VerticaPy

Python API for Vertica Data Science at Scale

Example: Methods in a Regression Model¶

In this example, we use the 'Winequality' dataset to demonstrate the methods available to regressor models.

In [19]:

from verticapy.datasets import load_winequality
winequality = load_winequality()
display(winequality)

	123 fixed_acidity Numeric(6,3)	123 volatile_acidity Numeric(7,4)	123 citric_acid Numeric(6,3)	123 residual_sugar Numeric(7,3)	123 chlorides Float	123 free_sulfur_dioxide Numeric(7,2)	123 total_sulfur_dioxide Numeric(7,2)	123 density Float	123 pH Numeric(6,3)	123 sulphates Numeric(6,3)	123 alcohol Float	123 quality Int	123 good Int	Abc color Varchar(20)
1	3.800	0.3100	0.020	11.100	0.036	20.00	114.00	0.99248	3.750	0.440	12.4	6	0	white
2	3.900	0.2250	0.400	4.200	0.03	29.00	118.00	0.989	3.570	0.360	12.8	8	1	white
3	4.200	0.1700	0.360	1.800	0.029	93.00	161.00	0.98999	3.650	0.890	12.0	7	1	white
4	4.200	0.2150	0.230	5.100	0.041	64.00	157.00	0.99688	3.420	0.440	8.0	3	0	white
5	4.400	0.3200	0.390	4.300	0.03	31.00	127.00	0.98904	3.460	0.360	12.8	8	1	white
6	4.400	0.4600	0.100	2.800	0.024	31.00	111.00	0.98816	3.480	0.340	13.1	6	0	white
7	4.400	0.5400	0.090	5.100	0.038	52.00	97.00	0.99022	3.410	0.400	12.2	7	1	white
8	4.500	0.1900	0.210	0.950	0.033	89.00	159.00	0.99332	3.340	0.420	8.0	5	0	white
9	4.600	0.4450	0.000	1.400	0.053	11.00	178.00	0.99426	3.790	0.550	10.2	5	0	white
10	4.600	0.5200	0.150	2.100	0.054	8.00	65.00	0.9934	3.900	0.560	13.1	4	0	red
11	4.700	0.1450	0.290	1.000	0.042	35.00	90.00	0.9908	3.760	0.490	11.3	6	0	white
12	4.700	0.3350	0.140	1.300	0.036	69.00	168.00	0.99212	3.470	0.460	10.5	5	0	white
13	4.700	0.4550	0.180	1.900	0.036	33.00	106.00	0.98746	3.210	0.830	14.0	7	1	white
14	4.700	0.6000	0.170	2.300	0.058	17.00	106.00	0.9932	3.850	0.600	12.9	6	0	red
15	4.700	0.6700	0.090	1.000	0.02	5.00	9.00	0.98722	3.300	0.340	13.6	5	0	white
16	4.700	0.7850	0.000	3.400	0.036	23.00	134.00	0.98981	3.530	0.920	13.8	6	0	white
17	4.800	0.1300	0.320	1.200	0.042	40.00	98.00	0.9898	3.420	0.640	11.8	7	1	white
18	4.800	0.1700	0.280	2.900	0.03	22.00	111.00	0.9902	3.380	0.340	11.3	7	1	white
19	4.800	0.2100	0.210	10.200	0.037	17.00	112.00	0.99324	3.660	0.480	12.2	7	1	white
20	4.800	0.2250	0.380	1.200	0.074	47.00	130.00	0.99132	3.310	0.400	10.3	6	0	white
21	4.800	0.2600	0.230	10.600	0.034	23.00	111.00	0.99274	3.460	0.280	11.5	7	1	white
22	4.800	0.2900	0.230	1.100	0.044	38.00	180.00	0.98924	3.280	0.340	11.9	6	0	white
23	4.800	0.3300	0.000	6.500	0.028	34.00	163.00	0.9937	3.350	0.610	9.9	5	0	white
24	4.800	0.3400	0.000	6.500	0.028	33.00	163.00	0.9939	3.360	0.610	9.9	6	0	white
25	4.800	0.6500	0.120	1.100	0.013	4.00	10.00	0.99246	3.320	0.360	13.5	4	0	white
26	4.900	0.2350	0.270	11.750	0.03	34.00	118.00	0.9954	3.070	0.500	9.4	6	0	white
27	4.900	0.3300	0.310	1.200	0.016	39.00	150.00	0.98713	3.330	0.590	14.0	8	1	white
28	4.900	0.3350	0.140	1.300	0.036	69.00	168.00	0.99212	3.470	0.460	10.4666666666667	5	0	white
29	4.900	0.3350	0.140	1.300	0.036	69.00	168.00	0.99212	3.470	0.460	10.4666666666667	5	0	white
30	4.900	0.3450	0.340	1.000	0.068	32.00	143.00	0.99138	3.240	0.400	10.1	5	0	white
31	4.900	0.3450	0.340	1.000	0.068	32.00	143.00	0.99138	3.240	0.400	10.1	5	0	white
32	4.900	0.4200	0.000	2.100	0.048	16.00	42.00	0.99154	3.710	0.740	14.0	7	1	red
33	4.900	0.4700	0.170	1.900	0.035	60.00	148.00	0.98964	3.270	0.350	11.5	6	0	white
34	5.000	0.1700	0.560	1.500	0.026	24.00	115.00	0.9906	3.480	0.390	10.8	7	1	white
35	5.000	0.2000	0.400	1.900	0.015	20.00	98.00	0.9897	3.370	0.550	12.05	6	0	white
36	5.000	0.2350	0.270	11.750	0.03	34.00	118.00	0.9954	3.070	0.500	9.4	6	0	white
37	5.000	0.2400	0.190	5.000	0.043	17.00	101.00	0.99438	3.670	0.570	10.0	5	0	white
38	5.000	0.2400	0.210	2.200	0.039	31.00	100.00	0.99098	3.690	0.620	11.7	6	0	white
39	5.000	0.2400	0.340	1.100	0.034	49.00	158.00	0.98774	3.320	0.320	13.1	7	1	white
40	5.000	0.2550	0.220	2.700	0.043	46.00	153.00	0.99238	3.750	0.760	11.3	6	0	white
41	5.000	0.2700	0.320	4.500	0.032	58.00	178.00	0.98956	3.450	0.310	12.6	7	1	white
42	5.000	0.2700	0.320	4.500	0.032	58.00	178.00	0.98956	3.450	0.310	12.6	7	1	white
43	5.000	0.2700	0.400	1.200	0.076	42.00	124.00	0.99204	3.320	0.470	10.1	6	0	white
44	5.000	0.2900	0.540	5.700	0.035	54.00	155.00	0.98976	3.270	0.340	12.9	8	1	white
45	5.000	0.3000	0.330	3.700	0.03	54.00	173.00	0.9887	3.360	0.300	13.0	7	1	white
46	5.000	0.3100	0.000	6.400	0.046	43.00	166.00	0.994	3.300	0.630	9.9	6	0	white
47	5.000	0.3300	0.160	1.500	0.049	10.00	97.00	0.9917	3.480	0.440	10.7	6	0	white
48	5.000	0.3300	0.160	1.500	0.049	10.00	97.00	0.9917	3.480	0.440	10.7	6	0	white
49	5.000	0.3300	0.160	1.500	0.049	10.00	97.00	0.9917	3.480	0.440	10.7	6	0	white
50	5.000	0.3300	0.180	4.600	0.032	40.00	124.00	0.99114	3.180	0.400	11.0	6	0	white
51	5.000	0.3300	0.230	11.800	0.03	23.00	158.00	0.99322	3.410	0.640	11.8	6	0	white
52	5.000	0.3500	0.250	7.800	0.031	24.00	116.00	0.99241	3.390	0.400	11.3	6	0	white
53	5.000	0.3500	0.250	7.800	0.031	24.00	116.00	0.99241	3.390	0.400	11.3	6	0	white
54	5.000	0.3800	0.010	1.600	0.048	26.00	60.00	0.99084	3.700	0.750	14.0	6	0	red
55	5.000	0.4000	0.500	4.300	0.046	29.00	80.00	0.9902	3.490	0.660	13.6	6	0	red
56	5.000	0.4200	0.240	2.000	0.06	19.00	50.00	0.9917	3.720	0.740	14.0	8	1	red
57	5.000	0.4400	0.040	18.600	0.039	38.00	128.00	0.9985	3.370	0.570	10.2	6	0	white
58	5.000	0.4550	0.180	1.900	0.036	33.00	106.00	0.98746	3.210	0.830	14.0	7	1	white
59	5.000	0.5500	0.140	8.300	0.032	35.00	164.00	0.9918	3.530	0.510	12.5	8	1	white
60	5.000	0.6100	0.120	1.300	0.009	65.00	100.00	0.9874	3.260	0.370	13.5	5	0	white
61	5.000	0.7400	0.000	1.200	0.041	16.00	46.00	0.99258	4.010	0.590	12.5	6	0	red
62	5.000	1.0200	0.040	1.400	0.045	41.00	85.00	0.9938	3.750	0.480	10.5	4	0	red
63	5.000	1.0400	0.240	1.600	0.05	32.00	96.00	0.9934	3.740	0.620	11.5	5	0	red
64	5.100	0.1100	0.320	1.600	0.028	12.00	90.00	0.99008	3.570	0.520	12.2	6	0	white
65	5.100	0.1400	0.250	0.700	0.039	15.00	89.00	0.9919	3.220	0.430	9.2	6	0	white
66	5.100	0.1650	0.220	5.700	0.047	42.00	146.00	0.9934	3.180	0.550	9.9	6	0	white
67	5.100	0.2100	0.280	1.400	0.047	48.00	148.00	0.99168	3.500	0.490	10.4	5	0	white
68	5.100	0.2300	0.180	1.000	0.053	13.00	99.00	0.98956	3.220	0.390	11.5	5	0	white
69	5.100	0.2500	0.360	1.300	0.035	40.00	78.00	0.9891	3.230	0.640	12.1	7	1	white
70	5.100	0.2600	0.330	1.100	0.027	46.00	113.00	0.98946	3.350	0.430	11.4	7	1	white
71	5.100	0.2600	0.340	6.400	0.034	26.00	99.00	0.99449	3.230	0.410	9.2	6	0	white
72	5.100	0.2900	0.280	8.300	0.026	27.00	107.00	0.99308	3.360	0.370	11.0	6	0	white
73	5.100	0.2900	0.280	8.300	0.026	27.00	107.00	0.99308	3.360	0.370	11.0	6	0	white
74	5.100	0.3000	0.300	2.300	0.048	40.00	150.00	0.98944	3.290	0.460	12.2	6	0	white
75	5.100	0.3050	0.130	1.750	0.036	17.00	73.00	0.99	3.400	0.510	12.3333333333333	5	0	white
76	5.100	0.3100	0.300	0.900	0.037	28.00	152.00	0.992	3.540	0.560	10.1	6	0	white
77	5.100	0.3300	0.220	1.600	0.027	18.00	89.00	0.9893	3.510	0.380	12.5	7	1	white
78	5.100	0.3300	0.220	1.600	0.027	18.00	89.00	0.9893	3.510	0.380	12.5	7	1	white
79	5.100	0.3300	0.220	1.600	0.027	18.00	89.00	0.9893	3.510	0.380	12.5	7	1	white
80	5.100	0.3300	0.270	6.700	0.022	44.00	129.00	0.99221	3.360	0.390	11.0	7	1	white
81	5.100	0.3500	0.260	6.800	0.034	36.00	120.00	0.99188	3.380	0.400	11.5	6	0	white
82	5.100	0.3500	0.260	6.800	0.034	36.00	120.00	0.99188	3.380	0.400	11.5	6	0	white
83	5.100	0.3500	0.260	6.800	0.034	36.00	120.00	0.99188	3.380	0.400	11.5	6	0	white
84	5.100	0.3900	0.210	1.700	0.027	15.00	72.00	0.9894	3.500	0.450	12.5	6	0	white
85	5.100	0.4200	0.000	1.800	0.044	18.00	88.00	0.99157	3.680	0.730	13.6	7	1	red
86	5.100	0.4200	0.010	1.500	0.017	25.00	102.00	0.9894	3.380	0.360	12.3	7	1	white
87	5.100	0.4700	0.020	1.300	0.034	18.00	44.00	0.9921	3.900	0.620	12.8	6	0	red
88	5.100	0.5100	0.180	2.100	0.042	16.00	101.00	0.9924	3.460	0.870	12.9	7	1	red
89	5.100	0.5200	0.060	2.700	0.052	30.00	79.00	0.9932	3.320	0.430	9.3	5	0	white
90	5.100	0.5850	0.000	1.700	0.044	14.00	86.00	0.99264	3.560	0.940	12.9	7	1	red
91	5.200	0.1550	0.330	1.600	0.028	13.00	59.00	0.98975	3.300	0.840	11.9	8	1	white
92	5.200	0.1550	0.330	1.600	0.028	13.00	59.00	0.98975	3.300	0.840	11.9	8	1	white
93	5.200	0.1600	0.340	0.800	0.029	26.00	77.00	0.99155	3.250	0.510	10.1	6	0	white
94	5.200	0.1700	0.270	0.700	0.03	11.00	68.00	0.99218	3.300	0.410	9.8	5	0	white
95	5.200	0.1850	0.220	1.000	0.03	47.00	123.00	0.99218	3.550	0.440	10.15	6	0	white
96	5.200	0.2000	0.270	3.200	0.047	16.00	93.00	0.99235	3.440	0.530	10.1	7	1	white
97	5.200	0.2100	0.310	1.700	0.048	17.00	61.00	0.98953	3.240	0.370	12.0	7	1	white
98	5.200	0.2200	0.460	6.200	0.066	41.00	187.00	0.99362	3.190	0.420	9.73333333333333	5	0	white
99	5.200	0.2400	0.150	7.100	0.043	32.00	134.00	0.99378	3.240	0.480	9.9	6	0	white
100	5.200	0.2400	0.450	3.800	0.027	21.00	128.00	0.992	3.550	0.490	11.2	8	1	white

Rows: 1-100 of 6497 | Columns: 14

Let's create a linear regression to predict the quality of each wine.

In [22]:

from verticapy.learn.linear_model import LinearRegression
model = LinearRegression("public.LR_winequality")
model.fit("public.winequality", ["alcohol"], "quality")

Out[22]:


=======
details
=======
predictor|coefficient|std_err |t_value |p_value 
---------+-----------+--------+--------+--------
Intercept|  2.40527  | 0.08594|27.98758| 0.00000
 alcohol |  0.32531  | 0.00814|39.97052| 0.00000


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


===========
call_string
===========
linear_reg('public.LR_winequality', 'public.winequality', '"quality"', '"alcohol"'
USING PARAMETERS optimizer='cgd', epsilon=0.0001, max_iterations=100, regularization='none', lambda=1, alpha=0.5)

===============
Additional Info
===============
       Name       |Value
------------------+-----
 iteration_count  |  1  
rejected_row_count|  0  
accepted_row_count|6497

Fitting the model creates new model attributes, which make methods easier to use.

In [23]:

model.X

Out[23]:

['"alcohol"']

In [24]:

model.y

Out[24]:

'"quality"'

In [25]:

model.input_relation

Out[25]:

'public.winequality'

In [26]:

model.test_relation

Out[26]:

'public.winequality'

Since we didn't write a test relation when fitting the model, the model will use the training relation as the test relation.

Let's compute the R2 of the model.

In [27]:

model.score(method = "r2")

Out[27]:

0.197418947221722

The 'score' method uses the 'y' attribute and the model prediction in the 'test_relation' to compute the accuracy of the model. You can change these attributes at any time to deploy the models on different columns.

Models have many useful attributes. For example, the 'coef_' attribute gives us the p-value of the model.

In [28]:

model.coef_

	Abc predictor Varchar(65000)	123 coefficient Float	123 std_err Float	123 t_value Float	123 p_value Float
1	Intercept	2.40526883383781	0.0859405708614197	27.9875826949804	7.70442131066327e-163
2	alcohol	0.325312038053542	0.00813879966075955	39.9705179649529	1.49650934284e-312

Out[28]:

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

In [29]:

model.get_attr()

	Abc attr_name Varchar(128)	Abc Long varchar(32000000)	123 #_of_rows Integer
1	details		2
2	regularization		1
3	iteration_count		1
4	rejected_row_count		1
5	accepted_row_count		1
6	call_string		1

Out[29]:

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

In [30]:

display(model.deploySQL())

PREDICT_LINEAR_REG("alcohol" USING PARAMETERS model_name = 'public.LR_winequality', match_by_pos = 'true')

The best way to evaluate this type of model is with the 'report' method.

In [31]:

model.report()

	value
explained_variance	0.197418947221787
max_error	3.50420051331244
median_absolute_error	0.495799486687561
mean_absolute_error	0.618753626974322
mean_squared_error	0.611933859491423
r2	0.197418947221722

Out[31]:

You can add this prediction to your vDataFrame.

In [32]:

model.predict(winequality, name = "pred_quality")

	123 fixed_acidity Numeric(6,3)	123 volatile_acidity Numeric(7,4)	123 citric_acid Numeric(6,3)	123 residual_sugar Numeric(7,3)	123 chlorides Float	123 free_sulfur_dioxide Numeric(7,2)	123 total_sulfur_dioxide Numeric(7,2)	123 density Float	123 pH Numeric(6,3)	123 sulphates Numeric(6,3)	123 alcohol Float	123 quality Int	123 good Int	Abc color Varchar(20)	123 pred_quality Float
1	3.800	0.3100	0.020	11.100	0.036	20.00	114.00	0.99248	3.750	0.440	12.4	6	0	white	6.43913810570173
2	3.900	0.2250	0.400	4.200	0.03	29.00	118.00	0.989	3.570	0.360	12.8	8	1	white	6.56926292092315
3	4.200	0.1700	0.360	1.800	0.029	93.00	161.00	0.98999	3.650	0.890	12.0	7	1	white	6.30901329048031
4	4.200	0.2150	0.230	5.100	0.041	64.00	157.00	0.99688	3.420	0.440	8.0	3	0	white	5.00776513826615
5	4.400	0.3200	0.390	4.300	0.03	31.00	127.00	0.98904	3.460	0.360	12.8	8	1	white	6.56926292092315
6	4.400	0.4600	0.100	2.800	0.024	31.00	111.00	0.98816	3.480	0.340	13.1	6	0	white	6.66685653233921
7	4.400	0.5400	0.090	5.100	0.038	52.00	97.00	0.99022	3.410	0.400	12.2	7	1	white	6.37407569809102
8	4.500	0.1900	0.210	0.950	0.033	89.00	159.00	0.99332	3.340	0.420	8.0	5	0	white	5.00776513826615
9	4.600	0.4450	0.000	1.400	0.053	11.00	178.00	0.99426	3.790	0.550	10.2	5	0	white	5.72345162198394
10	4.600	0.5200	0.150	2.100	0.054	8.00	65.00	0.9934	3.900	0.560	13.1	4	0	red	6.66685653233921
11	4.700	0.1450	0.290	1.000	0.042	35.00	90.00	0.9908	3.760	0.490	11.3	6	0	white	6.08129486384284
12	4.700	0.3350	0.140	1.300	0.036	69.00	168.00	0.99212	3.470	0.460	10.5	5	0	white	5.8210452334
13	4.700	0.4550	0.180	1.900	0.036	33.00	106.00	0.98746	3.210	0.830	14.0	7	1	white	6.9596373665874
14	4.700	0.6000	0.170	2.300	0.058	17.00	106.00	0.9932	3.850	0.600	12.9	6	0	red	6.6017941247285
15	4.700	0.6700	0.090	1.000	0.02	5.00	9.00	0.98722	3.300	0.340	13.6	5	0	white	6.82951255136598
16	4.700	0.7850	0.000	3.400	0.036	23.00	134.00	0.98981	3.530	0.920	13.8	6	0	white	6.89457495897669
17	4.800	0.1300	0.320	1.200	0.042	40.00	98.00	0.9898	3.420	0.640	11.8	7	1	white	6.24395088286961
18	4.800	0.1700	0.280	2.900	0.03	22.00	111.00	0.9902	3.380	0.340	11.3	7	1	white	6.08129486384284
19	4.800	0.2100	0.210	10.200	0.037	17.00	112.00	0.99324	3.660	0.480	12.2	7	1	white	6.37407569809102
20	4.800	0.2250	0.380	1.200	0.074	47.00	130.00	0.99132	3.310	0.400	10.3	6	0	white	5.75598282578929
21	4.800	0.2600	0.230	10.600	0.034	23.00	111.00	0.99274	3.460	0.280	11.5	7	1	white	6.14635727145354
22	4.800	0.2900	0.230	1.100	0.044	38.00	180.00	0.98924	3.280	0.340	11.9	6	0	white	6.27648208667496
23	4.800	0.3300	0.000	6.500	0.028	34.00	163.00	0.9937	3.350	0.610	9.9	5	0	white	5.62585801056788
24	4.800	0.3400	0.000	6.500	0.028	33.00	163.00	0.9939	3.360	0.610	9.9	6	0	white	5.62585801056788
25	4.800	0.6500	0.120	1.100	0.013	4.00	10.00	0.99246	3.320	0.360	13.5	4	0	white	6.79698134756063
26	4.900	0.2350	0.270	11.750	0.03	34.00	118.00	0.9954	3.070	0.500	9.4	6	0	white	5.4632019915411
27	4.900	0.3300	0.310	1.200	0.016	39.00	150.00	0.98713	3.330	0.590	14.0	8	1	white	6.9596373665874
28	4.900	0.3350	0.140	1.300	0.036	69.00	168.00	0.99212	3.470	0.460	10.4666666666667	5	0	white	5.81020149879823
29	4.900	0.3350	0.140	1.300	0.036	69.00	168.00	0.99212	3.470	0.460	10.4666666666667	5	0	white	5.81020149879823
30	4.900	0.3450	0.340	1.000	0.068	32.00	143.00	0.99138	3.240	0.400	10.1	5	0	white	5.69092041817858
31	4.900	0.3450	0.340	1.000	0.068	32.00	143.00	0.99138	3.240	0.400	10.1	5	0	white	5.69092041817858
32	4.900	0.4200	0.000	2.100	0.048	16.00	42.00	0.99154	3.710	0.740	14.0	7	1	red	6.9596373665874
33	4.900	0.4700	0.170	1.900	0.035	60.00	148.00	0.98964	3.270	0.350	11.5	6	0	white	6.14635727145354
34	5.000	0.1700	0.560	1.500	0.026	24.00	115.00	0.9906	3.480	0.390	10.8	7	1	white	5.91863884481606
35	5.000	0.2000	0.400	1.900	0.015	20.00	98.00	0.9897	3.370	0.550	12.05	6	0	white	6.32527889238299
36	5.000	0.2350	0.270	11.750	0.03	34.00	118.00	0.9954	3.070	0.500	9.4	6	0	white	5.4632019915411
37	5.000	0.2400	0.190	5.000	0.043	17.00	101.00	0.99438	3.670	0.570	10.0	5	0	white	5.65838921437323
38	5.000	0.2400	0.210	2.200	0.039	31.00	100.00	0.99098	3.690	0.620	11.7	6	0	white	6.21141967906425
39	5.000	0.2400	0.340	1.100	0.034	49.00	158.00	0.98774	3.320	0.320	13.1	7	1	white	6.66685653233921
40	5.000	0.2550	0.220	2.700	0.043	46.00	153.00	0.99238	3.750	0.760	11.3	6	0	white	6.08129486384284
41	5.000	0.2700	0.320	4.500	0.032	58.00	178.00	0.98956	3.450	0.310	12.6	7	1	white	6.50420051331244
42	5.000	0.2700	0.320	4.500	0.032	58.00	178.00	0.98956	3.450	0.310	12.6	7	1	white	6.50420051331244
43	5.000	0.2700	0.400	1.200	0.076	42.00	124.00	0.99204	3.320	0.470	10.1	6	0	white	5.69092041817858
44	5.000	0.2900	0.540	5.700	0.035	54.00	155.00	0.98976	3.270	0.340	12.9	8	1	white	6.6017941247285
45	5.000	0.3000	0.330	3.700	0.03	54.00	173.00	0.9887	3.360	0.300	13.0	7	1	white	6.63432532853386
46	5.000	0.3100	0.000	6.400	0.046	43.00	166.00	0.994	3.300	0.630	9.9	6	0	white	5.62585801056788
47	5.000	0.3300	0.160	1.500	0.049	10.00	97.00	0.9917	3.480	0.440	10.7	6	0	white	5.88610764101071
48	5.000	0.3300	0.160	1.500	0.049	10.00	97.00	0.9917	3.480	0.440	10.7	6	0	white	5.88610764101071
49	5.000	0.3300	0.160	1.500	0.049	10.00	97.00	0.9917	3.480	0.440	10.7	6	0	white	5.88610764101071
50	5.000	0.3300	0.180	4.600	0.032	40.00	124.00	0.99114	3.180	0.400	11.0	6	0	white	5.98370125242677
51	5.000	0.3300	0.230	11.800	0.03	23.00	158.00	0.99322	3.410	0.640	11.8	6	0	white	6.24395088286961
52	5.000	0.3500	0.250	7.800	0.031	24.00	116.00	0.99241	3.390	0.400	11.3	6	0	white	6.08129486384284
53	5.000	0.3500	0.250	7.800	0.031	24.00	116.00	0.99241	3.390	0.400	11.3	6	0	white	6.08129486384284
54	5.000	0.3800	0.010	1.600	0.048	26.00	60.00	0.99084	3.700	0.750	14.0	6	0	red	6.9596373665874
55	5.000	0.4000	0.500	4.300	0.046	29.00	80.00	0.9902	3.490	0.660	13.6	6	0	red	6.82951255136598
56	5.000	0.4200	0.240	2.000	0.06	19.00	50.00	0.9917	3.720	0.740	14.0	8	1	red	6.9596373665874
57	5.000	0.4400	0.040	18.600	0.039	38.00	128.00	0.9985	3.370	0.570	10.2	6	0	white	5.72345162198394
58	5.000	0.4550	0.180	1.900	0.036	33.00	106.00	0.98746	3.210	0.830	14.0	7	1	white	6.9596373665874
59	5.000	0.5500	0.140	8.300	0.032	35.00	164.00	0.9918	3.530	0.510	12.5	8	1	white	6.47166930950709
60	5.000	0.6100	0.120	1.300	0.009	65.00	100.00	0.9874	3.260	0.370	13.5	5	0	white	6.79698134756063
61	5.000	0.7400	0.000	1.200	0.041	16.00	46.00	0.99258	4.010	0.590	12.5	6	0	red	6.47166930950709
62	5.000	1.0200	0.040	1.400	0.045	41.00	85.00	0.9938	3.750	0.480	10.5	4	0	red	5.8210452334
63	5.000	1.0400	0.240	1.600	0.05	32.00	96.00	0.9934	3.740	0.620	11.5	5	0	red	6.14635727145354
64	5.100	0.1100	0.320	1.600	0.028	12.00	90.00	0.99008	3.570	0.520	12.2	6	0	white	6.37407569809102
65	5.100	0.1400	0.250	0.700	0.039	15.00	89.00	0.9919	3.220	0.430	9.2	6	0	white	5.3981395839304
66	5.100	0.1650	0.220	5.700	0.047	42.00	146.00	0.9934	3.180	0.550	9.9	6	0	white	5.62585801056788
67	5.100	0.2100	0.280	1.400	0.047	48.00	148.00	0.99168	3.500	0.490	10.4	5	0	white	5.78851402959465
68	5.100	0.2300	0.180	1.000	0.053	13.00	99.00	0.98956	3.220	0.390	11.5	5	0	white	6.14635727145354
69	5.100	0.2500	0.360	1.300	0.035	40.00	78.00	0.9891	3.230	0.640	12.1	7	1	white	6.34154449428567
70	5.100	0.2600	0.330	1.100	0.027	46.00	113.00	0.98946	3.350	0.430	11.4	7	1	white	6.11382606764819
71	5.100	0.2600	0.340	6.400	0.034	26.00	99.00	0.99449	3.230	0.410	9.2	6	0	white	5.3981395839304
72	5.100	0.2900	0.280	8.300	0.026	27.00	107.00	0.99308	3.360	0.370	11.0	6	0	white	5.98370125242677
73	5.100	0.2900	0.280	8.300	0.026	27.00	107.00	0.99308	3.360	0.370	11.0	6	0	white	5.98370125242677
74	5.100	0.3000	0.300	2.300	0.048	40.00	150.00	0.98944	3.290	0.460	12.2	6	0	white	6.37407569809102
75	5.100	0.3050	0.130	1.750	0.036	17.00	73.00	0.99	3.400	0.510	12.3333333333333	5	0	white	6.41745063649815
76	5.100	0.3100	0.300	0.900	0.037	28.00	152.00	0.992	3.540	0.560	10.1	6	0	white	5.69092041817858
77	5.100	0.3300	0.220	1.600	0.027	18.00	89.00	0.9893	3.510	0.380	12.5	7	1	white	6.47166930950709
78	5.100	0.3300	0.220	1.600	0.027	18.00	89.00	0.9893	3.510	0.380	12.5	7	1	white	6.47166930950709
79	5.100	0.3300	0.220	1.600	0.027	18.00	89.00	0.9893	3.510	0.380	12.5	7	1	white	6.47166930950709
80	5.100	0.3300	0.270	6.700	0.022	44.00	129.00	0.99221	3.360	0.390	11.0	7	1	white	5.98370125242677
81	5.100	0.3500	0.260	6.800	0.034	36.00	120.00	0.99188	3.380	0.400	11.5	6	0	white	6.14635727145354
82	5.100	0.3500	0.260	6.800	0.034	36.00	120.00	0.99188	3.380	0.400	11.5	6	0	white	6.14635727145354
83	5.100	0.3500	0.260	6.800	0.034	36.00	120.00	0.99188	3.380	0.400	11.5	6	0	white	6.14635727145354
84	5.100	0.3900	0.210	1.700	0.027	15.00	72.00	0.9894	3.500	0.450	12.5	6	0	white	6.47166930950709
85	5.100	0.4200	0.000	1.800	0.044	18.00	88.00	0.99157	3.680	0.730	13.6	7	1	red	6.82951255136598
86	5.100	0.4200	0.010	1.500	0.017	25.00	102.00	0.9894	3.380	0.360	12.3	7	1	white	6.40660690189638
87	5.100	0.4700	0.020	1.300	0.034	18.00	44.00	0.9921	3.900	0.620	12.8	6	0	red	6.56926292092315
88	5.100	0.5100	0.180	2.100	0.042	16.00	101.00	0.9924	3.460	0.870	12.9	7	1	red	6.6017941247285
89	5.100	0.5200	0.060	2.700	0.052	30.00	79.00	0.9932	3.320	0.430	9.3	5	0	white	5.43067078773575
90	5.100	0.5850	0.000	1.700	0.044	14.00	86.00	0.99264	3.560	0.940	12.9	7	1	red	6.6017941247285
91	5.200	0.1550	0.330	1.600	0.028	13.00	59.00	0.98975	3.300	0.840	11.9	8	1	white	6.27648208667496
92	5.200	0.1550	0.330	1.600	0.028	13.00	59.00	0.98975	3.300	0.840	11.9	8	1	white	6.27648208667496
93	5.200	0.1600	0.340	0.800	0.029	26.00	77.00	0.99155	3.250	0.510	10.1	6	0	white	5.69092041817858
94	5.200	0.1700	0.270	0.700	0.03	11.00	68.00	0.99218	3.300	0.410	9.8	5	0	white	5.59332680676252
95	5.200	0.1850	0.220	1.000	0.03	47.00	123.00	0.99218	3.550	0.440	10.15	6	0	white	5.70718602008126
96	5.200	0.2000	0.270	3.200	0.047	16.00	93.00	0.99235	3.440	0.530	10.1	7	1	white	5.69092041817858
97	5.200	0.2100	0.310	1.700	0.048	17.00	61.00	0.98953	3.240	0.370	12.0	7	1	white	6.30901329048031
98	5.200	0.2200	0.460	6.200	0.066	41.00	187.00	0.99362	3.190	0.420	9.73333333333333	5	0	white	5.57163933755895
99	5.200	0.2400	0.150	7.100	0.043	32.00	134.00	0.99378	3.240	0.480	9.9	6	0	white	5.62585801056788
100	5.200	0.2400	0.450	3.800	0.027	21.00	128.00	0.992	3.550	0.490	11.2	8	1	white	6.04876366003748

Out[32]:

Rows: 1-100 of 6497 | Columns: 15

The vDataFrame has also a method 'score' to evaluate the quality of your model.

In [33]:

winequality.score("quality", "pred_quality", method = "mse")

Out[33]:

0.611933859491424

Let's examine our prediction with a histogram and regression plot.

In [34]:

winequality.hist(["quality", "pred_quality"], h = (2, 2))

In [35]:

model.plot()