Teradata Package for Python Function Reference on VantageCloud Lake | 17.20 - XGBoost - Teradata Package for Python - Look here for syntax, methods and examples for the functions included in the Teradata Package for Python.

# Import required libraries.
import tempfile
import getpass
from teradataml import DataFrame, load_example_data, create_context, \
db_drop_table, remove_context, save_byom, retrieve_byom, delete_byom, list_byom
from teradataml.options.configure import configure

# Create the connection.
host = getpass.getpass("Host: ")
username = getpass.getpass("Username: ")
password = getpass.getpass("Password: ")

con = create_context(host=host, username=username, password=password)

iris_input = DataFrame("iris_input")

# Convert teradataml dataframe to pandas dataframe.
# features : Training data.
# target : Training targets.
train_pd = iris_train.to_pandas()
features = train_pd.columns.drop('species')
target = 'species'

# Import required libraries.
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from xgboost import XGBClassifier

# Generate the XGBoost Classifier model.
xgb_pipe_obj = Pipeline([
    ('scaler', StandardScaler()),
    ("xgbc", XGBClassifier(n_estimators=5))
])

xgb_pipe_obj.fit(train_pd[features], train_pd[target])

# Import required libraries.
from skl2onnx import to_onnx, convert_sklearn, update_registered_converter
from skl2onnx.common.shape_calculator import calculate_linear_classifier_output_shapes
from onnxmltools.convert.xgboost.operator_converters.XGBoost import convert_xgboost

# Create temporary filepath to save model.
temp_dir = tempfile.TemporaryDirectory()
model_file_path = f"{temp_dir.name}/iris_db_xgbc_model.onnx"

# Update or register a new converter for the model pipeline
update_registered_converter(
    XGBClassifier, 'XGBoostXGBClassifier',
    calculate_linear_classifier_output_shapes, convert_xgboost,
    options={'nocl': [True, False], 'zipmap': [True]})

# Convert XGBoost model to ONNX.
onx = to_onnx(xgb_pipe_obj, train_pd.iloc[:,:4].astype(np.float32),
                            target_opset={'':12,  'ai.onnx.ml': 2})

# Save the model in ONNX format.
with open(model_file_path, "wb") as f:
    f.write(onx.SerializeToString())

# Retrieve the model from table "byom_models", using the model id 'onnx_xgb_iris'.
modeldata = retrieve_byom("onnx_xgb_iris", "byom_models")

configure.byom_install_location = getpass.getpass("byom_install_location: ")

# Import required libraries
from teradataml import ONNXPredict

# Perform prediction using ONNXPredict() and the ONNX model stored in Vantage.
predict_output = ONNXPredict(
                    modeldata = modeldata,
                    newdata = iris_test,
                    accumulate = ["id","petal_length", "petal_width"],
                    overwrite_cached_models = '*',
                    model_output_fields = "output_label"
                    )