VerticaPy

Python API for Vertica Data Science at Scale

Example: Methods in a Decomposition Model¶

In this example, we use the 'Iris' dataset to demonstrate the methods available to decomposition models.

In [1]:

from verticapy.datasets import load_iris
iris = load_iris()
display(iris)

	123 SepalLengthCm Numeric(5,2)	123 SepalWidthCm Numeric(5,2)	123 PetalLengthCm Numeric(5,2)	123 PetalWidthCm Numeric(5,2)	Abc Species Varchar(30)
1	4.3	3.0	1.1	0.1	Iris-setosa
2	4.4	2.9	1.4	0.2	Iris-setosa
3	4.4	3.0	1.3	0.2	Iris-setosa
4	4.4	3.2	1.3	0.2	Iris-setosa
5	4.5	2.3	1.3	0.3	Iris-setosa
6	4.6	3.1	1.5	0.2	Iris-setosa
7	4.6	3.2	1.4	0.2	Iris-setosa
8	4.6	3.4	1.4	0.3	Iris-setosa
9	4.6	3.6	1.0	0.2	Iris-setosa
10	4.7	3.2	1.3	0.2	Iris-setosa
11	4.7	3.2	1.6	0.2	Iris-setosa
12	4.8	3.0	1.4	0.1	Iris-setosa
13	4.8	3.0	1.4	0.3	Iris-setosa
14	4.8	3.1	1.6	0.2	Iris-setosa
15	4.8	3.4	1.6	0.2	Iris-setosa
16	4.8	3.4	1.9	0.2	Iris-setosa
17	4.9	2.4	3.3	1.0	Iris-versicolor
18	4.9	2.5	4.5	1.7	Iris-virginica
19	4.9	3.0	1.4	0.2	Iris-setosa
20	4.9	3.1	1.5	0.1	Iris-setosa
21	4.9	3.1	1.5	0.1	Iris-setosa
22	4.9	3.1	1.5	0.1	Iris-setosa
23	5.0	2.0	3.5	1.0	Iris-versicolor
24	5.0	2.3	3.3	1.0	Iris-versicolor
25	5.0	3.0	1.6	0.2	Iris-setosa
26	5.0	3.2	1.2	0.2	Iris-setosa
27	5.0	3.3	1.4	0.2	Iris-setosa
28	5.0	3.4	1.5	0.2	Iris-setosa
29	5.0	3.4	1.6	0.4	Iris-setosa
30	5.0	3.5	1.3	0.3	Iris-setosa
31	5.0	3.5	1.6	0.6	Iris-setosa
32	5.0	3.6	1.4	0.2	Iris-setosa
33	5.1	2.5	3.0	1.1	Iris-versicolor
34	5.1	3.3	1.7	0.5	Iris-setosa
35	5.1	3.4	1.5	0.2	Iris-setosa
36	5.1	3.5	1.4	0.2	Iris-setosa
37	5.1	3.5	1.4	0.3	Iris-setosa
38	5.1	3.7	1.5	0.4	Iris-setosa
39	5.1	3.8	1.5	0.3	Iris-setosa
40	5.1	3.8	1.6	0.2	Iris-setosa
41	5.1	3.8	1.9	0.4	Iris-setosa
42	5.2	2.7	3.9	1.4	Iris-versicolor
43	5.2	3.4	1.4	0.2	Iris-setosa
44	5.2	3.5	1.5	0.2	Iris-setosa
45	5.2	4.1	1.5	0.1	Iris-setosa
46	5.3	3.7	1.5	0.2	Iris-setosa
47	5.4	3.0	4.5	1.5	Iris-versicolor
48	5.4	3.4	1.5	0.4	Iris-setosa
49	5.4	3.4	1.7	0.2	Iris-setosa
50	5.4	3.7	1.5	0.2	Iris-setosa
51	5.4	3.9	1.3	0.4	Iris-setosa
52	5.4	3.9	1.7	0.4	Iris-setosa
53	5.5	2.3	4.0	1.3	Iris-versicolor
54	5.5	2.4	3.7	1.0	Iris-versicolor
55	5.5	2.4	3.8	1.1	Iris-versicolor
56	5.5	2.5	4.0	1.3	Iris-versicolor
57	5.5	2.6	4.4	1.2	Iris-versicolor
58	5.5	3.5	1.3	0.2	Iris-setosa
59	5.5	4.2	1.4	0.2	Iris-setosa
60	5.6	2.5	3.9	1.1	Iris-versicolor
61	5.6	2.7	4.2	1.3	Iris-versicolor
62	5.6	2.8	4.9	2.0	Iris-virginica
63	5.6	2.9	3.6	1.3	Iris-versicolor
64	5.6	3.0	4.1	1.3	Iris-versicolor
65	5.6	3.0	4.5	1.5	Iris-versicolor
66	5.7	2.5	5.0	2.0	Iris-virginica
67	5.7	2.6	3.5	1.0	Iris-versicolor
68	5.7	2.8	4.1	1.3	Iris-versicolor
69	5.7	2.8	4.5	1.3	Iris-versicolor
70	5.7	2.9	4.2	1.3	Iris-versicolor
71	5.7	3.0	4.2	1.2	Iris-versicolor
72	5.7	3.8	1.7	0.3	Iris-setosa
73	5.7	4.4	1.5	0.4	Iris-setosa
74	5.8	2.6	4.0	1.2	Iris-versicolor
75	5.8	2.7	3.9	1.2	Iris-versicolor
76	5.8	2.7	4.1	1.0	Iris-versicolor
77	5.8	2.7	5.1	1.9	Iris-virginica
78	5.8	2.7	5.1	1.9	Iris-virginica
79	5.8	2.8	5.1	2.4	Iris-virginica
80	5.8	4.0	1.2	0.2	Iris-setosa
81	5.9	3.0	4.2	1.5	Iris-versicolor
82	5.9	3.0	5.1	1.8	Iris-virginica
83	5.9	3.2	4.8	1.8	Iris-versicolor
84	6.0	2.2	4.0	1.0	Iris-versicolor
85	6.0	2.2	5.0	1.5	Iris-virginica
86	6.0	2.7	5.1	1.6	Iris-versicolor
87	6.0	2.9	4.5	1.5	Iris-versicolor
88	6.0	3.0	4.8	1.8	Iris-virginica
89	6.0	3.4	4.5	1.6	Iris-versicolor
90	6.1	2.6	5.6	1.4	Iris-virginica
91	6.1	2.8	4.0	1.3	Iris-versicolor
92	6.1	2.8	4.7	1.2	Iris-versicolor
93	6.1	2.9	4.7	1.4	Iris-versicolor
94	6.1	3.0	4.6	1.4	Iris-versicolor
95	6.1	3.0	4.9	1.8	Iris-virginica
96	6.2	2.2	4.5	1.5	Iris-versicolor
97	6.2	2.8	4.8	1.8	Iris-virginica
98	6.2	2.9	4.3	1.3	Iris-versicolor
99	6.2	3.4	5.4	2.3	Iris-virginica
100	6.3	2.3	4.4	1.3	Iris-versicolor

Rows: 1-100 | Columns: 5

We start by creating a PCA model of the different flowers.

In [2]:

from verticapy.learn.decomposition import PCA
model = PCA("public.PCA_iris")
model.drop()
model.fit("public.iris", 
          ["PetalWidthCm", 
           "PetalLengthCm", 
           "SepalLengthCm", 
           "SepalWidthCm"])

Out[2]:


=======
columns
=======
index|    name     |  mean  |   sd   
-----+-------------+--------+--------
  1  |petalwidthcm | 1.19867| 0.76316
  2  |petallengthcm| 3.75867| 1.76442
  3  |sepallengthcm| 5.84333| 0.82807
  4  |sepalwidthcm | 3.05400| 0.43359


===============
singular_values
===============
index| value  |explained_variance|accumulated_explained_variance
-----+--------+------------------+------------------------------
  1  | 2.05544|      0.92462     |            0.92462           
  2  | 0.49218|      0.05302     |            0.97763           
  3  | 0.28022|      0.01719     |            0.99482           
  4  | 0.15389|      0.00518     |            1.00000           


====================
principal_components
====================
index|  PC1   |  PC2   |  PC3   |  PC4   
-----+--------+--------+--------+--------
  1  | 0.35884|-0.07471| 0.54906| 0.75112
  2  | 0.85657|-0.17577| 0.07252|-0.47972
  3  | 0.36159| 0.65654|-0.58100| 0.31725
  4  |-0.08227| 0.72971| 0.59642|-0.32409


========
counters
========
   counter_name   |counter_value
------------------+-------------
accepted_row_count|     150     
rejected_row_count|      0      
 iteration_count  |      1      


===========
call_string
===========
SELECT PCA('public.PCA_iris', 'public.iris', '"PetalWidthCm", "PetalLengthCm", "SepalLengthCm", "SepalWidthCm"'
USING PARAMETERS scale=false);

Fitting the model creates new model attributes.

In [3]:

model.X

Out[3]:

['"PetalWidthCm"', '"PetalLengthCm"', '"SepalLengthCm"', '"SepalWidthCm"']

In [4]:

model.input_relation

Out[4]:

'public.iris'

These attributes will be used when invoking the different model abstractions.

Models have many useful attributes. With a PCA model, for example, the 'components_', 'explainedvariance' and 'mean_' attributes can help you evaluate the accuracy of your model.

In [5]:

model.components_

Out[5]:

	123 PC1 Float	123 PC2 Float	123 PC3 Float	123 PC4 Float
1	0.358843926248216	-0.0747064701350342	0.549060910726603	0.751120560380823
2	0.856572105290528	-0.175767403428654	0.0725240754869635	-0.47971898732994
3	0.36158967738145	0.656539883285831	-0.580997279827618	0.31725454716854
4	-0.0822688898922142	0.729712371326497	0.596418087938103	-0.324094352417966

Rows: 1-4 | Columns: 5

In [6]:

model.explained_variance_

Out[6]:

	123 value Float	123 explained_variance Float	123 accumulated_explained_variance Float
1	2.05544174529956	0.924616207174268	0.924616207174268
2	0.492182457659266	0.0530155678505351	0.977631775024803
3	0.280221177097939	0.0171851395250068	0.99481691454981
4	0.153892907978245	0.00518308545018961	0.999999999999999

Rows: 1-4 | Columns: 4

In [7]:

model.mean_

Out[7]:

	Abc name Varchar(65000)	123 mean Float	123 sd Float
1	petalwidthcm	1.19866666666667	0.763160741700841
2	petallengthcm	3.75866666666667	1.76442041995226
3	sepallengthcm	5.84333333333333	0.828066127977863
4	sepalwidthcm	3.054	0.433594311362174

Rows: 1-4 | Columns: 4

You can view other attributes using the 'get_attr' method.

In [8]:

model.get_attr()

Out[8]:

	Abc attr_name Varchar(128)	Abc Long varchar(32000000)	123 #_of_rows Integer
1	columns		4
2	singular_values		4
3	principal_components		4
4	counters		3
5	call_string		1

Rows: 1-5 | Columns: 3

Let's look at the SQL query for our model.

In [9]:

display(model.deploySQL())

'APPLY_PCA("PetalWidthCm", "PetalLengthCm", "SepalLengthCm", "SepalWidthCm" USING PARAMETERS model_name = \'public.PCA_iris\', match_by_pos = \'true\', cutoff = 1)'

You can deploy an inverse PCA.

In [10]:

display(model.deployInverseSQL())

'APPLY_INVERSE_PCA("PetalWidthCm", "PetalLengthCm", "SepalLengthCm", "SepalWidthCm" USING PARAMETERS model_name = \'public.PCA_iris\', match_by_pos = \'true\')'

You can also use the 'transform' method to apply the model on a vDataFrame. In this example, we choose to keep 2 components with 'n_components'.

In [11]:

model.transform(iris, n_components = 2)

Out[11]:

	Abc Species Varchar(30)	123 col1 Float	123 col2 Float
1	Iris-setosa	-1.00907614291369	-5.36809865392851
2	Iris-setosa	-0.958598946592707	-5.08805935848075
3	Iris-setosa	-0.9091007038018	-5.1712900871522
4	Iris-setosa	-0.737786282743694	-5.20644356783793
5	Iris-setosa	-1.48104367386957	-4.98275231463299
6	Iris-setosa	-0.679356772546814	-5.0725001448649
7	Iris-setosa	-0.629858529755906	-5.15573087353635
8	Iris-setosa	-0.466770997687022	-5.11791311708943
9	Iris-setosa	-0.431865558592275	-5.48865378822215
10	Iris-setosa	-0.630133104869229	-5.22885550887844
11	Iris-setosa	-0.521656201654794	-5.03189354389269
12	Iris-setosa	-0.721177276575147	-5.20848992401028
13	Iris-setosa	-0.73763105455359	-5.06254744974498
14	Iris-setosa	-0.571429019559025	-5.02178745056333
15	Iris-setosa	-0.314457387971867	-5.07451767159192
16	Iris-setosa	-0.205980484757432	-4.87755570660617
17	Iris-versicolor	-0.58625776100288	-3.20633321652966
18	Iris-virginica	-0.124281160540637	-1.92526343700098
19	Iris-setosa	-0.693519772939547	-5.14298933389113
20	Iris-setosa	-0.563476705683127	-5.16788332303806
21	Iris-setosa	-0.563476705683127	-5.16788332303806
22	Iris-setosa	-0.563476705683127	-5.16788332303806
23	Iris-versicolor	-0.820684275017979	-3.01218892551454
24	Iris-versicolor	-0.636030578907111	-3.1962271232003
25	Iris-setosa	-0.585317444838435	-5.01915200424747
26	Iris-setosa	-0.558638894732909	-5.31692143824753
27	Iris-setosa	-0.400663748727567	-5.20319020193323
28	Iris-setosa	-0.278847570460369	-5.15511295394751
29	Iris-setosa	-0.259142380700667	-4.94351649135363
30	Iris-setosa	-0.273735184396828	-5.2310264338149
31	Iris-setosa	-0.189938948150057	-4.8151507574312
32	Iris-setosa	-0.143692117140408	-5.25592042296183
33	Iris-versicolor	-0.54553555742784	-3.36284197875263
34	Iris-setosa	-0.280983119855974	-4.79478517256304
35	Iris-setosa	-0.242963177835548	-5.16258360096102
36	Iris-setosa	-0.19346493504464	-5.24581432963247
37	Iris-setosa	-0.201691824033861	-5.17284309249982
38	Iris-setosa	-0.00244532422683205	-5.06937134772431
39	Iris-setosa	0.0914387752914419	-5.15991932519983
40	Iris-setosa	0.135824632018809	-5.1672365740039
41	Iris-setosa	0.2278477572548	-4.82433213475285
42	Iris-versicolor	-0.0375867010692723	-2.59566650009667
43	Iris-setosa	-0.243237752948871	-5.2357082363031
44	Iris-setosa	-0.121421574681673	-5.18763098831739
45	Iris-setosa	0.400748577481865	-5.36606266750723
46	Iris-setosa	0.0857772390012541	-5.23025511601662
47	Iris-versicolor	0.499880633207178	-2.19644284804813
48	Iris-setosa	-0.151763777939525	-5.03905306773623
49	Iris-setosa	-0.0629920644847923	-5.05368756534436
50	Iris-setosa	0.121661631626076	-5.23772576303012
51	Iris-setosa	0.204204339229448	-5.25824474610772
52	Iris-setosa	0.348840210182028	-4.99562879279339
53	Iris-versicolor	-0.228176508583652	-2.55508872856979
54	Iris-versicolor	-0.22631553430137	-2.98854114529635
55	Iris-versicolor	-0.198383455552447	-2.84991591983512
56	Iris-versicolor	-0.0568620875255468	-2.59024220925552
57	Iris-versicolor	0.181657882945308	-2.4181742334167
58	Iris-setosa	-0.0860863322834984	-5.34135090601506
59	Iris-setosa	0.549673109158016	-5.39873410008654
60	Iris-versicolor	-0.0406828846604274	-2.8093093188629
61	Iris-versicolor	0.222654661633671	-2.50155836029759
62	Iris-virginica	0.503836423405188	-1.54875852241182
63	Iris-versicolor	0.177015276262906	-2.93063577095482
64	Iris-versicolor	0.443467325482684	-2.61994256965477
65	Iris-versicolor	0.571649418456821	-2.21138414207513
66	Iris-virginica	0.318908152180997	-1.43784496006815
67	Iris-versicolor	-0.0555502634699112	-3.16994389666625
68	Iris-versicolor	0.3080372970494	-2.59225973598254
69	Iris-versicolor	0.45267316800198	-2.32964378266821
70	Iris-versicolor	0.429853475316598	-2.54418248799682
71	Iris-versicolor	0.523737574834872	-2.63473046547234
72	Iris-setosa	0.379063066516662	-5.07343523062368
73	Iris-setosa	0.812461505225467	-5.23723241220539
74	Iris-versicolor	0.144675189867193	-2.70320212777154
75	Iris-versicolor	0.1941734326581	-2.78643285644299
76	Iris-versicolor	0.282945146112833	-2.80106735405113
77	Iris-virginica	0.57049282259129	-1.48778633657145
78	Iris-virginica	0.57049282259129	-1.48778633657145
79	Iris-virginica	0.615015588174236	-1.14050689125106
80	Iris-setosa	0.413693930498086	-5.51730053709848
81	Iris-versicolor	0.570825693116851	-2.43075804810139
82	Iris-virginica	0.871575735792491	-1.6209584417462
83	Iris-versicolor	0.934413253636162	-1.85307388741768
84	Iris-versicolor	-0.109731089020932	-2.79377893469239
85	Iris-virginica	0.21072414341441	-1.77238286574331
86	Iris-versicolor	0.666942274808597	-1.7216413419964
87	Iris-versicolor	0.629529778427054	-2.22368998978628
88	Iris-virginica	0.798983225202878	-1.82539105374545
89	Iris-versicolor	1.0495889420831	-2.23860245436796
90	Iris-virginica	0.814418073573534	-1.52920778128943
91	Iris-versicolor	0.415415899810541	-2.68779631236513
92	Iris-versicolor	0.676755562966777	-2.3011896311977
93	Iris-versicolor	0.745958995517388	-2.17282389727527
94	Iris-versicolor	0.795457238308295	-2.25605462594672
95	Iris-virginica	0.871026585565845	-1.76720771243037
96	Iris-versicolor	0.101698089973329	-2.11559410141323
97	Iris-virginica	0.699437589394416	-1.80517886708673
98	Iris-versicolor	0.645434406178851	-2.51588173473575
99	Iris-virginica	1.3892002140515	-1.15185919350917
100	Iris-versicolor	0.2035345033675	-2.35223795136348

Rows: 1-100 | Columns: 3

We can filter the model further with 'cutoff'.

In [12]:

model.transform(iris, cutoff = 0.8)

Out[12]:

	Abc Species Varchar(30)	123 col1 Float
1	Iris-setosa	-1.00907614291369
2	Iris-setosa	-0.958598946592707
3	Iris-setosa	-0.9091007038018
4	Iris-setosa	-0.737786282743694
5	Iris-setosa	-1.48104367386957
6	Iris-setosa	-0.679356772546814
7	Iris-setosa	-0.629858529755906
8	Iris-setosa	-0.466770997687022
9	Iris-setosa	-0.431865558592275
10	Iris-setosa	-0.630133104869229
11	Iris-setosa	-0.521656201654794
12	Iris-setosa	-0.721177276575147
13	Iris-setosa	-0.73763105455359
14	Iris-setosa	-0.571429019559025
15	Iris-setosa	-0.314457387971867
16	Iris-setosa	-0.205980484757432
17	Iris-versicolor	-0.58625776100288
18	Iris-virginica	-0.124281160540637
19	Iris-setosa	-0.693519772939547
20	Iris-setosa	-0.563476705683127
21	Iris-setosa	-0.563476705683127
22	Iris-setosa	-0.563476705683127
23	Iris-versicolor	-0.820684275017979
24	Iris-versicolor	-0.636030578907111
25	Iris-setosa	-0.585317444838435
26	Iris-setosa	-0.558638894732909
27	Iris-setosa	-0.400663748727567
28	Iris-setosa	-0.278847570460369
29	Iris-setosa	-0.259142380700667
30	Iris-setosa	-0.273735184396828
31	Iris-setosa	-0.189938948150057
32	Iris-setosa	-0.143692117140408
33	Iris-versicolor	-0.54553555742784
34	Iris-setosa	-0.280983119855974
35	Iris-setosa	-0.242963177835548
36	Iris-setosa	-0.19346493504464
37	Iris-setosa	-0.201691824033861
38	Iris-setosa	-0.00244532422683205
39	Iris-setosa	0.0914387752914419
40	Iris-setosa	0.135824632018809
41	Iris-setosa	0.2278477572548
42	Iris-versicolor	-0.0375867010692723
43	Iris-setosa	-0.243237752948871
44	Iris-setosa	-0.121421574681673
45	Iris-setosa	0.400748577481865
46	Iris-setosa	0.0857772390012541
47	Iris-versicolor	0.499880633207178
48	Iris-setosa	-0.151763777939525
49	Iris-setosa	-0.0629920644847923
50	Iris-setosa	0.121661631626076
51	Iris-setosa	0.204204339229448
52	Iris-setosa	0.348840210182028
53	Iris-versicolor	-0.228176508583652
54	Iris-versicolor	-0.22631553430137
55	Iris-versicolor	-0.198383455552447
56	Iris-versicolor	-0.0568620875255468
57	Iris-versicolor	0.181657882945308
58	Iris-setosa	-0.0860863322834984
59	Iris-setosa	0.549673109158016
60	Iris-versicolor	-0.0406828846604274
61	Iris-versicolor	0.222654661633671
62	Iris-virginica	0.503836423405188
63	Iris-versicolor	0.177015276262906
64	Iris-versicolor	0.443467325482684
65	Iris-versicolor	0.571649418456821
66	Iris-virginica	0.318908152180997
67	Iris-versicolor	-0.0555502634699112
68	Iris-versicolor	0.3080372970494
69	Iris-versicolor	0.45267316800198
70	Iris-versicolor	0.429853475316598
71	Iris-versicolor	0.523737574834872
72	Iris-setosa	0.379063066516662
73	Iris-setosa	0.812461505225467
74	Iris-versicolor	0.144675189867193
75	Iris-versicolor	0.1941734326581
76	Iris-versicolor	0.282945146112833
77	Iris-virginica	0.57049282259129
78	Iris-virginica	0.57049282259129
79	Iris-virginica	0.615015588174236
80	Iris-setosa	0.413693930498086
81	Iris-versicolor	0.570825693116851
82	Iris-virginica	0.871575735792491
83	Iris-versicolor	0.934413253636162
84	Iris-versicolor	-0.109731089020932
85	Iris-virginica	0.21072414341441
86	Iris-versicolor	0.666942274808597
87	Iris-versicolor	0.629529778427054
88	Iris-virginica	0.798983225202878
89	Iris-versicolor	1.0495889420831
90	Iris-virginica	0.814418073573534
91	Iris-versicolor	0.415415899810541
92	Iris-versicolor	0.676755562966777
93	Iris-versicolor	0.745958995517388
94	Iris-versicolor	0.795457238308295
95	Iris-virginica	0.871026585565845
96	Iris-versicolor	0.101698089973329
97	Iris-virginica	0.699437589394416
98	Iris-versicolor	0.645434406178851
99	Iris-virginica	1.3892002140515
100	Iris-versicolor	0.2035345033675

Rows: 1-100 | Columns: 2

We can also reverse the transformation.

In [16]:

trans = model.transform(iris, cutoff = 0.8)
model.inverse_transform(trans, X = ["col1"])

Out[16]:

	Abc Species Varchar(30)	123 petalwidthcm Float	123 petallengthcm Float	123 sepallengthcm Float	123 sepalwidthcm Float
1	Iris-setosa	0.836565821660113	2.89432019053264	5.47846181636385	3.13701557409423
2	Iris-setosa	0.854679256973936	2.93755754885447	5.49671384949668	3.13286287118803
3	Iris-setosa	0.872441400759413	2.97995636289006	5.51461190313839	3.128790705702
4	Iris-setosa	0.933916540234843	3.12669951720243	5.57655742937958	3.11469685845903
5	Iris-setosa	0.667203139790228	2.49004596891299	5.307803229111	3.17584381893114
6	Iris-setosa	0.954883615082652	3.17674860576286	5.59768493712123	3.10988992751818
7	Iris-setosa	0.972645758868129	3.21914741979845	5.61558299076294	3.10581776203216
8	Iris-setosa	1.03116872919786	3.35884365048933	5.67455375886867	3.09240073181359
9	Iris-setosa	1.04369433401004	3.38874267594081	5.68717520532979	3.08952910008807
10	Iris-setosa	0.972547229256414	3.21891222641557	5.6154837072363	3.10584035102193
11	Iris-setosa	1.01147350711313	3.31183051577736	5.65470783567294	3.09691607661553
12	Iris-setosa	0.939876581219446	3.140926328583	5.58256307456169	3.11333045395933
13	Iris-setosa	0.933972242928045	3.12683248134003	5.57661355829076	3.11468408800815
14	Iris-setosa	0.993612833715938	3.26919650835889	5.63671049850459	3.10101083109132
15	Iris-setosa	1.08582554292908	3.48931123982744	5.72962878786637	3.07987006022685
16	Iris-setosa	1.1247518207858	3.58222952918923	5.76885291630302	3.07094578582045
17	Iris-versicolor	0.988291629914905	3.25649462208152	5.63134857866993	3.1022307751884
18	Iris-virginica	1.15406912705958	3.65221089133442	5.79839454858885	3.06422447311219
19	Iris-setosa	0.949801308414269	3.16461697469923	5.59256374237847	3.11105510183804
20	Iris-setosa	0.996466473249923	3.2760082385975	5.63958597311341	3.10035660305667
21	Iris-setosa	0.996466473249923	3.2760082385975	5.63958597311341	3.10035660305667
22	Iris-setosa	0.996466473249923	3.2760082385975	5.63958597311341	3.10035660305667
23	Iris-versicolor	0.904169099209045	3.05569140943569	5.54658237109755	3.12151678425773
24	Iris-versicolor	0.970430956517713	3.21386061466305	5.61335124150157	3.10632552966419
25	Iris-setosa	0.988629056659269	3.25730007067814	5.63168858728847	3.10215341642141
26	Iris-setosa	0.998202492325746	3.28015217250813	5.64133527561413	3.09995860172029
27	Iris-setosa	1.05489091396794	3.4154692759055	5.69845745769249	3.08696216182787
28	Iris-setosa	1.09860390965789	3.51981361618228	5.74250493029197	3.07694048007092
29	Iris-setosa	1.10567499731873	3.5366925320599	5.74963012349992	3.07531935598427
30	Iris-setosa	1.10043845834543	3.52419274347579	5.74435351631933	3.07651988974477
31	Iris-setosa	1.13050822876504	3.5959702619731	5.77465337034958	3.0696260664116
32	Iris-setosa	1.14710362318108	3.63558400737405	5.79137574705427	3.0658213909634
33	Iris-versicolor	1.00290454533125	3.29137612572986	5.64607330712289	3.09888060470632
34	Iris-setosa	1.09783758072808	3.51798436414053	5.74173273767498	3.077116169349
35	Iris-setosa	1.11148080599842	3.55055118591999	5.75548035624421	3.07398831092521
36	Iris-setosa	1.12924294978389	3.59294999995558	5.77337840988592	3.06991614543919
37	Iris-setosa	1.12629078063819	3.5859030763341	5.77040365175045	3.0705929624636
38	Iris-setosa	1.19778917692016	3.75657207014557	5.84244912933506	3.05420117410957
39	Iris-setosa	1.23147891580358	3.83699057092324	5.87639665059112	3.04647743346367
40	Iris-setosa	1.24740651090152	3.87501025766533	5.89244611820547	3.04282585830379
41	Iris-setosa	1.28042845046683	3.95383469978414	5.92572073037118	3.03525521794622
42	Iris-versicolor	1.18517890728025	3.72647094700083	5.82974237021986	3.05709221617168
43	Iris-setosa	1.1113822763867	3.55031599253712	5.75538107271756	3.07401089991498
44	Iris-setosa	1.15509527207665	3.6546603328139	5.79942854531704	3.06398921815803
45	Iris-setosa	1.34247285964865	4.10193671937249	5.98823988217608	3.02103085940468
46	Iris-setosa	1.22944730789261	3.83214105686398	5.87434949751047	3.04694320176935
47	Iris-versicolor	1.37804579574218	4.1868504730469	6.02408501022395	3.01287537522743
48	Iris-setosa	1.14420715672859	3.62867004789016	5.78845711782999	3.06648543753693
49	Iris-setosa	1.17606234692446	3.70470942137433	5.82055605305869	3.05918228721718
50	Iris-setosa	1.24232420423313	3.8628786266017	5.88732492346271	3.04399103262365
51	Iris-setosa	1.27194415351268	3.9335824074299	5.9171715144752	3.03720033570042
52	Iris-setosa	1.32384585732164	4.05747345991228	5.96947035239073	3.02530130315856
53	Iris-versicolor	1.1167869124489	3.56321703433133	5.76082706320854	3.07277182806066
54	Iris-versicolor	1.117454711767	3.56481109299019	5.76149997229889	3.07261872777234
55	Iris-versicolor	1.12747796857354	3.5887369324893	5.77159992364231	3.07032078666128
56	Iris-versicolor	1.17826205192433	3.7099601886437	5.82277258944973	3.05867798081768
57	Iris-versicolor	1.2638534946167	3.91426974190375	5.90901894862132	3.03905520762992
58	Iris-setosa	1.16777510919375	3.68492751578585	5.81220540421599	3.06108222699186
59	Iris-setosa	1.39591352330999	4.22950131899974	6.04208945553904	3.00877900350597
60	Iris-versicolor	1.18406786060402	3.72381884250379	5.82862282219402	3.05734693575863
61	Iris-versicolor	1.27856493964476	3.94938643893497	5.92384296060093	3.03568244815807
62	Iris-virginica	1.37946530702824	4.1902388925849	6.02551538312544	3.01254993675919
63	Iris-versicolor	1.26218752340676	3.91029301452377	5.90734022996882	3.03943714972789
64	Iris-versicolor	1.35780222290567	4.13852840728293	6.00368654048383	3.01751643542907
65	Iris-versicolor	1.40379958842322	4.24832561252233	6.05003586212843	3.00697103693603
66	Iris-virginica	1.31310492010786	4.03183449397465	5.95864722919477	3.02776378034249
67	Iris-versicolor	1.178732792019	3.7110838605368	5.82324693148679	3.05857005850889
68	Iris-versicolor	1.30920397977076	4.02252282270828	5.95471644019488	3.02865811352635
69	Iris-versicolor	1.36110568357972	4.14641387519066	6.00701527811041	3.01675908098449
70	Iris-versicolor	1.35291697546072	4.12686716298505	5.99876391279436	3.01863643176939
71	Iris-versicolor	1.38660671434413	4.20728566376273	6.03271143405042	3.01091269112349
72	Iris-setosa	1.33469114575119	4.08336151559073	5.98039862526232	3.02281490231854
73	Iris-setosa	1.49021354312731	4.45459852866516	6.13711102689266	2.98715969388494
74	Iris-versicolor	1.25058247982932	3.88259139863451	5.89564638856251	3.04209773273468
75	Iris-versicolor	1.26834462361479	3.9249902126701	5.91354444220422	3.03802556724866
76	Iris-versicolor	1.30019981381067	4.00102958615427	5.94564337743292	3.03072241692891
77	Iris-virginica	1.40338455102175	4.24733490476682	6.04961764900255	3.00706618879394
78	Iris-virginica	1.40338455102175	4.24733490476682	6.04961764900255	3.00706618879394
79	Iris-virginica	1.41936127503097	4.28547186381556	6.06571662144582	3.0034033502945
80	Iris-setosa	1.34711822095166	4.11302534765933	5.9929207881968	3.01996585958278
81	Iris-versicolor	1.40350399958808	4.24762003237369	6.0497380115485	3.00703880390532
82	Iris-virginica	1.51142632572112	4.50523412959458	6.15848612245204	2.98229643175936
83	Iris-versicolor	1.53397518733984	4.55905899454517	6.18120752025658	2.97712685892278
84	Iris-versicolor	1.1592903318509	3.66467407672818	5.80365570425554	3.06302745488042
85	Iris-virginica	1.27428374564479	3.93916708982669	5.91952900836703	3.03666395864781
86	Iris-versicolor	1.4379948511399	4.32995081510672	6.08449277531342	2.99913139942931
87	Iris-versicolor	1.4245696040476	4.29790431431701	6.07096480281679	3.00220928397471
88	Iris-virginica	1.48537694420493	4.44305340997051	6.13223741996763	2.98826853702006
89	Iris-versicolor	1.57530528359048	4.65771527647644	6.2228538602843	2.96765148289168
90	Iris-virginica	1.4909156457953	4.45627447053421	6.13781850181041	2.98699872917895
91	Iris-versicolor	1.34773613918062	4.11450033853854	5.99354343452495	3.01982419507901
92	Iris-versicolor	1.44151628999199	4.3383566040042	6.08804115901259	2.99832407110634
93	Iris-versicolor	1.4663495214383	4.3976343339174	6.11306440586226	2.99263078153367
94	Iris-versicolor	1.48411166522378	4.44003314795299	6.13096245950397	2.98855861604765
95	Iris-virginica	1.51122926649769	4.50476374282882	6.15828755539875	2.98234160973889
96	Iris-versicolor	1.23516040856464	3.84577841369915	5.8801063128771	3.04563341103374
97	Iris-virginica	1.44965559741055	4.35778539513357	6.09624274563092	2.99645804597164
98	Iris-versicolor	1.43027688311557	4.31152777479423	6.07671575203443	3.00090082790543
99	Iris-virginica	1.69717272582177	4.94861681868681	6.34565379055045	2.93971204055196
100	Iris-versicolor	1.27170378698204	3.93300864471543	5.91692930874198	3.03725544235319

Rows: 1-100 | Columns: 5

To evaluate the model, we'll apply and then reverse it.

We don't see much error here because the number of components is equal to the number of variables.

In [19]:

model.set_params({"n_components": 4})
model.score()

Out[19]:

	Score
PetalWidthCm	9.89394927062417e-09
PetalLengthCm	1.45228223207193e-08
SepalLengthCm	7.16232440767798e-09
SepalWidthCm	7.2056492635751e-09

Rows: 1-4 | Columns: 2

Our error increases when we retrieve fewer components.

In [18]:

model.set_params({"n_components": 1})
model.score()

Out[18]:

	Score
PetalWidthCm	0.560453608853424
PetalLengthCm	0.750949082360787
SepalLengthCm	1.70738568563443
SepalWidthCm	1.25433079158467

Rows: 1-4 | Columns: 2