT_NOAA'].notna()].copy()\n", "n_matches = len(dn); n_venues = dn['A5_Sede'].nunique()\n", "\n", "# Añadir variables para modelo mixto\n", "for eid, s in sedes.items():\n", " mask = dn['A5_Sede'] == s['ciudad']\n", " dn.loc[mask, 'altitud'] = s['alt_m']\n", " dn.loc[mask, 'lat'] = s['lat']\n", "dn['hora_num'] = pd.to_numeric(dn['A3_Hora_local'].str.split(':').str[0], errors='coerce')\n", "dn['ocupacion'] = pd.to_numeric(dn['C7_Ocupacion'], errors='coerce')\n", "\n", "print(\"=\" * 70)\n", "print(f\"ANÁLISIS COMPLETO — {n_matches} partidos, {n_venues} sedes\")\n", "print(\"=\" * 70)\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 1. ICC\n", "# ══════════════════════════════════════════════════════════════\n", "groups = [g['B1_WBGT_NOAA'].values for _, g in dn.groupby('A5_Sede')]\n", "k = len(groups)\n", "ns = [len(g) for g in groups]; n_total = sum(ns)\n", "grand_mean = np.mean(np.concatenate(groups))\n", "SS_between = sum(len(g) * (np.mean(g) - grand_mean)**2 for g in groups)\n", "SS_within = sum(np.sum((g - np.mean(g))**2) for g in groups)\n", "MS_between = SS_between / (k - 1)\n", "MS_within = SS_within / (n_total - k)\n", "n0 = (n_total - sum(n**2 for n in ns) / n_total) / (k - 1)\n", "ICC = (MS_between - MS_within) / (MS_between + (n0 - 1) * MS_within)\n", "F_stat = MS_between / MS_within\n", "df1 = k - 1; df2 = n_total - k\n", "p_icc = 1 - sp_stats.f.cdf(F_stat, df1, df2)\n", "\n", "# CI for ICC (Shrout & Fleiss)\n", "FL = F_stat / sp_stats.f.ppf(0.975, df1, df2)\n", "FU = F_stat / sp_stats.f.ppf(0.025, df1, df2)\n", "ICC_lower = (FL - 1) / (FL + n0 - 1)\n", "ICC_upper = (FU - 1) / (FU + n0 - 1)\n", "\n", "print(f\"\\n1. ICC(1,1)\")\n", "print(f\" ICC = {ICC:.3f} (95% CI: {ICC_lower:.3f} – {ICC_upper:.3f})\")\n", "print(f\" F({df1},{df2}) = {F_stat:.1f}, p < {p_icc:.2e}\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 2. Leave-one-venue-out ICC\n", "# ══════════════════════════════════════════════════════════════\n", "print(f\"\\n2. LEAVE-ONE-VENUE-OUT ICC\")\n", "loo_results = {}\n", "for venue_out in dn['A5_Sede'].unique():\n", " dn_loo = dn[dn['A5_Sede'] != venue_out]\n", " g_loo = [g['B1_WBGT_NOAA'].values for _, g in dn_loo.groupby('A5_Sede')]\n", " k_l = len(g_loo); ns_l = [len(g) for g in g_loo]; n_l = sum(ns_l)\n", " gm_l = np.mean(np.concatenate(g_loo))\n", " ssb_l = sum(len(g) * (np.mean(g) - gm_l)**2 for g in g_loo)\n", " ssw_l = sum(np.sum((g - np.mean(g))**2) for g in g_loo)\n", " msb_l = ssb_l / (k_l - 1); msw_l = ssw_l / (n_l - k_l)\n", " n0_l = (n_l - sum(n**2 for n in ns_l) / n_l) / (k_l - 1)\n", " icc_l = (msb_l - msw_l) / (msb_l + (n0_l - 1) * msw_l)\n", " loo_results[venue_out] = icc_l\n", " print(f\" Excl. {venue_out:20s}: ICC = {icc_l:.3f}\")\n", "print(f\" Rango: {min(loo_results.values()):.3f} – {max(loo_results.values()):.3f}\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 3. Dispersion metrics\n", "# ══════════════════════════════════════════════════════════════\n", "venue_means = dn.groupby('A5_Sede')['B1_WBGT_NOAA'].mean().sort_values(ascending=False)\n", "cv = (venue_means.std() / venue_means.mean()) * 100\n", "gini_vals = venue_means.values\n", "n_g = len(gini_vals)\n", "gini = np.sum(np.abs(np.subtract.outer(gini_vals, gini_vals))) / (2 * n_g**2 * np.mean(gini_vals))\n", "iqr = np.percentile(venue_means, 75) - np.percentile(venue_means, 25)\n", "p90_p10 = np.percentile(venue_means, 90) - np.percentile(venue_means, 10)\n", "\n", "print(f\"\\n3. DISPERSIÓN\")\n", "print(f\" Media global: {venue_means.mean():.2f}°C\")\n", "print(f\" SD inter-sede: {venue_means.std():.2f}°C\")\n", "print(f\" CV: {cv:.1f}%\")\n", "print(f\" Gini: {gini:.3f}\")\n", "print(f\" IQR: {iqr:.2f}°C\")\n", "print(f\" P90-P10: {p90_p10:.2f}°C\")\n", "print(f\" Disparity: {venue_means.max():.2f} - {venue_means.min():.2f} = {venue_means.max()-venue_means.min():.2f}°C\")\n", "print(f\" Hottest: {venue_means.idxmax()} ({venue_means.max():.2f}°C)\")\n", "print(f\" Coolest: {venue_means.idxmin()} ({venue_means.min():.2f}°C)\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 4. Bootstrap CI for disparity\n", "# ══════════════════════════════════════════════════════════════\n", "hot_venue = venue_means.idxmax(); cold_venue = venue_means.idxmin()\n", "hot_vals = dn[dn['A5_Sede']==hot_venue]['B1_WBGT_NOAA'].values\n", "cold_vals = dn[dn['A5_Sede']==cold_venue]['B1_WBGT_NOAA'].values\n", "obs_diff = hot_vals.mean() - cold_vals.mean()\n", "t_stat, t_pval = sp_stats.ttest_ind(hot_vals, cold_vals)\n", "np.random.seed(42)\n", "boot_diffs = [np.random.choice(hot_vals, len(hot_vals), replace=True).mean() -\n", " np.random.choice(cold_vals, len(cold_vals), replace=True).mean() for _ in range(10000)]\n", "ci_lo = np.percentile(boot_diffs, 2.5); ci_hi = np.percentile(boot_diffs, 97.5)\n", "\n", "print(f\"\\n4. BOOTSTRAP DISPARITY\")\n", "print(f\" {hot_venue} (n={len(hot_vals)}): {hot_vals.mean():.2f} ± {hot_vals.std():.2f}°C\")\n", "print(f\" {cold_venue} (n={len(cold_vals)}): {cold_vals.mean():.2f} ± {cold_vals.std():.2f}°C\")\n", "print(f\" Disparity: {obs_diff:.2f}°C [95% CI: {ci_lo:.1f} – {ci_hi:.1f}]\")\n", "print(f\" t = {t_stat:.1f}, p = {t_pval:.2e}\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 5. Mixed model (sin shadow)\n", "# ══════════════════════════════════════════════════════════════\n", "dn['wbgt'] = dn['B1_WBGT_NOAA']\n", "dn['sede'] = dn['A5_Sede']\n", "model = smf.mixedlm(\"wbgt ~ hora_num + altitud + lat\", dn, groups=dn[\"sede\"])\n", "result = model.fit(reml=True)\n", "print(f\"\\n5. MODELO MIXTO: WBGT ~ hora + altitud + lat, (1|sede)\")\n", "print(result.summary())\n", "var_sede = float(result.cov_re.iloc[0, 0])\n", "var_resid = float(result.scale)\n", "icc_model = var_sede / (var_sede + var_resid)\n", "print(f\"\\n σ²(sede) = {var_sede:.3f}\")\n", "print(f\" σ²(resid) = {var_resid:.3f}\")\n", "print(f\" ICC_adj = {icc_model:.3f}\")\n", "\n", "# VIF\n", "from statsmodels.stats.outliers_influence import variance_inflation_factor\n", "X = dn[['hora_num', 'altitud', 'lat']].dropna()\n", "X_c = sm.add_constant(X)\n", "vifs = {X.columns[i]: variance_inflation_factor(X_c.values, i+1) for i in range(len(X.columns))}\n", "print(f\" VIFs: {', '.join(f'{k}={v:.2f}' for k,v in vifs.items())}\")\n", "\n", "# Residual diagnostics\n", "resids = result.resid\n", "w_stat, w_pval = sp_stats.shapiro(resids)\n", "fitted = result.fittedvalues\n", "r_het, p_het = sp_stats.spearmanr(fitted, np.abs(resids))\n", "print(f\" Shapiro-Wilk: W={w_stat:.3f}, p={w_pval:.3f}\")\n", "print(f\" Heteroscedasticity: r={r_het:.3f}, p={p_het:.3f}\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 6. Spectator-degree-hours (INTEGRACIÓN HORARIA)\n", "# ══════════════════════════════════════════════════════════════\n", "print(f\"\\n6. SPECTATOR-DEGREE-HOURS (integración horaria)\")\n", "for threshold in [26, 28, 30]:\n", " col = f'B7_grados_hora_{threshold}'\n", " if col in dn.columns:\n", " dn[f'sdh_{threshold}'] = dn[col].fillna(0) * dn['ocupacion'].fillna(0)\n", " total = dn[f'sdh_{threshold}'].sum()\n", " print(f\"\\n Umbral {threshold}°C: Total sdh = {total:,.0f}\")\n", " by_venue = dn.groupby('A5_Sede')[f'sdh_{threshold}'].sum().sort_values(ascending=False)\n", " for v, val in by_venue.items():\n", " if val > 0:\n", " print(f\" {v:20s}: {val:>12,.0f} ({100*val/total:.0f}%)\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 7. Threshold sensitivity table\n", "# ══════════════════════════════════════════════════════════════\n", "print(f\"\\n7. TABLA DE SENSIBILIDAD AL UMBRAL\")\n", "print(f\"{'Threshold':>10} | {'Source':>8} | {'Matches':>8} | {'%':>6} | {'Venues':>6} | {'sdh':>12} | {'Disparity':>10}\")\n", "print(\"-\" * 75)\n", "disp = venue_means.max() - venue_means.min()\n", "for u, src in [(26,'ACSM'), (28,'FIFPRO'), (30,'ACSM'), (32,'FIFA')]:\n", " n_above = (dn['B1_WBGT_NOAA'] >= u).sum()\n", " pct = 100 * n_above / n_matches\n", " n_v = dn[dn['B1_WBGT_NOAA'] >= u]['A5_Sede'].nunique()\n", " col = f'sdh_{u}'\n", " sdh = dn[col].sum() if col in dn.columns else 0\n", " print(f\" {u}°C | {src:>8} | {n_above:>8} | {pct:>5.1f}% | {n_v:>6} | {sdh:>12,.0f} | {disp:.2f}°C\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# 8. sWBGT comparison\n", "# ══════════════════════════════════════════════════════════════\n", "if 'B1_sWBGT_NOAA' in dn.columns and dn['B1_sWBGT_NOAA'].notna().sum() > 0:\n", " print(f\"\\n8. sWBGT vs LILJEGREN\")\n", " sw = dn['B1_sWBGT_NOAA']; lj = dn['B1_WBGT_NOAA']\n", " diff_sw = lj - sw\n", " r_sw, _ = sp_stats.pearsonr(sw.dropna(), lj[sw.notna()])\n", " pct_sw = 100 * (sw >= 18.4).sum() / len(sw)\n", " pct_lj = 100 * (lj >= 18.4).sum() / len(lj)\n", " disp_sw = dn.groupby('A5_Sede')['B1_sWBGT_NOAA'].mean().max() - dn.groupby('A5_Sede')['B1_sWBGT_NOAA'].mean().min()\n", " print(f\" Mean: sWBGT={sw.mean():.2f}, Liljegren={lj.mean():.2f}, diff={diff_sw.mean():+.2f}\")\n", " print(f\" ≥18.4%: sWBGT={pct_sw:.1f}%, Liljegren={pct_lj:.1f}% (Craig: 67%)\")\n", " print(f\" ≥28: sWBGT={(sw>=28).sum()}, Liljegren={(lj>=28).sum()}\")\n", " print(f\" ≥30: sWBGT={(sw>=30).sum()}, Liljegren={(lj>=30).sum()}\")\n", " print(f\" Disparity: sWBGT={disp_sw:.2f}, Liljegren={disp:.2f}\")\n", " print(f\" R²={r_sw**2:.3f}\")\n", "\n", "# ══════════════════════════════════════════════════════════════\n", "# SUMMARY TABLE\n", "# ══════════════════════════════════════════════════════════════\n", "print(f\"\\n{'='*70}\")\n", "print(\"RESUMEN PARA EL MANUSCRITO\")\n", "print(f\"{'='*70}\")\n", "print(f\" n = {n_matches} partidos, {n_venues} sedes\")\n", "print(f\" ICC = {ICC:.3f} [{ICC_lower:.3f}–{ICC_upper:.3f}], F({df1},{df2})={F_stat:.1f}\")\n", "print(f\" LOO ICC range: {min(loo_results.values()):.3f}–{max(loo_results.values()):.3f}\")\n", "print(f\" Disparity = {obs_diff:.2f}°C [{ci_lo:.1f}–{ci_hi:.1f}], t={t_stat:.1f}, p={t_pval:.1e}\")\n", "print(f\" Mixed model: hora={result.fe_params['hora_num']:.3f}, alt={result.fe_params['altitud']:.5f}, lat={result.fe_params['lat']:.3f}\")\n", "print(f\" ICC_adj = {icc_model:.3f}\")\n", "print(f\" Gini = {gini:.3f}, IQR = {iqr:.2f}, P90-P10 = {p90_p10:.2f}\")\n", "sdh28 = dn['sdh_28'].sum() if 'sdh_28' in dn.columns else 'N/A'\n", "print(f\" sdh_28 (hourly integration) = {sdh28:,.0f}\" if isinstance(sdh28, (int,float)) else f\" sdh_28 = {sdh28}\")\n", "print(f\" NOAA-ERA5: R²={r**2:.3f}, RMSE={rmse:.2f}, bias={bias:+.2f}\")\n", "print(f\" Bland-Altman: LoA=[{lloa:.2f}, {uloa:.2f}], prop.bias r={r_pb:.3f}\")\n" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "======================================================================\n", "ANÁLISIS COMPLETO — 100 partidos, 15 sedes\n", "======================================================================\n", "\n", "1. ICC(1,1)\n", " ICC = 0.707 (95% CI: 0.528 – 0.866)\n", " F(14,85) = 17.1, p < 1.11e-16\n", "\n", "2. LEAVE-ONE-VENUE-OUT ICC\n", " Excl. Ciudad de Mexico : ICC = 0.693\n", " Excl. Toronto : ICC = 0.733\n", " Excl. Los Angeles : ICC = 0.694\n", " Excl. San Francisco : ICC = 0.697\n", " Excl. Nueva York/NJ : ICC = 0.721\n", " Excl. Boston : ICC = 0.725\n", " Excl. Vancouver : ICC = 0.707\n", " Excl. Houston : ICC = 0.678\n", " Excl. Dallas : ICC = 0.675\n", " Excl. Filadelfia : ICC = 0.729\n", " Excl. Monterrey : ICC = 0.708\n", " Excl. Atlanta : ICC = 0.700\n", " Excl. Seattle : ICC = 0.740\n", " Excl. Miami : ICC = 0.687\n", " Excl. Kansas City : ICC = 0.714\n", " Rango: 0.675 – 0.740\n", "\n", "3. DISPERSIÓN\n", " Media global: 22.48°C\n", " SD inter-sede: 4.20°C\n", " CV: 18.7%\n", " Gini: 0.103\n", " IQR: 6.89°C\n", " P90-P10: 10.59°C\n", " Disparity: 28.78 - 16.32 = 12.46°C\n", " Hottest: Houston (28.78°C)\n", " Coolest: San Francisco (16.32°C)\n", "\n", "4. BOOTSTRAP DISPARITY\n", " Houston (n=7): 28.78 ± 1.89°C\n", " San Francisco (n=6): 16.32 ± 3.34°C\n", " Disparity: 12.46°C [95% CI: 9.0 – 15.1]\n", " t = 7.8, p = 8.82e-06\n", "\n", "5. MODELO MIXTO: WBGT ~ hora + altitud + lat, (1|sede)\n", " Mixed Linear Model Regression Results\n", "=======================================================\n", "Model: MixedLM Dependent Variable: wbgt \n", "No. Observations: 100 Method: REML \n", "No. Groups: 15 Scale: 5.9256 \n", "Min. group size: 4 Log-Likelihood: -254.8089\n", "Max. group size: 9 Converged: Yes \n", "Mean group size: 6.7 \n", "-------------------------------------------------------\n", " Coef. Std.Err. z P>|z| [0.025 0.975]\n", "-------------------------------------------------------\n", "Intercept 43.021 5.308 8.105 0.000 32.618 53.424\n", "hora_num -0.328 0.080 -4.127 0.000 -0.484 -0.172\n", "altitud -0.005 0.002 -2.613 0.009 -0.009 -0.001\n", "lat -0.374 0.133 -2.819 0.005 -0.634 -0.114\n", "Group Var 9.670 1.889 \n", "=======================================================\n", "\n", "\n", " σ²(sede) = 9.670\n", " σ²(resid) = 5.926\n", " ICC_adj = 0.620\n", " VIFs: hora_num=1.06, altitud=1.59, lat=1.54\n", " Shapiro-Wilk: W=0.975, p=0.050\n", " Heteroscedasticity: r=-0.076, p=0.454\n", "\n", "6. SPECTATOR-DEGREE-HOURS (integración horaria)\n", "\n", " Umbral 26°C: Total sdh = 19,421,179\n", " Houston : 7,572,113 (39%)\n", " Dallas : 5,433,677 (28%)\n", " Atlanta : 3,515,043 (18%)\n", " Miami : 1,852,711 (10%)\n", " Filadelfia : 906,711 (5%)\n", " Toronto : 73,922 (0%)\n", " Boston : 67,002 (0%)\n", "\n", " Umbral 28°C: Total sdh = 5,286,952\n", " Houston : 2,901,175 (55%)\n", " Dallas : 1,083,737 (20%)\n", " Atlanta : 1,014,714 (19%)\n", " Filadelfia : 185,698 (4%)\n", " Miami : 101,628 (2%)\n", "\n", " Umbral 30°C: Total sdh = 517,543\n", " Houston : 383,240 (74%)\n", " Atlanta : 118,053 (23%)\n", " Dallas : 16,249 (3%)\n", "\n", "7. TABLA DE SENSIBILIDAD AL UMBRAL\n", " Threshold | Source | Matches | % | Venues | sdh | Disparity\n", "---------------------------------------------------------------------------\n", " 26°C | ACSM | 31 | 31.0% | 7 | 19,421,179 | 12.46°C\n", " 28°C | FIFPRO | 17 | 17.0% | 5 | 5,286,952 | 12.46°C\n", " 30°C | ACSM | 5 | 5.0% | 3 | 517,543 | 12.46°C\n", " 32°C | FIFA | 0 | 0.0% | 0 | 0 | 12.46°C\n", "\n", "8. sWBGT vs LILJEGREN\n", " Mean: sWBGT=22.07, Liljegren=22.75, diff=+0.68\n", " ≥18.4%: sWBGT=74.0%, Liljegren=83.0% (Craig: 67%)\n", " ≥28: sWBGT=9, Liljegren=17\n", " ≥30: sWBGT=0, Liljegren=5\n", " Disparity: sWBGT=11.78, Liljegren=12.46\n", " R²=0.986\n", "\n", "======================================================================\n", "RESUMEN PARA EL MANUSCRITO\n", "======================================================================\n", " n = 100 partidos, 15 sedes\n", " ICC = 0.707 [0.528–0.866], F(14,85)=17.1\n", " LOO ICC range: 0.675–0.740\n", " Disparity = 12.46°C [9.0–15.1], t=7.8, p=8.8e-06\n", " Mixed model: hora=-0.328, alt=-0.00527, lat=-0.374\n", " ICC_adj = 0.620\n", " Gini = 0.103, IQR = 6.89, P90-P10 = 10.59\n", " sdh_28 (hourly integration) = 5,286,952\n", " NOAA-ERA5: R²=0.933, RMSE=1.35, bias=+0.52\n", " Bland-Altman: LoA=[-1.93, 2.98], prop.bias r=0.286\n" ] } ], "execution_count": null }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 52 }, "id": "2o5B40iXhEuJ", "outputId": "1f869961-2069-4c1b-e1fc-0697f85bd6c5" }, "source": [ "# Celda 10 — Exportar Excel definitivo\n", "output = 'Mundial2026_WBGT_NOAA_15sedes_DEFINITIVO.xlsx'\n", "\n", "dn_export = df_noaa[df_noaa['B1_WBGT_NOAA'].notna()].copy()\n", "if 'error' in dn_export.columns: dn_export = dn_export.drop(columns=['error'])\n", "\n", "sede_summary = dn_export.groupby('A5_Sede').agg(\n", " ICAO=('Estacion', 'first'), Dist_km=('Dist_km', 'first'),\n", " WBGT_mean=('B1_WBGT_NOAA','mean'), WBGT_max=('B1_WBGT_NOAA','max'),\n", " n=('A1_ID','count'),\n", " n_mod=('B11_cat_NOAA', lambda x: (x=='Moderate').sum()),\n", " n_high=('B11_cat_NOAA', lambda x: (x=='High').sum()),\n", " bias=('B1_WBGT_diff','mean'),\n", ").sort_values('WBGT_mean', ascending=False)\n", "\n", "with pd.ExcelWriter(output, engine='openpyxl') as writer:\n", " dn_export.to_excel(writer, sheet_name='Datos por partido', index=False)\n", " sede_summary.to_excel(writer, sheet_name='Resumen por sede')\n", " era5_only = df_noaa[df_noaa['B1_WBGT_NOAA'].isna()]\n", " if len(era5_only) > 0:\n", " era5_only.to_excel(writer, sheet_name='ERA5 only', index=False)\n", " if len(df_corr) > 0:\n", " df_corr.to_excel(writer, sheet_name='Rad sensitivity', index=False)\n", "\n", "from google.colab import files\n", "files.download(output)\n", "files.download('NOAA_vs_ERA5_validation.png')\n", "files.download('Bland_Altman.png')\n", "print(f'✅ Guardado: {output}')\n", "print(f' NOAA: {len(dn_export)} partidos, {dn_export[\"A5_Sede\"].nunique()} sedes')\n" ], "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "application/javascript": [ "\n", " async function download(id, filename, size) {\n", " if (!google.colab.kernel.accessAllowed) {\n", " return;\n", " }\n", " const div = document.createElement('div');\n", " const label = document.createElement('label');\n", " label.textContent = `Downloading \"${filename}\": `;\n", " div.appendChild(label);\n", " const progress = document.createElement('progress');\n", " progress.max = size;\n", " div.appendChild(progress);\n", " document.body.appendChild(div);\n", "\n", " const buffers = [];\n", " let downloaded = 0;\n", "\n", " const channel = await google.colab.kernel.comms.open(id);\n", " // Send a message to notify the kernel that we're ready.\n", " channel.send({})\n", "\n", " for await (const message of channel.messages) {\n", " // Send a message to notify the kernel that we're ready.\n", " channel.send({})\n", " if (message.buffers) {\n", " for (const buffer of message.buffers) {\n", " buffers.push(buffer);\n", " downloaded += buffer.byteLength;\n", " progress.value = downloaded;\n", " }\n", " }\n", " }\n", " const blob = new Blob(buffers, {type: 'application/binary'});\n", " const a = document.createElement('a');\n", " a.href = window.URL.createObjectURL(blob);\n", " a.download = filename;\n", " div.appendChild(a);\n", " a.click();\n", " div.remove();\n", " }\n", " " ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "application/javascript": [ "download(\"download_8b7a7947-62e5-4076-809d-b5b9d3194330\", \"Mundial2026_WBGT_NOAA_15sedes_DEFINITIVO.xlsx\", 23907)" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "application/javascript": [ "\n", " async function download(id, filename, size) {\n", " if (!google.colab.kernel.accessAllowed) {\n", " return;\n", " }\n", " const div = document.createElement('div');\n", " const label = document.createElement('label');\n", " label.textContent = `Downloading \"${filename}\": `;\n", " div.appendChild(label);\n", " const progress = document.createElement('progress');\n", " progress.max = size;\n", " div.appendChild(progress);\n", " document.body.appendChild(div);\n", "\n", " const buffers = [];\n", " let downloaded = 0;\n", "\n", " const channel = await google.colab.kernel.comms.open(id);\n", " // Send a message to notify the kernel that we're ready.\n", " channel.send({})\n", "\n", " for await (const message of channel.messages) {\n", " // Send a message to notify the kernel that we're ready.\n", " channel.send({})\n", " if (message.buffers) {\n", " for (const buffer of message.buffers) {\n", " buffers.push(buffer);\n", " downloaded += buffer.byteLength;\n", " progress.value = downloaded;\n", " }\n", " }\n", " }\n", " const blob = new Blob(buffers, {type: 'application/binary'});\n", " const a = document.createElement('a');\n", " a.href = window.URL.createObjectURL(blob);\n", " a.download = filename;\n", " div.appendChild(a);\n", " a.click();\n", " div.remove();\n", " }\n", " " ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "application/javascript": [ "download(\"download_09260754-2db1-44ca-aea5-83d5226c2d34\", \"NOAA_vs_ERA5_validation.png\", 322576)" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "application/javascript": [ "\n", " async function download(id, filename, size) {\n", " if (!google.colab.kernel.accessAllowed) {\n", " return;\n", " }\n", " const div = document.createElement('div');\n", " const label = document.createElement('label');\n", " label.textContent = `Downloading \"${filename}\": `;\n", " div.appendChild(label);\n", " const progress = document.createElement('progress');\n", " progress.max = size;\n", " div.appendChild(progress);\n", " document.body.appendChild(div);\n", "\n", " const buffers = [];\n", " let downloaded = 0;\n", "\n", " const channel = await google.colab.kernel.comms.open(id);\n", " // Send a message to notify the kernel that we're ready.\n", " channel.send({})\n", "\n", " for await (const message of channel.messages) {\n", " // Send a message to notify the kernel that we're ready.\n", " channel.send({})\n", " if (message.buffers) {\n", " for (const buffer of message.buffers) {\n", " buffers.push(buffer);\n", " downloaded += buffer.byteLength;\n", " progress.value = downloaded;\n", " }\n", " }\n", " }\n", " const blob = new Blob(buffers, {type: 'application/binary'});\n", " const a = document.createElement('a');\n", " a.href = window.URL.createObjectURL(blob);\n", " a.download = filename;\n", " div.appendChild(a);\n", " a.click();\n", " div.remove();\n", " }\n", " " ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "application/javascript": [ "download(\"download_99c40729-b30b-4b88-b52f-15664c7b6e92\", \"Bland_Altman.png\", 562568)" ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "✅ Guardado: Mundial2026_WBGT_NOAA_15sedes_DEFINITIVO.xlsx\n", " NOAA: 100 partidos, 15 sedes\n" ] } ], "execution_count": null } ] }