Feedback

×

• Feedback
• Was this page helpful?*
  • Yes
  • No
• Do you have any additional feedback?
  • Yes
  • No
• Additional Feedback

verticapy.machine_learning.model_selection.best_k

verticapy.machine_learning.model_selection.best_k(input_relation: Annotated[str | vDataFrame, ''], X: Annotated[str | list[str], 'STRING representing one column or a list of columns'] | None = None, n_cluster: tuple | list = (1, 100), init: Literal['kmeanspp', 'random', None] = None, max_iter: int = 50, tol: float = 0.0001, use_kprototype: bool = False, gamma: float = 1.0, elbow_score_stop: float = 0.8, **kwargs) → int

Finds the KMeans / KPrototypes k based on a score.

Parameters

input_relation: SQLRelation

Relation used to train the model.

X: SQLColumns, optional

list of the predictor columns. If empty, all numerical columns are used.

n_cluster: tuple | list, optional

Tuple representing the number of clusters to start and end with. This can also be a customized list with various k values to test.

init: str | list, optional

The method used to find the initial cluster centers.

• kmeanspp:

  Only available when use_kprototype = False Use the k-means++ method to initialize the centers.

• random:

  Randomly subsamples the data to find initial centers.

Default value is kmeanspp if use_kprototype = False; otherwise, random.

max_iter: int, optional

The maximum number of iterations for the algorithm.

tol: float, optional

Determines whether the algorithm has converged. The algorithm is considered converged after no center has moved more than a distance of tol from the previous iteration.

use_kprototype: bool, optional

If set to True, the function uses the KPrototypes algorithm instead of KMeans. KPrototypes can handle categorical features.

gamma: float, optional

Only if use_kprototype = True. Weighting factor for categorical columns. It determines the relative importance of numerical and categorical attributes.

elbow_score_stop: float, optional

Stops searching for parameters when the specified elbow score is reached.

Returns

int

the k-means / k-prototypes k.

Examples

The following examples provide a basic understanding of usage. For more detailed examples, please refer to the: Elbow Curve page.

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	3.3	4.5	5.6	7.8	Iris-setosa
2	3.3	4.5	5.6	7.8	Iris-setosa
3	3.3	4.5	5.6	7.8	Iris-setosa
4	3.3	4.5	5.6	7.8	Iris-setosa
5	3.3	4.5	5.6	7.8	Iris-setosa
6	3.3	4.5	5.6	7.8	Iris-setosa
7	3.3	4.5	5.6	7.8	Iris-setosa
8	3.3	4.5	5.6	7.8	Iris-setosa
9	3.3	4.5	5.6	7.8	Iris-setosa
10	3.3	4.5	5.6	7.8	Iris-setosa
11	3.3	4.5	5.6	7.8	Iris-setosa
12	3.3	4.5	5.6	7.8	Iris-setosa
13	3.3	4.5	5.6	7.8	Iris-setosa
14	3.3	4.5	5.6	7.8	Iris-setosa
15	3.3	4.5	5.6	7.8	Iris-setosa
16	3.3	4.5	5.6	7.8	Iris-setosa
17	3.3	4.5	5.6	7.8	Iris-setosa
18	3.3	4.5	5.6	7.8	Iris-setosa
19	3.3	4.5	5.6	7.8	Iris-setosa
20	3.3	4.5	5.6	7.8	Iris-setosa
21	3.3	4.5	5.6	7.8	Iris-setosa
22	3.3	4.5	5.6	7.8	Iris-setosa
23	3.3	4.5	5.6	7.8	Iris-setosa
24	3.3	4.5	5.6	7.8	Iris-setosa
25	3.3	4.5	5.6	7.8	Iris-setosa
26	3.3	4.5	5.6	7.8	Iris-setosa
27	4.3	3.0	1.1	0.1	Iris-setosa
28	4.3	4.7	9.6	1.8	Iris-virginica
29	4.3	4.7	9.6	1.8	Iris-virginica
30	4.3	4.7	9.6	1.8	Iris-virginica
31	4.3	4.7	9.6	1.8	Iris-virginica
32	4.3	4.7	9.6	1.8	Iris-virginica
33	4.3	4.7	9.6	1.8	Iris-virginica
34	4.3	4.7	9.6	1.8	Iris-virginica
35	4.3	4.7	9.6	1.8	Iris-virginica
36	4.3	4.7	9.6	1.8	Iris-virginica
37	4.3	4.7	9.6	1.8	Iris-virginica
38	4.3	4.7	9.6	1.8	Iris-virginica
39	4.3	4.7	9.6	1.8	Iris-virginica
40	4.3	4.7	9.6	1.8	Iris-virginica
41	4.3	4.7	9.6	1.8	Iris-virginica
42	4.3	4.7	9.6	1.8	Iris-virginica
43	4.3	4.7	9.6	1.8	Iris-virginica
44	4.3	4.7	9.6	1.8	Iris-virginica
45	4.3	4.7	9.6	1.8	Iris-virginica
46	4.3	4.7	9.6	1.8	Iris-virginica
47	4.3	4.7	9.6	1.8	Iris-virginica
48	4.3	4.7	9.6	1.8	Iris-virginica
49	4.3	4.7	9.6	1.8	Iris-virginica
50	4.3	4.7	9.6	1.8	Iris-virginica
51	4.3	4.7	9.6	1.8	Iris-virginica
52	4.3	4.7	9.6	1.8	Iris-virginica
53	4.3	4.7	9.6	1.8	Iris-virginica
54	4.4	2.9	1.4	0.2	Iris-setosa
55	4.4	3.0	1.3	0.2	Iris-setosa
56	4.4	3.2	1.3	0.2	Iris-setosa
57	4.5	2.3	1.3	0.3	Iris-setosa
58	4.6	3.1	1.5	0.2	Iris-setosa
59	4.6	3.2	1.4	0.2	Iris-setosa
60	4.6	3.4	1.4	0.3	Iris-setosa
61	4.6	3.6	1.0	0.2	Iris-setosa
62	4.7	3.2	1.3	0.2	Iris-setosa
63	4.7	3.2	1.6	0.2	Iris-setosa
64	4.8	3.0	1.4	0.1	Iris-setosa
65	4.8	3.0	1.4	0.3	Iris-setosa
66	4.8	3.1	1.6	0.2	Iris-setosa
67	4.8	3.4	1.6	0.2	Iris-setosa
68	4.8	3.4	1.9	0.2	Iris-setosa
69	4.9	2.4	3.3	1.0	Iris-versicolor
70	4.9	2.5	4.5	1.7	Iris-virginica
71	4.9	3.0	1.4	0.2	Iris-setosa
72	4.9	3.1	1.5	0.1	Iris-setosa
73	4.9	3.1	1.5	0.1	Iris-setosa
74	4.9	3.1	1.5	0.1	Iris-setosa
75	5.0	2.0	3.5	1.0	Iris-versicolor
76	5.0	2.3	3.3	1.0	Iris-versicolor
77	5.0	3.0	1.6	0.2	Iris-setosa
78	5.0	3.2	1.2	0.2	Iris-setosa
79	5.0	3.3	1.4	0.2	Iris-setosa
80	5.0	3.4	1.5	0.2	Iris-setosa
81	5.0	3.4	1.6	0.4	Iris-setosa
82	5.0	3.5	1.3	0.3	Iris-setosa
83	5.0	3.5	1.6	0.6	Iris-setosa
84	5.0	3.6	1.4	0.2	Iris-setosa
85	5.1	2.5	3.0	1.1	Iris-versicolor
86	5.1	3.3	1.7	0.5	Iris-setosa
87	5.1	3.4	1.5	0.2	Iris-setosa
88	5.1	3.5	1.4	0.2	Iris-setosa
89	5.1	3.5	1.4	0.3	Iris-setosa
90	5.1	3.7	1.5	0.4	Iris-setosa
91	5.1	3.8	1.5	0.3	Iris-setosa
92	5.1	3.8	1.6	0.2	Iris-setosa
93	5.1	3.8	1.9	0.4	Iris-setosa
94	5.2	2.7	3.9	1.4	Iris-versicolor
95	5.2	3.4	1.4	0.2	Iris-setosa
96	5.2	3.5	1.5	0.2	Iris-setosa
97	5.2	4.1	1.5	0.1	Iris-setosa
98	5.3	3.7	1.5	0.2	Iris-setosa
99	5.4	3.0	4.5	1.5	Iris-versicolor
100	5.4	3.4	1.5	0.4	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.

Data Exploration

Through a quick scatter plot, we can observe that the data has three main clusters.

data.scatter(
    columns = ["PetalLengthCm", "SepalLengthCm"],
    by = "Species",
)

Elbow Score

Let’s compute the optimal k for our KMeans algorithm and check if it aligns with the three clusters we observed earlier.

from verticapy.machine_learning.model_selection import best_k

best_k(
    input_relation = data,
    X = data.get_columns(exclude_columns= "Species"), # All columns except Species
    n_cluster = (1, 100),
    init = "kmeanspp",
    elbow_score_stop = 0.9,
)

Out[3]: 4

Note

You can experiment with the Elbow score to determine the optimal number of clusters. The score is based on the ratio of Between -Cluster Sum of Squares to Total Sum of Squares, providing a way to assess the clustering accuracy. A score of 1 indicates a perfect clustering.

See also

elbow() : Draws an Elbow curve.