vDataFrame.score¶

In [ ]:

vDataFrame.score(y_true: str, 
                 y_score: str,
                 method: str,
                 nbins: int = 30,)

Computes the score using the input columns and the input method.

Parameters¶

Name	Type	Optional	Description
y_true	str	❌	Response column.
y_score	str	❌	Prediction.
method	str	❌	The method to use to compute the score. For Classification: accuracy : Accuracy auc : Area Under the Curve (ROC) best_cutoff : Cutoff which optimised the ROC Curve prediction. bm : Informedness = tpr + tnr - 1 csi : Critical Success Index = tp / (tp + fn + fp) f1 : F1 Score logloss : Log Loss mcc : Matthews Correlation Coefficient mk : Markedness = ppv + npv - 1 npv : Negative Predictive Value = tn / (tn + fn) prc_auc : Area Under the Curve (PRC) precision : Precision = tp / (tp + fp) recall : Recall = tp / (tp + fn) specificity : Specificity = tn / (tn + fp) For Regression: max : Max Error mae : Mean Absolute Error median : Median Absolute Error mse : Mean Squared Error msle : Mean Squared Log Error r2 : R-squared coefficient var : Explained Variance Plots: roc : ROC Curve prc : PRC Curve lift : Lift Chart
nbins	int	✓	[Only when method is set to auc\|prc_auc\|best_cutoff] An integer value that determines the number of decision boundaries. Decision boundaries are set at equally spaced intervals between 0 and 1, inclusive. Greater values for nbins give more precise estimations of the AUC, but can potentially decrease performance. The maximum value is 999,999. If negative, the maximum value is used.

Returns¶

float / tablesample : score / tablesample of the curve

Example¶

In [62]:

from verticapy.datasets import load_titanic
titanic = load_titanic().select(["age", "fare", "survived"])
display(titanic)

	123 age Numeric(6,3)	123 fare Numeric(10,5)	123 survived Int
1	2.000	151.55000	0
2	30.000	151.55000	0
3	25.000	151.55000	0
4	39.000	0.00000	0
5	71.000	49.50420	0
6	47.000	227.52500	0
7	[null]	25.92500	0
8	24.000	247.52080	0
9	36.000	75.24170	0
10	25.000	26.00000	0
11	45.000	35.50000	0
12	42.000	26.55000	0
13	41.000	30.50000	0
14	48.000	50.49580	0
15	[null]	39.60000	0
16	45.000	26.55000	0
17	[null]	31.00000	0
18	33.000	5.00000	0
19	28.000	47.10000	0
20	17.000	47.10000	0
21	49.000	26.00000	0
22	36.000	78.85000	0
23	46.000	61.17500	0
24	[null]	0.00000	0
25	27.000	136.77920	0
26	[null]	52.00000	0
27	47.000	25.58750	0
28	37.000	83.15830	0
29	[null]	26.55000	0
30	70.000	71.00000	0
31	39.000	71.28330	0
32	31.000	52.00000	0
33	50.000	106.42500	0
34	39.000	29.70000	0
35	36.000	31.67920	0
36	[null]	221.77920	0
37	30.000	27.75000	0
38	19.000	263.00000	0
39	64.000	263.00000	0
40	[null]	26.55000	0
41	[null]	0.00000	0
42	37.000	53.10000	0
43	47.000	38.50000	0
44	24.000	79.20000	0
45	71.000	34.65420	0
46	38.000	153.46250	0
47	46.000	79.20000	0
48	[null]	42.40000	0
49	45.000	83.47500	0
50	40.000	0.00000	0
51	55.000	93.50000	0
52	42.000	42.50000	0
53	[null]	51.86250	0
54	55.000	50.00000	0
55	42.000	52.00000	0
56	[null]	30.69580	0
57	50.000	28.71250	0
58	46.000	26.00000	0
59	50.000	26.00000	0
60	32.500	211.50000	0
61	58.000	29.70000	0
62	41.000	51.86250	0
63	[null]	26.55000	0
64	[null]	27.72080	0
65	29.000	30.00000	0
66	30.000	45.50000	0
67	30.000	26.00000	0
68	19.000	53.10000	0
69	46.000	75.24170	0
70	54.000	51.86250	0
71	28.000	82.17080	0
72	65.000	26.55000	0
73	44.000	90.00000	0
74	55.000	30.50000	0
75	47.000	42.40000	0
76	37.000	29.70000	0
77	58.000	113.27500	0
78	64.000	26.00000	0
79	65.000	61.97920	0
80	28.500	27.72080	0
81	[null]	0.00000	0
82	45.500	28.50000	0
83	23.000	93.50000	0
84	29.000	66.60000	0
85	18.000	108.90000	0
86	47.000	52.00000	0
87	38.000	0.00000	0
88	22.000	135.63330	0
89	[null]	227.52500	0
90	31.000	50.49580	0
91	[null]	50.00000	0
92	36.000	40.12500	0
93	55.000	59.40000	0
94	33.000	26.55000	0
95	61.000	262.37500	0
96	50.000	55.90000	0
97	56.000	26.55000	0
98	56.000	30.69580	0
99	24.000	60.00000	0
100	[null]	26.00000	0

Rows: 1-100 of 1234 | Columns: 3

In [63]:

from verticapy.learn.linear_model import LogisticRegression
model = LogisticRegression(name = "public.LR_titanic",
                           tol = 1e-4, 
                           C = 1.0, 
                           max_iter = 100, 
                           solver = 'CGD',
                           l1_ratio = 0.5)
model.fit("public.titanic", ["fare", "age"], "survived")
model.predict(titanic, name = "survived_pred")

	123 age Numeric(6,3)	123 fare Numeric(10,5)	123 survived Int	123 survived_pred Float
1	2.000	151.55000	0	0.902287137987944
2	30.000	151.55000	0	0.86058029983458
3	25.000	151.55000	0	0.868988340490406
4	39.000	0.00000	0	0.342456823846109
5	71.000	49.50420	0	0.414029113989722
6	47.000	227.52500	0	0.939923121186975
7	[null]	25.92500	0	[null]
8	24.000	247.52080	0	0.967395954658983
9	36.000	75.24170	0	0.635075649080458
10	25.000	26.00000	0	0.487751263444919
11	45.000	35.50000	0	0.452683907002755
12	42.000	26.55000	0	0.429216761960316
13	41.000	30.50000	0	0.447792486054408
14	48.000	50.49580	0	0.49971322568723
15	[null]	39.60000	0	[null]
16	45.000	26.55000	0	0.418678018840286
17	[null]	31.00000	0	[null]
18	33.000	5.00000	0	0.380187437748189
19	28.000	47.10000	0	0.558247754878829
20	17.000	47.10000	0	0.596833670206284
21	49.000	26.00000	0	0.402695575911559
22	36.000	78.85000	0	0.647904226645164
23	46.000	61.17500	0	0.548033233872829
24	[null]	0.00000	0	[null]
25	27.000	136.77920	0	0.836841341038647
26	[null]	52.00000	0	[null]
27	47.000	25.58750	0	0.408093270883223
28	37.000	83.15830	0	0.659723543412694
29	[null]	26.55000	0	[null]
30	70.000	71.00000	0	0.499846009538692
31	39.000	71.28330	0	0.610568047403653
32	31.000	52.00000	0	0.566271351391256
33	50.000	106.42500	0	0.697362224205815
34	39.000	29.70000	0	0.451851620327145
35	36.000	31.67920	0	0.470175980622248
36	[null]	221.77920	0	[null]
37	30.000	27.75000	0	0.476548622611
38	19.000	263.00000	0	0.975906172743917
39	64.000	263.00000	0	0.954958490722554
40	[null]	26.55000	0	[null]
41	[null]	0.00000	0	[null]
42	37.000	53.10000	0	0.54917807997722
43	47.000	38.50000	0	0.457050748370639
44	24.000	79.20000	0	0.687374102239646
45	71.000	34.65420	0	0.359641574716634
46	38.000	153.46250	0	0.8500005835631
47	46.000	79.20000	0	0.61571512557438
48	[null]	42.40000	0	[null]
49	45.000	83.47500	0	0.634571272671506
50	40.000	0.00000	0	0.339224975430521
51	55.000	93.50000	0	0.637150541510681
52	42.000	42.50000	0	0.490387504173356
53	[null]	51.86250	0	[null]
54	55.000	50.00000	0	0.472650396971738
55	42.000	52.00000	0	0.527078154230704
56	[null]	30.69580	0	[null]
57	50.000	28.71250	0	0.409339902436815
58	46.000	26.00000	0	0.413117914049503
59	50.000	26.00000	0	0.399240408375275
60	32.500	211.50000	0	0.937672852935814
61	58.000	29.70000	0	0.385443044656693
62	41.000	51.86250	0	0.530132926520432
63	[null]	26.55000	0	[null]
64	[null]	27.72080	0	[null]
65	29.000	30.00000	0	0.488825979510246
66	30.000	45.50000	0	0.545014535857961
67	30.000	26.00000	0	0.469804285663854
68	19.000	53.10000	0	0.612131629679044
69	46.000	75.24170	0	0.601136677890098
70	54.000	51.86250	0	0.483424140863347
71	28.000	82.17080	0	0.684873682886807
72	65.000	26.55000	0	0.350713668608726
73	44.000	90.00000	0	0.660862965877402
74	55.000	30.50000	0	0.398676025965298
75	47.000	42.40000	0	0.472047669134459
76	37.000	29.70000	0	0.458986841891317
77	58.000	113.27500	0	0.695421942724314
78	64.000	26.00000	0	0.352054220262656
79	65.000	61.97920	0	0.482967715783495
80	28.500	27.72080	0	0.481820954229194
81	[null]	0.00000	0	[null]
82	45.500	28.50000	0	0.424275206647782
83	23.000	93.50000	0	0.735622606643536
84	29.000	66.60000	0	0.627415614513485
85	18.000	108.90000	0	0.791394954471803
86	47.000	52.00000	0	0.509122344734676
87	38.000	0.00000	0	0.345703353743199
88	22.000	135.63330	0	0.84410848047684
89	[null]	227.52500	0	[null]
90	31.000	50.49580	0	0.560551060575476
91	[null]	50.00000	0	[null]
92	36.000	40.12500	0	0.502784282039499
93	55.000	59.40000	0	0.508953958690919
94	33.000	26.55000	0	0.461182774006888
95	61.000	262.37500	0	0.95637734057273
96	50.000	55.90000	0	0.51340520455764
97	56.000	26.55000	0	0.380732995250046
98	56.000	30.69580	0	0.395956313027424
99	24.000	60.00000	0	0.62034963876044
100	[null]	26.00000	0	[null]

Out[63]:

Rows: 1-100 of 1234 | Columns: 4

In [64]:

# Computing AUC
titanic.score(y_true  = "survived", 
              y_score = "survived_pred",
              method  = "auc")

Out[64]:

0.6974762740166146

In [65]:

# Computing MSE
titanic.score(y_true  = "survived", 
              y_score = "survived_pred",
              method  = "mse")

Out[65]:

0.224993557369594

In [39]:

# Drawing ROC Curve
titanic.score(y_true  = "survived", 
              y_score = "survived_pred",
              method  = "roc")

In [40]:

# Drawing PRC Curve
titanic.score(y_true  = "survived", 
              y_score = "survived_pred",
              method  = "prc")

vDataFrame.score¶

Parameters¶

Returns¶

Example¶

See Also¶