{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"7e0d0f4dd30a4fa08f9a641aaa59baf1": {
"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_bb1cb884e5cb486a9e33cdaba843fada",
"IPY_MODEL_792ec092eb6743d19e60f0d7a8843688",
"IPY_MODEL_d3ebe0e1e6b5474dae6f738dd18264dd"
],
"layout": "IPY_MODEL_6440257e7f4a42e7aa4d96dfe3827881"
}
},
"bb1cb884e5cb486a9e33cdaba843fada": {
"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_4f163a031f1a49208293d0978fe26d5d",
"placeholder": "",
"style": "IPY_MODEL_0058544726e94e05acf831a6df4f1c7d",
"value": "Processing Files (1 / 1) : 100%"
}
},
"792ec092eb6743d19e60f0d7a8843688": {
"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_2f395f11916b4515b93c24465b4e48e3",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_35b5cd2c7ef04d3bb881d2f4700b2c21",
"value": 1
}
},
"d3ebe0e1e6b5474dae6f738dd18264dd": {
"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_f763cbfca2bd4688aef8b605389f4579",
"placeholder": "",
"style": "IPY_MODEL_0bb2a6b6ddd648ac8463d0c850a3fc3c",
"value": " 1.47MB / 1.47MB, 1.47MB/s "
}
},
"6440257e7f4a42e7aa4d96dfe3827881": {
"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
}
},
"4f163a031f1a49208293d0978fe26d5d": {
"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
}
},
"0058544726e94e05acf831a6df4f1c7d": {
"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": ""
}
},
"2f395f11916b4515b93c24465b4e48e3": {
"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": "20px"
}
},
"35b5cd2c7ef04d3bb881d2f4700b2c21": {
"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": ""
}
},
"f763cbfca2bd4688aef8b605389f4579": {
"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
}
},
"0bb2a6b6ddd648ac8463d0c850a3fc3c": {
"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": ""
}
},
"a08718fc8a5943d6b8dd272f3880d4eb": {
"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_fa03e95df4424e22997bfca81e9acf36",
"IPY_MODEL_5d685dc3de704f2aa75544003ccfe90a",
"IPY_MODEL_c9a39dc32bc84b828dfec4a2c9989a45"
],
"layout": "IPY_MODEL_bb5289e777b44e6785480f2e77105218"
}
},
"fa03e95df4424e22997bfca81e9acf36": {
"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_48441715d3d64a01847030a7aaf94bc9",
"placeholder": "",
"style": "IPY_MODEL_94579929df6f4bbaa3733c5e8fcea366",
"value": "New Data Upload : 100%"
}
},
"5d685dc3de704f2aa75544003ccfe90a": {
"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_1dac0cc9bafb40d69b6b8b3abb7d29a1",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_4670e0643f3c482f81a1de0a69647a8e",
"value": 1
}
},
"c9a39dc32bc84b828dfec4a2c9989a45": {
"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_bd87b04e9965453fbedd53f803c2bffc",
"placeholder": "",
"style": "IPY_MODEL_21d781d9116d453da21c02185ebf4824",
"value": " 1.47MB / 1.47MB, 1.47MB/s "
}
},
"bb5289e777b44e6785480f2e77105218": {
"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
}
},
"48441715d3d64a01847030a7aaf94bc9": {
"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
}
},
"94579929df6f4bbaa3733c5e8fcea366": {
"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": ""
}
},
"1dac0cc9bafb40d69b6b8b3abb7d29a1": {
"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": "20px"
}
},
"4670e0643f3c482f81a1de0a69647a8e": {
"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": ""
}
},
"bd87b04e9965453fbedd53f803c2bffc": {
"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
}
},
"21d781d9116d453da21c02185ebf4824": {
"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": ""
}
},
"d1771982607e45eaaa8537d0bacb0dec": {
"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_4ccacf691f294713b96e211671394466",
"IPY_MODEL_85968d457b2144f69cd121c614d27e23",
"IPY_MODEL_a1246a1c7fcf49f0a16fa4b07068c364"
],
"layout": "IPY_MODEL_bedafee9c7a54472a94c6b9dda6ce568"
}
},
"4ccacf691f294713b96e211671394466": {
"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_2c79ca9caea24696833ed45d90fa1839",
"placeholder": "",
"style": "IPY_MODEL_978172b31afe44588e2b46f93af20403",
"value": " ...atp_classifier_winner.pkl: 100%"
}
},
"85968d457b2144f69cd121c614d27e23": {
"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_5ff904971fb34e22a3b8368d21e8b46f",
"max": 1467838,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_ffe60093c6b5402ea9859926ce1c9d64",
"value": 1467838
}
},
"a1246a1c7fcf49f0a16fa4b07068c364": {
"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_85c51ce7a6404e298a097f1d1bfbe5bb",
"placeholder": "",
"style": "IPY_MODEL_8aa9a68f91864fcaaf7c293173a2c8f7",
"value": " 1.47MB / 1.47MB "
}
},
"bedafee9c7a54472a94c6b9dda6ce568": {
"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
}
},
"2c79ca9caea24696833ed45d90fa1839": {
"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
}
},
"978172b31afe44588e2b46f93af20403": {
"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": ""
}
},
"5ff904971fb34e22a3b8368d21e8b46f": {
"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
}
},
"ffe60093c6b5402ea9859926ce1c9d64": {
"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": ""
}
},
"85c51ce7a6404e298a097f1d1bfbe5bb": {
"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
}
},
"8aa9a68f91864fcaaf7c293173a2c8f7": {
"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",
"source": [
"## **Assignment #2: Classification, Regression, Clustering, Evaluation**"
],
"metadata": {
"id": "w84cR3AZIU0e"
}
},
{
"cell_type": "markdown",
"source": [
"`Version: April 2026`"
],
"metadata": {
"id": "sDxa7s952Ukh"
}
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "DNz7MhZdeUem"
},
"execution_count": 52,
"outputs": []
},
{
"cell_type": "markdown",
"source": [],
"metadata": {
"id": "xi3YxJnH2YGd"
}
},
{
"cell_type": "markdown",
"source": [
"### **Overview**\n",
"\n",
"In this assignment, you'll level up your data science toolkit. While the first assignment focused on the data, on this one you will practice:\n",
"\n",
"- Classification models\n",
"\n",
"- Regression models\n",
"\n",
"- Feature Engineering\n",
"\n",
"- Evaluations\n",
"\n",
"You’ll go from raw data to insights by building a full modeling pipeline, enhancing your dataset, and training different models.\n",
"\n",
"This assignment will be completed individually."
],
"metadata": {
"id": "n7afdXdxIbLA"
}
},
{
"cell_type": "markdown",
"source": [
"### **Objectives**\n",
"\n",
"You’ll gain hands-on experience in:\n",
"- Evaluation\n",
"- Classification\n",
"- Regression\n",
"- Dataset preparation\n",
"- Explore various data hubs\n",
"- Engineering meaningful features\n",
"- Communicating findings clearly - visually and verbally\n",
"\n",
"
"
],
"metadata": {
"id": "lJAPMumvIUyW"
}
},
{
"cell_type": "markdown",
"source": [
"### **Submission Guidelines**\n",
"\n",
"1. Please note that this assignmnet must be submitted alone.\n",
"2. Submit the link to your HugingFace Model.\n",
"\n",
"Your HF model should include:\n",
"- README file: explanations, visuals, insights, etc.\n",
"- **Video**: Include the video of your presentation in the README file.\n",
"- **Python Notebook**: upload a copy of this notebook, with all of your coding work. Do not submit a Colab link; include the `.ipynb` file in the HF model.\n",
"- **ML Models:** Upload your models.\n",
"\n",
"Note: Students may be randomly chosen to present their work in a quick online session with the T.A., typically lasting ±10 minutes. Similar to Peer Review.\n",
"\n",
"
\n",
"\n"
],
"metadata": {
"id": "MwRmaJBiIjMR"
}
},
{
"cell_type": "markdown",
"source": [
"### **Evaluation Criteria**\n",
"\n",
"* **Data Handling & EDA (20%)**\n",
" Thoughtful and thorough data cleaning; handling of missing values, outliers, duplicates, and more; well-chosen visualizations; clear statistical summaries; use of EDA to guide modeling choices.\n",
"\n",
"* **Feature Engineering (20%)**\n",
" Creative and effective feature creation, transformation, encoding, selection, scaling, and more; integration of clustering results as features; clear explanation of feature choices and their impact.\n",
"\n",
"* **Model Training (20%)**\n",
" Appropriate selection of models; correct train/test split; reproducible code; logical modeling workflow with a solid baseline and improvements post-feature engineering. An iterative process.\n",
"\n",
"* **Evaluation & Interpretation (20%)**\n",
" Use of relevant evaluation metrics; structured model comparison; use of feature importance or visualizations to interpret results; clear discussion of what the model learned and how it performed.\n",
"\n",
"* **Presentation (20%)**\n",
" 4–6 minute video with clear delivery; structured narrative; visuals that support the explanation; confident, professional communication of findings and lessons.\n",
"\n",
"* **Bonus (up to +10%)**\n",
" Extra work such as trying data science tools, creative visualizations, advanced hyper param tuning, interactive dashboards, and deeper business/domain insights.\n",
"\n",
"* **Late Submission (-10% per day)**\n",
" Assignments submitted after the deadline will receive a 10% penalty per day.\n",
"\n",
"
"
],
"metadata": {
"id": "hD9SZmagIjOV"
}
},
{
"cell_type": "markdown",
"source": [
"### **Additional Guidelines**\n",
"\n",
"- The first thing you should do is download a copy of this notebook to your drive.\n",
"- Keep your dataset size manageable. If the dataset is too large, you can sample a subset.\n",
"- Run on Colab (CPU is fine). Colab free is enough. No GPU needed.\n",
"- You may use any Python package (scikit-learn, xgboost, lightgbm, catboost, etc.).\n",
"- No SHAP required. Use `feature_importances`, and similar tools.\n",
"- Make sure your results are reproducible (set **seeds** where needed).\n",
"- Be thoughtful with your cluster features — only use them if they help!\n",
"- Your presentation should tell a story; what worked, what didn’t, and why.\n",
"- Be creative, but also rigorous."
],
"metadata": {
"id": "h3vpVHSxIUwI"
}
},
{
"cell_type": "markdown",
"source": [
"### Assignment High-level Flow"
],
"metadata": {
"id": "7lTH1B5b5c12"
}
},
{
"cell_type": "markdown",
"source": [
""
],
"metadata": {
"id": "EK9fe2XygjgM"
}
},
{
"cell_type": "markdown",
"source": [
"
\n",
"\n",
"---\n",
"\n",
"---\n",
"\n",
"
"
],
"metadata": {
"id": "6kUonEv8Ipkp"
}
},
{
"cell_type": "markdown",
"source": [
"imports"
],
"metadata": {
"id": "acyYQrhPdEhB"
}
},
{
"cell_type": "code",
"source": [
"import os\n",
"import random\n",
"from pathlib import Path\n",
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"import seaborn\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import seaborn as sns\n",
"from pathlib import Path\n"
],
"metadata": {
"id": "H9ZazAMOc5jC"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Set Seeds"
],
"metadata": {
"id": "TPaWKBWmdGNF"
}
},
{
"cell_type": "code",
"source": [
"SEED = 42\n",
"\n",
"random.seed(SEED)\n",
"np.random.seed(SEED)\n",
"os.environ['PYTHONHASHSEED'] = str(SEED)\n",
"\n"
],
"metadata": {
"id": "zBaCUY21dHeF"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"For Jupyter Notebooks"
],
"metadata": {
"id": "INAizD1WeZcf"
}
},
{
"cell_type": "code",
"source": [
"%matplotlib inline\n",
"sns.set_theme(style=\"whitegrid\", context=\"notebook\")\n",
"plt.rcParams[\"figure.figsize\"] = (10, 6)\n",
"%config InlineBackend.figure_format = 'retina'"
],
"metadata": {
"id": "G0hg5eohd4s-"
},
"execution_count": 4,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Warnings"
],
"metadata": {
"id": "UwSXkPGvecLK"
}
},
{
"cell_type": "code",
"source": [
"import warnings\n",
"warnings.filterwarnings('ignore')"
],
"metadata": {
"id": "Nk9C78G3d7vp"
},
"execution_count": 5,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"
\n",
"\n",
"---\n",
"\n",
"
"
],
"metadata": {
"id": "evFmlLbzdgBj"
}
},
{
"cell_type": "markdown",
"source": [
"# **Part 1: Select a Regression Dataset**\n",
"\n",
"1. Choose a numeric & categorical tabular dataset. If you prefer, you may use open-source datasets; [Hugginface](https://huggingface.co/datasets?task_categories=task_categories:tabular-classification&sort=trending), [Kaggle](https://www.kaggle.com/datasets?tags=13302-Classification&minUsabilityRating=8.00+or+higher), etc.\n",
"\n",
"2. Avoid choosing a \"basic\"/\"small\" dataset.\n",
" - 10K rows and more.\n",
" - 15 features and more.\n",
" - Mix of Numeric & Categorial features are a must.\n",
"\n",
"3. The Label (target variable) is numeric.\n",
"\n",
"4. Please submit your dataset [here](https://forms.gle/zS8aZbBzuBV2z7wZ7), to share it with the class so everyone can see.\n",
"And make sure your chosen dataset is unique using this [link](https://docs.google.com/spreadsheets/d/1M8uojrzhSyVnOlSAJpzCKxrhWdzPR77k4x8Kxvr8VDk/edit?usp=sharing).\n",
"\n",
" *Note: Due to their popularity, the following are datasets you may not choose.*\n",
" > - Iris dataset\n",
" > - Wine dataset\n",
" > - Titanic dataset\n",
" > - Boston Housing dataset\n",
" > - ImageNet, Cifar, CelebFaces, IMDB\n",
"\n",
"5. Choose a dataset with a combination of numeric and textual values. This way you would have enough information to work on.\n",
"\n",
"6. Briefly describe your chosen dataset (source, size, features) and the question you want to answer."
],
"metadata": {
"id": "a_vsO0Q1IOMT"
}
},
{
"cell_type": "code",
"source": [
"#Data explanation"
],
"metadata": {
"id": "0rd-8KEclePe"
},
"execution_count": 6,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"My data set has Tennis games from 200-2017, Each match record describes the tournament (surface, level, round, format, date) and the two players (name, hand, height, age, country, and ATP rank).\n",
"It also records what happened: the final score, the duration in minutes, and on-court stats like aces, double faults, and break points."
],
"metadata": {
"id": "GFaHgQJyKwa5"
}
},
{
"cell_type": "code",
"source": [
"#The question"
],
"metadata": {
"id": "kKpEMf9sjhYV"
},
"execution_count": 7,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Which pre-match factors most strongly determine how long an ATP match lasts, and how accurately can a model predict match duration in minutes from those factors alone?\n"
],
"metadata": {
"id": "feShpqqn1hn5"
}
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "n0PmH7SrlzMq"
},
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"source": [
"os.makedirs(\"/root/.kaggle\", exist_ok=True)\n",
"!cp /content/kaggle.json /root/.kaggle/kaggle.json\n",
"!chmod 600 /root/.kaggle/kaggle.json\n",
"!pip install kaggle --quiet\n",
"!kaggle datasets download -d gmadevs/atp-matches-dataset -p /content/atp_data --unzip --force\n",
"\n",
"print(\"\\nFiles in /content/atp_data:\")\n",
"!ls /content/atp_data | head -30"
],
"metadata": {
"id": "OI0MZzohKwfE",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "f986a7c4-8028-4391-b488-f971d174a049"
},
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"cp: cannot stat '/content/kaggle.json': No such file or directory\n",
"chmod: cannot access '/root/.kaggle/kaggle.json': No such file or directory\n",
"Dataset URL: https://www.kaggle.com/datasets/gmadevs/atp-matches-dataset\n",
"License(s): CC-BY-NC-SA-4.0\n",
"Downloading atp-matches-dataset.zip to /content/atp_data\n",
"100% 2.69M/2.69M [00:00<00:00, 168MB/s]\n",
"\n",
"\n",
"Files in /content/atp_data:\n",
"atp_matches_2000.csv\n",
"atp_matches_2001.csv\n",
"atp_matches_2002.csv\n",
"atp_matches_2003.csv\n",
"atp_matches_2004.csv\n",
"atp_matches_2005.csv\n",
"atp_matches_2006.csv\n",
"atp_matches_2007.csv\n",
"atp_matches_2008.csv\n",
"atp_matches_2009.csv\n",
"atp_matches_2010.csv\n",
"atp_matches_2011.csv\n",
"atp_matches_2012.csv\n",
"atp_matches_2013.csv\n",
"atp_matches_2014.csv\n",
"atp_matches_2015.csv\n",
"atp_matches_2016.csv\n",
"atp_matches_2017.csv\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"DATA_DIR = Path(\"/content/atp_data\")\n",
"YEARS = range(2000, 2018) # 2000–2017 inclusive\n",
"\n",
"# Auto-find the CSVs (gmadevs sometimes nests them in a subfolder)\n",
"csv_files = sorted(DATA_DIR.rglob(\"atp_matches_*.csv\"))\n",
"print(f\"Found {len(csv_files)} ATP match CSVs\")\n",
"\n",
"dfs = []\n",
"for f in csv_files:\n",
" try:\n",
" year = int(f.stem.split(\"_\")[-1])\n",
" except ValueError:\n",
" continue\n",
" if year in YEARS:\n",
" df_y = pd.read_csv(f, low_memory=False)\n",
" df_y[\"source_year\"] = year\n",
" dfs.append(df_y)\n",
"\n",
"df = pd.concat(dfs, ignore_index=True)\n",
"print(f\"\\nLoaded {len(df):,} matches across {df['source_year'].nunique()} years\")\n",
"print(f\"Columns ({df.shape[1]}): {df.columns.tolist()}\")\n",
"df.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 321
},
"id": "lQ6NS60JisUT",
"outputId": "ad82eb2f-1a51-4a02-cbfe-07cf2a185378"
},
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Found 18 ATP match CSVs\n",
"\n",
"Loaded 53,571 matches across 18 years\n",
"Columns (50): ['tourney_id', 'tourney_name', 'surface', 'draw_size', 'tourney_level', 'tourney_date', 'match_num', 'winner_id', 'winner_seed', 'winner_entry', 'winner_name', 'winner_hand', 'winner_ht', 'winner_ioc', 'winner_age', 'winner_rank', 'winner_rank_points', 'loser_id', 'loser_seed', 'loser_entry', 'loser_name', 'loser_hand', 'loser_ht', 'loser_ioc', 'loser_age', 'loser_rank', 'loser_rank_points', 'score', 'best_of', 'round', 'minutes', 'w_ace', 'w_df', 'w_svpt', 'w_1stIn', 'w_1stWon', 'w_2ndWon', 'w_SvGms', 'w_bpSaved', 'w_bpFaced', 'l_ace', 'l_df', 'l_svpt', 'l_1stIn', 'l_1stWon', 'l_2ndWon', 'l_SvGms', 'l_bpSaved', 'l_bpFaced', 'source_year']\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
" tourney_id tourney_name surface draw_size tourney_level tourney_date \\\n",
"0 2000-717 Orlando Clay 32 A 20000501.0 \n",
"1 2000-717 Orlando Clay 32 A 20000501.0 \n",
"2 2000-717 Orlando Clay 32 A 20000501.0 \n",
"3 2000-717 Orlando Clay 32 A 20000501.0 \n",
"4 2000-717 Orlando Clay 32 A 20000501.0 \n",
"\n",
" match_num winner_id winner_seed winner_entry ... l_ace l_df l_svpt \\\n",
"0 1.0 102179 NaN NaN ... 13.0 4.0 110.0 \n",
"1 2.0 103602 NaN Q ... 0.0 0.0 57.0 \n",
"2 3.0 103387 NaN NaN ... 2.0 2.0 65.0 \n",
"3 4.0 101733 NaN NaN ... 4.0 6.0 104.0 \n",
"4 5.0 101727 4.0 NaN ... 0.0 3.0 47.0 \n",
"\n",
" l_1stIn l_1stWon l_2ndWon l_SvGms l_bpSaved l_bpFaced source_year \n",
"0 59.0 49.0 31.0 17.0 4.0 4.0 2000 \n",
"1 24.0 13.0 17.0 10.0 4.0 9.0 2000 \n",
"2 39.0 22.0 10.0 8.0 6.0 10.0 2000 \n",
"3 57.0 35.0 24.0 15.0 6.0 11.0 2000 \n",
"4 28.0 17.0 10.0 8.0 3.0 6.0 2000 \n",
"\n",
"[5 rows x 50 columns]"
],
"text/html": [
"\n",
"
| \n", " | tourney_id | \n", "tourney_name | \n", "surface | \n", "draw_size | \n", "tourney_level | \n", "tourney_date | \n", "match_num | \n", "winner_id | \n", "winner_seed | \n", "winner_entry | \n", "... | \n", "l_ace | \n", "l_df | \n", "l_svpt | \n", "l_1stIn | \n", "l_1stWon | \n", "l_2ndWon | \n", "l_SvGms | \n", "l_bpSaved | \n", "l_bpFaced | \n", "source_year | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "2000-717 | \n", "Orlando | \n", "Clay | \n", "32 | \n", "A | \n", "20000501.0 | \n", "1.0 | \n", "102179 | \n", "NaN | \n", "NaN | \n", "... | \n", "13.0 | \n", "4.0 | \n", "110.0 | \n", "59.0 | \n", "49.0 | \n", "31.0 | \n", "17.0 | \n", "4.0 | \n", "4.0 | \n", "2000 | \n", "
| 1 | \n", "2000-717 | \n", "Orlando | \n", "Clay | \n", "32 | \n", "A | \n", "20000501.0 | \n", "2.0 | \n", "103602 | \n", "NaN | \n", "Q | \n", "... | \n", "0.0 | \n", "0.0 | \n", "57.0 | \n", "24.0 | \n", "13.0 | \n", "17.0 | \n", "10.0 | \n", "4.0 | \n", "9.0 | \n", "2000 | \n", "
| 2 | \n", "2000-717 | \n", "Orlando | \n", "Clay | \n", "32 | \n", "A | \n", "20000501.0 | \n", "3.0 | \n", "103387 | \n", "NaN | \n", "NaN | \n", "... | \n", "2.0 | \n", "2.0 | \n", "65.0 | \n", "39.0 | \n", "22.0 | \n", "10.0 | \n", "8.0 | \n", "6.0 | \n", "10.0 | \n", "2000 | \n", "
| 3 | \n", "2000-717 | \n", "Orlando | \n", "Clay | \n", "32 | \n", "A | \n", "20000501.0 | \n", "4.0 | \n", "101733 | \n", "NaN | \n", "NaN | \n", "... | \n", "4.0 | \n", "6.0 | \n", "104.0 | \n", "57.0 | \n", "35.0 | \n", "24.0 | \n", "15.0 | \n", "6.0 | \n", "11.0 | \n", "2000 | \n", "
| 4 | \n", "2000-717 | \n", "Orlando | \n", "Clay | \n", "32 | \n", "A | \n", "20000501.0 | \n", "5.0 | \n", "101727 | \n", "4.0 | \n", "NaN | \n", "... | \n", "0.0 | \n", "3.0 | \n", "47.0 | \n", "28.0 | \n", "17.0 | \n", "10.0 | \n", "8.0 | \n", "3.0 | \n", "6.0 | \n", "2000 | \n", "
5 rows × 50 columns
\n", "