lec 10,11

README.md

@@ -14,6 +14,8 @@
 | 17.10.2024 | [Feature extraction. Настройка гиперпараметров](./lectures/lec7-feature_selection_hyperparams.odp) - [в формате pptx](./lectures/lec7-feature_selection_hyperparams.pptx) - код в [ноутбуке к mlflow](./assets/mlflow/research.ipynb) |
 | 24.10.2024 | [Архитекура сервиса. API](./lectures/lec8-api.odp) - [в формате pptx](./lectures/lec8-api.pptx) |
 | 14.11.2024 | [Создание микросервиса](./lectures/lec9-webserver.pptx) |
+| 19.11.2024 | [Docker compose](./lectures/lec10-docker_compose.pptx) |
+| 21.11.2024 | [Мониторинг сервиса. Prometheus. Graphana](./lectures/lec11-monitoring.pptx) |
 
 
 ## <span style="color:red">Перенос занятий</span>

assets/service/compose.yml

@@ -0,0 +1,15 @@
+name: lec_app
+
+services:
+  price-predict:
+    image: estate_model:0
+    ports:
+      - "8001:8000"
+    volumes:
+      - ./models:/models
+
+
+  requests:
+    image: test_requests:2
+
+

assets/service/ml_service/main.py

@@ -2,10 +2,22 @@
 import random
 from fastapi import FastAPI
 from api_handler import FastAPIHandler
+from prometheus_fastapi_instrumentator import Instrumentator
+from prometheus_client import Histogram, Gauge, Counter, Summary
+
  
 app = FastAPI()
 app.handler = FastAPIHandler()
 
+instrumentator = Instrumentator()
+instrumentator.instrument(app).expose(app)
+
+prediction_metric = Histogram(
+    'prediction_metric_histogram',
+    'histogram of predicted prices',
+    buckets=(100000, 1000000, 3000000, 5000000, 15000000, 50000000, 100000000)
+)
+
 @app.get('/')
 def root_dir():
     return({'Hello': 'world'})
@@ -13,6 +25,9 @@ def root_dir():
 @app.post('/api/prediction')
 def make_prediction(flat_id: int, item_features: dict):
     prediction = app.handler.predict(item_features)
+
+    prediction_metric.observe(prediction)
+
     return ({
              'price': prediction,
              'flat_id': flat_id

assets/service/ml_service/requirements.txt

@@ -3,3 +3,5 @@ uvicorn
 pandas
 pickle4
 scikit-learn
+requests
+prometheus_fastapi_instrumentator

assets/service/requests/Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11-slim
+
+COPY . /app
+WORKDIR /app
+
+RUN pip install requests
+
+CMD ["python3", "req.py"]
+
+# docker build . --tag test_requests:0
+# docker run test_requests:0

assets/service/requests/req.py

@@ -0,0 +1,23 @@
+import requests
+import time
+import random
+
+time.sleep(3)
+for i in range(50):
+    params = {'flat_id': i}
+    data = {
+        "geo_lat":	51.3153190612793,
+        "geo_lon":	      37.920509338378906,
+        "region":	5952,
+        "building_type":	3,
+        "level":	random.randint(1,20),
+        "levels":	9,
+        "rooms":	2,
+        "area":	random.uniform(10, 200),
+        "kitchen_area":	10,
+        "object_type":	1,
+        "floor_level":	      "mid"
+        } 
+    response = requests.post('http://localhost:8000/api/prediction', params=params, json=data)
+    time.sleep(4)
+    print(response.json())