{ "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": { "version_major": 2, "version_minor": 0, "state": { "17b9474f79034385a89897499533063b": { "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_d9ab537b954d4fcdae8a7cb95ab5f26b", "IPY_MODEL_5907888b3a8e46648f3ab2c0e7780d70", "IPY_MODEL_3faed7bcfa104073bd843ad5081cef39" ], "layout": "IPY_MODEL_20c14d2e8aa649789f914b3dbbc2032b" } }, "d9ab537b954d4fcdae8a7cb95ab5f26b": { "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_a311c909c8284916bd17b1d79812d022", "placeholder": "​", "style": "IPY_MODEL_74129ea9231247719ad8bf23ec6faaf7", "value": "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.15.0.json: " } }, "5907888b3a8e46648f3ab2c0e7780d70": { "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_8e2adb7cc4474ead808af9c3ef565463", "max": 66336, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_3d4946f06c1448d18a1e6cc22c3ead46", "value": 66336 } }, "3faed7bcfa104073bd843ad5081cef39": { "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_e61f7870540a412eabda614be460ec23", "placeholder": "​", "style": "IPY_MODEL_0d4d88a50a054275968d609ee1186a3a", "value": " 535k/? [00:00<00:00, 17.7MB/s]" } }, "20c14d2e8aa649789f914b3dbbc2032b": { "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 } }, "a311c909c8284916bd17b1d79812d022": { "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 } }, "74129ea9231247719ad8bf23ec6faaf7": { "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": "" } }, "8e2adb7cc4474ead808af9c3ef565463": { "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 } }, "3d4946f06c1448d18a1e6cc22c3ead46": { "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": "" } }, "e61f7870540a412eabda614be460ec23": { "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 } }, "0d4d88a50a054275968d609ee1186a3a": { "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": "" } }, "a6d358077a174721969e2b2d6e91e58f": { "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_c49dccf55ca64b1da4008a6356ca0402", "IPY_MODEL_77c3abf5a21940598d6ff90445d77987", "IPY_MODEL_54ecef9065a94182b45e917106d52a8f" ], "layout": "IPY_MODEL_0f06e8e04a164d8eb4de201505fc883c" } }, "c49dccf55ca64b1da4008a6356ca0402": { "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_263841fa3b8f4e41a91e8f74b586dc66", "placeholder": "​", "style": "IPY_MODEL_d3fdd1e0694b4d5884b2b9ccff6ca274", "value": "models/default.zip: reconstructing file: 100%" } }, "77c3abf5a21940598d6ff90445d77987": { "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_93b470ba983b49759f7dccdfead17e66", "max": 394024071, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_0f697eec321e4ddf9430d43c03638a3e", "value": 394024071 } }, "54ecef9065a94182b45e917106d52a8f": { "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_e3cdd2c0f4734a94880296f7187fbdbf", "placeholder": "​", "style": "IPY_MODEL_979f07c3c9b144b789abdc1c17a1df67", "value": "  394MB /  394MB, 32.4MB/s  " } }, "0f06e8e04a164d8eb4de201505fc883c": { "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 } }, "263841fa3b8f4e41a91e8f74b586dc66": { "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 } }, "d3fdd1e0694b4d5884b2b9ccff6ca274": { "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": "" } }, "93b470ba983b49759f7dccdfead17e66": { "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 } }, "0f697eec321e4ddf9430d43c03638a3e": { "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": "" } }, "e3cdd2c0f4734a94880296f7187fbdbf": { "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 } }, "979f07c3c9b144b789abdc1c17a1df67": { "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": "" } }, "8986c74367554ac49cdb0471bc4186e2": { "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_55ae9e63388a40cea8f77214441b08c1", "IPY_MODEL_bc8d1ec50d0a4f739e865b5b2c141f50", "IPY_MODEL_b20ef2d996144b7bb7f4f95047995342" ], "layout": "IPY_MODEL_fe863e9e46e9492cbff2670d2ddec132" } }, "55ae9e63388a40cea8f77214441b08c1": { "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_069b90ed1e9f41a088dfef18e3ba52c2", "placeholder": "​", "style": "IPY_MODEL_0aaaaead074a4a91b501dd04e8c482f8", "value": "models/default.zip: downloading bytes: " } }, "bc8d1ec50d0a4f739e865b5b2c141f50": { "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_bb37f7277845455b8a74a8988884485a", "max": 394024071, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d4e0b05a386c41968d577436b8d902f8", "value": 393470381 } }, "b20ef2d996144b7bb7f4f95047995342": { "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_a1f4d99c24b84043ae0296612d4c7854", "placeholder": "​", "style": "IPY_MODEL_981fc047830e482e8aeb9da25253b48f", "value": "  393MB, 31.8MB/s  " } }, "fe863e9e46e9492cbff2670d2ddec132": { "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 } }, "069b90ed1e9f41a088dfef18e3ba52c2": { "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 } }, "0aaaaead074a4a91b501dd04e8c482f8": { "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": "" } }, "bb37f7277845455b8a74a8988884485a": { "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 } }, "d4e0b05a386c41968d577436b8d902f8": { "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": "" } }, "a1f4d99c24b84043ae0296612d4c7854": { "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 } }, "981fc047830e482e8aeb9da25253b48f": { "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": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "hQAtXLliOJef", "outputId": "134b5797-c249-4f51-b3c0-6a313edebff3" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/2.0 MB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m74.6 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m34.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m794.2/794.2 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m610.9/610.9 kB\u001b[0m \u001b[31m14.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m418.7/418.7 kB\u001b[0m \u001b[31m19.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h" ] } ], "source": [ "\n", "!pip -q install stanza pandas\n" ] }, { "cell_type": "code", "source": [ "\n", "import stanza\n", "\n", "# Mengunduh model Bahasa Indonesia\n", "stanza.download(\"id\")\n", "\n", "# Membuat pipeline POS Tagging\n", "nlp = stanza.Pipeline(\n", " lang=\"id\",\n", " processors=\"tokenize,pos\",\n", " verbose=False\n", ")\n", "\n", "print(\"Model POS Tagging Bahasa Indonesia berhasil disiapkan!\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 254, "referenced_widgets": [ "17b9474f79034385a89897499533063b", "d9ab537b954d4fcdae8a7cb95ab5f26b", "5907888b3a8e46648f3ab2c0e7780d70", "3faed7bcfa104073bd843ad5081cef39", "20c14d2e8aa649789f914b3dbbc2032b", "a311c909c8284916bd17b1d79812d022", "74129ea9231247719ad8bf23ec6faaf7", "8e2adb7cc4474ead808af9c3ef565463", "3d4946f06c1448d18a1e6cc22c3ead46", "e61f7870540a412eabda614be460ec23", "0d4d88a50a054275968d609ee1186a3a", "a6d358077a174721969e2b2d6e91e58f", "c49dccf55ca64b1da4008a6356ca0402", "77c3abf5a21940598d6ff90445d77987", "54ecef9065a94182b45e917106d52a8f", "0f06e8e04a164d8eb4de201505fc883c", "263841fa3b8f4e41a91e8f74b586dc66", "d3fdd1e0694b4d5884b2b9ccff6ca274", "93b470ba983b49759f7dccdfead17e66", "0f697eec321e4ddf9430d43c03638a3e", "e3cdd2c0f4734a94880296f7187fbdbf", "979f07c3c9b144b789abdc1c17a1df67", "8986c74367554ac49cdb0471bc4186e2", "55ae9e63388a40cea8f77214441b08c1", "bc8d1ec50d0a4f739e865b5b2c141f50", "b20ef2d996144b7bb7f4f95047995342", "fe863e9e46e9492cbff2670d2ddec132", "069b90ed1e9f41a088dfef18e3ba52c2", "0aaaaead074a4a91b501dd04e8c482f8", "bb37f7277845455b8a74a8988884485a", "d4e0b05a386c41968d577436b8d902f8", "a1f4d99c24b84043ae0296612d4c7854", "981fc047830e482e8aeb9da25253b48f" ] }, "id": "p7R2HTvMOVYJ", "outputId": "35991078-b89a-42aa-8938-65d719228519" }, "execution_count": 2, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.15.0.json: 0%| …" ], "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, "model_id": "17b9474f79034385a89897499533063b" } }, "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ "INFO:stanza:Downloaded file to /root/.cache/stanza/1.15.0/resources/resources.json\n", "INFO:stanza:Downloading default packages for language: id (Indonesian) ...\n", "Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n", "WARNING:huggingface_hub.utils._http:Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "models/default.zip: reconstructing file: 0%| | 0.00B / 394MB " ], "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, "model_id": "a6d358077a174721969e2b2d6e91e58f" } }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "models/default.zip: downloading bytes: | 0.00B " ], "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, "model_id": "8986c74367554ac49cdb0471bc4186e2" } }, "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ "INFO:stanza:Downloaded file to /root/.cache/stanza/1.15.0/resources/id/default.zip\n", "INFO:stanza:Finished downloading models and saved to /root/.cache/stanza/1.15.0/resources\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "Model POS Tagging Bahasa Indonesia berhasil disiapkan!\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "import pandas as pd\n", "\n", "def pos_tagging(kalimat):\n", " \"\"\"\n", " Memberikan label kelas kata pada kalimat Bahasa Indonesia.\n", " \"\"\"\n", " doc = nlp(kalimat)\n", " hasil = []\n", "\n", " for sentence in doc.sentences:\n", " for word in sentence.words:\n", " hasil.append({\n", " \"Kata\": word.text,\n", " \"POS Tag\": word.upos,\n", " \"Penjelasan\": word.upos\n", " })\n", "\n", " return pd.DataFrame(\n", " hasil,\n", " columns=[\"Kata\", \"POS Tag\", \"Penjelasan\"]\n", " )\n", "\n", "print(\"Fungsi POS Tagging berhasil dibuat.\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "AYgpSkjnOhzj", "outputId": "5ef399f2-307f-4de0-801c-d76f456869f5" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Fungsi POS Tagging berhasil dibuat.\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "kalimat = \"Mahasiswa Universitas Bhayangkara belajar Python di laboratorium.\"\n", "\n", "hasil = pos_tagging(kalimat)\n", "\n", "print(\"Kalimat:\", kalimat)\n", "display(hasil)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 317 }, "id": "Otgve225OkYs", "outputId": "f88c62ff-dd4f-4577-a76b-e1168b605570" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Kalimat: Mahasiswa Universitas Bhayangkara belajar Python di laboratorium.\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ " Kata POS Tag Penjelasan\n", "0 Mahasiswa PROPN PROPN\n", "1 Universitas PROPN PROPN\n", "2 Bhayangkara PROPN PROPN\n", "3 belajar VERB VERB\n", "4 Python PROPN PROPN\n", "5 di ADP ADP\n", "6 laboratorium NOUN NOUN\n", "7 . PUNCT PUNCT" ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
KataPOS TagPenjelasan
0MahasiswaPROPNPROPN
1UniversitasPROPNPROPN
2BhayangkaraPROPNPROPN
3belajarVERBVERB
4PythonPROPNPROPN
5diADPADP
6laboratoriumNOUNNOUN
7.PUNCTPUNCT
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", " \n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "hasil", "summary": "{\n \"name\": \"hasil\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"Kata\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 8,\n \"samples\": [\n \"Universitas\",\n \"di\",\n \"Mahasiswa\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POS Tag\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"VERB\",\n \"PUNCT\",\n \"ADP\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Penjelasan\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"VERB\",\n \"PUNCT\",\n \"ADP\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "\n", "daftar_kalimat = [\n", " \"Saya sedang belajar pemrograman Python.\",\n", " \"Mahasiswa membaca buku di perpustakaan.\",\n", " \"Dosen menjelaskan materi kecerdasan buatan.\",\n", " \"Indonesia memiliki banyak bahasa daerah.\",\n", " \"Teknologi berkembang dengan sangat cepat.\"\n", "]\n", "\n", "semua_hasil = []\n", "\n", "for nomor, kalimat in enumerate(daftar_kalimat, start=1):\n", " doc = nlp(kalimat)\n", "\n", " for sentence in doc.sentences:\n", " for word in sentence.words:\n", " semua_hasil.append({\n", " \"Nomor Kalimat\": nomor,\n", " \"Kalimat\": kalimat,\n", " \"Kata\": word.text,\n", " \"POS Tag\": word.upos\n", " })\n", "\n", "df_hasil = pd.DataFrame(semua_hasil)\n", "\n", "display(df_hasil)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 990 }, "id": "y32aFxXPOoUo", "outputId": "aedaa9f2-8172-4dfe-a59a-957352f75cb0" }, "execution_count": 5, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ " Nomor Kalimat Kalimat Kata \\\n", "0 1 Saya sedang belajar pemrograman Python. Saya \n", "1 1 Saya sedang belajar pemrograman Python. sedang \n", "2 1 Saya sedang belajar pemrograman Python. belajar \n", "3 1 Saya sedang belajar pemrograman Python. pemrograman \n", "4 1 Saya sedang belajar pemrograman Python. Python \n", "5 1 Saya sedang belajar pemrograman Python. . \n", "6 2 Mahasiswa membaca buku di perpustakaan. Mahasiswa \n", "7 2 Mahasiswa membaca buku di perpustakaan. membaca \n", "8 2 Mahasiswa membaca buku di perpustakaan. buku \n", "9 2 Mahasiswa membaca buku di perpustakaan. di \n", "10 2 Mahasiswa membaca buku di perpustakaan. perpustakaan \n", "11 2 Mahasiswa membaca buku di perpustakaan. . \n", "12 3 Dosen menjelaskan materi kecerdasan buatan. Dosen \n", "13 3 Dosen menjelaskan materi kecerdasan buatan. menjelaskan \n", "14 3 Dosen menjelaskan materi kecerdasan buatan. materi \n", "15 3 Dosen menjelaskan materi kecerdasan buatan. kecerdasan \n", "16 3 Dosen menjelaskan materi kecerdasan buatan. buatan \n", "17 3 Dosen menjelaskan materi kecerdasan buatan. . \n", "18 4 Indonesia memiliki banyak bahasa daerah. Indonesia \n", "19 4 Indonesia memiliki banyak bahasa daerah. memiliki \n", "20 4 Indonesia memiliki banyak bahasa daerah. banyak \n", "21 4 Indonesia memiliki banyak bahasa daerah. bahasa \n", "22 4 Indonesia memiliki banyak bahasa daerah. daerah \n", "23 4 Indonesia memiliki banyak bahasa daerah. . \n", "24 5 Teknologi berkembang dengan sangat cepat. Teknologi \n", "25 5 Teknologi berkembang dengan sangat cepat. berkembang \n", "26 5 Teknologi berkembang dengan sangat cepat. dengan \n", "27 5 Teknologi berkembang dengan sangat cepat. sangat \n", "28 5 Teknologi berkembang dengan sangat cepat. cepat \n", "29 5 Teknologi berkembang dengan sangat cepat. . \n", "\n", " POS Tag \n", "0 PRON \n", "1 AUX \n", "2 VERB \n", "3 NOUN \n", "4 PROPN \n", "5 PUNCT \n", "6 PROPN \n", "7 VERB \n", "8 NOUN \n", "9 ADP \n", "10 NOUN \n", "11 PUNCT \n", "12 PROPN \n", "13 VERB \n", "14 NOUN \n", "15 NOUN \n", "16 NOUN \n", "17 PUNCT \n", "18 PROPN \n", "19 VERB \n", "20 ADV \n", "21 NOUN \n", "22 NOUN \n", "23 PUNCT \n", "24 PROPN \n", "25 VERB \n", "26 ADP \n", "27 ADV \n", "28 ADJ \n", "29 PUNCT " ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Nomor KalimatKalimatKataPOS Tag
01Saya sedang belajar pemrograman Python.SayaPRON
11Saya sedang belajar pemrograman Python.sedangAUX
21Saya sedang belajar pemrograman Python.belajarVERB
31Saya sedang belajar pemrograman Python.pemrogramanNOUN
41Saya sedang belajar pemrograman Python.PythonPROPN
51Saya sedang belajar pemrograman Python..PUNCT
62Mahasiswa membaca buku di perpustakaan.MahasiswaPROPN
72Mahasiswa membaca buku di perpustakaan.membacaVERB
82Mahasiswa membaca buku di perpustakaan.bukuNOUN
92Mahasiswa membaca buku di perpustakaan.diADP
102Mahasiswa membaca buku di perpustakaan.perpustakaanNOUN
112Mahasiswa membaca buku di perpustakaan..PUNCT
123Dosen menjelaskan materi kecerdasan buatan.DosenPROPN
133Dosen menjelaskan materi kecerdasan buatan.menjelaskanVERB
143Dosen menjelaskan materi kecerdasan buatan.materiNOUN
153Dosen menjelaskan materi kecerdasan buatan.kecerdasanNOUN
163Dosen menjelaskan materi kecerdasan buatan.buatanNOUN
173Dosen menjelaskan materi kecerdasan buatan..PUNCT
184Indonesia memiliki banyak bahasa daerah.IndonesiaPROPN
194Indonesia memiliki banyak bahasa daerah.memilikiVERB
204Indonesia memiliki banyak bahasa daerah.banyakADV
214Indonesia memiliki banyak bahasa daerah.bahasaNOUN
224Indonesia memiliki banyak bahasa daerah.daerahNOUN
234Indonesia memiliki banyak bahasa daerah..PUNCT
245Teknologi berkembang dengan sangat cepat.TeknologiPROPN
255Teknologi berkembang dengan sangat cepat.berkembangVERB
265Teknologi berkembang dengan sangat cepat.denganADP
275Teknologi berkembang dengan sangat cepat.sangatADV
285Teknologi berkembang dengan sangat cepat.cepatADJ
295Teknologi berkembang dengan sangat cepat..PUNCT
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", " \n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df_hasil", "summary": "{\n \"name\": \"df_hasil\",\n \"rows\": 30,\n \"fields\": [\n {\n \"column\": \"Nomor Kalimat\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 1,\n \"max\": 5,\n \"num_unique_values\": 5,\n \"samples\": [\n 2,\n 5,\n 3\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Kalimat\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Mahasiswa membaca buku di perpustakaan.\",\n \"Teknologi berkembang dengan sangat cepat.\",\n \"Dosen menjelaskan materi kecerdasan buatan.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Kata\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 26,\n \"samples\": [\n \"buku\",\n \"Indonesia\",\n \"Saya\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POS Tag\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 9,\n \"samples\": [\n \"ADV\",\n \"AUX\",\n \"PUNCT\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "\n", "nama_file = \"hasil_pos_tagging.csv\"\n", "\n", "df_hasil.to_csv(\n", " nama_file,\n", " index=False,\n", " encoding=\"utf-8-sig\"\n", ")\n", "\n", "print(f\"Hasil berhasil disimpan ke {nama_file}\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "HnjeYxDPOs02", "outputId": "50be2668-aa51-4feb-d948-9c8c6aad012e" }, "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Hasil berhasil disimpan ke hasil_pos_tagging.csv\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "from google.colab import files\n", "\n", "files.download(\"hasil_pos_tagging.csv\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "id": "d404yo_OOv8U", "outputId": "504764be-b7cc-47f2-b315-ac20f33c14e4" }, "execution_count": 7, "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_22138e6d-ea8b-4dbf-8dcd-72079babbd1e\", \"hasil_pos_tagging.csv\", 1706)" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "\n", "kalimat_input = input(\"Masukkan kalimat Bahasa Indonesia: \")\n", "\n", "hasil_input = pos_tagging(kalimat_input)\n", "\n", "print(\"\\nHasil POS Tagging:\")\n", "display(hasil_input)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 321 }, "id": "yj5DsDgLOzg1", "outputId": "6d7c2fc1-190b-48a7-80b0-f596f7a29e1b" }, "execution_count": 9, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Masukkan kalimat Bahasa Indonesia: Sistem komputer memproses data dengan cepat.\n", "\n", "Hasil POS Tagging:\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ " Kata POS Tag Penjelasan\n", "0 Sistem PROPN PROPN\n", "1 komputer NOUN NOUN\n", "2 memproses VERB VERB\n", "3 data NOUN NOUN\n", "4 dengan SCONJ SCONJ\n", "5 cepat ADJ ADJ\n", "6 . PUNCT PUNCT" ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
KataPOS TagPenjelasan
0SistemPROPNPROPN
1komputerNOUNNOUN
2memprosesVERBVERB
3dataNOUNNOUN
4denganSCONJSCONJ
5cepatADJADJ
6.PUNCTPUNCT
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", " \n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "hasil_input", "summary": "{\n \"name\": \"hasil_input\",\n \"rows\": 7,\n \"fields\": [\n {\n \"column\": \"Kata\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"Sistem\",\n \"komputer\",\n \"cepat\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POS Tag\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 6,\n \"samples\": [\n \"PROPN\",\n \"NOUN\",\n \"PUNCT\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Penjelasan\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 6,\n \"samples\": [\n \"PROPN\",\n \"NOUN\",\n \"PUNCT\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "\n", "import os\n", "import urllib.request\n", "\n", "os.makedirs(\"dataset\", exist_ok=True)\n", "\n", "base_url = (\n", " \"https://raw.githubusercontent.com/\"\n", " \"UniversalDependencies/UD_Indonesian-GSD/master/\"\n", ")\n", "\n", "file_dataset = [\n", " \"id_gsd-ud-train.conllu\",\n", " \"id_gsd-ud-dev.conllu\",\n", " \"id_gsd-ud-test.conllu\"\n", "]\n", "\n", "for nama_file in file_dataset:\n", " url = base_url + nama_file\n", " lokasi = os.path.join(\"dataset\", nama_file)\n", "\n", " urllib.request.urlretrieve(url, lokasi)\n", "\n", " print(f\"Berhasil mengunduh: {nama_file}\")\n", "\n", "print(\"\\nDataset selesai diunduh.\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "jVp8v8uaO5Zg", "outputId": "e670380f-4d5b-4973-b9fd-5f460e4a4572" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Berhasil mengunduh: id_gsd-ud-train.conllu\n", "Berhasil mengunduh: id_gsd-ud-dev.conllu\n", "Berhasil mengunduh: id_gsd-ud-test.conllu\n", "\n", "Dataset selesai diunduh.\n" ] } ] }, { "cell_type": "markdown", "source": [ "\n", "# POS Tagging Bahasa Indonesia\n", "\n", "## Mata Kuliah\n", "Natural Language Processing (NLP)\n", "\n", "## Identitas Mahasiswa\n", "- Nama: Awang Andriansyah Hermawan\n", "- NPM: 202310715155\n", "- Program Studi: Informatika\n", "- Universitas: Universitas Bhayangkara Jakarta Raya\n", "\n", "## Deskripsi\n", "Proyek ini dibuat untuk memenuhi tugas mata kuliah\n", "Natural Language Processing (NLP). Proyek ini\n", "mengimplementasikan Part-of-Speech (POS) Tagging\n", "pada teks Bahasa Indonesia menggunakan Python dan\n", "library Stanza.\n", "\n", "POS Tagging merupakan proses pemberian label kelas\n", "kata pada setiap kata dalam kalimat, seperti kata\n", "benda, kata kerja, kata sifat, dan kata keterangan.\n", "\n", "## Tujuan\n", "1. Memahami konsep POS Tagging dalam NLP.\n", "2. Mengidentifikasi kelas kata dalam kalimat Bahasa Indonesia.\n", "3. Mengimplementasikan POS Tagging menggunakan Python.\n", "4. Menampilkan hasil pelabelan kelas kata dalam tabel.\n", "5. Menyimpan hasil pemrosesan ke dalam file CSV.\n", "\n", "## Teknologi yang Digunakan\n", "- Python\n", "- Google Colab\n", "- Stanza\n", "- Pandas\n", "- GitLab\n", "\n", "## Dataset\n", "Proyek ini menggunakan model Bahasa Indonesia dari\n", "Stanza untuk melakukan prediksi POS Tagging.\n", "\n", "Sebagai sumber korpus berlabel, proyek ini juga\n", "menggunakan dataset Universal Dependencies Indonesian-GSD.\n", "\n", "Repository dataset:\n", "https://github.com/UniversalDependencies/UD_Indonesian-GSD\n", "\n", "## Metode\n", "1. Menyiapkan lingkungan Python.\n", "2. Menginstal library Stanza dan Pandas.\n", "3. Mengunduh model Bahasa Indonesia.\n", "4. Memproses kalimat dan melakukan POS Tagging.\n", "5. Menampilkan kata beserta label kelas katanya.\n", "6. Menyimpan hasil pemrosesan ke CSV.\n", "\n", "Catatan: model Stanza yang digunakan pada implementasi\n", "awal merupakan model yang telah dilatih sebelumnya.\n", "Dataset Indonesian-GSD diunduh sebagai sumber korpus\n", "dan belum berarti digunakan untuk melatih ulang model.\n", "\n", "## Struktur Repository\n", "- POS_Tagging_Bahasa_Indonesia.ipynb\n", "- README.md\n", "- hasil_pos_tagging.csv\n", "\n", "## Cara Menjalankan\n", "1. Buka file notebook di Google Colab.\n", "2. Jalankan sel kode secara berurutan.\n", "3. Tunggu proses instalasi dan pengunduhan model.\n", "4. Masukkan kalimat Bahasa Indonesia.\n", "5. Periksa hasil POS Tagging.\n", "6. Unduh hasil dalam format CSV.\n", "\n", "## Batasan\n", "Hasil prediksi dapat mengandung kesalahan, khususnya\n", "pada kata ambigu, nama khusus, atau kalimat informal.\n", "Hasil perlu diperiksa kembali untuk memastikan\n", "ketepatan pelabelan kelas kata.\n", "\n", "## Sumber Referensi\n", "- Stanza: https://stanfordnlp.github.io/stanza/\n", "- Universal Dependencies:\n", " https://universaldependencies.org/\n", "- UD Indonesian-GSD:\n", " https://github.com/UniversalDependencies/UD_Indonesian-GSD\n" ], "metadata": { "id": "AvAKlJNFPZsz" } } ] }