decile_table

scikitplot.kds.decile_table(y_true, y_probas, *args, pos_label=None, class_index=1, change_deciles=10, digits=3, labels=True, **kwargs)

Generates the Decile Table from labels and probabilities

The Decile Table is creared by first sorting the customers by their predicted probabilities, in decreasing order from highest (closest to one) to lowest (closest to zero). Splitting the customers into equally sized segments, we create groups containing the same numbers of customers, for example, 10 decile groups each containing 10% of the customer base.

Added in version 0.3.9.

Parameters:

y_truearray-like, shape (n_samples,)

Ground truth (correct/actual) target values.

y_probasarray-like, shape (n_samples, n_classes)

Prediction probabilities for each class returned by a classifier/algorithm.

pos_labelscalar, optional

The positive label for binary classification. If None, it defaults to classes[1].

Added in version 0.3.9.

class_indexint, optional

Index of the class for which to extract probabilities in multi-class case. If None, returns all class probabilities in the 2D case. Ignored if y_probas is 1D.

Added in version 0.3.9.

change_decilesint, optional, default=10

The number of partitions for creating the table. Defaults to 10 for deciles.

digitsint, optional, default=6

The decimal precision for the result.

Added in version 0.3.9.

labelsbool, optional, default=True

If True, prints a legend for the abbreviations of decile table column names.

**kwargsdict, optional

Added in version 0.3.9.

Returns:

pandas.DataFrame

The dataframe dt (decile-table) with the deciles and related information.

See also

print_labels

A legend for the abbreviations of decile table column names.

References

[1] tensorbored/kds

Examples

>>> from sklearn.datasets import load_breast_cancer as data_2_classes
>>> from sklearn.model_selection import train_test_split
>>> from sklearn.tree import DecisionTreeClassifier
>>> import scikitplot as skplt
>>> X, y = data_2_classes(return_X_y=True, as_frame=True)
>>> X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)
>>> clf = DecisionTreeClassifier(max_depth=1, random_state=0).fit(X_train, y_train)
>>> y_prob = clf.predict_proba(X_test)
>>> skplt.kds.decile_table(
>>>     y_test, y_prob, class_index=1
>>> )

LABELS INFO:

 prob_min         : Minimum probability in a particular decile
 prob_max         : Minimum probability in a particular decile
 prob_avg         : Average probability in a particular decile
 cnt_events       : Count of events in a particular decile
 cnt_resp         : Count of responders in a particular decile
 cnt_non_resp     : Count of non-responders in a particular decile
 cnt_resp_rndm    : Count of responders if events assigned randomly in a particular decile
 cnt_resp_wiz     : Count of best possible responders in a particular decile
 resp_rate        : Response Rate in a particular decile [(cnt_resp/cnt_cust)*100]
 cum_events       : Cumulative sum of events decile-wise 
 cum_resp         : Cumulative sum of responders decile-wise 
 cum_resp_wiz     : Cumulative sum of best possible responders decile-wise 
 cum_non_resp     : Cumulative sum of non-responders decile-wise 
 cum_events_pct   : Cumulative sum of percentages of events decile-wise 
 cum_resp_pct     : Cumulative sum of percentages of responders decile-wise 
 cum_resp_pct_wiz : Cumulative sum of percentages of best possible responders decile-wise 
 cum_non_resp_pct : Cumulative sum of percentages of non-responders decile-wise 
 KS               : KS Statistic decile-wise 
 lift             : Cumuative Lift Value decile-wise

	decile	prob_min	prob_max	prob_avg	cnt_cust	cnt_resp	cnt_non_resp	cnt_resp_rndm	cnt_resp_wiz	resp_rate	cum_cust	cum_resp	cum_resp_wiz	cum_non_resp	cum_cust_pct	cum_resp_pct	cum_resp_pct_wiz	cum_non_resp_pct	KS	lift
0	1	0.923	0.923	0.923	29.0	26.0	3.0	18.4	NaN	89.655	29.0	26.0	NaN	3.0	10.175	14.130	NaN	2.970	11.160	1.389
1	2	0.923	0.923	0.923	28.0	25.0	3.0	18.4	29.0	89.286	57.0	51.0	29.0	6.0	20.000	27.717	15.761	5.941	21.776	1.386
2	3	0.923	0.923	0.923	29.0	27.0	2.0	18.4	28.0	93.103	86.0	78.0	57.0	8.0	30.175	42.391	30.978	7.921	34.470	1.405
3	4	0.923	0.923	0.923	28.0	23.0	5.0	18.4	29.0	82.143	114.0	101.0	86.0	13.0	40.000	54.891	46.739	12.871	42.020	1.372
4	5	0.923	0.923	0.923	29.0	26.0	3.0	18.4	28.0	89.655	143.0	127.0	114.0	16.0	50.175	69.022	61.957	15.842	53.180	1.376
5	6	0.923	0.923	0.923	28.0	26.0	2.0	18.4	29.0	92.857	171.0	153.0	143.0	18.0	60.000	83.152	77.717	17.822	65.330	1.386
6	7	0.049	0.923	0.833	29.0	24.0	5.0	18.4	28.0	82.759	200.0	177.0	171.0	23.0	70.175	96.196	92.935	22.772	73.424	1.371
7	8	0.049	0.049	0.049	28.0	2.0	26.0	18.4	13.0	7.143	228.0	179.0	184.0	49.0	80.000	97.283	100.000	48.515	48.768	1.216
8	9	0.049	0.049	0.049	29.0	1.0	28.0	18.4	0.0	3.448	257.0	180.0	184.0	77.0	90.175	97.826	100.000	76.238	21.588	1.085
9	10	0.049	0.049	0.049	28.0	4.0	24.0	18.4	0.0	14.286	285.0	184.0	184.0	101.0	100.000	100.000	100.000	100.000	0.000	1.000

Make live