initial checkin (#1)

.github/workflows/fetch.yaml

@@ -0,0 +1,35 @@
+name: Fetch Data
+
+on:
+  workflow_dispatch:
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  on_schedule:
+    name: Scheduled Run
+
+    runs-on: ubuntu-22.04
+
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v4
+        id: checkout-source
+
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+
+      - uses: 'google-github-actions/auth@v2'
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
+
+      - name: execute
+        run: |
+          python src/weather_data_loader.py
+

.gitignore

@@ -0,0 +1,155 @@
+# Byte-compiled / optimized / DLL files
+**/__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+# .env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+**/venv/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# locust stats files
+false_*.csv
+true_*.csv
+
+#intellij
+*.iml
+*.idea
+
+envs/
+
+# OS files
+.DS_Store
+
+
+google_credential.json
+application_default_credentials.json
+
+**/.terraform
+terraform/.terraform.lock.hcl
+terraform/terraform.tfstate
+terraform/terraform.tfstate.backup
+
+

Makefile

@@ -0,0 +1,21 @@
+
+# Variables
+TERRAFORM_DIR := terraform
+CURRENT_DIR := $(shell pwd)
+
+.PHONY: list
+list:
+	@LC_ALL=C $(MAKE) -pRrq -f $(firstword $(MAKEFILE_LIST)) : 2>/dev/null | awk -v RS= -F: '/(^|\n)# Files(\n|$$)/,/(^|\n)# Finished Make data base/ {if ($$1 !~ "^[#.]") {print $$1}}' | sort | egrep -v -e '^[^[:alnum:]]' -e '^$@$$'
+
+
+tf_init:
+	 cd $(TERRAFORM_DIR) && terraform init ; cd $(CURRENT_DIR)
+
+
+tf_plan:
+	cd $(TERRAFORM_DIR) && terraform plan ; cd $(CURRENT_DIR)
+
+tf_apply:
+	cd $(TERRAFORM_DIR) && terraform apply ; cd $(CURRENT_DIR)
+
+

note.md

@@ -0,0 +1,137 @@
+
+#
+
+make tf_plan output
+
+
+```
+Terraform used the selected providers to generate the following execution plan. Resource actions are indicated with the following symbols:
+  + create
+
+Terraform will perform the following actions:
+
+  # google_bigquery_dataset.project_dataset will be created
+  + resource "google_bigquery_dataset" "project_dataset" {
+      + creation_time              = (known after apply)
+      + dataset_id                 = "project_dataset"
+      + default_collation          = (known after apply)
+      + delete_contents_on_destroy = false
+      + effective_labels           = (known after apply)
+      + etag                       = (known after apply)
+      + id                         = (known after apply)
+      + is_case_insensitive        = (known after apply)
+      + last_modified_time         = (known after apply)
+      + location                   = "US"
+      + max_time_travel_hours      = (known after apply)
+      + project                    = "axial-gist-411121"
+      + self_link                  = (known after apply)
+      + storage_billing_model      = (known after apply)
+      + terraform_labels           = (known after apply)
+    }
+
+  # google_storage_bucket.project-bucket will be created
+  + resource "google_storage_bucket" "project-bucket" {
+      + effective_labels            = (known after apply)
+      + force_destroy               = true
+      + id                          = (known after apply)
+      + location                    = "US"
+      + name                        = "data-engineering-zoomcamp-2024-project"
+      + project                     = (known after apply)
+      + public_access_prevention    = (known after apply)
+      + self_link                   = (known after apply)
+      + storage_class               = "STANDARD"
+      + terraform_labels            = (known after apply)
+      + uniform_bucket_level_access = (known after apply)
+      + url                         = (known after apply)
+
+      + lifecycle_rule {
+          + action {
+              + type = "AbortIncompleteMultipartUpload"
+            }
+          + condition {
+              + age                   = 1
+              + matches_prefix        = []
+              + matches_storage_class = []
+              + matches_suffix        = []
+              + with_state            = (known after apply)
+            }
+        }
+    }
+
+Plan: 2 to add, 0 to change, 0 to destroy.
+
+```
+
+# make tf_apply output
+
+
+```
+Terraform used the selected providers to generate the following execution plan. Resource actions are indicated with the following symbols:
+  + create
+
+Terraform will perform the following actions:
+
+  # google_bigquery_dataset.project_dataset will be created
+  + resource "google_bigquery_dataset" "project_dataset" {
+      + creation_time              = (known after apply)
+      + dataset_id                 = "project_dataset"
+      + default_collation          = (known after apply)
+      + delete_contents_on_destroy = false
+      + effective_labels           = (known after apply)
+      + etag                       = (known after apply)
+      + id                         = (known after apply)
+      + is_case_insensitive        = (known after apply)
+      + last_modified_time         = (known after apply)
+      + location                   = "US"
+      + max_time_travel_hours      = (known after apply)
+      + project                    = "axial-gist-411121"
+      + self_link                  = (known after apply)
+      + storage_billing_model      = (known after apply)
+      + terraform_labels           = (known after apply)
+    }
+
+  # google_storage_bucket.project-bucket will be created
+  + resource "google_storage_bucket" "project-bucket" {
+      + effective_labels            = (known after apply)
+      + force_destroy               = true
+      + id                          = (known after apply)
+      + location                    = "US"
+      + name                        = "data-engineering-zoomcamp-2024-project"
+      + project                     = (known after apply)
+      + public_access_prevention    = (known after apply)
+      + self_link                   = (known after apply)
+      + storage_class               = "STANDARD"
+      + terraform_labels            = (known after apply)
+      + uniform_bucket_level_access = (known after apply)
+      + url                         = (known after apply)
+
+      + lifecycle_rule {
+          + action {
+              + type = "AbortIncompleteMultipartUpload"
+            }
+          + condition {
+              + age                   = 1
+              + matches_prefix        = []
+              + matches_storage_class = []
+              + matches_suffix        = []
+              + with_state            = (known after apply)
+            }
+        }
+    }
+
+Plan: 2 to add, 0 to change, 0 to destroy.
+
+Do you want to perform these actions?
+  Terraform will perform the actions described above.
+  Only 'yes' will be accepted to approve.
+
+  Enter a value: yes
+
+google_bigquery_dataset.project_dataset: Creating...
+google_storage_bucket.project-bucket: Creating...
+google_bigquery_dataset.project_dataset: Creation complete after 1s [id=projects/axial-gist-411121/datasets/project_dataset]
+google_storage_bucket.project-bucket: Creation complete after 1s [id=data-engineering-zoomcamp-2024-project]
+
+Apply complete! Resources: 2 added, 0 changed, 0 destroyed.
+
+```

src/requirements.txt

@@ -0,0 +1,4 @@
+requests==2.31.0
+pandas==2.2.1
+pyarrow==15.0.2
+google-cloud-storage==2.16.0