Train Test Split¶

Before you test a supervised model, you’ll need separate, non-overlapping sets for training and testing.

In VerticaPy, the train_test_split() method uses a random number generator to decide how to split the data.

%load_ext verticapy.sql

%sql -c "SELECT SEEDED_RANDOM(0);"

	123 SEEDED_RANDOM Float(22) 100%
1	0.548813502304256

The SEEDED_RANDOM function chooses a number in the interval [0,1). Since the seed is user-provided, these results are reproducible. In this example, passing 0 as the seed always returns the same value.

%sql -c "SELECT SEEDED_RANDOM(0);"

	123 SEEDED_RANDOM Float(22) 100%
1	0.548813502304256

A different seed will generate a different value.

%%sql -c "SELECT SEEDED_RANDOM(1);"

	123 SEEDED_RANDOM Float(22) 100%
1	0.417021998437122

The train_test_split() function generates a random seed and we can then share that seed between the training and testing sets.

from verticapy.datasets import load_titanic

titanic = load_titanic()

train, test = titanic.train_test_split()

titanic.shape()
Out[4]: (1234, 14)

train.shape()
Out[5]: (827, 14)

test.shape()
Out[6]: (407, 14)

Note that SEEDED_RANDOM depends on the order of your data. That is, if your data isn’t sorted by a unique feature, the selected data might be inconsistent. To avoid this, we’ll want to use the order_by parameter.

train, test = titanic.train_test_split(order_by = {"fare": "asc"})

Even if the fare has duplicates, ordering the data alone will drastically decrease the likelihood of a collision.

Let’s create a model and evaluate it.

from verticapy.machine_learning.vertica import LinearRegression

model = LinearRegression()

When fitting the model with the fit() method, you can use the parameter test_relation to score your data on a specific relation.

model.fit(
    train,
    ["age", "fare"],
    "survived",
    test,
)



=======
details
=======
predictor|coefficient|std_err |t_value |p_value 
---------+-----------+--------+--------+--------
Intercept|  0.38856  | 0.04280| 9.07873| 0.00000
   age   | -0.00292  | 0.00130|-2.25072| 0.02474
  fare   |  0.00230  | 0.00036| 6.47534| 0.00000


==============
regularization
==============
type| lambda 
----+--------
none| 1.00000


===========
call_string
===========
linear_reg('"public"."_verticapy_tmp_linearregression_v_mldb_c6571bb297bd11efa8720242ac120002_"', '"public"."_verticapy_tmp_view_v_mldb_c6be2e4c97bd11efa8720242ac120002_"', '"survived"', '"age", "fare"'
USING PARAMETERS optimizer='newton', epsilon=1e-06, max_iterations=100, regularization='none', lambda=1, alpha=0.5, fit_intercept=true)

===============
Additional Info
===============
       Name       |Value
------------------+-----
 iteration_count  |  1  
rejected_row_count| 171 
accepted_row_count| 656 

model.report()

	value
explained_variance	0.108102286704887
max_error	0.735080433990816
median_absolute_error	0.368522239457606
mean_absolute_error	0.440148554172583
mean_squared_error	0.224313432279204
root_mean_squared_error	0.464134935901705
r2	0.106661816740212
r2_adj	0.101360106453804
aic	-502.076724332947
bic	-490.714887480117

All model evaluation abstractions will now use the test relation for the scoring. After that, you can evaluate the efficiency of your model.