Intro to ML: Language Processing

I used BigQuery for data processing and exploratory data analysis and the Vertex AI platform to train and deploy a custom TensorFlow Regressor model to predict customer lifetime value. 

 

Vertex AI is Google Cloud's next generation, unified platform for machine learning development and the successor to AI Platform ➡️ you can leverage the latest ML pre-built components and AutoML

 

실제 클라우드 서비스에서 hands-on lab을 해보았다.

 

project명과 아이디 등 민감한 정보가 많아 캡쳐본을 올리지는 못하지만, cloud service를 activate, authorize 해주고 (task1),

Create Vertex AI custom service account for Vertex Tensorboard integration 해준다.

 

Recency: how recently have customers purchased?

Frequency: how often are customers purchasing?¶

Monetary: how much are customers spending?¶

 

ax = baseline.plot(kind='scatter',
                   x='predicted_monetary_value_3M', 
                   y='target_monetary_value_3M',
                   title='Actual vs. Predicted customer 3-month monetary value',
                   figsize=(5,5),
                   grid=True)

lims = [
    np.min([ax.get_xlim(), ax.get_ylim()]),  # min of both axes
    np.max([ax.get_xlim(), ax.get_ylim()]),  # max of both axes
]

# now plot both limits against eachother
ax.plot(lims, lims, 'k-', alpha=0.5, zorder=0)
ax.set_aspect('equal')
ax.set_xlim(lims)
ax.set_ylim(lims);