Post-Tagging-MK-NLP/postTagging.ipynb

1704 lines
64 KiB
Plaintext
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"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": {
"703e00ba7a654c29856b37562a0da8cc": {
"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_a22860bf9581407e8ed7ffad6f246d7a",
"IPY_MODEL_f8046c4f9b3f403e89f0628d4f7fd518",
"IPY_MODEL_89711a863681423b95041b3e089e028f"
],
"layout": "IPY_MODEL_c6a56c54837a41f2b0612bfd1c8d7ef2"
}
},
"a22860bf9581407e8ed7ffad6f246d7a": {
"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_a6c56cfe3e6944ac9ff5496afa5ac7e8",
"placeholder": "​",
"style": "IPY_MODEL_3076237a5c5d4b01b2da1e493a10a130",
"value": "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.15.0.json: "
}
},
"f8046c4f9b3f403e89f0628d4f7fd518": {
"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_83f497dfe4f64942b374c3f7de84a882",
"max": 66336,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_e45bf75598cc488788b9cc83b4effa39",
"value": 66336
}
},
"89711a863681423b95041b3e089e028f": {
"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_df10e76fbe164bc09f6babe3841e246b",
"placeholder": "​",
"style": "IPY_MODEL_c7940608e8a847e0946cae3ccc68e644",
"value": " 535k/? [00:00<00:00, 20.3MB/s]"
}
},
"c6a56c54837a41f2b0612bfd1c8d7ef2": {
"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
}
},
"a6c56cfe3e6944ac9ff5496afa5ac7e8": {
"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
}
},
"3076237a5c5d4b01b2da1e493a10a130": {
"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": ""
}
},
"83f497dfe4f64942b374c3f7de84a882": {
"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
}
},
"e45bf75598cc488788b9cc83b4effa39": {
"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": ""
}
},
"df10e76fbe164bc09f6babe3841e246b": {
"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
}
},
"c7940608e8a847e0946cae3ccc68e644": {
"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": ""
}
},
"23ef8b6e4a8f4a2ba0078c93c3473a94": {
"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_97c1d93f7c24412b9ac76fcaa3d69fc0",
"IPY_MODEL_2ea93abd115042488e453a53c993a674",
"IPY_MODEL_5fdae25157a04f5c8ed4c459796bec28"
],
"layout": "IPY_MODEL_6a1319915d194c7b84bd987f6a3e9492"
}
},
"97c1d93f7c24412b9ac76fcaa3d69fc0": {
"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_d4b1427ac1ee4f6c8d6ab77edb275382",
"placeholder": "​",
"style": "IPY_MODEL_6c247959674843ad8947ce5de4f81800",
"value": "models/default.zip: reconstructing file: 100%"
}
},
"2ea93abd115042488e453a53c993a674": {
"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_d28caad0e9e34e629b45b8c12a92d730",
"max": 394024071,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_0bfe2aabb6b34f3685618b94ade2f029",
"value": 394024071
}
},
"5fdae25157a04f5c8ed4c459796bec28": {
"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_5214fbaee92443608956b75f8ce52064",
"placeholder": "​",
"style": "IPY_MODEL_fd532ccf30f04554a477c8886282819e",
"value": "  394MB /  394MB, 34.5MB/s  "
}
},
"6a1319915d194c7b84bd987f6a3e9492": {
"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
}
},
"d4b1427ac1ee4f6c8d6ab77edb275382": {
"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
}
},
"6c247959674843ad8947ce5de4f81800": {
"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": ""
}
},
"d28caad0e9e34e629b45b8c12a92d730": {
"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
}
},
"0bfe2aabb6b34f3685618b94ade2f029": {
"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": ""
}
},
"5214fbaee92443608956b75f8ce52064": {
"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
}
},
"fd532ccf30f04554a477c8886282819e": {
"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": ""
}
},
"1d140436ba2d4c63a30e19ff737babe1": {
"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_c62bd0de2ab944efb8e6bb71e113c4e4",
"IPY_MODEL_36d0c9a7930043f9b1b0256fd13915ac",
"IPY_MODEL_3a633228d4674a3c916a4dac4a08ce59"
],
"layout": "IPY_MODEL_249ccda5e8094e6a81f0163e262440e3"
}
},
"c62bd0de2ab944efb8e6bb71e113c4e4": {
"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_b278b3c1c9d645129c6e165f1e6eb391",
"placeholder": "​",
"style": "IPY_MODEL_e1a5c6c03d8747458ccc096c69b67350",
"value": "models/default.zip: downloading bytes: "
}
},
"36d0c9a7930043f9b1b0256fd13915ac": {
"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_920a196b97cb44ed977f853a15743598",
"max": 394024071,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_a4b3960cabd3426d907643fe8411e2e4",
"value": 393470381
}
},
"3a633228d4674a3c916a4dac4a08ce59": {
"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_5f1de8b0484f4f55b05f61dea3cb3d47",
"placeholder": "​",
"style": "IPY_MODEL_633e44f5afc64f3d8226a1cf70d397db",
"value": "  393MB, 32.4MB/s  "
}
},
"249ccda5e8094e6a81f0163e262440e3": {
"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
}
},
"b278b3c1c9d645129c6e165f1e6eb391": {
"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
}
},
"e1a5c6c03d8747458ccc096c69b67350": {
"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": ""
}
},
"920a196b97cb44ed977f853a15743598": {
"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
}
},
"a4b3960cabd3426d907643fe8411e2e4": {
"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": ""
}
},
"5f1de8b0484f4f55b05f61dea3cb3d47": {
"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
}
},
"633e44f5afc64f3d8226a1cf70d397db": {
"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": ""
}
},
"4714b653573f41d4af98d0b05d4eeab5": {
"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_102083fd229a4f3aa6c5155e34ae2914",
"IPY_MODEL_257636d445a0480686a81c2e73f9d05f",
"IPY_MODEL_72722df004a64b679142e9cb15c9805a"
],
"layout": "IPY_MODEL_3883c6aaccf040389b4e15d560f23441"
}
},
"102083fd229a4f3aa6c5155e34ae2914": {
"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_bba16ab3a59a43578b30d3a8292cbb98",
"placeholder": "​",
"style": "IPY_MODEL_df2707f12e2a4a088fb95c67daa2a732",
"value": "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.15.0.json: "
}
},
"257636d445a0480686a81c2e73f9d05f": {
"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_7415bbc86fcc46519a4c58f7bbc0e094",
"max": 66336,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_64ae5a24fe7c4798b25c78e5550d9c99",
"value": 66336
}
},
"72722df004a64b679142e9cb15c9805a": {
"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_777164fbf2b946928fd3b27dc7166aa6",
"placeholder": "​",
"style": "IPY_MODEL_14035c6384134dc0a7b834c999e2ec67",
"value": " 535k/? [00:00<00:00, 18.6MB/s]"
}
},
"3883c6aaccf040389b4e15d560f23441": {
"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
}
},
"bba16ab3a59a43578b30d3a8292cbb98": {
"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
}
},
"df2707f12e2a4a088fb95c67daa2a732": {
"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": ""
}
},
"7415bbc86fcc46519a4c58f7bbc0e094": {
"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
}
},
"64ae5a24fe7c4798b25c78e5550d9c99": {
"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": ""
}
},
"777164fbf2b946928fd3b27dc7166aa6": {
"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
}
},
"14035c6384134dc0a7b834c999e2ec67": {
"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": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000,
"referenced_widgets": [
"703e00ba7a654c29856b37562a0da8cc",
"a22860bf9581407e8ed7ffad6f246d7a",
"f8046c4f9b3f403e89f0628d4f7fd518",
"89711a863681423b95041b3e089e028f",
"c6a56c54837a41f2b0612bfd1c8d7ef2",
"a6c56cfe3e6944ac9ff5496afa5ac7e8",
"3076237a5c5d4b01b2da1e493a10a130",
"83f497dfe4f64942b374c3f7de84a882",
"e45bf75598cc488788b9cc83b4effa39",
"df10e76fbe164bc09f6babe3841e246b",
"c7940608e8a847e0946cae3ccc68e644",
"23ef8b6e4a8f4a2ba0078c93c3473a94",
"97c1d93f7c24412b9ac76fcaa3d69fc0",
"2ea93abd115042488e453a53c993a674",
"5fdae25157a04f5c8ed4c459796bec28",
"6a1319915d194c7b84bd987f6a3e9492",
"d4b1427ac1ee4f6c8d6ab77edb275382",
"6c247959674843ad8947ce5de4f81800",
"d28caad0e9e34e629b45b8c12a92d730",
"0bfe2aabb6b34f3685618b94ade2f029",
"5214fbaee92443608956b75f8ce52064",
"fd532ccf30f04554a477c8886282819e",
"1d140436ba2d4c63a30e19ff737babe1",
"c62bd0de2ab944efb8e6bb71e113c4e4",
"36d0c9a7930043f9b1b0256fd13915ac",
"3a633228d4674a3c916a4dac4a08ce59",
"249ccda5e8094e6a81f0163e262440e3",
"b278b3c1c9d645129c6e165f1e6eb391",
"e1a5c6c03d8747458ccc096c69b67350",
"920a196b97cb44ed977f853a15743598",
"a4b3960cabd3426d907643fe8411e2e4",
"5f1de8b0484f4f55b05f61dea3cb3d47",
"633e44f5afc64f3d8226a1cf70d397db",
"4714b653573f41d4af98d0b05d4eeab5",
"102083fd229a4f3aa6c5155e34ae2914",
"257636d445a0480686a81c2e73f9d05f",
"72722df004a64b679142e9cb15c9805a",
"3883c6aaccf040389b4e15d560f23441",
"bba16ab3a59a43578b30d3a8292cbb98",
"df2707f12e2a4a088fb95c67daa2a732",
"7415bbc86fcc46519a4c58f7bbc0e094",
"64ae5a24fe7c4798b25c78e5550d9c99",
"777164fbf2b946928fd3b27dc7166aa6",
"14035c6384134dc0a7b834c999e2ec67"
]
},
"id": "_LTJRy_1YUxD",
"outputId": "1d86b0c4-8137-4cb1-ffd3-c85f90a556a7"
},
"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": "703e00ba7a654c29856b37562a0da8cc"
}
},
"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"
]
},
{
"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": "23ef8b6e4a8f4a2ba0078c93c3473a94"
}
},
"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": "1d140436ba2d4c63a30e19ff737babe1"
}
},
"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",
"INFO:stanza:Checking for updates to resources.json in case models have been updated. Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
]
},
{
"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": "4714b653573f41d4af98d0b05d4eeab5"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"INFO:stanza:Downloaded file to /root/.cache/stanza/1.15.0/resources/resources.json\n",
"WARNING:stanza:Language id package default expects mwt, which has been added\n",
"INFO:stanza:Loading these models for language: id (Indonesian):\n",
"============================\n",
"| Processor | Package |\n",
"----------------------------\n",
"| tokenize | gsd_nocharlm |\n",
"| mwt | gsd |\n",
"| pos | gsd_charlm |\n",
"============================\n",
"\n",
"INFO:stanza:Using device: cpu\n",
"INFO:stanza:Loading: tokenize\n",
"INFO:stanza:Loading: mwt\n",
"INFO:stanza:Loading: pos\n",
"INFO:stanza:Done loading processors!\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"--- Memproses teks ---\n",
"\n",
"Kalimat 1:\n",
"Pemerintah -> NOUN\n",
"merencanakan -> VERB\n",
"pembangunan -> NOUN\n",
"infrastruktur -> NOUN\n",
"jalan -> NOUN\n",
"tol -> NOUN\n",
"baru -> ADJ\n",
"di -> ADP\n",
"wilayah -> NOUN\n",
"Jawa -> PROPN\n",
"Barat -> PROPN\n",
"pada -> ADP\n",
"tahun -> NOUN\n",
"depan -> ADJ\n",
". -> PUNCT\n",
"------------------------------\n",
"Kalimat 2:\n",
"Proyek -> PROPN\n",
"ini -> DET\n",
"diharapkan -> VERB\n",
"dapat -> AUX\n",
"mengurangi -> VERB\n",
"kemacetan -> NOUN\n",
"logistik -> ADJ\n",
"yang -> PRON\n",
"sering -> ADV\n",
"terjadi -> VERB\n",
"di -> ADP\n",
"jalur -> NOUN\n",
"utama -> ADJ\n",
"Pantai -> PROPN\n",
"Utara -> PROPN\n",
". -> PUNCT\n",
"------------------------------\n",
"Kalimat 3:\n",
"Sementara -> SCONJ\n",
"itu -> PRON\n",
", -> PUNCT\n",
"para -> DET\n",
"pengamat -> NOUN\n",
"ekonomi -> NOUN\n",
"menyambut -> VERB\n",
"baik -> ADJ\n",
"rencana -> NOUN\n",
"tersebut -> DET\n",
". -> PUNCT\n",
"------------------------------\n",
"Kalimat 4:\n",
"Mereka -> PRON\n",
"menilai -> VERB\n",
"bahwa -> SCONJ\n",
"kelancaran -> NOUN\n",
"distribusi -> NOUN\n",
"barang -> NOUN\n",
"akan -> AUX\n",
"berdampak -> VERB\n",
"positif -> ADJ\n",
"pada -> ADP\n",
"penurunan -> NOUN\n",
"harga -> NOUN\n",
"kebutuhan -> NOUN\n",
"pokok -> NOUN\n",
"di -> ADP\n",
"pasar -> NOUN\n",
"tradisional -> ADJ\n",
". -> PUNCT\n",
"------------------------------\n"
]
}
],
"source": [
"import stanza\n",
"\n",
"# Mengunduh model bahasa Indonesia\n",
"stanza.download('id')\n",
"\n",
"# Menginisialisasi pipeline NLP (tokenisasi dan POS tagging)\n",
"nlp = stanza.Pipeline('id', processors='tokenize,pos')\n",
"\n",
"# Teks berita (bisa Anda ganti dengan paragraf lain)\n",
"teks_berita = \"\"\"\n",
"Pemerintah merencanakan pembangunan infrastruktur jalan tol baru di wilayah Jawa Barat pada tahun depan.\n",
"Proyek ini diharapkan dapat mengurangi kemacetan logistik yang sering terjadi di jalur utama Pantai Utara.\n",
"\n",
"Sementara itu, para pengamat ekonomi menyambut baik rencana tersebut. Mereka menilai bahwa kelancaran\n",
"distribusi barang akan berdampak positif pada penurunan harga kebutuhan pokok di pasar tradisional.\n",
"\"\"\"\n",
"\n",
"print(\"\\n--- Memproses teks ---\\n\")\n",
"doc = nlp(teks_berita)\n",
"\n",
"# Mencetak hasil POS Tagging\n",
"for sentence_idx, sentence in enumerate(doc.sentences):\n",
" print(f\"Kalimat {sentence_idx + 1}:\")\n",
" for word in sentence.words:\n",
" print(f\"{word.text:15} -> {word.upos}\")\n",
" print(\"-\" * 30)"
]
},
{
"cell_type": "code",
"source": [
"print(\"--- Ekstraksi Informasi Berdasarkan POS Tag ---\")\n",
"\n",
"entitas_penting = []\n",
"kata_kerja = []\n",
"\n",
"# Kita gunakan 'doc' dari proses di cell sebelumnya\n",
"for sentence in doc.sentences:\n",
" for word in sentence.words:\n",
" # Jika kata tersebut adalah Proper Noun (Nama Diri/Tempat)\n",
" if word.upos == 'PROPN':\n",
" entitas_penting.append(word.text)\n",
"\n",
" # Jika kata tersebut adalah Kata Kerja (Aktivitas)\n",
" elif word.upos == 'VERB':\n",
" kata_kerja.append(word.text)\n",
"\n",
"print(\"\\nDaftar Entitas/Tempat (PROPN):\")\n",
"# Menggunakan set() untuk menghilangkan kata yang duplikat\n",
"print(set(entitas_penting))\n",
"\n",
"print(\"\\nDaftar Aktivitas/Kata Kerja (VERB):\")\n",
"print(set(kata_kerja))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Cw5VywT-bvy-",
"outputId": "e9a5092e-d002-445f-af60-4cbeb92433c4"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"--- Ekstraksi Informasi Berdasarkan POS Tag ---\n",
"\n",
"Daftar Entitas/Tempat (PROPN):\n",
"{'Jawa', 'Barat', 'Proyek', 'Utara', 'Pantai'}\n",
"\n",
"Daftar Aktivitas/Kata Kerja (VERB):\n",
"{'diharapkan', 'menilai', 'terjadi', 'mengurangi', 'berdampak', 'menyambut', 'merencanakan'}\n"
]
}
]
}
]
}