diff --git a/.github/workflows/retag.yaml b/.github/workflows/retag.yaml index 5bc1dae..3098baa 100644 --- a/.github/workflows/retag.yaml +++ b/.github/workflows/retag.yaml @@ -14,7 +14,7 @@ env: PROJECT_ID: wizeline-deb GAR_LOCATION: us-central1 REPOSITORY: deb-capstone-airflow-gke - IMAGE: airflow2.7.1-custom + IMAGE: airflow2.7.3-custom VALUES_FILE: argocd-app/my-airflow/values-dev.yaml jobs: diff --git a/Dockerfile b/Dockerfile index 7bd7602..7e4b034 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,5 +1,5 @@ # Define the Airflow version -ARG AIRFLOW_VERSION=2.7.2 +ARG AIRFLOW_VERSION=2.7.3 # Using the official Apache Airflow image FROM apache/airflow:${AIRFLOW_VERSION} @@ -8,7 +8,7 @@ ARG AIRFLOW_VERSION WORKDIR /usr/local/airflow -USER root +USER root RUN mkdir /root/.dbt COPY profiles.yml /root/.dbt @@ -30,4 +30,4 @@ COPY requirements.txt . RUN pip install --upgrade pip && \ pip install --no-cache-dir \ - "apache-airflow==${AIRFLOW_VERSION}" -r requirements.txt \ No newline at end of file + "apache-airflow==${AIRFLOW_VERSION}" -r requirements.txt diff --git a/pyspark-scripts/config.py b/pyspark-scripts/config.py index bf9de21..0b2ddc2 100644 --- a/pyspark-scripts/config.py +++ b/pyspark-scripts/config.py @@ -1,7 +1,7 @@ import os GCS_BUCKET = "deb-capstone" - + # Data directories MOVIE_FILES = os.path.join("project-data", "movie_reviews") LOG_FILES = os.path.join("project-data", "log_reviews") @@ -23,4 +23,4 @@ # Define BigQuery dataset and table BQ_DATASET_NAME = "movie_analytics" BQ_MOVIE_REVIEWS_TABLE = "classified_movie_review" -BQ_LOG_REVIEWS_TABLE = "review_logs" \ No newline at end of file +BQ_LOG_REVIEWS_TABLE = "review_logs"