Teradata Package for Python Function Reference | 20.00 - SVR - Teradata Package for Python - Look here for syntax, methods and examples for the functions included in the Teradata Package for Python.

Teradata® Package for Python Function Reference - 20.00

Deployment

VantageCloud

VantageCore

Edition

Enterprise

IntelliFlex

VMware

Product

Teradata Package for Python

Release Number

20.00.00.03

Published

December 2024

ft:locale

en-US

ft:lastEdition

2024-12-19

dita:id

TeradataPython_FxRef_Enterprise_2000

lifecycle

latest

Product Category

Teradata Vantage

PMMLPredict() with Support Vector Machine model using Regression¶

Setup.¶

In [1]:

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

In [2]:

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

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

Host: ········
Username: ········
Password: ········

Load Example Data.¶

In [3]:

load_example_data("decisionforest", "boston")

WARNING: Skipped loading table boston since it already exists in the database.

In [4]:

boston_input = DataFrame("boston")

In [5]:

# Create 2 samples of input data - sample 1 will have 80% of total rows and sample 2 will have 20% of total rows.
boston_sample = boston_input.sample(frac=[0.8, 0.2])

In [6]:

# Create train dataset from sample 1 by filtering on "sampleid" and drop "sampleid" column as it is not required for training model.
boston_train = boston_sample[boston_sample.sampleid == "1"].drop("sampleid", axis = 1)
boston_train

Out[6]:

id	crim	zn	indus	chas	nox	rm	age	dis	rad	tax	ptratio	black	lstat	medv
448	9.92485	0	18.1	0	0.74	6.251	96	2.198	24	666	20.2	388.52	16.44	12.6
223	0.62356	0	6.2	1	0.507	6.879	77	3.2721	8	307	17.4	390.39	9.93	27.5
488	4.83567	0	18.1	0	0.583	5.905	53	3.1523	24	666	20.2	388.22	11.45	20.6
305	0.05515	33	2.18	0	0.472	7.236	41	4.022	7	222	18.4	393.68	6.93	36.1
427	12.2472	0	18.1	0	0.584	5.837	59	1.9976	24	666	20.2	24.65	15.69	10.2
469	15.5757	0	18.1	0	0.58	5.926	71	2.9084	24	666	20.2	368.74	18.13	19.1
61	0.14932	25	5.13	0	0.453	5.741	66	7.2254	8	284	19.7	395.11	13.15	18.7
326	0.19186	0	7.38	0	0.493	6.431	14	5.4159	5	287	19.6	393.68	5.08	24.6
101	0.14866	0	8.56	0	0.52	6.727	79	2.7778	5	384	20.9	394.76	9.42	27.5
40	0.02763	75	2.95	0	0.428	6.595	21	5.4011	3	252	18.3	395.63	4.32	30.8

In [7]:

# Create test dataset from sample 2 by filtering on "sampleid" and drop "sampleid" column as it is not required for scoring.
boston_test = boston_sample[boston_sample.sampleid == "2"].drop("sampleid", axis = 1)
boston_test

Out[7]:

id	crim	zn	indus	chas	nox	rm	age	dis	rad	tax	ptratio	black	lstat	medv
160	1.42502	0	19.58	0	0.871	6.51	100	1.7659	5	403	14.7	364.31	7.39	23.3
57	0.02055	85	0.74	0	0.41	6.383	35	9.1876	2	313	17.3	396.9	5.77	24.7
118	0.15098	0	10.01	0	0.547	6.021	82	2.7474	6	432	17.8	394.51	10.3	19.2
282	0.03705	20	3.33	0	0.4429	6.968	37	5.2447	5	216	14.9	392.23	4.59	35.4
299	0.06466	70	2.24	0	0.4	6.345	20	7.8278	5	358	14.8	368.24	4.97	22.5
467	3.77498	0	18.1	0	0.655	5.952	84	2.8715	24	666	20.2	22.01	17.15	19.0
221	0.35809	0	6.2	1	0.507	6.951	88	2.8617	8	307	17.4	391.7	9.71	26.7
116	0.17134	0	10.01	0	0.547	5.928	88	2.4631	6	432	17.8	344.91	15.76	18.3
34	1.15172	0	8.14	0	0.538	5.701	95	3.7872	4	307	21.0	358.77	18.35	13.1
162	1.46336	0	19.58	0	0.605	7.489	90	1.9709	5	403	14.7	374.43	1.73	50.0

Train SVM Regression Model¶

In [8]:

# Import required libraries.
import numpy as np
from nyoka import skl_to_pmml
from sklearn.pipeline import Pipeline
from sklearn.svm import SVR

In [9]:

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

In [10]:

# Generate the SVM Regression model.
regr = Pipeline([
    ("svr", SVR(kernel= 'linear'))
                ])

In [11]:

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

Out[11]:

Pipeline(steps=[('svr', SVR(kernel='linear'))])

Save the model in PMML format.¶

In [12]:

temp_dir = tempfile.TemporaryDirectory()
model_file_path = f"{temp_dir.name}/boston_db_svr_model.pmml"

In [13]:

skl_to_pmml(regr, features, target, model_file_path)

Save the model in Vantage.¶

In [14]:

# Save the PMML Model in Vantage.
save_byom("pmml_svr_boston", model_file_path, "byom_models")

Created the model table 'byom_models' as it does not exist.
Model is saved.

List the models from Vanatge¶

In [15]:

# List the PMML Models in Vantage.
list_byom("byom_models")

                                    model
model_id                                 
pmml_svr_boston  b'3C3F786D6C20766572...'

Retrieve the model from Vantage.¶

In [16]:

# Retrieve the model from table "byom_models", using the model id 'pmml_svr_boston'.

modeldata = retrieve_byom("pmml_svr_boston", "byom_models")

Set "configure.byom_install_location" to the database where BYOM functions are installed.¶

In [17]:

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

byom_install_location: ········

Score the model.¶

In [18]:

# Perform prediction using PMMLPredict() and the PMML model stored in Vantage.
result = PMMLPredict(
                    modeldata = modeldata,
                    newdata = boston_test,
                    accumulate = ['id', 'rm', 'lstat','ptratio'],
                    overwrite_cached_models = '*',
                    )

In [19]:

# Print the query.
print(result.show_query())

SELECT * FROM "mldb".PMMLPredict(
	ON "MLDB"."ml__select__1645517679699217" AS InputTable
	PARTITION BY ANY 
	ON (select model_id,model from "MLDB"."ml__filter__1645521215241325") AS ModelTable
	DIMENSION
	USING
	Accumulate('id','rm','lstat','ptratio')
	OverwriteCachedModel('*')
) as sqlmr

In [20]:

# Print the result.
result.result

Out[20]:

id	rm	lstat	ptratio	prediction	json_report
467	5.952	17.15	20.2	11.312941660878282	{"predicted_medv":11.312941660878282}
322	6.376	6.87	19.6	24.24203555205095	{"predicted_medv":24.24203555205095}
301	6.871	6.07	14.8	29.780764973146873	{"predicted_medv":29.780764973146873}
406	5.683	22.98	20.2	9.163877780148328	{"predicted_medv":9.163877780148328}
278	6.826	4.16	17.6	32.04837204324504	{"predicted_medv":32.04837204324504}
160	6.51	7.39	14.7	26.214879231825037	{"predicted_medv":26.214879231825037}
465	6.209	13.22	20.2	19.157576835196963	{"predicted_medv":19.157576835196963}
177	6.02	10.11	16.6	24.57108833740422	{"predicted_medv":24.57108833740422}
343	6.54	8.65	15.9	24.04016286752376	{"predicted_medv":24.04016286752376}
282	6.968	4.59	14.9	33.103048511903765	{"predicted_medv":33.103048511903765}

Cleanup.¶

In [21]:

# Delete the model from table "byom_models", using the model id 'pmml_svr_boston'.
delete_byom("pmml_svr_boston", "byom_models")

Model is deleted.

In [22]:

# Drop models table.
db_drop_table("byom_models")

Out[22]:

True

In [24]:

# Drop input data tables. 
db_drop_table("boston")

Out[24]:

True

In [25]:

# One must run remove_context() to close the connection and garbage collect internally generated objects.
remove_context()

Out[25]:

True

In [ ]: