From 3eb48f54a6ca4bc8729e247284a4c6cf84923860 Mon Sep 17 00:00:00 2001
From: hugoPonthieu <hugo.ponthieu@etu.umontpellier.fr>
Date: Mon, 28 Oct 2024 17:14:25 +0100
Subject: [PATCH] init

---
 README.md                       | 16 +++++++++
 airflow/application.yaml        | 61 +++++++++++++++++++++++++++++++++
 dags/pipeline.py                | 51 +++++++++++++++++++++++++++
 infrastructure/application.yaml | 28 +++++++++++++++
 4 files changed, 156 insertions(+)
 create mode 100644 README.md
 create mode 100644 airflow/application.yaml
 create mode 100644 dags/pipeline.py
 create mode 100644 infrastructure/application.yaml

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..5020651
--- /dev/null
+++ b/README.md
@@ -0,0 +1,16 @@
+# Airflow X ArgoCD
+
+## Prérequis
+
+- Avoir un cluster kubernetes
+- Installer helm
+
+## Installation de ArgoCD
+
+Pour installer ArgoCD il suffit de lancer les commandes suivantes :
+
+``` bash
+kubectl create namespace argocd
+helm repo add argo https://argoproj.github.io/argo-helm
+helm install my-argo-cd argo/argo-cd --version 7.6.8 -n argocd
+```
diff --git a/airflow/application.yaml b/airflow/application.yaml
new file mode 100644
index 0000000..12b4531
--- /dev/null
+++ b/airflow/application.yaml
@@ -0,0 +1,61 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: airflow
+  namespace: argocd
+spec: 
+  project: default
+  source:
+    repoURL: https://github.com/airflow-helm/charts.git  # Airflow Helm chart repository
+    targetRevision: main
+    path: charts/airflow  # The path where the Helm chart is located in the repo
+    helm:
+      values: |
+        airflow:
+          executor: "KubernetesExecutor"
+
+        config:
+          AIRFLOW__CORE__LOAD_EXAMPLES: "False"
+          AIRFLOW__WEBSERVER__EXPOSE_CONFIG: "True"
+
+        flower:
+          enabled: false
+
+        redis:
+          enabled: false
+
+        postgresql:
+          enabled: false
+
+        workers:
+          enabled: false
+        
+        pgbouncer:
+          enabled: false
+
+        dags:
+          persistence:
+            enabled: false
+
+        web:
+          defaultUser:
+            enabled: true
+            username: "admin"
+            password: "admin"
+
+        externalDatabase:
+          type: postgres
+          host: postgresql-ha-postgresql
+          port: 5432
+          database: postgres
+          user: postgres
+          passwordSecret: "postgresql-ha-postgresql"
+          passwordSecretKey: "password"
+          
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: airflow
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
\ No newline at end of file
diff --git a/dags/pipeline.py b/dags/pipeline.py
new file mode 100644
index 0000000..1e8f940
--- /dev/null
+++ b/dags/pipeline.py
@@ -0,0 +1,51 @@
+from airflow import DAG
+from airflow.operators.python import PythonOperator, BranchPythonOperator
+from airflow.operators.bash import BashOperator
+from datetime import datetime
+from random import randint
+
+def _choose_best_model(ti):
+  accuracies = ti.xcom_pull(task_ids=[
+    'training_model_A',
+    'training_model_B',
+    'training_model_C'
+  ])
+  if max(accuracies) > 8:
+    return 'is_accurate'
+  return 'is_inaccurate'
+
+def _training_model(model):
+  print(model)
+  return randint(1, 10)
+
+with DAG("my_dag",
+  start_date=datetime(2023, 1 ,1), 
+  schedule_interval='@daily', 
+  catchup=False):
+
+  training_model_tasks = [
+    PythonOperator(
+      task_id=f"training_model_{model_id}",
+      python_callable=_training_model,
+      op_kwargs={
+        "model": model_id
+      }
+    ) for model_id in ['A', 'B', 'C']
+  ]
+
+  choose_best_model = BranchPythonOperator(
+    task_id="choose_best_model",
+    python_callable=_choose_best_model
+  )
+
+  accurate = BashOperator(
+    task_id="is_accurate",
+    bash_command="echo 'accurate'"
+  )
+
+  inaccurate = BashOperator(
+    task_id="is_inaccurate",
+    bash_command=" echo 'inaccurate'"
+  )
+
+  training_model_tasks >> choose_best_model >> [is_accurate, is_inaccurate]
\ No newline at end of file
diff --git a/infrastructure/application.yaml b/infrastructure/application.yaml
new file mode 100644
index 0000000..4e00b3b
--- /dev/null
+++ b/infrastructure/application.yaml
@@ -0,0 +1,28 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: postgresql-ha
+  namespace: argocd  # Or the namespace where Argo CD is installed
+spec:
+  project: default
+
+  source:
+    repoURL: 'https://charts.bitnami.com/bitnami'  # Example: Bitnami Helm chart repository
+    targetRevision: 14.2.34
+    chart: postgresql-ha
+    helm:
+      values: |
+        postgresql:
+          replicaCount: 3
+        replication:
+          enabled: true
+          readReplicas: 1
+
+  destination:
+    server: https://kubernetes.default.svc  # The Kubernetes API server address
+    namespace: airflow  # Namespace where PostgreSQL will be deployed
+
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true