Decision Trees - Práctica de regresión

Índice de contenido

python

from sklearn import datasets
import graphviz
from sklearn import tree
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
import pandas as pd

python

diabetes = datasets.load_diabetes()

python

diabetes.data

array([[ 0.03807591,  0.05068012,  0.06169621, ..., -0.00259226,
         0.01990842, -0.01764613],
       [-0.00188202, -0.04464164, -0.05147406, ..., -0.03949338,
        -0.06832974, -0.09220405],
       [ 0.08529891,  0.05068012,  0.04445121, ..., -0.00259226,
         0.00286377, -0.02593034],
       ...,
       [ 0.04170844,  0.05068012, -0.01590626, ..., -0.01107952,
        -0.04687948,  0.01549073],
       [-0.04547248, -0.04464164,  0.03906215, ...,  0.02655962,
         0.04452837, -0.02593034],
       [-0.04547248, -0.04464164, -0.0730303 , ..., -0.03949338,
        -0.00421986,  0.00306441]])

python

diabetes.target

array([151.,  75., 141., 206., 135.,  97., 138.,  63., 110., 310., 101.,
        69., 179., 185., 118., 171., 166., 144.,  97., 168.,  68.,  49.,
        68., 245., 184., 202., 137.,  85., 131., 283., 129.,  59., 341.,
        87.,  65., 102., 265., 276., 252.,  90., 100.,  55.,  61.,  92.,
       259.,  53., 190., 142.,  75., 142., 155., 225.,  59., 104., 182.,
       128.,  52.,  37., 170., 170.,  61., 144.,  52., 128.,  71., 163.,
       150.,  97., 160., 178.,  48., 270., 202., 111.,  85.,  42., 170.,
       200., 252., 113., 143.,  51.,  52., 210.,  65., 141.,  55., 134.,
        42., 111.,  98., 164.,  48.,  96.,  90., 162., 150., 279.,  92.,
        83., 128., 102., 302., 198.,  95.,  53., 134., 144., 232.,  81.,
       104.,  59., 246., 297., 258., 229., 275., 281., 179., 200., 200.,
       173., 180.,  84., 121., 161.,  99., 109., 115., 268., 274., 158.,
       107.,  83., 103., 272.,  85., 280., 336., 281., 118., 317., 235.,
        60., 174., 259., 178., 128.,  96., 126., 288.,  88., 292.,  71.,
       197., 186.,  25.,  84.,  96., 195.,  53., 217., 172., 131., 214.,
        59.,  70., 220., 268., 152.,  47.,  74., 295., 101., 151., 127.,
       237., 225.,  81., 151., 107.,  64., 138., 185., 265., 101., 137.,
       143., 141.,  79., 292., 178.,  91., 116.,  86., 122.,  72., 129.,
       142.,  90., 158.,  39., 196., 222., 277.,  99., 196., 202., 155.,
        77., 191.,  70.,  73.,  49.,  65., 263., 248., 296., 214., 185.,
        78.,  93., 252., 150.,  77., 208.,  77., 108., 160.,  53., 220.,
       154., 259.,  90., 246., 124.,  67.,  72., 257., 262., 275., 177.,
        71.,  47., 187., 125.,  78.,  51., 258., 215., 303., 243.,  91.,
       150., 310., 153., 346.,  63.,  89.,  50.,  39., 103., 308., 116.,
       145.,  74.,  45., 115., 264.,  87., 202., 127., 182., 241.,  66.,
        94., 283.,  64., 102., 200., 265.,  94., 230., 181., 156., 233.,
        60., 219.,  80.,  68., 332., 248.,  84., 200.,  55.,  85.,  89.,
        31., 129.,  83., 275.,  65., 198., 236., 253., 124.,  44., 172.,
       114., 142., 109., 180., 144., 163., 147.,  97., 220., 190., 109.,
       191., 122., 230., 242., 248., 249., 192., 131., 237.,  78., 135.,
       244., 199., 270., 164.,  72.,  96., 306.,  91., 214.,  95., 216.,
       263., 178., 113., 200., 139., 139.,  88., 148.,  88., 243.,  71.,
        77., 109., 272.,  60.,  54., 221.,  90., 311., 281., 182., 321.,
        58., 262., 206., 233., 242., 123., 167.,  63., 197.,  71., 168.,
       140., 217., 121., 235., 245.,  40.,  52., 104., 132.,  88.,  69.,
       219.,  72., 201., 110.,  51., 277.,  63., 118.,  69., 273., 258.,
        43., 198., 242., 232., 175.,  93., 168., 275., 293., 281.,  72.,
       140., 189., 181., 209., 136., 261., 113., 131., 174., 257.,  55.,
        84.,  42., 146., 212., 233.,  91., 111., 152., 120.,  67., 310.,
        94., 183.,  66., 173.,  72.,  49.,  64.,  48., 178., 104., 132.,
       220.,  57.])

python

regressor = tree.DecisionTreeRegressor()

python

param_grid = {"max_depth": range(1, 101)}

python

gs = GridSearchCV(estimator = regressor,
                 param_grid= param_grid,
                 scoring=None,
                 cv = None)

python

X_train, X_test, y_train, y_test = train_test_split(diabetes.data, diabetes.target, test_size = 0.1)

python

gs.fit(X_train, y_train)

GridSearchCV(estimator=DecisionTreeRegressor(),
             param_grid={'max_depth': range(1, 101)})

python

pd.DataFrame(gs.cv_results_)

	mean_fit_time	std_fit_time	mean_score_time	std_score_time	param_max_depth	params	split0_test_score	split1_test_score	split2_test_score	split3_test_score	split4_test_score	mean_test_score	std_test_score	rank_test_score
0	0.0024	8.000374e-04	0.0012	0.000400	1	{'max_depth': 1}	-0.060515	0.169450	0.237667	0.239624	0.277944	0.172834	0.121799	5
1	0.0020	9.536743e-08	0.0018	0.000400	2	{'max_depth': 2}	0.157606	0.345946	0.390015	0.376850	0.420685	0.338220	0.093442	2
2	0.0036	4.900376e-04	0.0022	0.000400	3	{'max_depth': 3}	0.192454	0.376758	0.450917	0.461504	0.333924	0.363111	0.097522	1
3	0.0022	7.483665e-04	0.0014	0.000490	4	{'max_depth': 4}	0.236153	0.233785	0.447801	0.481629	0.277903	0.335454	0.107236	3
4	0.0030	6.324097e-04	0.0010	0.000632	5	{'max_depth': 5}	0.114858	0.054706	0.303211	0.489421	0.224088	0.237257	0.152589	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
95	0.0046	4.900182e-04	0.0014	0.000490	96	{'max_depth': 96}	-0.396410	-0.246646	0.069781	0.320491	-0.288523	-0.108261	0.264652	69
96	0.0070	3.033323e-03	0.0026	0.002245	97	{'max_depth': 97}	-0.359487	-0.373346	0.078477	0.305255	-0.261482	-0.122117	0.268986	80
97	0.0050	6.324097e-04	0.0012	0.000400	98	{'max_depth': 98}	-0.265533	-0.368183	0.009950	0.389968	-0.247807	-0.096321	0.273225	54
98	0.0052	3.999949e-04	0.0018	0.000748	99	{'max_depth': 99}	-0.299163	-0.334341	0.092851	0.222707	-0.275652	-0.118719	0.230224	77
99	0.0062	2.482189e-03	0.0016	0.000490	100	{'max_depth': 100}	-0.293294	-0.283854	0.029438	0.284367	-0.229963	-0.098661	0.224739	56

100 rows × 14 columns

python

best_model = gs.best_estimator_
best_model

DecisionTreeRegressor(max_depth=3)

python

best_model.predict(X_test)

array([ 94.49032258,  94.49032258, 157.10714286,  94.49032258,
       221.6       , 208.25      ,  94.49032258, 157.10714286,
       142.66071429,  94.49032258, 142.66071429, 267.11428571,
        94.49032258, 157.10714286, 208.25      , 157.10714286,
       208.25      ,  94.49032258, 187.43243243,  94.49032258,
       208.25      ,  94.49032258, 187.43243243,  94.49032258,
       187.43243243, 142.66071429, 187.43243243,  94.49032258,
       208.25      , 157.10714286,  94.49032258, 253.        ,
        94.49032258,  94.49032258, 142.66071429, 142.66071429,
        94.49032258, 187.43243243,  94.49032258, 157.10714286,
       187.43243243, 208.25      , 208.25      , 208.25      ,
       267.11428571])

python

pd.DataFrame({"y_test": y_test, "y_pred": best_model.predict(X_test)})

	y_test	y_pred
0	125.0	94.490323
1	116.0	94.490323
2	145.0	157.107143
3	200.0	94.490323
4	295.0	221.600000
5	296.0	208.250000
6	111.0	94.490323
7	196.0	157.107143
8	209.0	142.660714
9	98.0	94.490323
10	131.0	142.660714
11	109.0	267.114286
12	158.0	94.490323
13	111.0	157.107143
14	265.0	208.250000
15	279.0	157.107143
16	113.0	208.250000
17	70.0	94.490323
18	249.0	187.432432
19	89.0	94.490323
20	175.0	208.250000
21	49.0	94.490323
22	168.0	187.432432
23	88.0	94.490323
24	131.0	187.432432
25	185.0	142.660714
26	58.0	187.432432
27	63.0	94.490323
28	52.0	208.250000
29	121.0	157.107143
30	61.0	94.490323
31	89.0	253.000000
32	160.0	94.490323
33	40.0	94.490323
34	120.0	142.660714
35	214.0	142.660714
36	132.0	94.490323
37	107.0	187.432432
38	230.0	94.490323
39	259.0	157.107143
40	181.0	187.432432
41	265.0	208.250000
42	258.0	208.250000
43	283.0	208.250000
44	215.0	267.114286

python

X_test[0]

array([-0.02730979, -0.04464164, -0.03530688, -0.02977071, -0.05660707,
       -0.05862005,  0.03023191, -0.03949338, -0.04986847, -0.12948301])

python

best_model.score(X_test, y_test)

0.042966591843769275

python

diabetes.feature_names

['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']

python

data = tree.export_graphviz(best_model, out_file=None,
                           feature_names = diabetes.feature_names,
                           filled = True,
                           rounded = True)
graph = graphviz.Source(data)
graph.render("C:/users/User/Desktop/diabetes_best_v2")

'C:/users/User/Desktop\\diabetes_best_v2.pdf'