diff --git "a/Assignment_04_Miami_Hotel_Search.ipynb" "b/Assignment_04_Miami_Hotel_Search.ipynb"
new file mode 100644--- /dev/null
+++ "b/Assignment_04_Miami_Hotel_Search.ipynb"
@@ -0,0 +1,2470 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "TPU",
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "7974ef878bd74038ac047d1f8b04f1c4": {
+          "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_d2ff26eaaa07434090a57295feb73e19",
+              "IPY_MODEL_4243917723e643f896fd3dae4f110bce",
+              "IPY_MODEL_392a859772634a6caff03aac53f7d3d6"
+            ],
+            "layout": "IPY_MODEL_b31aabad028947dbb455d5eb977d5ff1"
+          }
+        },
+        "d2ff26eaaa07434090a57295feb73e19": {
+          "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_ce01116cccd64fed820e079b7d907df1",
+            "placeholder": "​",
+            "style": "IPY_MODEL_47dfac8bc887458b9cf5993e78a85027",
+            "value": "Batches: 100%"
+          }
+        },
+        "4243917723e643f896fd3dae4f110bce": {
+          "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_db03ae99ca71496f9eb4dafacccc9332",
+            "max": 1,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_501453a4e7ad49a0ab9f54592b7cb4c1",
+            "value": 1
+          }
+        },
+        "392a859772634a6caff03aac53f7d3d6": {
+          "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_e23a9d0bcb7d4684ac27273d4bd2954b",
+            "placeholder": "​",
+            "style": "IPY_MODEL_9806e9bd7b3e4ffb9cbb30f72821adb6",
+            "value": " 1/1 [00:00<00:00, 20.99it/s]"
+          }
+        },
+        "b31aabad028947dbb455d5eb977d5ff1": {
+          "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
+          }
+        },
+        "ce01116cccd64fed820e079b7d907df1": {
+          "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
+          }
+        },
+        "47dfac8bc887458b9cf5993e78a85027": {
+          "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": ""
+          }
+        },
+        "db03ae99ca71496f9eb4dafacccc9332": {
+          "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
+          }
+        },
+        "501453a4e7ad49a0ab9f54592b7cb4c1": {
+          "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": ""
+          }
+        },
+        "e23a9d0bcb7d4684ac27273d4bd2954b": {
+          "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
+          }
+        },
+        "9806e9bd7b3e4ffb9cbb30f72821adb6": {
+          "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": ""
+          }
+        },
+        "faba2b91c175464b8b8f12b4298890e6": {
+          "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_ac0406e564a8489e9f5aaa3597b8c017",
+              "IPY_MODEL_20812b1a71fa4b12bd688a315142efe1",
+              "IPY_MODEL_4a2087e6368043e1894751d4584d42c1"
+            ],
+            "layout": "IPY_MODEL_032cd6f158e44929bf6961dd40947801"
+          }
+        },
+        "ac0406e564a8489e9f5aaa3597b8c017": {
+          "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_865768bcc5a64812806c3802d2d7d142",
+            "placeholder": "​",
+            "style": "IPY_MODEL_7556c598e3ba427ab000194f522b11ac",
+            "value": "Batches: 100%"
+          }
+        },
+        "20812b1a71fa4b12bd688a315142efe1": {
+          "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_6329054f598a4060ab2b959116810006",
+            "max": 1,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_8ece034822c64bb897026a665f1413ec",
+            "value": 1
+          }
+        },
+        "4a2087e6368043e1894751d4584d42c1": {
+          "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_ad71bf69758e4edb90da58225003a91b",
+            "placeholder": "​",
+            "style": "IPY_MODEL_00c4a0f4ba93474aa0925a8f41ac304d",
+            "value": " 1/1 [00:00<00:00, 24.43it/s]"
+          }
+        },
+        "032cd6f158e44929bf6961dd40947801": {
+          "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
+          }
+        },
+        "865768bcc5a64812806c3802d2d7d142": {
+          "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
+          }
+        },
+        "7556c598e3ba427ab000194f522b11ac": {
+          "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": ""
+          }
+        },
+        "6329054f598a4060ab2b959116810006": {
+          "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
+          }
+        },
+        "8ece034822c64bb897026a665f1413ec": {
+          "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": ""
+          }
+        },
+        "ad71bf69758e4edb90da58225003a91b": {
+          "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
+          }
+        },
+        "00c4a0f4ba93474aa0925a8f41ac304d": {
+          "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",
+      "source": [
+        "import pandas as pd\n",
+        "pd.set_option('display.max_columns', None)  # show all columns\n",
+        "pd.set_option('display.expand_frame_repr', False)  # do not wrap row values"
+      ],
+      "metadata": {
+        "id": "8g_mJI1vTOIk"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Data Exploration"
+      ],
+      "metadata": {
+        "id": "eRQgdecrU8Lo"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df = pd.read_csv('https://raw.githubusercontent.com/hamzafarooq/maven-mlsystem-design-cohort-1/main/data/miami_hotels.csv')"
+      ],
+      "metadata": {
+        "id": "U8OIj4vOTP2E"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.name.value_counts()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "6ZTaN0R5TY3t",
+        "outputId": "c54ea111-e29b-4506-e0c9-a60416631b5d"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Faena Miami Beach                          45\n",
+              "Setai Hotel Miami                          45\n",
+              "Best Western Plus Atlantic Beach Resort    45\n",
+              "1 Hotel South Beach                        45\n",
+              "Nobu Hotel Miami Beach                     45\n",
+              "                                           ..\n",
+              "The Julia Hotel, Miami Beach                6\n",
+              "Beach Park Hotel                            4\n",
+              "Bikini Lodge                                4\n",
+              "Baltic Hotel                                2\n",
+              "Sherry Frontenac Hotel                      1\n",
+              "Name: name, Length: 65, dtype: int64"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 15
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df = df.drop_duplicates()"
+      ],
+      "metadata": {
+        "id": "BqMuCbcvTcP0"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.shape"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "i5i1Mu1JTkRh",
+        "outputId": "1f4e7e6b-9cb1-4b5e-f9be-6d675d7a55b0"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(2511, 27)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 17
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 833
+        },
+        "id": "wLtOv6CJTygx",
+        "outputId": "f38c9eaa-9c6c-4bbe-c92c-d7e3c4ba0b97"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "        id   type               name                                              image awards  rankingPosition priceLevel     priceRange category  rating  hotelClass hotelClassAttribution        phone                                            address                              email amenities  numberOfRooms prices   latitude  longitude                                             webUrl                            website                    rankingString  rankingDenominator  numberOfReviews                                             review                                           title\n",
+              "0  7787044  HOTEL  Faena Miami Beach  https://media-cdn.tripadvisor.com/media/photo-...     []                5       $$$$  $729 - $1,426    hotel     4.5         0.0                   NaN  13055348800  3201 Collins Ave Faena District, Miami Beach, ...  reservations-miamibeach@faena.com        []            179     []  25.807375  -80.12364  https://www.tripadvisor.com/Hotel_Review-g3443...  https://www.faena.com/miami-beach  #5 of 235 hotels in Miami Beach                 235             2123  Hands down my absolute favorite hotel in South...  My favorite hotel in Miami--Petar is the best!\n",
+              "1  7787044  HOTEL  Faena Miami Beach  https://media-cdn.tripadvisor.com/media/photo-...     []                5       $$$$  $729 - $1,426    hotel     4.5         0.0                   NaN  13055348800  3201 Collins Ave Faena District, Miami Beach, ...  reservations-miamibeach@faena.com        []            179     []  25.807375  -80.12364  https://www.tripadvisor.com/Hotel_Review-g3443...  https://www.faena.com/miami-beach  #5 of 235 hotels in Miami Beach                 235             2123  There are not enough words to explain the sump...                                  Exquisite Stay\n",
+              "2  7787044  HOTEL  Faena Miami Beach  https://media-cdn.tripadvisor.com/media/photo-...     []                5       $$$$  $729 - $1,426    hotel     4.5         0.0                   NaN  13055348800  3201 Collins Ave Faena District, Miami Beach, ...  reservations-miamibeach@faena.com        []            179     []  25.807375  -80.12364  https://www.tripadvisor.com/Hotel_Review-g3443...  https://www.faena.com/miami-beach  #5 of 235 hotels in Miami Beach                 235             2123  I went for the Burlesque show which was absolu...                                   Burlesqu Show\n",
+              "3  7787044  HOTEL  Faena Miami Beach  https://media-cdn.tripadvisor.com/media/photo-...     []                5       $$$$  $729 - $1,426    hotel     4.5         0.0                   NaN  13055348800  3201 Collins Ave Faena District, Miami Beach, ...  reservations-miamibeach@faena.com        []            179     []  25.807375  -80.12364  https://www.tripadvisor.com/Hotel_Review-g3443...  https://www.faena.com/miami-beach  #5 of 235 hotels in Miami Beach                 235             2123  Dana at Gitano made the night magical! He make...                   Dana at Gitano is a rockstar!\n",
+              "4  7787044  HOTEL  Faena Miami Beach  https://media-cdn.tripadvisor.com/media/photo-...     []                5       $$$$  $729 - $1,426    hotel     4.5         0.0                   NaN  13055348800  3201 Collins Ave Faena District, Miami Beach, ...  reservations-miamibeach@faena.com        []            179     []  25.807375  -80.12364  https://www.tripadvisor.com/Hotel_Review-g3443...  https://www.faena.com/miami-beach  #5 of 235 hotels in Miami Beach                 235             2123  I would like to give our very very heartfelt t...                                   Perfect Place"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-e8d8331d-aec9-47d4-9f9a-4e57ce8dee99\" class=\"colab-df-container\">\n",
+              "    <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>id</th>\n",
+              "      <th>type</th>\n",
+              "      <th>name</th>\n",
+              "      <th>image</th>\n",
+              "      <th>awards</th>\n",
+              "      <th>rankingPosition</th>\n",
+              "      <th>priceLevel</th>\n",
+              "      <th>priceRange</th>\n",
+              "      <th>category</th>\n",
+              "      <th>rating</th>\n",
+              "      <th>hotelClass</th>\n",
+              "      <th>hotelClassAttribution</th>\n",
+              "      <th>phone</th>\n",
+              "      <th>address</th>\n",
+              "      <th>email</th>\n",
+              "      <th>amenities</th>\n",
+              "      <th>numberOfRooms</th>\n",
+              "      <th>prices</th>\n",
+              "      <th>latitude</th>\n",
+              "      <th>longitude</th>\n",
+              "      <th>webUrl</th>\n",
+              "      <th>website</th>\n",
+              "      <th>rankingString</th>\n",
+              "      <th>rankingDenominator</th>\n",
+              "      <th>numberOfReviews</th>\n",
+              "      <th>review</th>\n",
+              "      <th>title</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>7787044</td>\n",
+              "      <td>HOTEL</td>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>https://media-cdn.tripadvisor.com/media/photo-...</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>5</td>\n",
+              "      <td>$$$$</td>\n",
+              "      <td>$729 - $1,426</td>\n",
+              "      <td>hotel</td>\n",
+              "      <td>4.5</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>13055348800</td>\n",
+              "      <td>3201 Collins Ave Faena District, Miami Beach, ...</td>\n",
+              "      <td>reservations-miamibeach@faena.com</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>179</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>25.807375</td>\n",
+              "      <td>-80.12364</td>\n",
+              "      <td>https://www.tripadvisor.com/Hotel_Review-g3443...</td>\n",
+              "      <td>https://www.faena.com/miami-beach</td>\n",
+              "      <td>#5 of 235 hotels in Miami Beach</td>\n",
+              "      <td>235</td>\n",
+              "      <td>2123</td>\n",
+              "      <td>Hands down my absolute favorite hotel in South...</td>\n",
+              "      <td>My favorite hotel in Miami--Petar is the best!</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>7787044</td>\n",
+              "      <td>HOTEL</td>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>https://media-cdn.tripadvisor.com/media/photo-...</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>5</td>\n",
+              "      <td>$$$$</td>\n",
+              "      <td>$729 - $1,426</td>\n",
+              "      <td>hotel</td>\n",
+              "      <td>4.5</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>13055348800</td>\n",
+              "      <td>3201 Collins Ave Faena District, Miami Beach, ...</td>\n",
+              "      <td>reservations-miamibeach@faena.com</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>179</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>25.807375</td>\n",
+              "      <td>-80.12364</td>\n",
+              "      <td>https://www.tripadvisor.com/Hotel_Review-g3443...</td>\n",
+              "      <td>https://www.faena.com/miami-beach</td>\n",
+              "      <td>#5 of 235 hotels in Miami Beach</td>\n",
+              "      <td>235</td>\n",
+              "      <td>2123</td>\n",
+              "      <td>There are not enough words to explain the sump...</td>\n",
+              "      <td>Exquisite Stay</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>7787044</td>\n",
+              "      <td>HOTEL</td>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>https://media-cdn.tripadvisor.com/media/photo-...</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>5</td>\n",
+              "      <td>$$$$</td>\n",
+              "      <td>$729 - $1,426</td>\n",
+              "      <td>hotel</td>\n",
+              "      <td>4.5</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>13055348800</td>\n",
+              "      <td>3201 Collins Ave Faena District, Miami Beach, ...</td>\n",
+              "      <td>reservations-miamibeach@faena.com</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>179</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>25.807375</td>\n",
+              "      <td>-80.12364</td>\n",
+              "      <td>https://www.tripadvisor.com/Hotel_Review-g3443...</td>\n",
+              "      <td>https://www.faena.com/miami-beach</td>\n",
+              "      <td>#5 of 235 hotels in Miami Beach</td>\n",
+              "      <td>235</td>\n",
+              "      <td>2123</td>\n",
+              "      <td>I went for the Burlesque show which was absolu...</td>\n",
+              "      <td>Burlesqu Show</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>7787044</td>\n",
+              "      <td>HOTEL</td>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>https://media-cdn.tripadvisor.com/media/photo-...</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>5</td>\n",
+              "      <td>$$$$</td>\n",
+              "      <td>$729 - $1,426</td>\n",
+              "      <td>hotel</td>\n",
+              "      <td>4.5</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>13055348800</td>\n",
+              "      <td>3201 Collins Ave Faena District, Miami Beach, ...</td>\n",
+              "      <td>reservations-miamibeach@faena.com</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>179</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>25.807375</td>\n",
+              "      <td>-80.12364</td>\n",
+              "      <td>https://www.tripadvisor.com/Hotel_Review-g3443...</td>\n",
+              "      <td>https://www.faena.com/miami-beach</td>\n",
+              "      <td>#5 of 235 hotels in Miami Beach</td>\n",
+              "      <td>235</td>\n",
+              "      <td>2123</td>\n",
+              "      <td>Dana at Gitano made the night magical! He make...</td>\n",
+              "      <td>Dana at Gitano is a rockstar!</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>7787044</td>\n",
+              "      <td>HOTEL</td>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>https://media-cdn.tripadvisor.com/media/photo-...</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>5</td>\n",
+              "      <td>$$$$</td>\n",
+              "      <td>$729 - $1,426</td>\n",
+              "      <td>hotel</td>\n",
+              "      <td>4.5</td>\n",
+              "      <td>0.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>13055348800</td>\n",
+              "      <td>3201 Collins Ave Faena District, Miami Beach, ...</td>\n",
+              "      <td>reservations-miamibeach@faena.com</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>179</td>\n",
+              "      <td>[]</td>\n",
+              "      <td>25.807375</td>\n",
+              "      <td>-80.12364</td>\n",
+              "      <td>https://www.tripadvisor.com/Hotel_Review-g3443...</td>\n",
+              "      <td>https://www.faena.com/miami-beach</td>\n",
+              "      <td>#5 of 235 hotels in Miami Beach</td>\n",
+              "      <td>235</td>\n",
+              "      <td>2123</td>\n",
+              "      <td>I would like to give our very very heartfelt t...</td>\n",
+              "      <td>Perfect Place</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e8d8331d-aec9-47d4-9f9a-4e57ce8dee99')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-e8d8331d-aec9-47d4-9f9a-4e57ce8dee99 button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-e8d8331d-aec9-47d4-9f9a-4e57ce8dee99');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "<div id=\"df-7af90cf7-8d72-4272-9ab7-d422ed1f2b23\">\n",
+              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-7af90cf7-8d72-4272-9ab7-d422ed1f2b23')\"\n",
+              "            title=\"Suggest charts\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "     width=\"24px\">\n",
+              "    <g>\n",
+              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+              "    </g>\n",
+              "</svg>\n",
+              "  </button>\n",
+              "\n",
+              "<style>\n",
+              "  .colab-df-quickchart {\n",
+              "      --bg-color: #E8F0FE;\n",
+              "      --fill-color: #1967D2;\n",
+              "      --hover-bg-color: #E2EBFA;\n",
+              "      --hover-fill-color: #174EA6;\n",
+              "      --disabled-fill-color: #AAA;\n",
+              "      --disabled-bg-color: #DDD;\n",
+              "  }\n",
+              "\n",
+              "  [theme=dark] .colab-df-quickchart {\n",
+              "      --bg-color: #3B4455;\n",
+              "      --fill-color: #D2E3FC;\n",
+              "      --hover-bg-color: #434B5C;\n",
+              "      --hover-fill-color: #FFFFFF;\n",
+              "      --disabled-bg-color: #3B4455;\n",
+              "      --disabled-fill-color: #666;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart {\n",
+              "    background-color: var(--bg-color);\n",
+              "    border: none;\n",
+              "    border-radius: 50%;\n",
+              "    cursor: pointer;\n",
+              "    display: none;\n",
+              "    fill: var(--fill-color);\n",
+              "    height: 32px;\n",
+              "    padding: 0;\n",
+              "    width: 32px;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart:hover {\n",
+              "    background-color: var(--hover-bg-color);\n",
+              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "    fill: var(--button-hover-fill-color);\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart-complete:disabled,\n",
+              "  .colab-df-quickchart-complete:disabled:hover {\n",
+              "    background-color: var(--disabled-bg-color);\n",
+              "    fill: var(--disabled-fill-color);\n",
+              "    box-shadow: none;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-spinner {\n",
+              "    border: 2px solid var(--fill-color);\n",
+              "    border-color: transparent;\n",
+              "    border-bottom-color: var(--fill-color);\n",
+              "    animation:\n",
+              "      spin 1s steps(1) infinite;\n",
+              "  }\n",
+              "\n",
+              "  @keyframes spin {\n",
+              "    0% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "      border-left-color: var(--fill-color);\n",
+              "    }\n",
+              "    20% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    30% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    40% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    60% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    80% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "    90% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "  }\n",
+              "</style>\n",
+              "\n",
+              "  <script>\n",
+              "    async function quickchart(key) {\n",
+              "      const quickchartButtonEl =\n",
+              "        document.querySelector('#' + key + ' button');\n",
+              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
+              "      try {\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      } catch (error) {\n",
+              "        console.error('Error during call to suggestCharts:', error);\n",
+              "      }\n",
+              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+              "    }\n",
+              "    (() => {\n",
+              "      let quickchartButtonEl =\n",
+              "        document.querySelector('#df-7af90cf7-8d72-4272-9ab7-d422ed1f2b23 button');\n",
+              "      quickchartButtonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "    })();\n",
+              "  </script>\n",
+              "</div>\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 18
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.columns"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "-cDtE40yT0xK",
+        "outputId": "342e12ea-0214-4853-cea1-f29bf94a634a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Index(['id', 'type', 'name', 'image', 'awards', 'rankingPosition',\n",
+              "       'priceLevel', 'priceRange', 'category', 'rating', 'hotelClass',\n",
+              "       'hotelClassAttribution', 'phone', 'address', 'email', 'amenities',\n",
+              "       'numberOfRooms', 'prices', 'latitude', 'longitude', 'webUrl', 'website',\n",
+              "       'rankingString', 'rankingDenominator', 'numberOfReviews', 'review',\n",
+              "       'title'],\n",
+              "      dtype='object')"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 19
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Create Vectors"
+      ],
+      "metadata": {
+        "id": "EvJOQOr0VAWU"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import re\n",
+        "\n",
+        "# combine tile and review columns into one col called combined\n",
+        "df[\"combined\"] = (\n",
+        "    df.title.str.strip() + ' ' + df.review.str.strip()\n",
+        ")\n",
+        "\n",
+        "df_combined = df.copy()\n",
+        "\n",
+        "# remove all non-alphanumeric characters\n",
+        "df_combined['combined'] = df_combined['combined'].apply(lambda x: re.sub('[^a-zA-z0-9\\s]','',str(x)))\n",
+        "\n",
+        "# convert all txt to lower case\n",
+        "def lower_case(input_str):\n",
+        "    input_str = input_str.lower()\n",
+        "    return input_str\n",
+        "\n",
+        "df_combined['combined']= df_combined['combined'].apply(lambda x: lower_case(x))"
+      ],
+      "metadata": {
+        "id": "OixPCLrNVExS"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_combined[['name', 'combined']].head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "ZVw1msB5XRue",
+        "outputId": "174ed80f-0aac-41c5-aef8-b33fff188479"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "                name                                           combined\n",
+              "0  Faena Miami Beach  my favorite hotel in miamipetar is the best ha...\n",
+              "1  Faena Miami Beach  exquisite stay there are not enough words to e...\n",
+              "2  Faena Miami Beach  burlesqu show i went for the burlesque show wh...\n",
+              "3  Faena Miami Beach  dana at gitano is a rockstar dana at gitano ma...\n",
+              "4  Faena Miami Beach  perfect place i would like to give our very ve..."
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-8d5428dc-d2b5-4467-a519-10713c001f11\" class=\"colab-df-container\">\n",
+              "    <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>name</th>\n",
+              "      <th>combined</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>my favorite hotel in miamipetar is the best ha...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>exquisite stay there are not enough words to e...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>burlesqu show i went for the burlesque show wh...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>dana at gitano is a rockstar dana at gitano ma...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>Faena Miami Beach</td>\n",
+              "      <td>perfect place i would like to give our very ve...</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-8d5428dc-d2b5-4467-a519-10713c001f11')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-8d5428dc-d2b5-4467-a519-10713c001f11 button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-8d5428dc-d2b5-4467-a519-10713c001f11');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "<div id=\"df-e63a7d67-43a3-4d6c-aae7-411758cf6751\">\n",
+              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-e63a7d67-43a3-4d6c-aae7-411758cf6751')\"\n",
+              "            title=\"Suggest charts\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "     width=\"24px\">\n",
+              "    <g>\n",
+              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+              "    </g>\n",
+              "</svg>\n",
+              "  </button>\n",
+              "\n",
+              "<style>\n",
+              "  .colab-df-quickchart {\n",
+              "      --bg-color: #E8F0FE;\n",
+              "      --fill-color: #1967D2;\n",
+              "      --hover-bg-color: #E2EBFA;\n",
+              "      --hover-fill-color: #174EA6;\n",
+              "      --disabled-fill-color: #AAA;\n",
+              "      --disabled-bg-color: #DDD;\n",
+              "  }\n",
+              "\n",
+              "  [theme=dark] .colab-df-quickchart {\n",
+              "      --bg-color: #3B4455;\n",
+              "      --fill-color: #D2E3FC;\n",
+              "      --hover-bg-color: #434B5C;\n",
+              "      --hover-fill-color: #FFFFFF;\n",
+              "      --disabled-bg-color: #3B4455;\n",
+              "      --disabled-fill-color: #666;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart {\n",
+              "    background-color: var(--bg-color);\n",
+              "    border: none;\n",
+              "    border-radius: 50%;\n",
+              "    cursor: pointer;\n",
+              "    display: none;\n",
+              "    fill: var(--fill-color);\n",
+              "    height: 32px;\n",
+              "    padding: 0;\n",
+              "    width: 32px;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart:hover {\n",
+              "    background-color: var(--hover-bg-color);\n",
+              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "    fill: var(--button-hover-fill-color);\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart-complete:disabled,\n",
+              "  .colab-df-quickchart-complete:disabled:hover {\n",
+              "    background-color: var(--disabled-bg-color);\n",
+              "    fill: var(--disabled-fill-color);\n",
+              "    box-shadow: none;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-spinner {\n",
+              "    border: 2px solid var(--fill-color);\n",
+              "    border-color: transparent;\n",
+              "    border-bottom-color: var(--fill-color);\n",
+              "    animation:\n",
+              "      spin 1s steps(1) infinite;\n",
+              "  }\n",
+              "\n",
+              "  @keyframes spin {\n",
+              "    0% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "      border-left-color: var(--fill-color);\n",
+              "    }\n",
+              "    20% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    30% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    40% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    60% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    80% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "    90% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "  }\n",
+              "</style>\n",
+              "\n",
+              "  <script>\n",
+              "    async function quickchart(key) {\n",
+              "      const quickchartButtonEl =\n",
+              "        document.querySelector('#' + key + ' button');\n",
+              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
+              "      try {\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      } catch (error) {\n",
+              "        console.error('Error during call to suggestCharts:', error);\n",
+              "      }\n",
+              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+              "    }\n",
+              "    (() => {\n",
+              "      let quickchartButtonEl =\n",
+              "        document.querySelector('#df-e63a7d67-43a3-4d6c-aae7-411758cf6751 button');\n",
+              "      quickchartButtonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "    })();\n",
+              "  </script>\n",
+              "</div>\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 21
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install -U sentence-transformers rank_bm25 --quiet"
+      ],
+      "metadata": {
+        "id": "_-VkP02zYLeR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sentence_transformers import SentenceTransformer, util\n",
+        "\n",
+        "embedder = SentenceTransformer('all-mpnet-base-v2')\n",
+        "# embedder = SentenceTransformer('wvprevue/e5-mistral-7b-instruct')"
+      ],
+      "metadata": {
+        "id": "ek7XUay6XT91"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import time\n",
+        "import torch\n",
+        "\n",
+        "if not torch.cuda.is_available():\n",
+        "    print(\"Warning: No GPU found. Please add GPU to your notebook\")\n",
+        "else:\n",
+        "  print(\"GPU Found!\")\n",
+        "  embedder =  embedder.to('cuda')\n",
+        "\n",
+        "df_embedding = df_combined.copy()\n",
+        "\n",
+        "startTime = time.time()\n",
+        "df_embedding[\"embedding\"] = df_embedding.combined.apply(lambda x: embedder.encode(x))\n",
+        "executionTime = (time.time() - startTime)\n",
+        "\n",
+        "print('Execution time in seconds: ' + str(executionTime))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 408
+        },
+        "id": "azaI56B8YjCO",
+        "outputId": "b08987a7-db13-4ee6-890b-e2bd8cf083be"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Warning: No GPU found. Please add GPU to your notebook\n"
+          ]
+        },
+        {
+          "output_type": "error",
+          "ename": "KeyboardInterrupt",
+          "evalue": "",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+            "\u001b[0;32m<ipython-input-24-3a75b97da1c9>\u001b[0m in \u001b[0;36m<cell line: 13>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[0mstartTime\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m \u001b[0mdf_embedding\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"embedding\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf_embedding\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcombined\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0membedder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0mexecutionTime\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mstartTime\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/core/series.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(self, func, convert_dtype, args, **kwargs)\u001b[0m\n\u001b[1;32m   4769\u001b[0m         \u001b[0mdtype\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mfloat64\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4770\u001b[0m         \"\"\"\n\u001b[0;32m-> 4771\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mSeriesApply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconvert_dtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   4772\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4773\u001b[0m     def _reduce(\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/core/apply.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1121\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1122\u001b[0m         \u001b[0;31m# self.f is Callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1123\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_standard\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1124\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1125\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0magg\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/core/apply.py\u001b[0m in \u001b[0;36mapply_standard\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1172\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1173\u001b[0m                 \u001b[0mvalues\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobject\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1174\u001b[0;31m                 mapped = lib.map_infer(\n\u001b[0m\u001b[1;32m   1175\u001b[0m                     \u001b[0mvalues\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1176\u001b[0m                     \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/pandas/_libs/lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.map_infer\u001b[0;34m()\u001b[0m\n",
+            "\u001b[0;32m<ipython-input-24-3a75b97da1c9>\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(x)\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[0mstartTime\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m \u001b[0mdf_embedding\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"embedding\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf_embedding\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcombined\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0membedder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0mexecutionTime\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mstartTime\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sentence_transformers/SentenceTransformer.py\u001b[0m in \u001b[0;36mencode\u001b[0;34m(self, sentences, batch_size, show_progress_bar, output_value, convert_to_numpy, convert_to_tensor, device, normalize_embeddings)\u001b[0m\n\u001b[1;32m    282\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    283\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mno_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 284\u001b[0;31m                 \u001b[0mout_features\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    285\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    286\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0moutput_value\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"token_embeddings\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/container.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    213\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    214\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mmodule\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 215\u001b[0;31m             \u001b[0minput\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodule\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    216\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    217\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1517\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1518\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1519\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1520\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1525\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1526\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1528\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1529\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sentence_transformers/models/Transformer.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, features)\u001b[0m\n\u001b[1;32m     96\u001b[0m             \u001b[0mtrans_features\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"token_type_ids\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfeatures\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"token_type_ids\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     97\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 98\u001b[0;31m         \u001b[0moutput_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mauto_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mtrans_features\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreturn_dict\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     99\u001b[0m         \u001b[0moutput_tokens\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0moutput_states\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1517\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1518\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1519\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1520\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1525\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1526\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1528\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1529\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mpnet/modeling_mpnet.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input_ids, attention_mask, position_ids, head_mask, inputs_embeds, output_attentions, output_hidden_states, return_dict, **kwargs)\u001b[0m\n\u001b[1;32m    549\u001b[0m         \u001b[0mhead_mask\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_head_mask\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhead_mask\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_hidden_layers\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    550\u001b[0m         \u001b[0membedding_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0membeddings\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_ids\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minput_ids\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mposition_ids\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mposition_ids\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs_embeds\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minputs_embeds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 551\u001b[0;31m         encoder_outputs = self.encoder(\n\u001b[0m\u001b[1;32m    552\u001b[0m             \u001b[0membedding_output\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    553\u001b[0m             \u001b[0mattention_mask\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mextended_attention_mask\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1517\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1518\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1519\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1520\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1525\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1526\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1528\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1529\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mpnet/modeling_mpnet.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, output_attentions, output_hidden_states, return_dict, **kwargs)\u001b[0m\n\u001b[1;32m    339\u001b[0m                 \u001b[0mall_hidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mall_hidden_states\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mhidden_states\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    340\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 341\u001b[0;31m             layer_outputs = layer_module(\n\u001b[0m\u001b[1;32m    342\u001b[0m                 \u001b[0mhidden_states\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    343\u001b[0m                 \u001b[0mattention_mask\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1517\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1518\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1519\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1520\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1525\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1526\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1528\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1529\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mpnet/modeling_mpnet.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, position_bias, output_attentions, **kwargs)\u001b[0m\n\u001b[1;32m    309\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    310\u001b[0m         \u001b[0mintermediate_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mintermediate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mattention_output\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 311\u001b[0;31m         \u001b[0mlayer_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mintermediate_output\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mattention_output\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    312\u001b[0m         \u001b[0moutputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mlayer_output\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0moutputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    313\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0moutputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1517\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1518\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1519\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1520\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1525\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1526\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1528\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1529\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mpnet/modeling_mpnet.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, hidden_states, input_tensor)\u001b[0m\n\u001b[1;32m    276\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    277\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhidden_states\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput_tensor\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensor\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 278\u001b[0;31m         \u001b[0mhidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdense\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhidden_states\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    279\u001b[0m         \u001b[0mhidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdropout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhidden_states\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    280\u001b[0m         \u001b[0mhidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLayerNorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhidden_states\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0minput_tensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1517\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1518\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1519\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1520\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1525\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1526\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1528\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1529\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/linear.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    112\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    113\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 114\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mF\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbias\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    115\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    116\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mextra_repr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_embedding = df_combined.copy()\n",
+        "\n",
+        "\n",
+        "df_embedding[\"embedding\"] = df_embedding.combined.apply(lambda x: embedder.encode(x))"
+      ],
+      "metadata": {
+        "id": "BKEJpt3xbl-D"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# !pip install umap-learn"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "lu1Y-SJ0g8Jn",
+        "outputId": "12044563-9ae5-43f3-833a-9727f3a16bf7"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting umap-learn\n",
+            "  Downloading umap-learn-0.5.5.tar.gz (90 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.9/90.9 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from umap-learn) (1.23.5)\n",
+            "Requirement already satisfied: scipy>=1.3.1 in /usr/local/lib/python3.10/dist-packages (from umap-learn) (1.11.4)\n",
+            "Requirement already satisfied: scikit-learn>=0.22 in /usr/local/lib/python3.10/dist-packages (from umap-learn) (1.2.2)\n",
+            "Requirement already satisfied: numba>=0.51.2 in /usr/local/lib/python3.10/dist-packages (from umap-learn) (0.58.1)\n",
+            "Collecting pynndescent>=0.5 (from umap-learn)\n",
+            "  Downloading pynndescent-0.5.11-py3-none-any.whl (55 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m55.8/55.8 kB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from umap-learn) (4.66.1)\n",
+            "Requirement already satisfied: llvmlite<0.42,>=0.41.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba>=0.51.2->umap-learn) (0.41.1)\n",
+            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.10/dist-packages (from pynndescent>=0.5->umap-learn) (1.3.2)\n",
+            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.22->umap-learn) (3.2.0)\n",
+            "Building wheels for collected packages: umap-learn\n",
+            "  Building wheel for umap-learn (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Created wheel for umap-learn: filename=umap_learn-0.5.5-py3-none-any.whl size=86832 sha256=887f10c7c74893c7e09fda5a2cb4d0a2d93631b4b9006d546938551ac33c380b\n",
+            "  Stored in directory: /root/.cache/pip/wheels/3a/70/07/428d2b58660a1a3b431db59b806a10da736612ebbc66c1bcc5\n",
+            "Successfully built umap-learn\n",
+            "Installing collected packages: pynndescent, umap-learn\n",
+            "Successfully installed pynndescent-0.5.11 umap-learn-0.5.5\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# import umap\n",
+        "# import numpy as np\n",
+        "# from tqdm import tqdm\n",
+        "\n",
+        "# embeddings = df_embedding['embedding'].apply(np.array).apply(np.ravel)\n",
+        "# umap_transform = umap.UMAP(random_state=0, transform_seed=0).fit(embeddings.values.reshape(-1, embeddings.size))"
+      ],
+      "metadata": {
+        "id": "BAqv8L6sgrNW"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# def project_embeddings(embeddings, umap_transform):\n",
+        "#     umap_embeddings = np.empty((len(embeddings),2))\n",
+        "#     for i, embedding in enumerate(tqdm(embeddings)):\n",
+        "#         umap_embeddings[i] = umap_transform.transform([embedding])\n",
+        "#     return umap_embeddings"
+      ],
+      "metadata": {
+        "id": "EM4566Adg4BS"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# projected_dataset_embeddings = project_embeddings(embeddings, umap_transform)"
+      ],
+      "metadata": {
+        "id": "Vtl4nrdGg56P"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# import matplotlib.pyplot as plt\n",
+        "\n",
+        "# plt.figure()\n",
+        "# plt.scatter(projected_dataset_embeddings[:, 0], projected_dataset_embeddings[:, 1], s=10)\n",
+        "# plt.gca().set_aspect('equal', 'datalim')\n",
+        "# plt.title('Projected Embeddings')\n",
+        "# plt.axis('off')"
+      ],
+      "metadata": {
+        "id": "XmSImtgXhrQA"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#### Save Data to GoogleDrive"
+      ],
+      "metadata": {
+        "id": "p0WWGo6saEGd"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!mkdir Semantic_Search"
+      ],
+      "metadata": {
+        "id": "ALS7cU3faGZD"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# save\n",
+        "\n",
+        "import os\n",
+        "from humanize import naturalsize\n",
+        "\n",
+        "file_path = 'Semantic_Search/hotel_review_full_data.pkl'\n",
+        "\n",
+        "df_embedding.to_pickle(file_path)\n",
+        "\n",
+        "file_size = os.path.getsize(file_path)\n",
+        "\n",
+        "print(f\"Size of {file_path}: {naturalsize(file_size)}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 245
+        },
+        "id": "ZXoQF6IqaHQi",
+        "outputId": "6fe08937-4f0b-4e61-bb47-ef5001fe7296"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "error",
+          "ename": "NameError",
+          "evalue": "name 'df_embedding' is not defined",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+            "\u001b[0;32m<ipython-input-2-342b72e56bd3>\u001b[0m in \u001b[0;36m<cell line: 8>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0mfile_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'Semantic_Search/hotel_review_full_data.pkl'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0mdf_embedding\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_pickle\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      9\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0mfile_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetsize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;31mNameError\u001b[0m: name 'df_embedding' is not defined"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# load\n",
+        "\n",
+        "import pandas as pd\n",
+        "df_hotels = pd.read_pickle('Semantic_Search/hotel_review_full_data.pkl')"
+      ],
+      "metadata": {
+        "id": "p0x7Oej3gjAD"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Semantic Search"
+      ],
+      "metadata": {
+        "id": "5yhNdu6IaxsE"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install faiss-gpu"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ZAvJUFu3cpmD",
+        "outputId": "a7167ed6-8860-45fd-eef1-11cc5e9db70a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting faiss-gpu\n",
+            "  Downloading faiss_gpu-1.7.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (85.5 MB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.5/85.5 MB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hInstalling collected packages: faiss-gpu\n",
+            "Successfully installed faiss-gpu-1.7.2\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Query inputs\n",
+        "\n",
+        "k = 25\n",
+        "query1 = 'close to the beach with free breakfast for a good value'\n",
+        "\n",
+        "query_embedding1 = embedder.encode(query1,show_progress_bar=True)\n",
+        "query_embedding1.shape"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 66,
+          "referenced_widgets": [
+            "7974ef878bd74038ac047d1f8b04f1c4",
+            "d2ff26eaaa07434090a57295feb73e19",
+            "4243917723e643f896fd3dae4f110bce",
+            "392a859772634a6caff03aac53f7d3d6",
+            "b31aabad028947dbb455d5eb977d5ff1",
+            "ce01116cccd64fed820e079b7d907df1",
+            "47dfac8bc887458b9cf5993e78a85027",
+            "db03ae99ca71496f9eb4dafacccc9332",
+            "501453a4e7ad49a0ab9f54592b7cb4c1",
+            "e23a9d0bcb7d4684ac27273d4bd2954b",
+            "9806e9bd7b3e4ffb9cbb30f72821adb6"
+          ]
+        },
+        "id": "89FG7RKtcXUl",
+        "outputId": "6307d2ec-f3de-48d3-ca23-24635ff605c0"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Batches:   0%|          | 0/1 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "7974ef878bd74038ac047d1f8b04f1c4"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(768,)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 24
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "JFdrbxGId_Tt"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Query inputs\n",
+        "\n",
+        "k = 25\n",
+        "query2 = 'Best place to visit in Summer which has a good sea view site and bigger pools'\n",
+        "\n",
+        "query_embedding2 = embedder.encode(query2,show_progress_bar=True)\n",
+        "query_embedding2.shape"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 66,
+          "referenced_widgets": [
+            "faba2b91c175464b8b8f12b4298890e6",
+            "ac0406e564a8489e9f5aaa3597b8c017",
+            "20812b1a71fa4b12bd688a315142efe1",
+            "4a2087e6368043e1894751d4584d42c1",
+            "032cd6f158e44929bf6961dd40947801",
+            "865768bcc5a64812806c3802d2d7d142",
+            "7556c598e3ba427ab000194f522b11ac",
+            "6329054f598a4060ab2b959116810006",
+            "8ece034822c64bb897026a665f1413ec",
+            "ad71bf69758e4edb90da58225003a91b",
+            "00c4a0f4ba93474aa0925a8f41ac304d"
+          ]
+        },
+        "outputId": "801909ac-6868-4a90-de34-2c447c93104c",
+        "id": "EFSYmgj3d_zG"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Batches:   0%|          | 0/1 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "faba2b91c175464b8b8f12b4298890e6"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(768,)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 29
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "k = 5\n",
+        "query3 = 'Best place to visit in Summer which has a good sea view site and bigger pools'\n",
+        "\n",
+        "query_embedding3 = embedder.encode(query3,show_progress_bar=True)\n",
+        "query_embedding3.shape"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 228
+        },
+        "id": "TF8CJ09_39ub",
+        "outputId": "e2237465-200d-4ab5-de76-b55767a72e9d"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "error",
+          "ename": "NameError",
+          "evalue": "name 'embedder' is not defined",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+            "\u001b[0;32m<ipython-input-1-7251f3956452>\u001b[0m in \u001b[0;36m<cell line: 4>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mquery3\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'Best place to visit in Summer which has a good sea view site and bigger pools'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mquery_embedding3\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0membedder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquery3\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mshow_progress_bar\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0mquery_embedding3\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;31mNameError\u001b[0m: name 'embedder' is not defined"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import faiss\n",
+        "import numpy as np\n",
+        "\n",
+        "# Initialize a new index with the same dimension as the query vector\n",
+        "d = query_embedding1.shape[0]\n",
+        "index = faiss.IndexFlatL2(d)\n",
+        "\n",
+        "# Add the embedding column to the index\n",
+        "startTime = time.time()\n",
+        "X = np.vstack(df_hotels['embedding'].to_numpy())  # convert the embedding column to a NumPy array and stack it into a 2D array\n",
+        "index.add(X)\n",
+        "executionTime = (time.time() - startTime)\n",
+        "print('Index build time in seconds: ' + str(executionTime))\n",
+        "\n",
+        "# Perform similarity search using the query vector\n",
+        "startTime = time.time()\n",
+        "distances, indices = index.search(np.array([query_embedding1]), k=k)\n",
+        "executionTime = (time.time() - startTime)\n",
+        "print('Search time in seconds: ' + str(executionTime))\n",
+        "\n",
+        "# Get the corresponding row indices in the original DataFrame\n",
+        "closest_neighbors1 = df_hotels.iloc[indices[0]]  # get the closest neighbors\n",
+        "closest_neighbors1['similarity_score'] = distances[0]  # add a new column with the similarity scores\n",
+        "closest_neighbors1 = closest_neighbors1.sort_values(by='similarity_score', ascending=False)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Fjag_y0iazmh",
+        "outputId": "c1788bbf-7b21-411c-b3da-ea1e40979224"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Index build time in seconds: 0.008175849914550781\n",
+            "Search time in seconds: 0.002689838409423828\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "<ipython-input-26-efece75ac1d0>:23: SettingWithCopyWarning: \n",
+            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+            "Try using .loc[row_indexer,col_indexer] = value instead\n",
+            "\n",
+            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+            "  closest_neighbors1['similarity_score'] = distances[0]  # add a new column with the similarity scores\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import faiss\n",
+        "import numpy as np\n",
+        "\n",
+        "# Initialize a new index with the same dimension as the query vector\n",
+        "d = query_embedding2.shape[0]\n",
+        "index = faiss.IndexFlatL2(d)\n",
+        "\n",
+        "\n",
+        "# Add the embedding column to the index\n",
+        "startTime = time.time()\n",
+        "X = np.vstack(df_hotels['embedding'].to_numpy())  # convert the embedding column to a NumPy array and stack it into a 2D array\n",
+        "index.add(X)\n",
+        "executionTime = (time.time() - startTime)\n",
+        "print('Index build time in seconds: ' + str(executionTime))\n",
+        "\n",
+        "# Perform similarity search using the query vector\n",
+        "startTime = time.time()\n",
+        "distances, indices = index.search(np.array([query_embedding2]), k=k)\n",
+        "executionTime = (time.time() - startTime)\n",
+        "print('Search time in seconds: ' + str(executionTime))\n",
+        "\n",
+        "# Get the corresponding row indices in the original DataFrame\n",
+        "closest_neighbors2 = df_hotels.iloc[indices[0]]  # get the closest neighbors\n",
+        "closest_neighbors2['similarity_score'] = distances[0]  # add a new column with the similarity scores\n",
+        "closest_neighbors2 = closest_neighbors2.sort_values(by='similarity_score', ascending=False)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "JjAkFYQ5i_5O",
+        "outputId": "b2e6f4f3-d61b-4da7-b5ee-ccebe800a2d7"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Index build time in seconds: 0.008663654327392578\n",
+            "Search time in seconds: 0.0028831958770751953\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "<ipython-input-30-ccbd2990accf>:23: SettingWithCopyWarning: \n",
+            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+            "Try using .loc[row_indexer,col_indexer] = value instead\n",
+            "\n",
+            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+            "  closest_neighbors2['similarity_score'] = distances[0]  # add a new column with the similarity scores\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(closest_neighbors1[['name','similarity_score']].head())"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "b7OAb33Fcnh6",
+        "outputId": "f6aa4257-f863-41c7-84ab-ad3dbd522b46"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "                                                   name  similarity_score\n",
+            "708   Hilton Grand Vacations Club McAlpin Ocean Plaz...          0.664502\n",
+            "811                                  The Meridian Miami          0.662270\n",
+            "1244                                      Penguin Hotel          0.658242\n",
+            "791                                  The Meridian Miami          0.653557\n",
+            "1042                       The Savoy Hotel & Beach Club          0.651536\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "LCkTpsKe2P9m"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import faiss\n",
+        "import numpy as np\n",
+        "\n",
+        "# Initialize a new index with the same dimension as the query vector\n",
+        "d = query_embedding2.shape[0]\n",
+        "index = faiss.IndexFlatL2(d)\n",
+        "\n",
+        "%%time\n",
+        "xq = model.encode([\" A person is dancing and enjoying in the rain\"])\n",
+        "k=5\n",
+        "D, I = lsh_index.search(xq, k)  # search\n",
+        "print(I)\n",
+        "# Add the embedding column to the index\n",
+        "startTime = time.time()\n",
+        "X = np.vstack(df_hotels['embedding'].to_numpy())  # convert the embedding column to a NumPy array and stack it into a 2D array\n",
+        "index.add(X)\n",
+        "executionTime = (time.time() - startTime)\n",
+        "print('Index build time in seconds: ' + str(executionTime))\n",
+        "\n",
+        "# Perform similarity search using the query vector\n",
+        "startTime = time.time()\n",
+        "distances, indices = index.search(np.array([query_embedding2]), k=k)\n",
+        "executionTime = (time.time() - startTime)\n",
+        "print('Search time in seconds: ' + str(executionTime))\n",
+        "\n",
+        "# Get the corresponding row indices in the original DataFrame\n",
+        "closest_neighbors2 = df_hotels.iloc[indices[0]]  # get the closest neighbors\n",
+        "closest_neighbors2['similarity_score'] = distances[0]  # add a new column with the similarity scores\n",
+        "closest_neighbors2 = closest_neighbors2.sort_values(by='similarity_score', ascending=False)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "b2e6f4f3-d61b-4da7-b5ee-ccebe800a2d7",
+        "id": "UMwn8KG92Q7d"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Index build time in seconds: 0.008663654327392578\n",
+            "Search time in seconds: 0.0028831958770751953\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "<ipython-input-30-ccbd2990accf>:23: SettingWithCopyWarning: \n",
+            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+            "Try using .loc[row_indexer,col_indexer] = value instead\n",
+            "\n",
+            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+            "  closest_neighbors2['similarity_score'] = distances[0]  # add a new column with the similarity scores\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print('Query:', query1, '\\n')\n",
+        "\n",
+        "for index, row in closest_neighbors1.head().iterrows():\n",
+        "  print(\"HOTEL NAME:\\t\"+row['name'],'\\n',\n",
+        "        \"SIMILARITY SCORE:\\t\",row['similarity_score'],\n",
+        "        '\\n',\"TEXT IDENTIFIED:\\t\" ,row['combined'],'\\n')\n",
+        "df_new1=pd.DataFrame(print(closest_neighbors1[['name','combined','similarity_score']].head()))\n",
+        "q_name_1 = 'qyery1.xlsx'\n",
+        "\n",
+        "# saving the excel\n",
+        "df_new1.to_excel(q_name_1)\n",
+        "print('DataFrame is written to Excel File successfully.')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "gFLxp568c7-3",
+        "outputId": "6a30f8c0-2884-41b3-e35b-1ba477e63548"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Query: close to the beach with free breakfast for a good value \n",
+            "\n",
+            "HOTEL NAME:\tHilton Grand Vacations Club McAlpin Ocean Plaza Miami \n",
+            " SIMILARITY SCORE:\t 0.6645020842552185 \n",
+            " TEXT IDENTIFIED:\t fantastic spot on south beach stayed a week here and thoroughly enjoyed it the staff were very friendly and attentive hotel is located in the perfect spot right in the heart of south beach close to restaurants nightlife starbucks and the beach its far enough down ocean blvd however to avoid the noise highly recommend  we will be back soon \n",
+            "\n",
+            "HOTEL NAME:\tThe Meridian Miami \n",
+            " SIMILARITY SCORE:\t 0.662269651889801 \n",
+            " TEXT IDENTIFIED:\t great would recommend clean walking distance from beach  nice pool and sitting area luis was very friendly and helpful coffee and snacks are available  luis recommended close by places to eat and gave directions  nice \n",
+            "\n",
+            "HOTEL NAME:\tPenguin Hotel \n",
+            " SIMILARITY SCORE:\t 0.6582424640655518 \n",
+            " TEXT IDENTIFIED:\t great location for the price i love this quaint little place directly across from the beach  the welcome drinks and breakfast make it a great value david was the best at the front desk he was friendly and helpful and truly the bombcom  i will be back again \n",
+            "\n",
+            "HOTEL NAME:\tThe Meridian Miami \n",
+            " SIMILARITY SCORE:\t 0.6535568833351135 \n",
+            " TEXT IDENTIFIED:\t well placed hotel we stayed one night in this hotel before joining a cruise  the hotel is in a good spot and the rooms are clean  there is a coffee shop and a small bar in this hotel  the hotel reception staff are very helpful and welcoming  you can walk to nearby restaurants and shops from here \n",
+            "\n",
+            "HOTEL NAME:\tThe Savoy Hotel & Beach Club \n",
+            " SIMILARITY SCORE:\t 0.6515356302261353 \n",
+            " TEXT IDENTIFIED:\t best place awesome service  pool staff at the bar and food was amazing  had a great time by the beach  everything extremely clean  \n",
+            "everyone there was so nice  very family friendly place \n",
+            "we spend most the time at the beach and pool and the managers at bar went out of their way to accommodate every need we had  \n",
+            "\n",
+            "                                                   name                                           combined  similarity_score\n",
+            "708   Hilton Grand Vacations Club McAlpin Ocean Plaz...  fantastic spot on south beach stayed a week he...          0.664502\n",
+            "811                                  The Meridian Miami  great would recommend clean walking distance f...          0.662270\n",
+            "1244                                      Penguin Hotel  great location for the price i love this quain...          0.658242\n",
+            "791                                  The Meridian Miami  well placed hotel we stayed one night in this ...          0.653557\n",
+            "1042                       The Savoy Hotel & Beach Club  best place awesome service  pool staff at the ...          0.651536\n",
+            "DataFrame is written to Excel File successfully.\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print('Query:', query2, '\\n')\n",
+        "\n",
+        "for index, row in closest_neighbors2.head().iterrows():\n",
+        "  print(\"HOTEL NAME:\\t\"+row['name'],'\\n',\n",
+        "        \"SIMILARITY SCORE:\\t\",row['similarity_score'],\n",
+        "        '\\n',\"TEXT IDENTIFIED:\\t\" ,row['combined'],'\\n')\n",
+        "df_new2=pd.DataFrame(print(closest_neighbors2[['name','combined','similarity_score']].head()))"
+      ],
+      "metadata": {
+        "id": "j_JLBlZWdttZ",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "f2351c82-a57a-4cac-b282-43b9aaeed0b5"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Query: Best place to visit in Summer which has a good sea view site and bigger pools \n",
+            "\n",
+            "HOTEL NAME:\tHotel Breakwater South Beach \n",
+            " SIMILARITY SCORE:\t 0.7800235152244568 \n",
+            " TEXT IDENTIFIED:\t love great spot on ocean drive staff lilykaielza were amazing  very politehelpful answered all our questions we are heading back in june for another week we were there first week in march nice pool nice option if you dont want the beach \n",
+            "\n",
+            "HOTEL NAME:\tThe Marlin Hotel \n",
+            " SIMILARITY SCORE:\t 0.7773655652999878 \n",
+            " TEXT IDENTIFIED:\t best place that we have stayed at in south beach hotels on south beach can be so hit and miss due to old buildings and being a noisy area but we were super happy with the marlin  \n",
+            "\n",
+            "great reception staff quiet rooms at night beach towels and chairs supplied valet parking for 35 per night perfect location comfortable bedding and amazing soft robes to use \n",
+            "\n",
+            "we will be using this hotel again when we return \n",
+            "\n",
+            "HOTEL NAME:\tNautilus by Arlo \n",
+            " SIMILARITY SCORE:\t 0.7743663191795349 \n",
+            " TEXT IDENTIFIED:\t my extensive hotel research paid off staff helpful warm fivestar service oscar lana arianna melody tea giuliano and jackie take pride in this retro boutique hotel and provided worldclass service\n",
+            "\n",
+            "room we booked a king ocean front with a pullout sofa bed it was fantastic and huge the bathroom was massive especially for south beach the minibar was epically stocked and there was an espresso machine too we watched the glorious sunset and sunrise from our huge window it was so quiet i thought maybe no one was on either side of us until i saw our neighbors the next morning heading to the rooftop terrace with coffee the rooftop terrace was incredible oscar even made sure we knew how to access the terrace\n",
+            "\n",
+            "pool the pool was topnotch the water was the perfect temperature crystal clear not crowded tranquil quality guests and very polished staff i love that they have a delightful young man dedicated to escorting you to available padded loungers im sure this would be especially helpful at times when its near capacity  no awkward weaving through the chairs and scooting them around to fit your group \n",
+            "\n",
+            "cabana we were so fortunate to have a cabana our first day as we wanted to heal our sunburns from our cruise svetlana took excellent care of us and anticipated our every need the cabana had a large cushioned couch cushioned ottoman coffee table smeg mini fridge standing retro cooler fan large tv towels storage and a super rad orange safe the pia coladas were boozy and not too sugary protip go with a double lunch review below\n",
+            "\n",
+            "beach direct easy access the private beach is steps from the hotel  just stroll through the bamboo tunnel which runs parallel to the pool exit the secure door you need a room key to get in a few steps across the bikewalking trail to a cute little sandy trail and youll see the navy and white striped nautilus umbrellas and loungers \n",
+            "\n",
+            "food the cappuccinos at the coffee bar in the lobby were perfect the lunch from the cabana club was delish we ordered the cubano tuna togarashi salad and kids hamburger this was our 4th cuban sandwich on our vacation and it was the best \n",
+            "\n",
+            "location i preferred the location of nautilus 18th and collins on south beach over the other hotel 9th street and collins we stayed at before our cruise it is quieter and more upscale its a short walk or uber to espaola way the shops and restaurants on lincoln road and the port of miami was only about 15 minutes \n",
+            "\n",
+            "final thoughts our 8 year old kid said this resort was her favorite part of our vacation  beating atlantis and the cruise ship we were married at four seasons the biltmore santa barbara and the service level at nautilus was beyond any four seasons weve stayed at it was truly paradise and were already planning a return trip my only regret is that we didnt stay longer \n",
+            "\n",
+            "HOTEL NAME:\tKimpton Angler's Hotel \n",
+            " SIMILARITY SCORE:\t 0.7728005051612854 \n",
+            " TEXT IDENTIFIED:\t kiloton anglers south beach great location two blocks from ocean ave the rooms are large and modern very very clean hotel parking is valet only but with inout privileges at the front of the hotel did not try the pool as it was cold during our stay but the bar is nice and has a generous menu \n",
+            "\n",
+            "HOTEL NAME:\tHilton Grand Vacations Club McAlpin Ocean Plaza Miami \n",
+            " SIMILARITY SCORE:\t 0.7708964943885803 \n",
+            " TEXT IDENTIFIED:\t fantastic location cant beat staying on ocean drivenow pedestrian steps from the beach rooms are clean with great amenities ive stayed here 6 times and have always had an amazing experience if you need help or advice be sure to ask tall paul \n",
+            "\n",
+            "                                                   name                                           combined  similarity_score\n",
+            "2067                       Hotel Breakwater South Beach  love great spot on ocean drive staff lilykaiel...          0.780024\n",
+            "2258                                   The Marlin Hotel  best place that we have stayed at in south bea...          0.777366\n",
+            "380                                    Nautilus by Arlo  my extensive hotel research paid off staff hel...          0.774366\n",
+            "1001                             Kimpton Angler's Hotel  kiloton anglers south beach great location two...          0.772801\n",
+            "735   Hilton Grand Vacations Club McAlpin Ocean Plaz...  fantastic location cant beat staying on ocean ...          0.770896\n"
+          ]
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file