update cron job

.github/workflows/actions.yml

@@ -1,15 +1,15 @@
 name: Update Job Database
-
 on:
   schedule:
-    - cron: "0 0 * * *" # Runs once a day at midnight
+    - cron: "0 0 * * *" # Daily at midnight (main.py)
+    - cron: "0 0 * * 0" # Weekly on Sunday at midnight (training_pipeline.ipynb)
   workflow_dispatch: # Allows manual triggering
 
 permissions:
   contents: write
 
 jobs:
-  update-database:
+  daily-update:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
@@ -32,7 +32,7 @@ jobs:
         with:
           timezoneLinux: "Europe/Stockholm"
 
-      - name: Run update script
+      - name: Run daily update script
         env:
           PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
         run: python main.py
@@ -43,3 +43,40 @@ jobs:
           git config --local user.name "github-actions[bot]"
           git add timestamp2.txt
           git diff --quiet && git diff --staged --quiet || (git commit -m "Update timestamp" && git push)
+
+  weekly-training:
+    runs-on: ubuntu-latest
+    if: github.event.schedule == '0 0 * * 0' # Only run on weekly schedule
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install nbconvert jupyter
+
+      - name: Run training pipeline
+        env:
+          HOPSWORKS_API_KEY: ${{ secrets.HOPSWORKS_API_KEY }}
+        run: |
+          jupyter nbconvert --to python training_pipeline.ipynb
+          python training_pipeline.py
+
+      - name: Run bootstrap script
+        run: python bootstrap.py
+
+      - name: Commit and push changes
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add .
+          git diff --quiet && git diff --staged --quiet || (git commit -m "Weekly training update" && git push)

bootstrap.py

@@ -16,6 +16,7 @@ if __name__ == '__main__':
     """
     # Initialize Pinecone handler
     handler = PineconeHandler()
+    handler.recreate_index()
     log.info('Pinecone connection initialized')
 
     if PLACES or OCCUPATIONS:

feature_pipeline.ipynb

@@ -1,282 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import hopsworks\n",
-    "import os\n",
-    "import re\n",
-    "from dotenv import load_dotenv"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2025-01-08 19:51:38,754 INFO: Closing external client and cleaning up certificates.\n",
-      "Connection closed.\n",
-      "2025-01-08 19:51:38,758 INFO: Initializing external client\n",
-      "2025-01-08 19:51:38,758 INFO: Base URL: https://c.app.hopsworks.ai:443\n",
-      "2025-01-08 19:51:39,828 INFO: Python Engine initialized.\n",
-      "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/1158296\n"
-     ]
-    }
-   ],
-   "source": [
-    "load_dotenv()\n",
-    "\n",
-    "api_key = os.getenv(\"HOPSWORKS_API_KEY\")\n",
-    "project = hopsworks.login(project=\"orestavf\", api_key_value=api_key)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "fs = project.get_feature_store()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieve feature groups\n",
-    "feedback_fg = fs.get_feature_group(name=\"job_feedback\", version=1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Finished: Reading data from Hopsworks, using Hopsworks Feature Query Service (0.93s) \n"
-     ]
-    }
-   ],
-   "source": [
-    "feedback_df = feedback_fg.read()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "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>job_id</th>\n",
-       "      <th>resume_text</th>\n",
-       "      <th>job_headline</th>\n",
-       "      <th>job_occupation</th>\n",
-       "      <th>job_description</th>\n",
-       "      <th>is_relevant</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>29321628</td>\n",
-       "      <td>Filip Orestav  \\nTransformatorvägen 6, Sollent...</td>\n",
-       "      <td>Junior Projektadmin till talangprogram på AFRY...</td>\n",
-       "      <td>Projektledare, bygg och anläggning</td>\n",
-       "      <td>Vill du kickstarta din karriär hos en av Sveri...</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "     job_id                                        resume_text  \\\n",
-       "0  29321628  Filip Orestav  \\nTransformatorvägen 6, Sollent...   \n",
-       "\n",
-       "                                        job_headline  \\\n",
-       "0  Junior Projektadmin till talangprogram på AFRY...   \n",
-       "\n",
-       "                       job_occupation  \\\n",
-       "0  Projektledare, bygg och anläggning   \n",
-       "\n",
-       "                                     job_description  is_relevant  \n",
-       "0  Vill du kickstarta din karriär hos en av Sveri...         True  "
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "feedback_df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Columns to preprocess\n",
-    "columns_to_process = ['resume_text', 'job_headline', 'job_occupation', 'job_description']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define preprocessing functions\n",
-    "def preprocess_text(text):\n",
-    "    if isinstance(text, str):\n",
-    "        # Lowercase\n",
-    "        text = text.lower()\n",
-    "        # Remove special characters (preserving letters, numbers, and spaces)\n",
-    "        text = re.sub(r\"[^a-zåäöA-Z0-9\\s]\", \"\", text)\n",
-    "        # Remove extra spaces\n",
-    "        text = re.sub(r\"\\s+\", \" \", text)\n",
-    "        return text.strip()  # Strip leading/trailing spaces\n",
-    "    return text"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2025-01-08 18:38:35,968 WARNING: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.\n",
-      "\n"
-     ]
-    },
-    {
-     "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>job_id</th>\n",
-       "      <th>resume_text</th>\n",
-       "      <th>job_headline</th>\n",
-       "      <th>job_occupation</th>\n",
-       "      <th>job_description</th>\n",
-       "      <th>is_relevant</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>29321628</td>\n",
-       "      <td>filip orestav transformatorvägen 6 sollentuna ...</td>\n",
-       "      <td>junior projektadmin till talangprogram på afry...</td>\n",
-       "      <td>projektledare bygg och anläggning</td>\n",
-       "      <td>vill du kickstarta din karriär hos en av sveri...</td>\n",
-       "      <td>True</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "     job_id                                        resume_text  \\\n",
-       "0  29321628  filip orestav transformatorvägen 6 sollentuna ...   \n",
-       "\n",
-       "                                        job_headline  \\\n",
-       "0  junior projektadmin till talangprogram på afry...   \n",
-       "\n",
-       "                      job_occupation  \\\n",
-       "0  projektledare bygg och anläggning   \n",
-       "\n",
-       "                                     job_description  is_relevant  \n",
-       "0  vill du kickstarta din karriär hos en av sveri...         True  "
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Apply preprocessing\n",
-    "feedback_df[columns_to_process] = feedback_df[columns_to_process].applymap(preprocess_text)\n",
-    "\n",
-    "# Display processed dataframe\n",
-    "feedback_df.head()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "venv",
-   "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": "3.12.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

pinecone_handler.py

@@ -199,6 +199,29 @@ class PineconeHandler:
             filter=metadata_filter if metadata_filter else None
         )
         return results.matches
+    
+    def recreate_index(self) -> None:
+        """Recreate the Pinecone index"""
+        try:
+            self.pc.delete_index(PINECONE_INDEX_NAME)
+            log.info(f"Deleted index '{PINECONE_INDEX_NAME}'")
+
+            log.info(f"Creating new index '{PINECONE_INDEX_NAME}'")
+            spec = ServerlessSpec(
+                cloud="aws",
+                region="us-east-1"
+            )
+            
+            self.pc.create_index(
+                name=PINECONE_INDEX_NAME,
+                dimension=384,
+                metric="cosine",
+                spec=spec
+            )
+            self.index = self.pc.Index(PINECONE_INDEX_NAME)
+            log.info(f"Connected to new index '{PINECONE_INDEX_NAME}'")
+        except Exception as e:
+            log.error(f"Error deleting index: {str(e)}")
 
 def load_all(all_ads):
     handler = PineconeHandler()

timestamp2.txt

@@ -1 +1 @@
-2025-01-08T02:29:02
+2025-01-08T21:34:31