verticapy.machine_learning.vertica.naive_bayes.NaiveBayes¶

class verticapy.machine_learning.vertica.naive_bayes.NaiveBayes(name: str = None, overwrite_model: bool = False, alpha: Annotated[int | float | Decimal, 'Python Numbers'] = 1.0, nbtype: Literal['auto', 'bernoulli', 'categorical', 'multinomial', 'gaussian'] = 'auto')¶

Creates a NaiveBayes object using the Vertica Naive Bayes algorithm. It is a “probabilistic classifier” based on applying Bayes’ theorem with strong (naïve) independence assumptions between the features.

Parameters¶

name: str, optional

Name of the model. The model is stored in the database.

overwrite_model: bool, optional

If set to True, training a model with the same name as an existing model overwrites the existing model.

alpha: float, optional

A float that specifies use of Laplace smoothing if the event model is categorical, multinomial, or Bernoulli.

nbtype: str, optional

Naive Bayes type.

auto:
Vertica NaiveBayes objects treat columns according to data type:
- FLOAT:
  values are assumed to follow some Gaussian distribution.
- INTEGER:
  values are assumed to belong to one multinomial distribution.
- CHAR/VARCHAR:
  values are assumed to follow some categorical distribution. The string values stored in these columns must be no greater than 128 characters.
- BOOLEAN:
  values are treated as categorical with two values.
bernoulli:
Casts the variables to boolean.
categorical:
Casts the variables to categorical.
multinomial:
Casts the variables to integer.
gaussian:
Casts the variables to float.

Attributes¶

Many attributes are created during the fitting phase.

prior_: numpy.array: The model’s classes probabilities.
attributes: list of dict: list of the model’s attributes. Each feature is represented by a dictionary, which differs based on the distribution.
classes_: numpy.array: The classes labels.

Note

All attributes can be accessed using the get_attributes() method.

Note

Several other attributes can be accessed by using the get_vertica_attributes() method.

Examples¶

The following examples provide a basic understanding of usage. For more detailed examples, please refer to the Machine Learning or the Examples section on the website.

Load data for machine learning¶

We import verticapy:

import verticapy as vp

Hint

By assigning an alias to verticapy, we mitigate the risk of code collisions with other libraries. This precaution is necessary because verticapy uses commonly known function names like “average” and “median”, which can potentially lead to naming conflicts. The use of an alias ensures that the functions from verticapy are used as intended without interfering with functions from other libraries.

For this example, we will use the iris dataset.

import verticapy.datasets as vpd

data = vpd.load_iris()

	123 SepalLengthCm Numeric(7)	123 SepalWidthCm Numeric(7)	123 PetalLengthCm Numeric(7)	123 PetalWidthCm Numeric(7)	Abc Species Varchar(30)
1	4.6	3.6	1.0	0.2	Iris-setosa
2	4.7	3.2	1.3	0.2	Iris-setosa
3	4.7	3.2	1.6	0.2	Iris-setosa
4	4.8	3.0	1.4	0.1	Iris-setosa
5	4.8	3.1	1.6	0.2	Iris-setosa
6	4.8	3.4	1.9	0.2	Iris-setosa
7	4.9	3.0	1.4	0.2	Iris-setosa
8	4.9	3.1	1.5	0.1	Iris-setosa
9	4.9	3.1	1.5	0.1	Iris-setosa
10	4.9	3.1	1.5	0.1	Iris-setosa
11	5.0	2.3	3.3	1.0	Iris-versicolor
12	5.0	3.4	1.5	0.2	Iris-setosa
13	5.1	3.5	1.4	0.2	Iris-setosa
14	5.4	3.0	4.5	1.5	Iris-versicolor
15	5.4	3.4	1.5	0.4	Iris-setosa
16	5.4	3.9	1.3	0.4	Iris-setosa
17	5.5	2.4	3.7	1.0	Iris-versicolor
18	5.5	2.4	3.8	1.1	Iris-versicolor
19	5.6	2.7	4.2	1.3	Iris-versicolor
20	5.7	3.0	4.2	1.2	Iris-versicolor
21	5.7	4.4	1.5	0.4	Iris-setosa
22	5.8	2.8	5.1	2.4	Iris-virginica
23	5.9	3.2	4.8	1.8	Iris-versicolor
24	6.1	3.0	4.6	1.4	Iris-versicolor
25	6.1	3.0	4.9	1.8	Iris-virginica
26	6.3	2.5	4.9	1.5	Iris-versicolor
27	6.3	3.3	4.7	1.6	Iris-versicolor
28	6.3	3.3	6.0	2.5	Iris-virginica
29	6.4	2.9	4.3	1.3	Iris-versicolor
30	6.5	3.0	5.5	1.8	Iris-virginica
31	6.5	3.0	5.8	2.2	Iris-virginica
32	6.7	3.0	5.0	1.7	Iris-versicolor
33	6.8	2.8	4.8	1.4	Iris-versicolor
34	6.8	3.2	5.9	2.3	Iris-virginica
35	7.0	3.2	4.7	1.4	Iris-versicolor
36	7.1	3.0	5.9	2.1	Iris-virginica
37	7.7	3.8	6.7	2.2	Iris-virginica
38	4.4	2.9	1.4	0.2	Iris-setosa
39	4.5	2.3	1.3	0.3	Iris-setosa
40	4.8	3.4	1.6	0.2	Iris-setosa
41	5.0	2.0	3.5	1.0	Iris-versicolor
42	5.1	3.3	1.7	0.5	Iris-setosa
43	5.1	3.4	1.5	0.2	Iris-setosa
44	5.2	2.7	3.9	1.4	Iris-versicolor
45	5.2	3.5	1.5	0.2	Iris-setosa
46	5.2	4.1	1.5	0.1	Iris-setosa
47	5.4	3.9	1.7	0.4	Iris-setosa
48	5.5	3.5	1.3	0.2	Iris-setosa
49	5.6	3.0	4.1	1.3	Iris-versicolor
50	5.8	2.7	3.9	1.2	Iris-versicolor
51	5.8	2.7	5.1	1.9	Iris-virginica
52	5.8	2.7	5.1	1.9	Iris-virginica
53	5.9	3.0	4.2	1.5	Iris-versicolor
54	5.9	3.0	5.1	1.8	Iris-virginica
55	6.0	2.7	5.1	1.6	Iris-versicolor
56	6.0	2.9	4.5	1.5	Iris-versicolor
57	6.1	2.8	4.7	1.2	Iris-versicolor
58	6.2	2.8	4.8	1.8	Iris-virginica
59	6.2	2.9	4.3	1.3	Iris-versicolor
60	6.3	2.3	4.4	1.3	Iris-versicolor
61	6.3	2.7	4.9	1.8	Iris-virginica
62	6.4	3.2	5.3	2.3	Iris-virginica
63	6.5	2.8	4.6	1.5	Iris-versicolor
64	6.5	3.0	5.2	2.0	Iris-virginica
65	6.5	3.2	5.1	2.0	Iris-virginica
66	6.6	2.9	4.6	1.3	Iris-versicolor
67	6.6	3.0	4.4	1.4	Iris-versicolor
68	6.7	3.1	4.4	1.4	Iris-versicolor
69	6.7	3.1	4.7	1.5	Iris-versicolor
70	6.9	3.1	4.9	1.5	Iris-versicolor
71	6.9	3.1	5.4	2.1	Iris-virginica
72	6.9	3.2	5.7	2.3	Iris-virginica
73	7.2	3.0	5.8	1.6	Iris-virginica
74	7.2	3.2	6.0	1.8	Iris-virginica
75	7.3	2.9	6.3	1.8	Iris-virginica
76	7.7	2.6	6.9	2.3	Iris-virginica
77	3.3	4.5	5.6	7.8	Iris-setosa
78	3.3	4.5	5.6	7.8	Iris-setosa
79	3.3	4.5	5.6	7.8	Iris-setosa
80	3.3	4.5	5.6	7.8	Iris-setosa
81	3.3	4.5	5.6	7.8	Iris-setosa
82	3.3	4.5	5.6	7.8	Iris-setosa
83	3.3	4.5	5.6	7.8	Iris-setosa
84	3.3	4.5	5.6	7.8	Iris-setosa
85	3.3	4.5	5.6	7.8	Iris-setosa
86	3.3	4.5	5.6	7.8	Iris-setosa
87	3.3	4.5	5.6	7.8	Iris-setosa
88	3.3	4.5	5.6	7.8	Iris-setosa
89	3.3	4.5	5.6	7.8	Iris-setosa
90	3.3	4.5	5.6	7.8	Iris-setosa
91	3.3	4.5	5.6	7.8	Iris-setosa
92	3.3	4.5	5.6	7.8	Iris-setosa
93	3.3	4.5	5.6	7.8	Iris-setosa
94	3.3	4.5	5.6	7.8	Iris-setosa
95	3.3	4.5	5.6	7.8	Iris-setosa
96	3.3	4.5	5.6	7.8	Iris-setosa
97	3.3	4.5	5.6	7.8	Iris-setosa
98	3.3	4.5	5.6	7.8	Iris-setosa
99	3.3	4.5	5.6	7.8	Iris-setosa
100	3.3	4.5	5.6	7.8	Iris-setosa

Rows: 1-100 | Columns: 5

Note

VerticaPy offers a wide range of sample datasets that are ideal for training and testing purposes. You can explore the full list of available datasets in the Datasets, which provides detailed information on each dataset and how to use them effectively. These datasets are invaluable resources for honing your data analysis and machine learning skills within the VerticaPy environment.

You can easily divide your dataset into training and testing subsets using the vDataFrame.train_test_split() method. This is a crucial step when preparing your data for machine learning, as it allows you to evaluate the performance of your models accurately.

data = vpd.load_iris()
train, test = data.train_test_split(test_size = 0.2)

Warning

In this case, VerticaPy utilizes seeded randomization to guarantee the reproducibility of your data split. However, please be aware that this approach may lead to reduced performance. For a more efficient data split, you can use the vDataFrame.to_db() method to save your results into tables or temporary tables. This will help enhance the overall performance of the process.

Balancing the Dataset¶

In VerticaPy, balancing a dataset to address class imbalances is made straightforward through the balance() function within the preprocessing module. This function enables users to rectify skewed class distributions efficiently. By specifying the target variable and setting parameters like the method for balancing, users can effortlessly achieve a more equitable representation of classes in their dataset. Whether opting for over-sampling, under-sampling, or a combination of both, VerticaPy’s balance() function streamlines the process, empowering users to enhance the performance and fairness of their machine learning models trained on imbalanced data.

To balance the dataset, use the following syntax.

from verticapy.machine_learning.vertica.preprocessing import balance

balanced_train = balance(
    name = "my_schema.train_balanced",
    input_relation = train,
    y = "good",
    method = "hybrid",
)

Note

With this code, a table named train_balanced is created in the my_schema schema. It can then be used to train the model. In the rest of the example, we will work with the full dataset.

Hint

Balancing the dataset is a crucial step in improving the accuracy of machine learning models, particularly when faced with imbalanced class distributions. By addressing disparities in the number of instances across different classes, the model becomes more adept at learning patterns from all classes rather than being biased towards the majority class. This, in turn, enhances the model’s ability to make accurate predictions for under-represented classes. The balanced dataset ensures that the model is not dominated by the majority class and, as a result, leads to more robust and unbiased model performance. Therefore, by employing techniques such as over-sampling, under-sampling, or a combination of both during dataset preparation, practitioners can significantly contribute to achieving higher accuracy and better generalization of their machine learning models.

Model Initialization¶

First we import the NaiveBayes model:

from verticapy.machine_learning.vertica import NaiveBayes

Then we can create the model:

model = NaiveBayes()

Hint

In verticapy 1.0.x and higher, you do not need to specify the model name, as the name is automatically assigned. If you need to re-use the model, you can fetch the model name from the model’s attributes.

Important

The model name is crucial for the model management system and versioning. It’s highly recommended to provide a name if you plan to reuse the model later.

Model Training¶

We can now fit the model:

model.fit(
    train,
    [
        "SepalLengthCm",
        "SepalWidthCm",
        "PetalLengthCm",
        "PetalWidthCm",
    ],
    "Species",
    test,
)



=======
details
=======
index|  predictor  |  type   
-----+-------------+---------
  0  |   Species   |ResponseC
  1  |SepalLengthCm|Gaussian 
  2  |SepalWidthCm |Gaussian 
  3  |PetalLengthCm|Gaussian 
  4  |PetalWidthCm |Gaussian 


=====
prior
=====
     class     |probability
---------------+-----------
  Iris-setosa  |  0.41500  
Iris-versicolor|  0.19500  
Iris-virginica |  0.39000  


===========
call_string
===========
naive_bayes('"public"."_verticapy_tmp_naivebayes_v_mldb_3135b3cc979a11efa8720242ac120002_"', '"public"."_verticapy_tmp_view_v_mldb_316d4026979a11efa8720242ac120002_"', '"species"', '"SepalLengthCm", "SepalWidthCm", "PetalLengthCm", "PetalWidthCm"' USING PARAMETERS exclude_columns='', alpha=1)

====================
gaussian.Iris-setosa
====================
index|   mu   |sigma_sq
-----+--------+--------
  1  | 4.08554| 0.79369
  2  | 3.98675| 0.38507
  3  | 3.71687| 4.26044
  4  | 4.34217|14.33637


========================
gaussian.Iris-versicolor
========================
index|   mu   |sigma_sq
-----+--------+--------
  1  | 5.91026| 0.28094
  2  | 2.75385| 0.09571
  3  | 4.22564| 0.22933
  4  | 1.32051| 0.04009


=======================
gaussian.Iris-virginica
=======================
index|   mu   |sigma_sq
-----+--------+--------
  1  | 5.54744| 1.53006
  2  | 3.74872| 0.80669
  3  | 7.38077| 4.23846
  4  | 1.91667| 0.05517


===============
Additional Info
===============
       Name       | Value  
------------------+--------
      alpha       | 1.00000
accepted_row_count|  200   
rejected_row_count|   0    

Important

To train a model, you can directly use the vDataFrame or the name of the relation stored in the database. The test set is optional and is only used to compute the test metrics. In verticapy, we don’t work using X matrices and y vectors. Instead, we work directly with lists of predictors and the response name.

Metrics¶

We can get the entire report using:

model.report()

	Iris-setosa	Iris-versicolor	Iris-virginica	avg_macro	avg_weighted	avg_micro
auc	1.0	0.9976689976689976	0.9983766233766234	0.9986818736818736	0.9987728937728937	[null]
prc_auc	1.0	0.9920798898071624	0.9979787998562702	0.996686229887811	0.9973682476943346	[null]
accuracy	1.0	0.98	0.98	0.9866666666666667	0.9868000000000001	0.9866666666666667
log_loss	0.00109386792206096	0.0172986331108811	0.0178135394391364	0.012068680157359487	0.012015571731114585	[null]
precision	1.0	0.9166666666666666	1.0	0.9722222222222222	0.9816666666666666	0.98
recall	1.0	1.0	0.9545454545454546	0.9848484848484849	0.98	0.98
f1_score	1.0	0.9565217391304348	0.9767441860465117	0.9777553083923155	0.9802022244691608	0.98
mcc	1.0	0.9450726919990827	0.9600156738532383	0.9683627886174403	0.9703228887352231	0.97
informedness	1.0	0.9743589743589745	0.9545454545454546	0.9763014763014763	0.9743589743589743	0.97
markedness	1.0	0.9166666666666665	0.9655172413793105	0.960727969348659	0.9664942528735634	0.97
csi	1.0	0.9166666666666666	0.9545454545454546	0.9570707070707071	0.9616666666666666	0.9607843137254902

Rows: 1-11 | Columns: 7

Important

Most metrics are computed using a single SQL query, but some of them might require multiple SQL queries. Selecting only the necessary metrics in the report can help optimize performance. E.g. model.report(metrics = ["auc", "accuracy"]).

For classification models, we can easily modify the cutoff to observe the effect on different metrics:

model.report(cutoff = 0.2)

	Iris-setosa	Iris-versicolor	Iris-virginica	avg_macro	avg_weighted	avg_micro
auc	1.0	0.9976689976689976	0.9983766233766234	0.9986818736818736	0.9987728937728937	[null]
prc_auc	1.0	0.9920798898071624	0.9979787998562702	0.996686229887811	0.9973682476943346	[null]
accuracy	1.0	0.98	0.98	0.9866666666666667	0.9868000000000001	0.9866666666666667
log_loss	0.00109386792206096	0.0172986331108811	0.0178135394391364	0.012068680157359487	0.012015571731114585	[null]
precision	1.0	0.9166666666666666	0.9565217391304348	0.9577294685990339	0.962536231884058	0.9615384615384616
recall	1.0	1.0	1.0	1.0	1.0	1.0
f1_score	1.0	0.9565217391304348	0.9777777777777777	0.9780998389694041	0.9806570048309178	0.9803921568627451
mcc	1.0	0.9450726919990827	0.9603958811069554	0.9684895243686794	0.9704901799268586	0.9707253433941511
informedness	1.0	0.9743589743589745	0.9642857142857144	0.9795482295482296	0.9786446886446888	0.98
markedness	1.0	0.9166666666666665	0.9565217391304348	0.9577294685990339	0.962536231884058	0.9615384615384617
csi	1.0	0.9166666666666666	0.9565217391304348	0.9577294685990339	0.962536231884058	0.9615384615384616

Rows: 1-11 | Columns: 7

You can also use the NaiveBayes.score function to compute any classification metric. The default metric is the accuracy:

model.score(metric = "f1", average = "macro")
Out[4]: 0.9777553083923155

Note

For multi-class scoring, verticapy allows the flexibility to use three averaging techniques: micro, macro and weighted. Please refer to this link for more details on how they are calculated.

Prediction¶

Prediction is straight-forward:

model.predict(
    test,
    [
        "SepalLengthCm",
        "SepalWidthCm",
        "PetalLengthCm",
        "PetalWidthCm",
    ],
    "prediction",
)

	123 SepalLengthCm Numeric(7)	123 SepalWidthCm Numeric(7)	123 PetalLengthCm Numeric(7)	123 PetalWidthCm Numeric(7)	Abc Species Varchar(30)	Abc prediction Varchar(100)
1	4.6	3.6	1.0	0.2	Iris-setosa	Iris-setosa
2	4.8	3.4	1.9	0.2	Iris-setosa	Iris-setosa
3	5.0	2.3	3.3	1.0	Iris-versicolor	Iris-versicolor
4	5.1	3.5	1.4	0.2	Iris-setosa	Iris-setosa
5	6.1	3.0	4.6	1.4	Iris-versicolor	Iris-versicolor
6	6.4	2.9	4.3	1.3	Iris-versicolor	Iris-versicolor
7	6.7	3.0	5.0	1.7	Iris-versicolor	Iris-versicolor
8	6.8	3.2	5.9	2.3	Iris-virginica	Iris-virginica
9	7.1	3.0	5.9	2.1	Iris-virginica	Iris-virginica
10	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa
11	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa
12	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa
13	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa
14	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa
15	4.3	3.0	1.1	0.1	Iris-setosa	Iris-setosa
16	5.0	3.5	1.3	0.3	Iris-setosa	Iris-setosa
17	5.0	3.5	1.6	0.6	Iris-setosa	Iris-setosa
18	5.1	3.5	1.4	0.3	Iris-setosa	Iris-setosa
19	5.5	2.6	4.4	1.2	Iris-versicolor	Iris-versicolor
20	6.0	3.4	4.5	1.6	Iris-versicolor	Iris-versicolor
21	6.1	2.8	4.0	1.3	Iris-versicolor	Iris-versicolor
22	6.3	2.5	5.0	1.9	Iris-virginica	Iris-virginica
23	6.9	3.1	5.1	2.3	Iris-virginica	Iris-virginica
24	5.2	3.5	1.5	0.2	Iris-setosa	Iris-setosa
25	5.2	4.1	1.5	0.1	Iris-setosa	Iris-setosa
26	5.5	3.5	1.3	0.2	Iris-setosa	Iris-setosa
27	6.1	2.8	4.7	1.2	Iris-versicolor	Iris-versicolor
28	6.3	2.3	4.4	1.3	Iris-versicolor	Iris-versicolor
29	6.3	2.7	4.9	1.8	Iris-virginica	Iris-versicolor
30	6.9	3.1	5.4	2.1	Iris-virginica	Iris-virginica
31	6.9	3.2	5.7	2.3	Iris-virginica	Iris-virginica
32	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
33	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
34	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
35	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
36	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
37	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
38	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
39	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
40	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
41	4.4	3.2	1.3	0.2	Iris-setosa	Iris-setosa
42	5.5	4.2	1.4	0.2	Iris-setosa	Iris-setosa
43	5.7	2.8	4.5	1.3	Iris-versicolor	Iris-versicolor
44	6.4	3.2	4.5	1.5	Iris-versicolor	Iris-versicolor
45	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
46	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
47	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
48	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
49	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica
50	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica

Rows: 1-50 | Columns: 6

Note

Predictions can be made automatically using the test set, in which case you don’t need to specify the predictors. Alternatively, you can pass only the vDataFrame to the predict() function, but in this case, it’s essential that the column names of the vDataFrame match the predictors and response name in the model.

Probabilities¶

It is also easy to get the model’s probabilities:

model.predict_proba(
    test,
    [
        "SepalLengthCm",
        "SepalWidthCm",
        "PetalLengthCm",
        "PetalWidthCm",
    ],
    "prediction",
)

	123 SepalLengthCm Numeric(7)	123 SepalWidthCm Numeric(7)	123 PetalLengthCm Numeric(7)	123 PetalWidthCm Numeric(7)	Abc Species Varchar(30)	Abc prediction Varchar(100)	Abc prediction_irissetosa Varchar(100)	Abc prediction_irisversicolor Varchar(100)	Abc prediction_irisvirginica Varchar(100)
1	4.6	3.6	1.0	0.2	Iris-setosa	Iris-setosa	1	1.99673e-17	7.13812e-13
2	4.8	3.4	1.9	0.2	Iris-setosa	Iris-setosa	1	1.12607e-11	2.45985e-12
3	5.0	2.3	3.3	1.0	Iris-versicolor	Iris-versicolor	0.0220485	0.97766	0.000291911
4	5.1	3.5	1.4	0.2	Iris-setosa	Iris-setosa	1	8.48865e-14	2.24375e-12
5	6.1	3.0	4.6	1.4	Iris-versicolor	Iris-versicolor	0.000245307	0.996889	0.00286587
6	6.4	2.9	4.3	1.3	Iris-versicolor	Iris-versicolor	6.93524e-05	0.999395	0.000535208
7	6.7	3.0	5.0	1.7	Iris-versicolor	Iris-versicolor	0.000964116	0.545336	0.4537
8	6.8	3.2	5.9	2.3	Iris-virginica	Iris-virginica	0.00277814	2.04969e-07	0.997222
9	7.1	3.0	5.9	2.1	Iris-virginica	Iris-virginica	0.000319768	6.21202e-06	0.999674
10	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa	1	2.74274e-239	1.97778e-136
11	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa	1	2.74274e-239	1.97778e-136
12	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa	1	2.74274e-239	1.97778e-136
13	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa	1	2.74274e-239	1.97778e-136
14	3.3	4.5	5.6	7.8	Iris-setosa	Iris-setosa	1	2.74274e-239	1.97778e-136
15	4.3	3.0	1.1	0.1	Iris-setosa	Iris-setosa	1	6.82381e-17	4.78456e-14
16	5.0	3.5	1.3	0.3	Iris-setosa	Iris-setosa	1	2.34306e-13	3.51505e-11
17	5.0	3.5	1.6	0.6	Iris-setosa	Iris-setosa	1	4.68594e-09	1.22179e-07
18	5.1	3.5	1.4	0.3	Iris-setosa	Iris-setosa	1	1.19124e-12	4.4719e-11
19	5.5	2.6	4.4	1.2	Iris-versicolor	Iris-versicolor	0.000237094	0.999595	0.000168385
20	6.0	3.4	4.5	1.6	Iris-versicolor	Iris-versicolor	0.00806317	0.816023	0.175914
21	6.1	2.8	4.0	1.3	Iris-versicolor	Iris-versicolor	8.38083e-05	0.999612	0.000303761
22	6.3	2.5	5.0	1.9	Iris-virginica	Iris-virginica	0.00114306	0.191146	0.807711
23	6.9	3.1	5.1	2.3	Iris-virginica	Iris-virginica	0.00368549	3.16115e-05	0.996283
24	5.2	3.5	1.5	0.2	Iris-setosa	Iris-setosa	1	4.04714e-13	2.87186e-12
25	5.2	4.1	1.5	0.1	Iris-setosa	Iris-setosa	1	2.38416e-17	8.65558e-14
26	5.5	3.5	1.3	0.2	Iris-setosa	Iris-setosa	1	1.12599e-13	4.04774e-12
27	6.1	2.8	4.7	1.2	Iris-versicolor	Iris-versicolor	0.000128818	0.99961	0.000260846
28	6.3	2.3	4.4	1.3	Iris-versicolor	Iris-versicolor	2.48038e-05	0.999365	0.000610549
29	6.3	2.7	4.9	1.8	Iris-virginica	Iris-versicolor	0.00105369	0.600495	0.398451
30	6.9	3.1	5.4	2.1	Iris-virginica	Iris-virginica	0.000991242	0.000205446	0.998803
31	6.9	3.2	5.7	2.3	Iris-virginica	Iris-virginica	0.00253763	6.79503e-07	0.997462
32	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
33	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
34	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
35	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
36	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
37	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
38	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
39	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
40	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
41	4.4	3.2	1.3	0.2	Iris-setosa	Iris-setosa	1	8.42109e-15	1.12566e-12
42	5.5	4.2	1.4	0.2	Iris-setosa	Iris-setosa	1	9.59925e-17	3.1532e-12
43	5.7	2.8	4.5	1.3	Iris-versicolor	Iris-versicolor	0.000210141	0.999274	0.000515488
44	6.4	3.2	4.5	1.5	Iris-versicolor	Iris-versicolor	0.000621606	0.977122	0.0222561
45	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
46	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
47	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
48	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
49	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652
50	4.3	4.7	9.6	1.8	Iris-virginica	Iris-virginica	0.00534796	6.42903e-38	0.994652

Rows: 1-50 | Columns: 9

Note

Probabilities are added to the vDataFrame, and VerticaPy uses the corresponding probability function in SQL behind the scenes. You can use the pos_label parameter to add only the probability of the selected category.

Confusion Matrix¶

You can obtain the confusion matrix.

model.confusion_matrix()
Out[5]: 
array([[17,  0,  0],
       [ 0, 11,  0],
       [ 0,  1, 21]])

Hint

In the context of multi-class classification, you typically work with an overall confusion matrix that summarizes the classification efficiency across all classes. However, you have the flexibility to specify a pos_label and adjust the cutoff threshold. In this case, a binary confusion matrix is computed, where the chosen class is treated as the positive class, allowing you to evaluate its efficiency as if it were a binary classification problem.

model.confusion_matrix(pos_label = "Iris-setosa", cutoff = 0.6)
Out[6]: 
array([[33,  0],
       [ 0, 17]])

Note

In classification, the cutoff is a threshold value used to determine class assignment based on predicted probabilities or scores from a classification model. In binary classification, if the predicted probability for a specific class is greater than or equal to the cutoff, the instance is assigned to the positive class; otherwise, it is assigned to the negative class. Adjusting the cutoff allows for trade-offs between true positives and false positives, enabling the model to be optimized for specific objectives or to consider the relative costs of different classification errors. The choice of cutoff is critical for tailoring the model’s performance to meet specific needs.

Main Plots (Classification Curves)¶

Classification models allow for the creation of various plots that are very helpful in understanding the model, such as the ROC Curve, PRC Curve, Cutoff Curve, Gain Curve, and more.

Most of the classification curves can be found in the Machine Learning - Classification Curve.

For example, let’s draw the model’s ROC curve.

model.roc_curve(pos_label = "Iris-setosa")

Important

Most of the curves have a parameter called nbins, which is essential for estimating metrics. The larger the nbins, the more precise the estimation, but it can significantly impact performance. Exercise caution when increasing this parameter excessively.

Hint

In binary classification, various curves can be easily plotted. However, in multi-class classification, it’s important to select the pos_label, representing the class to be treated as positive when drawing the curve.

Other Plots¶

Contour plot is another useful plot that can be produced for models with two predictors.

model.contour(pos_label = "Iris-setosa")

Important

Machine learning models with two predictors can usually benefit from their own contour plot. This visual representation aids in exploring predictions and gaining a deeper understanding of how these models perform in different scenarios. Please refer to Contour Plot for more examples.

Parameter Modification¶

In order to see the parameters:

model.get_params()
Out[7]: {'alpha': 1.0, 'nbtype': 'auto'}

And to manually change some of the parameters:

model.set_params({'alpha': 0.9})

Model Register¶

In order to register the model for tracking and versioning:

model.register("model_v1")

Please refer to /notebooks/ml/model_tracking_versioning/index.ipynb for more details on model tracking and versioning.

Model Exporting¶

To Memmodel

model.to_memmodel()

Note

MemModel objects serve as in-memory representations of machine learning models. They can be used for both in-database and in-memory prediction tasks. These objects can be pickled in the same way that you would pickle a scikit-learn model.

The following methods for exporting the model use MemModel, and it is recommended to use MemModel directly.

To SQL

You can get the SQL code by:

model.to_sql()
Out[9]: 'CASE WHEN "SepalLengthCm" IS NULL OR "SepalWidthCm" IS NULL OR "PetalLengthCm" IS NULL OR "PetalWidthCm" IS NULL THEN NULL WHEN 0.32251957572020434 * EXP(- POWER("SepalLengthCm" - 5.5474358974359, 2) / 3.06011655011654) * 0.44417860091853717 * EXP(- POWER("SepalWidthCm" - 3.74871794871795, 2) / 1.613373293373328) * 0.19377877157815893 * EXP(- POWER("PetalLengthCm" - 7.38076923076923, 2) / 8.47691308691294) * 1.698424069445676 * EXP(- POWER("PetalWidthCm" - 1.91666666666667, 2) / 0.1103463203463292) * 0.39 >= 0.4478002956817784 * EXP(- POWER("SepalLengthCm" - 4.0855421686747, 2) / 1.58738172200995) * 0.642898499888941 * EXP(- POWER("SepalWidthCm" - 3.98674698795181, 2) / 0.77013223626212) * 0.19327810066060777 * EXP(- POWER("PetalLengthCm" - 3.71686746987952, 2) / 8.520887452248) * 0.1053635639885031 * EXP(- POWER("PetalWidthCm" - 4.3421686746988, 2) / 28.6727416985012) * 0.415 AND 0.32251957572020434 * EXP(- POWER("SepalLengthCm" - 5.5474358974359, 2) / 3.06011655011654) * 0.44417860091853717 * EXP(- POWER("SepalWidthCm" - 3.74871794871795, 2) / 1.613373293373328) * 0.19377877157815893 * EXP(- POWER("PetalLengthCm" - 7.38076923076923, 2) / 8.47691308691294) * 1.698424069445676 * EXP(- POWER("PetalWidthCm" - 1.91666666666667, 2) / 0.1103463203463292) * 0.39 >= 0.7526614411763235 * EXP(- POWER("SepalLengthCm" - 5.91025641025641, 2) / 0.561889338731422) * 1.2895399654494928 * EXP(- POWER("SepalWidthCm" - 2.75384615384615, 2) / 0.191417004048581) * 0.8330750754134963 * EXP(- POWER("PetalLengthCm" - 4.22564102564103, 2) / 0.45865047233468) * 1.9923601374340967 * EXP(- POWER("PetalWidthCm" - 1.32051282051282, 2) / 0.0801889338731448) * 0.195 THEN \'Iris-virginica\' WHEN 0.7526614411763235 * EXP(- POWER("SepalLengthCm" - 5.91025641025641, 2) / 0.561889338731422) * 1.2895399654494928 * EXP(- POWER("SepalWidthCm" - 2.75384615384615, 2) / 0.191417004048581) * 0.8330750754134963 * EXP(- POWER("PetalLengthCm" - 4.22564102564103, 2) / 0.45865047233468) * 1.9923601374340967 * EXP(- POWER("PetalWidthCm" - 1.32051282051282, 2) / 0.0801889338731448) * 0.195 >= 0.4478002956817784 * EXP(- POWER("SepalLengthCm" - 4.0855421686747, 2) / 1.58738172200995) * 0.642898499888941 * EXP(- POWER("SepalWidthCm" - 3.98674698795181, 2) / 0.77013223626212) * 0.19327810066060777 * EXP(- POWER("PetalLengthCm" - 3.71686746987952, 2) / 8.520887452248) * 0.1053635639885031 * EXP(- POWER("PetalWidthCm" - 4.3421686746988, 2) / 28.6727416985012) * 0.415 THEN \'Iris-versicolor\' ELSE \'Iris-setosa\' END'

To Python

To obtain the prediction function in Python syntax, use the following code:

X = [[5, 2, 3, 1]]

model.to_python()(X)
Out[11]: array(['Iris-versicolor'], dtype='<U15')

Hint

The to_python() method is used to retrieve predictions, probabilities, or cluster distances. For specific details on how to use this method for different model types, refer to the relevant documentation for each model.

__init__(name: str = None, overwrite_model: bool = False, alpha: Annotated[int | float | Decimal, 'Python Numbers'] = 1.0, nbtype: Literal['auto', 'bernoulli', 'categorical', 'multinomial', 'gaussian'] = 'auto') → None¶: Must be overridden in the child class

Methods

`__init__`([name, overwrite_model, alpha, nbtype])	Must be overridden in the child class
`classification_report`([metrics, cutoff, ...])	Computes a classification report using multiple model evaluation metrics (`auc`, `accuracy`, `f1`...).
`confusion_matrix`([pos_label, cutoff])	Computes the model confusion matrix.
`contour`([pos_label, nbins, chart])	Draws the model's contour plot.
`cutoff_curve`([pos_label, nbins, show, chart])	Draws the model Cutoff curve.
`deploySQL`([X, pos_label, cutoff, allSQL])	Returns the SQL code needed to deploy the model.
`does_model_exists`(name[, raise_error, ...])	Checks whether the model is stored in the Vertica database.
`drop`()	Drops the model from the Vertica database.
`export_models`(name, path[, kind])	Exports machine learning models.
`fit`(input_relation, X, y[, test_relation, ...])	Trains the model.
`get_attributes`([attr_name])	Returns the model attributes.
`get_match_index`(x, col_list[, str_check])	Returns the matching index.
`get_params`()	Returns the parameters of the model.
`get_plotting_lib`([class_name, chart, ...])	Returns the first available library (Plotly, Matplotlib, or Highcharts) to draw a specific graphic.
`get_vertica_attributes`([attr_name])	Returns the model Vertica attributes.
`import_models`(path[, schema, kind])	Imports machine learning models.
`lift_chart`([pos_label, nbins, show, chart])	Draws the model Lift Chart.
`prc_curve`([pos_label, nbins, show, chart])	Draws the model PRC curve.
`predict`(vdf[, X, name, cutoff, inplace])	Predicts using the input relation.
`predict_proba`(vdf[, X, name, pos_label, inplace])	Returns the model's probabilities using the input relation.
`register`(registered_name[, raise_error])	Registers the model and adds it to in-DB Model versioning environment with a status of 'under_review'.
`report`([metrics, cutoff, labels, nbins])	Computes a classification report using multiple model evaluation metrics (`auc`, `accuracy`, `f1`...).
`roc_curve`([pos_label, nbins, show, chart])	Draws the model ROC curve.
`score`([metric, average, pos_label, cutoff, ...])	Computes the model score.
`set_params`([parameters])	Sets the parameters of the model.
`summarize`()	Summarizes the model.
`to_binary`(path)	Exports the model to the Vertica Binary format.
`to_memmodel`()	Converts the model to an InMemory object that can be used for different types of predictions.
`to_pmml`(path)	Exports the model to PMML.
`to_python`([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in Vertica functions.
`to_sql`([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in Vertica functions.
`to_tf`(path)	Exports the model to the Frozen Graph format (TensorFlow).

Attributes

object_type