# Steps

Create simple machine learning model
Export the model in binary format
load the model into the code
Create Simple HTTP Get Web API and add Load model into it

# Install Packages

pip install scikit-learn

pip install pandas

# Download Data

We need to download the Music file

https://github.com/mosh-hamedani/python-supplementary-materials

https://github.com/mosh-hamedani/python-supplementary-materials/blob/main/music.csv

# Codes for ML

# Step 1: ML Learning code

Sample learning code

import pandas as pd
from sklearn.tree import DecisionTreeClassifier 
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

music_data = pd.read_csv('music.csv')
X = music_data.drop(columns = ['genre'])
y = music_data['genre']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)

model = DecisionTreeClassifier()
model.fit(X_train,y_train)
predictions = model.predict(X_test)
score = accuracy_score(y_test, predictions)
print(score)

Expected result

# Step 2: Save the Model

Export the model into joblib format

import pandas as pd
from sklearn.tree import DecisionTreeClassifier 
from sklearn import tree
import joblib

music_data = pd.read_csv('music.csv')
X = music_data.drop(columns = ['genre'])
y = music_data['genre']

model = DecisionTreeClassifier()
model.fit(X,y)

joblib.dump(model,'music-recommender.joblob')

Expected Result (New file will be created)

# Step3: Load the model

Load the model into the code

import joblib

model = joblib.load('music-recommender.joblob')

predictions = model.predict([[21,1]])
print(predictions)

Expected result

# Create Simple HTTP Get Method with load ML model

Code

from fastapi import FastAPI, HTTPException
import uvicorn
import joblib
app = FastAPI()

@app.get("/chat")
def char(number=20):

    model = joblib.load('music-recommender.joblob')
    predictions = model.predict([[number,1]])

    return {"predictions for the age: "+ number +"" :predictions[0]}

if __name__ == "__main__":

    uvicorn.run(app, host="127.0.0.1", port=8080)

Create Requirements file

File

fastapi[all]==0.109.0
uvicorn[standard]==0.27.0
joblib==1.4.2
scikit-learn==1.5.2

Noting that we don't any other library

Create Docker file

File

# For more information, please refer to https://aka.ms/vscode-docker-python
FROM python:3-slim

EXPOSE 8080

# Keeps Python from generating .pyc files in the container
ENV PYTHONDONTWRITEBYTECODE=1

# Turns off buffering for easier container logging
ENV PYTHONUNBUFFERED=1

# Install pip requirements
COPY requirements.txt .
RUN python -m pip install -r requirements.txt

WORKDIR /app
COPY . /app

# Creates a non-root user with an explicit UID and adds permission to access the /app folder
# For more info, please refer to https://aka.ms/vscode-docker-python-configure-containers
RUN adduser -u 5678 --disabled-password --gecos "" appuser && chown -R appuser /app
USER appuser

# During debugging, this entry point will be overridden. For more information, please refer to https://aka.ms/vscode-docker-python-debug
#CMD ["gunicorn", "--bind", "0.0.0.0:8080", "-k", "uvicorn.workers.UvicornWorker", "main:app"]
CMD ["uvicorn","main:app","--host" ,"0.0.0.0", "--port","8080" ]

Exclude files

Create .dockerignore file

1_learn.py
2_export.py
3_load.py
music.csv

Noting excluding unneeded files from the production docker
File tree

# Build the code and dockerfile into docker (Image)

Command line
- docker build -t ml_docker:v1 .
- Expected result
- docker images
  - Expected result
- docker run -p 8080:8080 ml_docker:v1
  - Expected result

# Verify the Model response from the web browser

http://127.0.0.1:8080/chat?number=35
Expected result

# Resources

https://hub.docker.com/repository/docker/sariabuqoura/ml_docker/general