diff --git a/examples/PyCaret_2_HousePrice_Regresion.ipynb b/examples/PyCaret_2_HousePrice_Regresion.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..28cc2b1759c8a3cb287e1171fb62b04d52ec766f
--- /dev/null
+++ b/examples/PyCaret_2_HousePrice_Regresion.ipynb
@@ -0,0 +1,3206 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "name": "PyCaret 2 HousePrice Regresion.ipynb",
+ "provenance": [],
+ "collapsed_sections": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.8.2"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "84cd4922236448a3a306a3f6e7e43c88": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_47375cce9026442183ab428080b82e11",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 13,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 3,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_fefbae2c76574bf7b31541e5f1e022ef"
+ }
+ },
+ "47375cce9026442183ab428080b82e11": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "fefbae2c76574bf7b31541e5f1e022ef": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "562caa85cf7d4a2fbf4decac3fc6983b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "TextModel",
+ "state": {
+ "_view_name": "TextView",
+ "style": "IPY_MODEL_30410561071f463ab76e219406f2fa9c",
+ "_dom_classes": [],
+ "description": "",
+ "_model_name": "TextModel",
+ "placeholder": "",
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": "Following data types have been inferred automatically, if they are correct press enter to continue or type 'quit' otherwise.",
+ "_view_count": null,
+ "disabled": false,
+ "_view_module_version": "1.5.0",
+ "continuous_update": true,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_55e0f67422e244a9842b8dcc917d493d"
+ }
+ },
+ "30410561071f463ab76e219406f2fa9c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "DescriptionStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "55e0f67422e244a9842b8dcc917d493d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": "100%",
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "cd5ab1a14de5402985b82653a139d818": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_6e28825ce0c1497287c54a26ed64fb9b",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 241,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 238,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_c45d6e58845e4a7e860c7fde14ed94d2"
+ }
+ },
+ "6e28825ce0c1497287c54a26ed64fb9b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "c45d6e58845e4a7e860c7fde14ed94d2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "3c29f19233864b53ba8da01af51d572a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_c59e1582725c43f282f196e76d7f8883",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 14,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 14,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_629dd21d247a4a63a3705add599b59dd"
+ }
+ },
+ "c59e1582725c43f282f196e76d7f8883": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "629dd21d247a4a63a3705add599b59dd": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "5ea1974eab714e209d781a04564f38aa": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_51b30e1917584733bcc1ad280f657a6f",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 14,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 14,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_e3c23703d9304ea09d7233dadc0b067f"
+ }
+ },
+ "51b30e1917584733bcc1ad280f657a6f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "e3c23703d9304ea09d7233dadc0b067f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "3d8c5beac0da40168f86729f70acbb79": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_08c8a60ba9e94046bd2d98afe7cc741a",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 14,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 14,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_367ad9468f49427ca8475e5301a95ddb"
+ }
+ },
+ "08c8a60ba9e94046bd2d98afe7cc741a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "367ad9468f49427ca8475e5301a95ddb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "838a3f746e6a4b6b9f3d05d6c3d506cb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_3a2d5a31c1d1444ab603e67934aa6acc",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 16,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 16,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_11fdc00d65ad4d82950b754c7f5ef6b0"
+ }
+ },
+ "3a2d5a31c1d1444ab603e67934aa6acc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "11fdc00d65ad4d82950b754c7f5ef6b0": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "3e621330c9144f568bdc0eef124afb1a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_ce93bca57c684aa3b46265d0c37eb746",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 16,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 16,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_c485ec5deb47455fad921d447491bb7f"
+ }
+ },
+ "ce93bca57c684aa3b46265d0c37eb746": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "c485ec5deb47455fad921d447491bb7f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "5ff4ebf9ceed4072bf633bb282423dca": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_17633bba196a4c1897ecce8482066c29",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 16,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 16,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_583f1dc1beea4d75b9fe1c1f1de719e1"
+ }
+ },
+ "17633bba196a4c1897ecce8482066c29": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "583f1dc1beea4d75b9fe1c1f1de719e1": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ },
+ "47c66341f17d40de815a82eedaf43dba": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "IntProgressModel",
+ "state": {
+ "_view_name": "ProgressView",
+ "style": "IPY_MODEL_c77287c6a0dd4892b02f8e94f83360d6",
+ "_dom_classes": [],
+ "description": "Processing: ",
+ "_model_name": "IntProgressModel",
+ "bar_style": "",
+ "max": 14,
+ "_view_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "value": 14,
+ "_view_count": null,
+ "_view_module_version": "1.5.0",
+ "orientation": "horizontal",
+ "min": 0,
+ "description_tooltip": null,
+ "_model_module": "@jupyter-widgets/controls",
+ "layout": "IPY_MODEL_2656c119068c4faa86003a43ddb52453"
+ }
+ },
+ "c77287c6a0dd4892b02f8e94f83360d6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "state": {
+ "_view_name": "StyleView",
+ "_model_name": "ProgressStyleModel",
+ "description_width": "",
+ "_view_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.5.0",
+ "_view_count": null,
+ "_view_module_version": "1.2.0",
+ "bar_color": null,
+ "_model_module": "@jupyter-widgets/controls"
+ }
+ },
+ "2656c119068c4faa86003a43ddb52453": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "state": {
+ "_view_name": "LayoutView",
+ "grid_template_rows": null,
+ "right": null,
+ "justify_content": null,
+ "_view_module": "@jupyter-widgets/base",
+ "overflow": null,
+ "_model_module_version": "1.2.0",
+ "_view_count": null,
+ "flex_flow": null,
+ "width": null,
+ "min_width": null,
+ "border": null,
+ "align_items": null,
+ "bottom": null,
+ "_model_module": "@jupyter-widgets/base",
+ "top": null,
+ "grid_column": null,
+ "overflow_y": null,
+ "overflow_x": null,
+ "grid_auto_flow": null,
+ "grid_area": null,
+ "grid_template_columns": null,
+ "flex": null,
+ "_model_name": "LayoutModel",
+ "justify_items": null,
+ "grid_row": null,
+ "max_height": null,
+ "align_content": null,
+ "visibility": null,
+ "align_self": null,
+ "height": null,
+ "min_height": null,
+ "padding": null,
+ "grid_auto_rows": null,
+ "grid_gap": null,
+ "max_width": null,
+ "order": null,
+ "_view_module_version": "1.2.0",
+ "grid_template_areas": null,
+ "object_position": null,
+ "object_fit": null,
+ "grid_auto_columns": null,
+ "margin": null,
+ "display": null,
+ "left": null
+ }
+ }
+ }
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "I76BhvxwrMfn",
+ "colab_type": "text"
+ },
+ "source": [
+ "# PyCaret 2 House Price Prediction Example"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "wSSQFNvlrMfp",
+ "colab_type": "text"
+ },
+ "source": [
+ "This notebook is created using PyCaret 2.0. Last updated : 04-08-2020"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "colab_type": "text",
+ "id": "gobl5HA-juwP"
+ },
+ "source": [
+ "House Price Prediction data set from Kaggle https://www.kaggle.com/c/house-prices-advanced-regression-techniques
\n",
+ "Train Dataset consists of 1460 Samples with 81 features including the SalePrice
\n",
+ "Test Dataset consists of 1459 Samples wit 80 features"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "ICXiqtC_TacA",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 34
+ },
+ "outputId": "49a1f1f6-c4e7-499a-eb34-4d19bceb4562"
+ },
+ "source": [
+ "# Mount Google Drive \n",
+ "# Skip this step if using on local hardware \n",
+ "from google.colab import drive\n",
+ "drive.mount('/content/gdrive')"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "text": [
+ "Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n"
+ ],
+ "name": "stdout"
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "pD-STV05yakD",
+ "colab": {}
+ },
+ "source": [
+ "# Works with pycaret and pycaret 2\n",
+ "#!pip install pycaret==2.0\n",
+ "from pycaret.regression import *\n",
+ "import pandas as pd"
+ ],
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "y0qd3_m7rMfu",
+ "colab_type": "code",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 34
+ },
+ "outputId": "eff3c677-6bf6-4e21-de39-2c1e901254ce"
+ },
+ "source": [
+ "# check version\n",
+ "from pycaret.utils import version\n",
+ "version()"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "text": [
+ "2.0\n"
+ ],
+ "name": "stdout"
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "IVl3sVtl32im",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 34
+ },
+ "outputId": "5c427692-f3ce-400f-a5ac-ae916ad6d11c"
+ },
+ "source": [
+ "# Chane path as per your file structure\n",
+ "# Remove root_path if using local hardware\n",
+ "\n",
+ "root_path = 'gdrive/My Drive/Colab Notebooks/'\n",
+ "\n",
+ "data = pd.read_csv('gdrive/My Drive/Colab Notebooks/HousePrice/train.csv')\n",
+ "\n",
+ "test_data = pd.read_csv('gdrive/My Drive/Colab Notebooks/HousePrice/test.csv')\n",
+ "\n",
+ "print(data.shape, test_data.shape)"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "text": [
+ "(1460, 81) (1459, 80)\n"
+ ],
+ "name": "stdout"
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "kpCdQOa9ZZnH",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 256
+ },
+ "outputId": "7faadb2f-8e76-4a34-a85e-e24f285a5113"
+ },
+ "source": [
+ "data.head()"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Id | \n",
+ " MSSubClass | \n",
+ " MSZoning | \n",
+ " LotFrontage | \n",
+ " LotArea | \n",
+ " Street | \n",
+ " Alley | \n",
+ " LotShape | \n",
+ " LandContour | \n",
+ " Utilities | \n",
+ " LotConfig | \n",
+ " LandSlope | \n",
+ " Neighborhood | \n",
+ " Condition1 | \n",
+ " Condition2 | \n",
+ " BldgType | \n",
+ " HouseStyle | \n",
+ " OverallQual | \n",
+ " OverallCond | \n",
+ " YearBuilt | \n",
+ " YearRemodAdd | \n",
+ " RoofStyle | \n",
+ " RoofMatl | \n",
+ " Exterior1st | \n",
+ " Exterior2nd | \n",
+ " MasVnrType | \n",
+ " MasVnrArea | \n",
+ " ExterQual | \n",
+ " ExterCond | \n",
+ " Foundation | \n",
+ " BsmtQual | \n",
+ " BsmtCond | \n",
+ " BsmtExposure | \n",
+ " BsmtFinType1 | \n",
+ " BsmtFinSF1 | \n",
+ " BsmtFinType2 | \n",
+ " BsmtFinSF2 | \n",
+ " BsmtUnfSF | \n",
+ " TotalBsmtSF | \n",
+ " Heating | \n",
+ " ... | \n",
+ " CentralAir | \n",
+ " Electrical | \n",
+ " 1stFlrSF | \n",
+ " 2ndFlrSF | \n",
+ " LowQualFinSF | \n",
+ " GrLivArea | \n",
+ " BsmtFullBath | \n",
+ " BsmtHalfBath | \n",
+ " FullBath | \n",
+ " HalfBath | \n",
+ " BedroomAbvGr | \n",
+ " KitchenAbvGr | \n",
+ " KitchenQual | \n",
+ " TotRmsAbvGrd | \n",
+ " Functional | \n",
+ " Fireplaces | \n",
+ " FireplaceQu | \n",
+ " GarageType | \n",
+ " GarageYrBlt | \n",
+ " GarageFinish | \n",
+ " GarageCars | \n",
+ " GarageArea | \n",
+ " GarageQual | \n",
+ " GarageCond | \n",
+ " PavedDrive | \n",
+ " WoodDeckSF | \n",
+ " OpenPorchSF | \n",
+ " EnclosedPorch | \n",
+ " 3SsnPorch | \n",
+ " ScreenPorch | \n",
+ " PoolArea | \n",
+ " PoolQC | \n",
+ " Fence | \n",
+ " MiscFeature | \n",
+ " MiscVal | \n",
+ " MoSold | \n",
+ " YrSold | \n",
+ " SaleType | \n",
+ " SaleCondition | \n",
+ " SalePrice | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 | \n",
+ " 1 | \n",
+ " 60 | \n",
+ " RL | \n",
+ " 65.0 | \n",
+ " 8450 | \n",
+ " Pave | \n",
+ " NaN | \n",
+ " Reg | \n",
+ " Lvl | \n",
+ " AllPub | \n",
+ " Inside | \n",
+ " Gtl | \n",
+ " CollgCr | \n",
+ " Norm | \n",
+ " Norm | \n",
+ " 1Fam | \n",
+ " 2Story | \n",
+ " 7 | \n",
+ " 5 | \n",
+ " 2003 | \n",
+ " 2003 | \n",
+ " Gable | \n",
+ " CompShg | \n",
+ " VinylSd | \n",
+ " VinylSd | \n",
+ " BrkFace | \n",
+ " 196.0 | \n",
+ " Gd | \n",
+ " TA | \n",
+ " PConc | \n",
+ " Gd | \n",
+ " TA | \n",
+ " No | \n",
+ " GLQ | \n",
+ " 706 | \n",
+ " Unf | \n",
+ " 0 | \n",
+ " 150 | \n",
+ " 856 | \n",
+ " GasA | \n",
+ " ... | \n",
+ " Y | \n",
+ " SBrkr | \n",
+ " 856 | \n",
+ " 854 | \n",
+ " 0 | \n",
+ " 1710 | \n",
+ " 1 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " 1 | \n",
+ " 3 | \n",
+ " 1 | \n",
+ " Gd | \n",
+ " 8 | \n",
+ " Typ | \n",
+ " 0 | \n",
+ " NaN | \n",
+ " Attchd | \n",
+ " 2003.0 | \n",
+ " RFn | \n",
+ " 2 | \n",
+ " 548 | \n",
+ " TA | \n",
+ " TA | \n",
+ " Y | \n",
+ " 0 | \n",
+ " 61 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " 2008 | \n",
+ " WD | \n",
+ " Normal | \n",
+ " 208500 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " 2 | \n",
+ " 20 | \n",
+ " RL | \n",
+ " 80.0 | \n",
+ " 9600 | \n",
+ " Pave | \n",
+ " NaN | \n",
+ " Reg | \n",
+ " Lvl | \n",
+ " AllPub | \n",
+ " FR2 | \n",
+ " Gtl | \n",
+ " Veenker | \n",
+ " Feedr | \n",
+ " Norm | \n",
+ " 1Fam | \n",
+ " 1Story | \n",
+ " 6 | \n",
+ " 8 | \n",
+ " 1976 | \n",
+ " 1976 | \n",
+ " Gable | \n",
+ " CompShg | \n",
+ " MetalSd | \n",
+ " MetalSd | \n",
+ " None | \n",
+ " 0.0 | \n",
+ " TA | \n",
+ " TA | \n",
+ " CBlock | \n",
+ " Gd | \n",
+ " TA | \n",
+ " Gd | \n",
+ " ALQ | \n",
+ " 978 | \n",
+ " Unf | \n",
+ " 0 | \n",
+ " 284 | \n",
+ " 1262 | \n",
+ " GasA | \n",
+ " ... | \n",
+ " Y | \n",
+ " SBrkr | \n",
+ " 1262 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 1262 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " 2 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " 1 | \n",
+ " TA | \n",
+ " 6 | \n",
+ " Typ | \n",
+ " 1 | \n",
+ " TA | \n",
+ " Attchd | \n",
+ " 1976.0 | \n",
+ " RFn | \n",
+ " 2 | \n",
+ " 460 | \n",
+ " TA | \n",
+ " TA | \n",
+ " Y | \n",
+ " 298 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 0 | \n",
+ " 5 | \n",
+ " 2007 | \n",
+ " WD | \n",
+ " Normal | \n",
+ " 181500 | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " 3 | \n",
+ " 60 | \n",
+ " RL | \n",
+ " 68.0 | \n",
+ " 11250 | \n",
+ " Pave | \n",
+ " NaN | \n",
+ " IR1 | \n",
+ " Lvl | \n",
+ " AllPub | \n",
+ " Inside | \n",
+ " Gtl | \n",
+ " CollgCr | \n",
+ " Norm | \n",
+ " Norm | \n",
+ " 1Fam | \n",
+ " 2Story | \n",
+ " 7 | \n",
+ " 5 | \n",
+ " 2001 | \n",
+ " 2002 | \n",
+ " Gable | \n",
+ " CompShg | \n",
+ " VinylSd | \n",
+ " VinylSd | \n",
+ " BrkFace | \n",
+ " 162.0 | \n",
+ " Gd | \n",
+ " TA | \n",
+ " PConc | \n",
+ " Gd | \n",
+ " TA | \n",
+ " Mn | \n",
+ " GLQ | \n",
+ " 486 | \n",
+ " Unf | \n",
+ " 0 | \n",
+ " 434 | \n",
+ " 920 | \n",
+ " GasA | \n",
+ " ... | \n",
+ " Y | \n",
+ " SBrkr | \n",
+ " 920 | \n",
+ " 866 | \n",
+ " 0 | \n",
+ " 1786 | \n",
+ " 1 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " 1 | \n",
+ " 3 | \n",
+ " 1 | \n",
+ " Gd | \n",
+ " 6 | \n",
+ " Typ | \n",
+ " 1 | \n",
+ " TA | \n",
+ " Attchd | \n",
+ " 2001.0 | \n",
+ " RFn | \n",
+ " 2 | \n",
+ " 608 | \n",
+ " TA | \n",
+ " TA | \n",
+ " Y | \n",
+ " 0 | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 0 | \n",
+ " 9 | \n",
+ " 2008 | \n",
+ " WD | \n",
+ " Normal | \n",
+ " 223500 | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " 4 | \n",
+ " 70 | \n",
+ " RL | \n",
+ " 60.0 | \n",
+ " 9550 | \n",
+ " Pave | \n",
+ " NaN | \n",
+ " IR1 | \n",
+ " Lvl | \n",
+ " AllPub | \n",
+ " Corner | \n",
+ " Gtl | \n",
+ " Crawfor | \n",
+ " Norm | \n",
+ " Norm | \n",
+ " 1Fam | \n",
+ " 2Story | \n",
+ " 7 | \n",
+ " 5 | \n",
+ " 1915 | \n",
+ " 1970 | \n",
+ " Gable | \n",
+ " CompShg | \n",
+ " Wd Sdng | \n",
+ " Wd Shng | \n",
+ " None | \n",
+ " 0.0 | \n",
+ " TA | \n",
+ " TA | \n",
+ " BrkTil | \n",
+ " TA | \n",
+ " Gd | \n",
+ " No | \n",
+ " ALQ | \n",
+ " 216 | \n",
+ " Unf | \n",
+ " 0 | \n",
+ " 540 | \n",
+ " 756 | \n",
+ " GasA | \n",
+ " ... | \n",
+ " Y | \n",
+ " SBrkr | \n",
+ " 961 | \n",
+ " 756 | \n",
+ " 0 | \n",
+ " 1717 | \n",
+ " 1 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " 1 | \n",
+ " Gd | \n",
+ " 7 | \n",
+ " Typ | \n",
+ " 1 | \n",
+ " Gd | \n",
+ " Detchd | \n",
+ " 1998.0 | \n",
+ " Unf | \n",
+ " 3 | \n",
+ " 642 | \n",
+ " TA | \n",
+ " TA | \n",
+ " Y | \n",
+ " 0 | \n",
+ " 35 | \n",
+ " 272 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " 2006 | \n",
+ " WD | \n",
+ " Abnorml | \n",
+ " 140000 | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " 5 | \n",
+ " 60 | \n",
+ " RL | \n",
+ " 84.0 | \n",
+ " 14260 | \n",
+ " Pave | \n",
+ " NaN | \n",
+ " IR1 | \n",
+ " Lvl | \n",
+ " AllPub | \n",
+ " FR2 | \n",
+ " Gtl | \n",
+ " NoRidge | \n",
+ " Norm | \n",
+ " Norm | \n",
+ " 1Fam | \n",
+ " 2Story | \n",
+ " 8 | \n",
+ " 5 | \n",
+ " 2000 | \n",
+ " 2000 | \n",
+ " Gable | \n",
+ " CompShg | \n",
+ " VinylSd | \n",
+ " VinylSd | \n",
+ " BrkFace | \n",
+ " 350.0 | \n",
+ " Gd | \n",
+ " TA | \n",
+ " PConc | \n",
+ " Gd | \n",
+ " TA | \n",
+ " Av | \n",
+ " GLQ | \n",
+ " 655 | \n",
+ " Unf | \n",
+ " 0 | \n",
+ " 490 | \n",
+ " 1145 | \n",
+ " GasA | \n",
+ " ... | \n",
+ " Y | \n",
+ " SBrkr | \n",
+ " 1145 | \n",
+ " 1053 | \n",
+ " 0 | \n",
+ " 2198 | \n",
+ " 1 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " 1 | \n",
+ " 4 | \n",
+ " 1 | \n",
+ " Gd | \n",
+ " 9 | \n",
+ " Typ | \n",
+ " 1 | \n",
+ " TA | \n",
+ " Attchd | \n",
+ " 2000.0 | \n",
+ " RFn | \n",
+ " 3 | \n",
+ " 836 | \n",
+ " TA | \n",
+ " TA | \n",
+ " Y | \n",
+ " 192 | \n",
+ " 84 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " 0 | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " NaN | \n",
+ " 0 | \n",
+ " 12 | \n",
+ " 2008 | \n",
+ " WD | \n",
+ " Normal | \n",
+ " 250000 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
5 rows × 81 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Id MSSubClass MSZoning ... SaleType SaleCondition SalePrice\n",
+ "0 1 60 RL ... WD Normal 208500\n",
+ "1 2 20 RL ... WD Normal 181500\n",
+ "2 3 60 RL ... WD Normal 223500\n",
+ "3 4 70 RL ... WD Abnorml 140000\n",
+ "4 5 60 RL ... WD Normal 250000\n",
+ "\n",
+ "[5 rows x 81 columns]"
+ ]
+ },
+ "metadata": {
+ "tags": []
+ },
+ "execution_count": 5
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "hRT-l3CUYvgW",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 973,
+ "referenced_widgets": [
+ "84cd4922236448a3a306a3f6e7e43c88",
+ "47375cce9026442183ab428080b82e11",
+ "fefbae2c76574bf7b31541e5f1e022ef",
+ "562caa85cf7d4a2fbf4decac3fc6983b",
+ "30410561071f463ab76e219406f2fa9c",
+ "55e0f67422e244a9842b8dcc917d493d"
+ ]
+ },
+ "outputId": "6834803b-b97a-478b-e92b-e262e6bdf6a6"
+ },
+ "source": [
+ "# Ignoring features with high null values \n",
+ "\n",
+ "demo = setup(data = data, target = 'SalePrice', \n",
+ " ignore_features = ['Alley','PoolQC','MiscFeature','Fence','FireplaceQu','Utilities'],normalize = True,\n",
+ " transformation= True, transformation_method = 'yeo-johnson', \n",
+ " transform_target = True, remove_outliers= True,\n",
+ " remove_multicollinearity = True,\n",
+ " ignore_low_variance = True, combine_rare_levels = True) "
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "text": [
+ " \n",
+ "Setup Succesfully Completed.\n"
+ ],
+ "name": "stdout"
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/html": [
+ " | Description | Value |
\n",
+ " \n",
+ " 0 | \n",
+ " session_id | \n",
+ " 2553 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " Transform Target | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " Transform Target Method | \n",
+ " box-cox | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " Original Data | \n",
+ " (1460, 81) | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " Missing Values | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 5 | \n",
+ " Numeric Features | \n",
+ " 21 | \n",
+ "
\n",
+ " \n",
+ " 6 | \n",
+ " Categorical Features | \n",
+ " 59 | \n",
+ "
\n",
+ " \n",
+ " 7 | \n",
+ " Ordinal Features | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 8 | \n",
+ " High Cardinality Features | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 9 | \n",
+ " High Cardinality Method | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 10 | \n",
+ " Sampled Data | \n",
+ " (1387, 81) | \n",
+ "
\n",
+ " \n",
+ " 11 | \n",
+ " Transformed Train Set | \n",
+ " (970, 244) | \n",
+ "
\n",
+ " \n",
+ " 12 | \n",
+ " Transformed Test Set | \n",
+ " (417, 244) | \n",
+ "
\n",
+ " \n",
+ " 13 | \n",
+ " Numeric Imputer | \n",
+ " mean | \n",
+ "
\n",
+ " \n",
+ " 14 | \n",
+ " Categorical Imputer | \n",
+ " constant | \n",
+ "
\n",
+ " \n",
+ " 15 | \n",
+ " Normalize | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 16 | \n",
+ " Normalize Method | \n",
+ " zscore | \n",
+ "
\n",
+ " \n",
+ " 17 | \n",
+ " Transformation | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 18 | \n",
+ " Transformation Method | \n",
+ " yeo-johnson | \n",
+ "
\n",
+ " \n",
+ " 19 | \n",
+ " PCA | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 20 | \n",
+ " PCA Method | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 21 | \n",
+ " PCA Components | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 22 | \n",
+ " Ignore Low Variance | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 23 | \n",
+ " Combine Rare Levels | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 24 | \n",
+ " Rare Level Threshold | \n",
+ " 0.100000 | \n",
+ "
\n",
+ " \n",
+ " 25 | \n",
+ " Numeric Binning | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 26 | \n",
+ " Remove Outliers | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 27 | \n",
+ " Outliers Threshold | \n",
+ " 0.050000 | \n",
+ "
\n",
+ " \n",
+ " 28 | \n",
+ " Remove Multicollinearity | \n",
+ " True | \n",
+ "
\n",
+ " \n",
+ " 29 | \n",
+ " Multicollinearity Threshold | \n",
+ " 0.900000 | \n",
+ "
\n",
+ " \n",
+ " 30 | \n",
+ " Clustering | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 31 | \n",
+ " Clustering Iteration | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 32 | \n",
+ " Polynomial Features | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 33 | \n",
+ " Polynomial Degree | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 34 | \n",
+ " Trignometry Features | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 35 | \n",
+ " Polynomial Threshold | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 36 | \n",
+ " Group Features | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 37 | \n",
+ " Feature Selection | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 38 | \n",
+ " Features Selection Threshold | \n",
+ " None | \n",
+ "
\n",
+ " \n",
+ " 39 | \n",
+ " Feature Interaction | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 40 | \n",
+ " Feature Ratio | \n",
+ " False | \n",
+ "
\n",
+ " \n",
+ " 41 | \n",
+ " Interaction Threshold | \n",
+ " None | \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "tags": []
+ }
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "v8tsvaw4aHHp",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000,
+ "referenced_widgets": [
+ "cd5ab1a14de5402985b82653a139d818",
+ "6e28825ce0c1497287c54a26ed64fb9b",
+ "c45d6e58845e4a7e860c7fde14ed94d2"
+ ]
+ },
+ "outputId": "1708f0d0-a5ff-4841-a3f5-634598ee507a"
+ },
+ "source": [
+ "# Blacklist Theil–Sen Regressor \n",
+ "# Auto sort on R2 \n",
+ "compare_models(blacklist = ['tr'])"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/html": [
+ " | Model | MAE | MSE | RMSE | R2 | RMSLE | MAPE | TT (Sec) |
\n",
+ " \n",
+ " 0 | \n",
+ " CatBoost Regressor | \n",
+ " 15313.6607 | \n",
+ " 776434230.5449 | \n",
+ " 25574.6520 | \n",
+ " 0.8966 | \n",
+ " 0.1216 | \n",
+ " 0.0854 | \n",
+ " 6.0545 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " Huber Regressor | \n",
+ " 14604.9714 | \n",
+ " 912236241.9322 | \n",
+ " 25213.0988 | \n",
+ " 0.8939 | \n",
+ " 0.1190 | \n",
+ " 0.0833 | \n",
+ " 0.1802 | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " Support Vector Machine | \n",
+ " 15387.0710 | \n",
+ " 795925878.7054 | \n",
+ " 26206.2707 | \n",
+ " 0.8893 | \n",
+ " 0.1252 | \n",
+ " 0.0865 | \n",
+ " 0.2447 | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " Bayesian Ridge | \n",
+ " 15381.1023 | \n",
+ " 920602470.6363 | \n",
+ " 26383.7903 | \n",
+ " 0.8880 | \n",
+ " 0.1212 | \n",
+ " 0.0855 | \n",
+ " 0.0722 | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " Light Gradient Boosting Machine | \n",
+ " 16799.0399 | \n",
+ " 837267455.9643 | \n",
+ " 27326.6238 | \n",
+ " 0.8817 | \n",
+ " 0.1303 | \n",
+ " 0.0925 | \n",
+ " 0.2839 | \n",
+ "
\n",
+ " \n",
+ " 5 | \n",
+ " Gradient Boosting Regressor | \n",
+ " 16988.6879 | \n",
+ " 900162869.8805 | \n",
+ " 27414.7745 | \n",
+ " 0.8814 | \n",
+ " 0.1312 | \n",
+ " 0.0943 | \n",
+ " 0.7129 | \n",
+ "
\n",
+ " \n",
+ " 6 | \n",
+ " Extreme Gradient Boosting | \n",
+ " 17203.8522 | \n",
+ " 890529209.3684 | \n",
+ " 27723.6269 | \n",
+ " 0.8793 | \n",
+ " 0.1338 | \n",
+ " 0.0964 | \n",
+ " 0.4334 | \n",
+ "
\n",
+ " \n",
+ " 7 | \n",
+ " Ridge Regression | \n",
+ " 16198.3462 | \n",
+ " 996008412.4994 | \n",
+ " 27658.9915 | \n",
+ " 0.8776 | \n",
+ " 0.1255 | \n",
+ " 0.0893 | \n",
+ " 0.0130 | \n",
+ "
\n",
+ " \n",
+ " 8 | \n",
+ " Random Forest | \n",
+ " 17884.1543 | \n",
+ " 918488672.4057 | \n",
+ " 28876.3710 | \n",
+ " 0.8683 | \n",
+ " 0.1407 | \n",
+ " 0.0996 | \n",
+ " 1.5661 | \n",
+ "
\n",
+ " \n",
+ " 9 | \n",
+ " Orthogonal Matching Pursuit | \n",
+ " 17525.4920 | \n",
+ " 1180290533.4058 | \n",
+ " 30383.1262 | \n",
+ " 0.8544 | \n",
+ " 0.1384 | \n",
+ " 0.0986 | \n",
+ " 0.0142 | \n",
+ "
\n",
+ " \n",
+ " 10 | \n",
+ " K Neighbors Regressor | \n",
+ " 20935.8666 | \n",
+ " 1263777102.8334 | \n",
+ " 33958.8645 | \n",
+ " 0.8201 | \n",
+ " 0.1578 | \n",
+ " 0.1129 | \n",
+ " 0.0197 | \n",
+ "
\n",
+ " \n",
+ " 11 | \n",
+ " Linear Regression | \n",
+ " 18579.5821 | \n",
+ " 1412999991.7642 | \n",
+ " 34303.1362 | \n",
+ " 0.8149 | \n",
+ " 0.8875 | \n",
+ " 0.1016 | \n",
+ " 0.0375 | \n",
+ "
\n",
+ " \n",
+ " 12 | \n",
+ " Extra Trees Regressor | \n",
+ " 21077.7765 | \n",
+ " 1450475526.5097 | \n",
+ " 37113.8801 | \n",
+ " 0.7864 | \n",
+ " 0.1648 | \n",
+ " 0.1114 | \n",
+ " 1.5526 | \n",
+ "
\n",
+ " \n",
+ " 13 | \n",
+ " Passive Aggressive Regressor | \n",
+ " 23476.6379 | \n",
+ " 1455925010.0713 | \n",
+ " 34983.9284 | \n",
+ " 0.7832 | \n",
+ " 0.1663 | \n",
+ " 0.1258 | \n",
+ " 0.0310 | \n",
+ "
\n",
+ " \n",
+ " 14 | \n",
+ " AdaBoost Regressor | \n",
+ " 24871.3695 | \n",
+ " 1596338786.3069 | \n",
+ " 38377.7193 | \n",
+ " 0.7702 | \n",
+ " 0.1783 | \n",
+ " 0.1330 | \n",
+ " 0.4744 | \n",
+ "
\n",
+ " \n",
+ " 15 | \n",
+ " Random Sample Consensus | \n",
+ " 20436.4470 | \n",
+ " 2024540158.8414 | \n",
+ " 42271.7509 | \n",
+ " 0.7199 | \n",
+ " 1.8876 | \n",
+ " 0.1166 | \n",
+ " 2.4091 | \n",
+ "
\n",
+ " \n",
+ " 16 | \n",
+ " Decision Tree | \n",
+ " 28313.9691 | \n",
+ " 2362204385.5155 | \n",
+ " 46922.6999 | \n",
+ " 0.6505 | \n",
+ " 0.2193 | \n",
+ " 0.1556 | \n",
+ " 0.0383 | \n",
+ "
\n",
+ " \n",
+ " 17 | \n",
+ " Elastic Net | \n",
+ " 48540.7327 | \n",
+ " 5644074263.3008 | \n",
+ " 73662.8744 | \n",
+ " 0.1642 | \n",
+ " 0.3367 | \n",
+ " 0.2630 | \n",
+ " 0.0100 | \n",
+ "
\n",
+ " \n",
+ " 18 | \n",
+ " Lasso Regression | \n",
+ " 55943.9350 | \n",
+ " 6918562280.5182 | \n",
+ " 81883.4356 | \n",
+ " -0.0385 | \n",
+ " 0.3877 | \n",
+ " 0.3102 | \n",
+ " 0.0097 | \n",
+ "
\n",
+ " \n",
+ " 19 | \n",
+ " Lasso Least Angle Regression | \n",
+ " 55943.9350 | \n",
+ " 6918562280.5182 | \n",
+ " 81883.4356 | \n",
+ " -0.0385 | \n",
+ " 0.3877 | \n",
+ " 0.3102 | \n",
+ " 0.0123 | \n",
+ "
\n",
+ " \n",
+ " 20 | \n",
+ " Least Angle Regression | \n",
+ " 5993932134656973907951616.0000 | \n",
+ " 34849194485222397251019231724335227216317654899884032.0000 | \n",
+ " 59033380261709037822803968.0000 | \n",
+ " -5421370651881711978246612473249811579011072.0000 | \n",
+ " 9.7590 | \n",
+ " 31547047712188772352.0000 | \n",
+ " 0.1863 | \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "tags": []
+ }
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "tags": []
+ },
+ "execution_count": 7
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "wXxDMgpWe_nj",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 297,
+ "referenced_widgets": [
+ "3c29f19233864b53ba8da01af51d572a",
+ "c59e1582725c43f282f196e76d7f8883",
+ "629dd21d247a4a63a3705add599b59dd",
+ "5ea1974eab714e209d781a04564f38aa",
+ "51b30e1917584733bcc1ad280f657a6f",
+ "e3c23703d9304ea09d7233dadc0b067f",
+ "3d8c5beac0da40168f86729f70acbb79",
+ "08c8a60ba9e94046bd2d98afe7cc741a",
+ "367ad9468f49427ca8475e5301a95ddb"
+ ]
+ },
+ "outputId": "1e60ba0d-cf32-4c8e-cb9b-a084e6a0106d"
+ },
+ "source": [
+ "# Creating models for the best estimators \n",
+ "huber = create_model('huber')\n",
+ "bayesian_ridge = create_model('br')\n",
+ "cat_boost = create_model('catboost')"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/html": [
+ " | MAE | MSE | RMSE | R2 | RMSLE | MAPE |
\n",
+ " \n",
+ " 0 | \n",
+ " 14464.0462 | \n",
+ " 796631140.1868 | \n",
+ " 28224.6548 | \n",
+ " 0.8678 | \n",
+ " 0.1055 | \n",
+ " 0.0744 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " 12317.9481 | \n",
+ " 486929512.7377 | \n",
+ " 22066.4794 | \n",
+ " 0.8870 | \n",
+ " 0.1081 | \n",
+ " 0.0685 | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " 15872.2935 | \n",
+ " 582156173.3834 | \n",
+ " 24127.9127 | \n",
+ " 0.9094 | \n",
+ " 0.1512 | \n",
+ " 0.1058 | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " 16292.3554 | \n",
+ " 623678424.8092 | \n",
+ " 24973.5545 | \n",
+ " 0.9091 | \n",
+ " 0.1106 | \n",
+ " 0.0862 | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " 25111.9159 | \n",
+ " 3283563129.2471 | \n",
+ " 57302.3833 | \n",
+ " 0.7460 | \n",
+ " 0.1700 | \n",
+ " 0.1107 | \n",
+ "
\n",
+ " \n",
+ " 5 | \n",
+ " 12310.8000 | \n",
+ " 301712699.9034 | \n",
+ " 17369.8791 | \n",
+ " 0.9566 | \n",
+ " 0.0936 | \n",
+ " 0.0705 | \n",
+ "
\n",
+ " \n",
+ " 6 | \n",
+ " 14194.3649 | \n",
+ " 427569376.3631 | \n",
+ " 20677.7508 | \n",
+ " 0.9369 | \n",
+ " 0.1294 | \n",
+ " 0.0855 | \n",
+ "
\n",
+ " \n",
+ " 7 | \n",
+ " 15042.6148 | \n",
+ " 463198310.0888 | \n",
+ " 21522.0424 | \n",
+ " 0.8863 | \n",
+ " 0.1489 | \n",
+ " 0.1021 | \n",
+ "
\n",
+ " \n",
+ " 8 | \n",
+ " 15624.3454 | \n",
+ " 522717385.2126 | \n",
+ " 22863.0135 | \n",
+ " 0.9212 | \n",
+ " 0.1124 | \n",
+ " 0.0843 | \n",
+ "
\n",
+ " \n",
+ " 9 | \n",
+ " 11905.9229 | \n",
+ " 276186153.5170 | \n",
+ " 16618.8493 | \n",
+ " 0.9455 | \n",
+ " 0.0864 | \n",
+ " 0.0654 | \n",
+ "
\n",
+ " \n",
+ " Mean | \n",
+ " 15313.6607 | \n",
+ " 776434230.5449 | \n",
+ " 25574.6520 | \n",
+ " 0.8966 | \n",
+ " 0.1216 | \n",
+ " 0.0854 | \n",
+ "
\n",
+ " \n",
+ " SD | \n",
+ " 3591.9983 | \n",
+ " 847985780.9750 | \n",
+ " 11062.1610 | \n",
+ " 0.0568 | \n",
+ " 0.0259 | \n",
+ " 0.0154 | \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "tags": []
+ }
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "RyfTEP0RhzAy",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 297,
+ "referenced_widgets": [
+ "838a3f746e6a4b6b9f3d05d6c3d506cb",
+ "3a2d5a31c1d1444ab603e67934aa6acc",
+ "11fdc00d65ad4d82950b754c7f5ef6b0",
+ "3e621330c9144f568bdc0eef124afb1a",
+ "ce93bca57c684aa3b46265d0c37eb746",
+ "c485ec5deb47455fad921d447491bb7f",
+ "5ff4ebf9ceed4072bf633bb282423dca",
+ "17633bba196a4c1897ecce8482066c29",
+ "583f1dc1beea4d75b9fe1c1f1de719e1"
+ ]
+ },
+ "outputId": "65c8f299-4e28-4131-8d96-6523ab5edfca"
+ },
+ "source": [
+ "# Tuning the created models \n",
+ "huber = tune_model(huber)\n",
+ "bayesian_ridge = tune_model(bayesian_ridge)\n",
+ "cat_boost = tune_model(cat_boost)"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/html": [
+ " | MAE | MSE | RMSE | R2 | RMSLE | MAPE |
\n",
+ " \n",
+ " 0 | \n",
+ " 15222.1797 | \n",
+ " 670566500.0937 | \n",
+ " 25895.2988 | \n",
+ " 0.8887 | \n",
+ " 0.1090 | \n",
+ " 0.0828 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " 12700.3444 | \n",
+ " 471383401.7861 | \n",
+ " 21711.3657 | \n",
+ " 0.8906 | \n",
+ " 0.1074 | \n",
+ " 0.0704 | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " 16694.3988 | \n",
+ " 633569183.1174 | \n",
+ " 25170.8002 | \n",
+ " 0.9014 | \n",
+ " 0.1566 | \n",
+ " 0.1098 | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " 17282.1157 | \n",
+ " 742530620.7051 | \n",
+ " 27249.4151 | \n",
+ " 0.8918 | \n",
+ " 0.1192 | \n",
+ " 0.0909 | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " 27664.4349 | \n",
+ " 3328893846.1072 | \n",
+ " 57696.5670 | \n",
+ " 0.7424 | \n",
+ " 0.1762 | \n",
+ " 0.1211 | \n",
+ "
\n",
+ " \n",
+ " 5 | \n",
+ " 13631.0586 | \n",
+ " 342263029.3862 | \n",
+ " 18500.3521 | \n",
+ " 0.9508 | \n",
+ " 0.1028 | \n",
+ " 0.0786 | \n",
+ "
\n",
+ " \n",
+ " 6 | \n",
+ " 14448.9475 | \n",
+ " 421609729.3052 | \n",
+ " 20533.1373 | \n",
+ " 0.9378 | \n",
+ " 0.1256 | \n",
+ " 0.0870 | \n",
+ "
\n",
+ " \n",
+ " 7 | \n",
+ " 16189.5874 | \n",
+ " 533125793.0337 | \n",
+ " 23089.5170 | \n",
+ " 0.8691 | \n",
+ " 0.1575 | \n",
+ " 0.1096 | \n",
+ "
\n",
+ " \n",
+ " 8 | \n",
+ " 16572.7477 | \n",
+ " 600491213.8336 | \n",
+ " 24504.9222 | \n",
+ " 0.9094 | \n",
+ " 0.1163 | \n",
+ " 0.0884 | \n",
+ "
\n",
+ " \n",
+ " 9 | \n",
+ " 12919.5620 | \n",
+ " 300757106.7155 | \n",
+ " 17342.3501 | \n",
+ " 0.9406 | \n",
+ " 0.0914 | \n",
+ " 0.0709 | \n",
+ "
\n",
+ " \n",
+ " Mean | \n",
+ " 16332.5377 | \n",
+ " 804519042.4084 | \n",
+ " 26169.3726 | \n",
+ " 0.8923 | \n",
+ " 0.1262 | \n",
+ " 0.0909 | \n",
+ "
\n",
+ " \n",
+ " SD | \n",
+ " 4079.7390 | \n",
+ " 852280183.3400 | \n",
+ " 10939.9718 | \n",
+ " 0.0559 | \n",
+ " 0.0264 | \n",
+ " 0.0164 | \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "tags": []
+ }
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "rjXOLZR6lTRf",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 297,
+ "referenced_widgets": [
+ "47c66341f17d40de815a82eedaf43dba",
+ "c77287c6a0dd4892b02f8e94f83360d6",
+ "2656c119068c4faa86003a43ddb52453"
+ ]
+ },
+ "outputId": "da06d194-0efd-40e3-9b50-f35120d5e76c"
+ },
+ "source": [
+ "# Blending models\n",
+ "blender = blend_models(estimator_list = [huber, bayesian_ridge, cat_boost])"
+ ],
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/html": [
+ " | MAE | MSE | RMSE | R2 | RMSLE | MAPE |
\n",
+ " \n",
+ " 0 | \n",
+ " 13233.5963 | \n",
+ " 463761320.6194 | \n",
+ " 21535.1183 | \n",
+ " 0.9230 | \n",
+ " 0.0971 | \n",
+ " 0.0713 | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " 11504.8842 | \n",
+ " 413827989.5399 | \n",
+ " 20342.7626 | \n",
+ " 0.9039 | \n",
+ " 0.1018 | \n",
+ " 0.0655 | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " 14194.1861 | \n",
+ " 464560920.4938 | \n",
+ " 21553.6753 | \n",
+ " 0.9277 | \n",
+ " 0.1431 | \n",
+ " 0.0960 | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " 14860.3248 | \n",
+ " 579523794.9158 | \n",
+ " 24073.3005 | \n",
+ " 0.9156 | \n",
+ " 0.1046 | \n",
+ " 0.0793 | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " 25506.1659 | \n",
+ " 4270880912.6006 | \n",
+ " 65351.9771 | \n",
+ " 0.6696 | \n",
+ " 0.1825 | \n",
+ " 0.1149 | \n",
+ "
\n",
+ " \n",
+ " 5 | \n",
+ " 12604.3339 | \n",
+ " 295248634.9563 | \n",
+ " 17182.8006 | \n",
+ " 0.9576 | \n",
+ " 0.0916 | \n",
+ " 0.0708 | \n",
+ "
\n",
+ " \n",
+ " 6 | \n",
+ " 12364.6512 | \n",
+ " 352687304.7260 | \n",
+ " 18779.9708 | \n",
+ " 0.9479 | \n",
+ " 0.1155 | \n",
+ " 0.0750 | \n",
+ "
\n",
+ " \n",
+ " 7 | \n",
+ " 14421.4822 | \n",
+ " 438085842.0711 | \n",
+ " 20930.5003 | \n",
+ " 0.8924 | \n",
+ " 0.1395 | \n",
+ " 0.0943 | \n",
+ "
\n",
+ " \n",
+ " 8 | \n",
+ " 13692.8294 | \n",
+ " 351155335.6424 | \n",
+ " 18739.1391 | \n",
+ " 0.9470 | \n",
+ " 0.1016 | \n",
+ " 0.0777 | \n",
+ "
\n",
+ " \n",
+ " 9 | \n",
+ " 10979.4809 | \n",
+ " 232445546.8403 | \n",
+ " 15246.1650 | \n",
+ " 0.9541 | \n",
+ " 0.0821 | \n",
+ " 0.0619 | \n",
+ "
\n",
+ " \n",
+ " Mean | \n",
+ " 14336.1935 | \n",
+ " 786217760.2406 | \n",
+ " 24373.5410 | \n",
+ " 0.9039 | \n",
+ " 0.1160 | \n",
+ " 0.0807 | \n",
+ "
\n",
+ " \n",
+ " SD | \n",
+ " 3909.8622 | \n",
+ " 1165240457.9300 | \n",
+ " 13861.7553 | \n",
+ " 0.0808 | \n",
+ " 0.0289 | \n",
+ " 0.0155 | \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "tags": []
+ }
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "dT_dnYL1na25",
+ "colab": {}
+ },
+ "source": [
+ "# Finaliszing model for predictions \n",
+ "model = finalize_model(blender)\n",
+ "predictions = predict_model(model, data = test_data)"
+ ],
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab_type": "code",
+ "id": "_3lQxyHcoCzH",
+ "colab": {}
+ },
+ "source": [
+ "# Generating CSV for Kaggle Submissions \n",
+ "sub = pd.DataFrame({\n",
+ " \"Id\": predictions['Id'],\n",
+ " \"SalePrice\": predictions['Label']\n",
+ " })\n",
+ "\n",
+ "sub.to_csv('gdrive/My Drive/Colab Notebooks/HousePrice/submission.csv', index=False)"
+ ],
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file