Dev

.github/workflows/azure-static-web-apps-ambitious-river-027ce991e.yml

@@ -0,0 +1,46 @@
+name: Azure Static Web Apps CI/CD
+
+on:
+  push:
+    branches:
+      - dev
+  pull_request:
+    types: [opened, synchronize, reopened, closed]
+    branches:
+      - dev
+
+jobs:
+  build_and_deploy_job:
+    if: github.event_name == 'push' || (github.event_name == 'pull_request' && github.event.action != 'closed')
+    runs-on: ubuntu-latest
+    name: Build and Deploy Job
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          submodules: true
+          lfs: false
+      - name: Build And Deploy
+        id: builddeploy
+        uses: Azure/static-web-apps-deploy@v1
+        with:
+          azure_static_web_apps_api_token: ${{ secrets.AZURE_STATIC_WEB_APPS_API_TOKEN_AMBITIOUS_RIVER_027CE991E }}
+          repo_token: ${{ secrets.GITHUB_TOKEN }} # Used for Github integrations (i.e. PR comments)
+          action: "upload"
+          ###### Repository/Build Configurations - These values can be configured to match your app requirements. ######
+          # For more information regarding Static Web App workflow configurations, please visit: https://aka.ms/swaworkflowconfig
+          app_location: "./web" # App source code path
+          api_location: "" # Api source code path - optional
+          output_location: "." # Built app content directory - optional
+          ###### End of Repository/Build Configurations ######
+
+  close_pull_request_job:
+    if: github.event_name == 'pull_request' && github.event.action == 'closed'
+    runs-on: ubuntu-latest
+    name: Close Pull Request Job
+    steps:
+      - name: Close Pull Request
+        id: closepullrequest
+        uses: Azure/static-web-apps-deploy@v1
+        with:
+          azure_static_web_apps_api_token: ${{ secrets.AZURE_STATIC_WEB_APPS_API_TOKEN_AMBITIOUS_RIVER_027CE991E }}
+          action: "close"

.gitignore

@@ -10,7 +10,14 @@ __pycache__/
 # C extensions
 *.so
 
+*.pbix
+
 # Distribution / packaging
+topic_senti_model
+Recommender_System_Newdata.csv
+restaurant_recommender_Final_model/
+api/*.json
+.vscode/
 .Python
 doc/
 yelp_dataset/

App/preprocess/checkindata_process.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "C:\\Lambton\\Term_3\\BDM 3035 - Big Data Capstone Project 01\\project"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# Load the data\n",
+    "input_file = '..\\..\\yelp_dataset\\medium\\yelp.checkin.csv'  # Update this to your file path\n",
+    "output_file = '..\\..\\yelp_dataset\\medium\\processed_checkin.csv'\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Read the CSV file'..\\..\\yelp_dataset\\medium\\yelp.checkin.csv'\n",
+    "df = pd.read_csv(input_file)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<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>business_id</th>\n",
+       "      <th>date</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>---kPU91CF4Lq2-WlRu9Lw</td>\n",
+       "      <td>2020-03-13 21:10:56, 2020-06-02 22:18:06, 2020...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>--0iUa4sNDFiZFrAdIWhZQ</td>\n",
+       "      <td>2010-09-13 21:43:09, 2011-05-04 23:08:15, 2011...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>--30_8IhuyMHbSOcNWd6DQ</td>\n",
+       "      <td>2013-06-14 23:29:17, 2014-08-13 23:20:22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>--7PUidqRWpRSpXebiyxTg</td>\n",
+       "      <td>2011-02-15 17:12:00, 2011-07-28 02:46:10, 2012...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>--7jw19RH9JKXgFohspgQw</td>\n",
+       "      <td>2014-04-21 20:42:11, 2014-04-28 21:04:46, 2014...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49995</th>\n",
+       "      <td>NJaR_2hke7NNAC6l1Ohr8g</td>\n",
+       "      <td>2015-01-16 02:17:10, 2015-01-16 04:45:59, 2015...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49996</th>\n",
+       "      <td>NJcoVbVwnYigsQVDOgl29Q</td>\n",
+       "      <td>2013-07-27 23:05:38, 2013-08-10 22:42:26, 2013...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49997</th>\n",
+       "      <td>NJe5fkia_63rdKXRdJlmkA</td>\n",
+       "      <td>2018-12-08 02:43:45, 2018-12-09 23:34:42, 2018...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49998</th>\n",
+       "      <td>NJg2ookzRGD2Ej-VNpuY-w</td>\n",
+       "      <td>2010-11-02 23:09:05, 2010-11-05 14:10:24, 2011...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49999</th>\n",
+       "      <td>NJhWEmpgMTo_QtndFqu3Hg</td>\n",
+       "      <td>2018-04-03 01:12:08, 2018-04-11 00:48:20, 2018...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>50000 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  business_id  \\\n",
+       "0      ---kPU91CF4Lq2-WlRu9Lw   \n",
+       "1      --0iUa4sNDFiZFrAdIWhZQ   \n",
+       "2      --30_8IhuyMHbSOcNWd6DQ   \n",
+       "3      --7PUidqRWpRSpXebiyxTg   \n",
+       "4      --7jw19RH9JKXgFohspgQw   \n",
+       "...                       ...   \n",
+       "49995  NJaR_2hke7NNAC6l1Ohr8g   \n",
+       "49996  NJcoVbVwnYigsQVDOgl29Q   \n",
+       "49997  NJe5fkia_63rdKXRdJlmkA   \n",
+       "49998  NJg2ookzRGD2Ej-VNpuY-w   \n",
+       "49999  NJhWEmpgMTo_QtndFqu3Hg   \n",
+       "\n",
+       "                                                    date  \n",
+       "0      2020-03-13 21:10:56, 2020-06-02 22:18:06, 2020...  \n",
+       "1      2010-09-13 21:43:09, 2011-05-04 23:08:15, 2011...  \n",
+       "2               2013-06-14 23:29:17, 2014-08-13 23:20:22  \n",
+       "3      2011-02-15 17:12:00, 2011-07-28 02:46:10, 2012...  \n",
+       "4      2014-04-21 20:42:11, 2014-04-28 21:04:46, 2014...  \n",
+       "...                                                  ...  \n",
+       "49995  2015-01-16 02:17:10, 2015-01-16 04:45:59, 2015...  \n",
+       "49996  2013-07-27 23:05:38, 2013-08-10 22:42:26, 2013...  \n",
+       "49997  2018-12-08 02:43:45, 2018-12-09 23:34:42, 2018...  \n",
+       "49998  2010-11-02 23:09:05, 2010-11-05 14:10:24, 2011...  \n",
+       "49999  2018-04-03 01:12:08, 2018-04-11 00:48:20, 2018...  \n",
+       "\n",
+       "[50000 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Processed data saved to ..\\..\\yelp_dataset\\medium\\processed_checkin.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Split the 'date' column to multiple rows based on commas and trim spaces\n",
+    "df = df.assign(date=df['date'].str.split(',')).explode('date')\n",
+    "df['date'] = df['date'].str.strip()\n",
+    "\n",
+    "# Save the processed data to a new CSV file\n",
+    "df.to_csv(output_file, index=False)\n",
+    "\n",
+    "print(f\"Processed data saved to {output_file}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}