Appli

.github/workflows/test.yaml

@@ -28,4 +28,4 @@ jobs:
         run: |
           pylint src --fail-under=6
       - name: Test Python code
-        run: python main.py
+        run: python train.py

.gitignore

@@ -1,4 +1,5 @@
 config.yaml
 __pycache__/
 data/**/*.csv
-titanic/
+titanic/
+model.joblib

Dockerfile

@@ -6,6 +6,7 @@ RUN apt-get -y update && \
 # Install project dependencies
 COPY requirements.txt .
 RUN pip install -r requirements.txt
-COPY main.py .
+COPY train.py .
 COPY src ./src
-CMD ["python3", "main.py"]
+COPY api ./api
+CMD ["bash", "-c", "./api/run.sh"]

api/main.py

@@ -0,0 +1,51 @@
+"""A simple API to expose our trained RandomForest model for Tutanic survival."""
+from fastapi import FastAPI
+from joblib import load
+
+import pandas as pd
+
+model = load('model.joblib')
+
+app = FastAPI(
+    title="Prédiction de survie sur le Titanic",
+    description=
+    "Application de prédiction de survie sur le Titanic 🚢 <br>Une version par API pour faciliter la réutilisation du modèle 🚀" +\
+        "<br><br><img src=\"https://media.vogue.fr/photos/5faac06d39c5194ff9752ec9/1:1/w_2404,h_2404,c_limit/076_CHL_126884.jpg\" width=\"200\">"
+    )
+
+
+@app.get("/", tags=["Welcome"])
+def show_welcome_page():
+    """
+    Show welcome page with model name and version.
+    """
+
+    return {
+        "Message": "API de prédiction de survie sur le Titanic",
+        "Model_name": 'Titanic ML',
+        "Model_version": "0.1",
+    }
+
+
+@app.get("/predict", tags=["Predict"])
+async def predict(
+    sex: str = "female",
+    age: float = 29.0,
+    fare: float = 16.5,
+    embarked: str = "S"
+) -> str:
+    """
+    """
+
+    df = pd.DataFrame(
+        {
+            "Sex": [sex],
+            "Age": [age],
+            "Fare": [fare],
+            "Embarked": [embarked],
+        }
+    )
+
+    prediction = "Survived 🎉" if int(model.predict(df)) == 1 else "Dead ⚰️"
+
+    return prediction

api/run.sh

@@ -0,0 +1,3 @@
+#/bin/bash
+python3 train.py
+uvicorn api.main:app --reload --host "0.0.0.0" --port 5000

main.py → train.py

@@ -5,6 +5,7 @@
 import argparse
 import pathlib
 import pandas as pd
+from joblib import dump
 
 from src.data.import_data import import_yaml_config
 from src.pipeline.build_pipeline import split_train_test, create_pipeline
@@ -53,6 +54,7 @@
 
 pipe.fit(X_train, y_train)
 
+dump(pipe, 'model.joblib')
 
 # Evaluate the model
 score, matrix = evaluate_model(pipe, X_test, y_test)