Decision Tree Model | BYOM | Teradata Vantage - 2.0 - Decision Tree Model - Teradata Vantage

Teradata Vantageā„¢ - Bring Your Own Model User Guide

Product
Teradata Vantage
Release Number
2.0
Release Date
October 2021
Content Type
User Guide
Publication ID
B700-1111-051K
Language
English (United States)

This Python pipeline creates a PMML Decision Tree model. Scikit-learn APIs fetch the data from Teradata Vantage. Therefore, this pipeline must specify the connection, predictors, and variables.

"""
iris_db_dt_model.py: Creates Decision Tree model
********************
*  Generated model file is in PMML format.
*  To score this model , user needs insert/upload PMML model into Vantage table
********************
"""
from sklearn import datasets, tree
import pandas as pd

from sklearn2pmml.pipeline import PMMLPipeline
from sklearn2pmml import sklearn2pmml

import os
import time
from teradataml import *

display.print_sqlmr_query = True
passwd = "alice"
uid = "alice"

con = create_context(host="server123@mydomain.com", username=uid, password=passwd)
con

train_df = DataFrame.from_query("select * from iris_train")
traid_pd = train_df.to_pandas()
traid_pd
type(traid_pd)

X = traid_pd[['sepal_length','sepal_width','petal_length', 'petal_width' ]]
y=traid_pd[['species']]
X
pipeline = PMMLPipeline([
    ("classifier", tree.DecisionTreeClassifier())
])

pipeline.fit(X, y.values.ravel())

sklearn2pmml(pipeline, "iris_db_dt_model.pmml", with_repr = True)