Added an example of grafane monitoring dashboard

module6/grafana_monitoring_dashboard/config/grafana_dashboards.yaml

@@ -0,0 +1,24 @@
+apiVersion: 1
+
+providers:
+  # <string> an unique provider name. Required
+  - name: 'Evidently Dashboards'
+    # <int> Org id. Default to 1
+    orgId: 1
+    # <string> name of the dashboard folder.
+    folder: ''
+    # <string> folder UID. will be automatically generated if not specified
+    folderUid: ''
+    # <string> provider type. Default to 'file'
+    type: file
+    # <bool> disable dashboard deletion
+    disableDeletion: false
+    # <int> how often Grafana will scan for changed dashboards
+    updateIntervalSeconds: 10
+    # <bool> allow updating provisioned dashboards from the UI
+    allowUiUpdates: false
+    options:
+      # <string, required> path to dashboard files on disk. Required when using the 'file' type
+      path: /opt/grafana/dashboards
+      # <bool> use folder names from filesystem to create folders in Grafana
+      foldersFromFilesStructure: true

module6/grafana_monitoring_dashboard/config/grafana_datasources.yaml

@@ -0,0 +1,25 @@
+# config file version
+apiVersion: 1
+
+# list of datasources that should be deleted from the database
+deleteDatasources:
+  - name: Prometheus
+    orgId: 1
+
+# list of datasources to insert/update
+# available in the database
+datasources:
+#  - name: Prometheus
+#    type: prometheus
+#    access: proxy
+#    url: http://prometheus.:9090
+  - name: PostgreSQL
+    type: postgres
+    access: proxy
+    url: db.:5432
+    database: test
+    user: postgres
+    secureJsonData:
+      password: 'example'
+    jsonData:
+      sslmode: 'disable'

module6/grafana_monitoring_dashboard/docker-compose.yml

@@ -0,0 +1,42 @@
+version: '3.7'
+
+volumes:
+    grafana_data: {}
+
+networks:
+  front-tier:
+  back-tier:
+
+services:
+  db:
+    image: postgres
+    restart: always
+    environment:
+      POSTGRES_PASSWORD: example
+    ports:
+      - "5432:5432"
+    networks:
+      - back-tier
+
+  adminer:
+    image: adminer
+    restart: always
+    ports:
+      - "8080:8080"
+    networks:
+      - back-tier
+      - front-tier
+
+  grafana:
+    image: grafana/grafana:8.5.21
+    user: "472"
+    ports:
+      - "3000:3000"
+    volumes:
+      - ./config/grafana_datasources.yaml:/etc/grafana/provisioning/datasources/datasource.yaml:ro
+      - ./config/grafana_dashboards.yaml:/etc/grafana/provisioning/dashboards/dashboards.yaml:ro
+      - ./dashboards:/opt/grafana/dashboards
+    networks:
+      - back-tier
+      - front-tier
+    restart: always

module6/grafana_monitoring_dashboard/metrics_calculation_and_logging.py

@@ -0,0 +1,70 @@
+import datetime
+import time
+import logging 
+import psycopg
+
+import pandas as pd
+
+from sklearn import datasets
+
+from evidently.report import Report
+from evidently.metrics import ColumnDriftMetric, DatasetDriftMetric
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s]: %(message)s")
+
+
+create_table_statement = """
+drop table if exists drift_metrics;
+create table drift_metrics(
+	timestamp timestamp,
+	target_drift float,
+	share_drifted_columns float
+)
+"""
+
+bank_marketing = datasets.fetch_openml(name='bank-marketing', as_frame='auto')
+bank_marketing_data = bank_marketing.frame
+
+reference_data = bank_marketing_data[5000:5500]
+prod_simulation_data = bank_marketing_data[7000:]
+mini_batch_size = 50
+
+def prep_db():
+	with psycopg.connect("host=localhost port=5432 user=postgres password=example", autocommit=True) as conn:
+		res = conn.execute("SELECT 1 FROM pg_database WHERE datname='test'")
+		if len(res.fetchall()) == 0:
+			conn.execute("create database test;")
+		with psycopg.connect("host=localhost port=5432 dbname=test user=postgres password=example") as conn:
+			conn.execute(create_table_statement)
+
+def calculate_metrics_postgresql(curr, i):
+	report = Report(
+		metrics=[
+			DatasetDriftMetric(),
+			ColumnDriftMetric(column_name="Class"),
+		])
+
+	report.run(reference_data=reference_data, current_data=prod_simulation_data[i * mini_batch_size : (i + 1) * mini_batch_size])
+
+	result = report.as_dict()
+
+	target_drift = result['metrics'][1]['result']['drift_score']
+	share_drifted_columns = result['metrics'][0]['result']['share_of_drifted_columns']
+
+	curr.execute(
+		"insert into drift_metrics(timestamp, target_drift, share_drifted_columns) values (%s, %s, %s)",
+		(datetime.datetime.now(), target_drift, share_drifted_columns)
+	)
+
+def batch_monitoring_backfill():
+	prep_db()
+	with psycopg.connect("host=localhost port=5432 dbname=test user=postgres password=example", autocommit=True) as conn:
+		for i in range(50):
+			with conn.cursor() as curr:
+				calculate_metrics_postgresql(curr, i)
+			logging.info("data sent")
+			time.sleep(3)
+
+
+if __name__ == '__main__':
+	batch_monitoring_backfill()

module6/grafana_monitoring_dashboard/requirements.txt

@@ -0,0 +1,10 @@
+evidently==0.4.8
+pandas>=1.3.5
+numpy>=1.19.5
+scikit-learn>=0.24.0
+jupyter>=1.0.0
+
+requests
+pyarrow
+psycopg
+psycopg_binary