plot_report with examples#

An example showing the report function with a scikit-learn classifier (e.g., LogisticRegression) instance.

# Authors: The scikit-plots developers
# SPDX-License-Identifier: BSD-3-Clause

from sklearn.datasets import (
    load_breast_cancer as data_2_classes,
    # load_iris as data_3_classes,
)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

# importing pylab or pyplot
import matplotlib.pyplot as plt
import numpy as np; np.random.seed(0)  # reproducibility

# Import scikit-plot
import scikitplot as sp

# Load the data
X, y = data_2_classes(return_X_y=True, as_frame=False)
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.5, random_state=0)

# Create an instance of the LogisticRegression
model = LogisticRegression(max_iter=int(1e5), random_state=0).fit(X_train, y_train)

# Perform predictions
y_val_prob = model.predict_proba(X_val)

sp.kds.decile_table(
    y_val,
    y_val_prob,
    save_fig=True,
    save_fig_filename="",
    # overwrite=True,
    add_timestamp=True,
    # verbose=True,
    display_term_tables=True,
)

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	1.000	1.000	1.000	29.0	29.0	0.0	18.4	29	100.000	29.0	29.0	29	0.0	10.175	15.761	15.761	0.000	15.761	1.549
1	2	0.999	1.000	1.000	28.0	28.0	0.0	18.4	28	100.000	57.0	57.0	57	0.0	20.000	30.978	30.978	0.000	30.978	1.549
2	3	0.998	0.999	0.999	29.0	29.0	0.0	18.4	29	100.000	86.0	86.0	86	0.0	30.175	46.739	46.739	0.000	46.739	1.549
3	4	0.993	0.997	0.996	28.0	28.0	0.0	18.4	28	100.000	114.0	114.0	114	0.0	40.000	61.957	61.957	0.000	61.957	1.549
4	5	0.960	0.992	0.980	29.0	29.0	0.0	18.4	29	100.000	143.0	143.0	143	0.0	50.175	77.717	77.717	0.000	77.717	1.549
5	6	0.772	0.956	0.888	28.0	25.0	3.0	18.4	28	89.286	171.0	168.0	171	3.0	60.000	91.304	92.935	2.970	88.334	1.522
6	7	0.066	0.769	0.346	29.0	16.0	13.0	18.4	13	55.172	200.0	184.0	184	16.0	70.175	100.000	100.000	15.842	84.158	1.425
7	8	0.000	0.048	0.011	28.0	0.0	28.0	18.4	0	0.000	228.0	184.0	184	44.0	80.000	100.000	100.000	43.564	56.436	1.250
8	9	0.000	0.000	0.000	29.0	0.0	29.0	18.4	0	0.000	257.0	184.0	184	73.0	90.175	100.000	100.000	72.277	27.723	1.109
9	10	0.000	0.000	0.000	28.0	0.0	28.0	18.4	0	0.000	285.0	184.0	184	101.0	100.000	100.000	100.000	100.000	0.000	1.000

Plot!

ax = sp.kds.report(
    y_val,
    y_val_prob,
    save_fig=True,
    save_fig_filename="",
    # overwrite=True,
    add_timestamp=True,
    # verbose=True,
    display_term_tables=True,
)

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

Tags: model-type: classification model-workflow: model evaluation plot-type: line plot-type: decile level: beginner purpose: showcase

Total running time of the script: (0 minutes 1.351 seconds)

Related examples