Preparação de dados conversacional

from coreplexml import CorePlexMLClient

client = CorePlexMLClient(
    base_url="https://api.coreplexml.io",
    api_key="sk_your_api_key"
)

# Start a conversational ETL session
session = client.builder.create_session(
    project_id="proj_abc",
    file_path="raw_customers.csv"
)
print(f"Session: {session['id']}")
print(f"Rows: {session['row_count']}, Cols: {session['col_count']}")

# Chat with the AI to clean data
resp = client.builder.chat(
    session_id=session["id"],
    message="Drop the customer_id column and fill missing ages with median"
)
print(resp["reply"])
print(f"Script: {resp['script']}")  # Shows generated Python

# Execute the cleaning step
result = client.builder.execute(
    session_id=session["id"],
    step="cleaning"
)
print(f"Rows after cleaning: {result['row_count']}")

# Ask for encoding recommendations
resp = client.builder.chat(
    session_id=session["id"],
    message="One-hot encode the categorical columns and scale numerics"
)

# Export the prepared dataset
final = client.builder.finalize(session_id=session["id"])
print(f"Dataset version: {final['dataset_version_id']}")
print(f"Ready for AutoML training")