瞎BB

1.實現根據樣本數據（用眼距離distance、最長持續用眼時長duration、總用眼時長total_time、戶外運動時長outdoor、用眼角度angle、健康環境光照用眼比例proportion）判別是否需要近視預警
2.樣本實在太少，結果還行，原理都是一樣的

代碼

導入數據

切分訓練集測試集

            
              
                from
              
               sklearn
              
                .
              
              model_selection 
              
                import
              
               train_test_split
patients_data
              
                =
              
              patients
              
                .
              
              loc
              
                [
              
              
                :
              
              
                ,
              
              
                'distance'
              
              
                :
              
              
                'proportion'
              
              
                ]
              
              
patients_target
              
                =
              
              patients
              
                .
              
              loc
              
                [
              
              
                :
              
              
                ,
              
              
                'warning'
              
              
                ]
              
              
data_train
              
                ,
              
              data_test
              
                ,
              
              target_train
              
                ,
              
              target_test
              
                =
              
              train_test_split
              
                (
              
              patients_data
              
                ,
              
              patients_target
              
                ,
              
              test_size
              
                =
              
              
                0.1
              
              
                ,
              
              random_state
              
                =
              
              
                42
              
              
                )

找到最有用的幾個屬性

            
              
                import
              
               numpy 
              
                as
              
               np

              
                from
              
               sklearn
              
                .
              
              feature_selection 
              
                import
              
               SelectKBest
              
                ,
              
               f_classif

              
                import
              
               matplotlib
              
                .
              
              pyplot 
              
                as
              
               plt
predictors 
              
                =
              
              
                [
              
              
                "distance"
              
              
                ,
              
              
                "duration"
              
              
                ,
              
              
                "total_time"
              
              
                ,
              
              
                "outdoor"
              
              
                ,
              
              
                "angle"
              
              
                ,
              
              
                "proportion"
              
              
                ]
              
              

selector 
              
                =
              
               SelectKBest
              
                (
              
              f_classif
              
                ,
              
               k
              
                =
              
              
                5
              
              
                )
              
              
selector
              
                .
              
              fit
              
                (
              
              data_train
              
                ,
              
               target_train
              
                )
              
              

scores 
              
                =
              
              
                -
              
              np
              
                .
              
              log10
              
                (
              
              selector
              
                .
              
              pvalues_
              
                )
              
              

plt
              
                .
              
              bar
              
                (
              
              
                range
              
              
                (
              
              
                len
              
              
                (
              
              predictors
              
                )
              
              
                )
              
              
                ,
              
               scores
              
                )
              
              
plt
              
                .
              
              xticks
              
                (
              
              
                range
              
              
                (
              
              
                len
              
              
                (
              
              predictors
              
                )
              
              
                )
              
              
                ,
              
               predictors
              
                ,
              
               rotation
              
                =
              
              
                'vertical'
              
              
                )
              
              
plt
              
                .
              
              show
              
                (
              
              
                )

根據上面的代碼更改屬性

            
              predictors_best 
              
                =
              
              
                [
              
              
                "distance"
              
              
                ,
              
              
                "total_time"
              
              
                ,
              
              
                "angle"
              
              
                ,
              
              
                "proportion"
              
              
                ]
              
              
data_train 
              
                =
              
               data_train
              
                [
              
              predictors_best
              
                ]
              
              
data_test 
              
                =
              
               data_test
              
                [
              
              predictors_best
              
                ]

參數組合遍歷找最優

            
              
                from
              
               sklearn
              
                .
              
              model_selection 
              
                import
              
               GridSearchCV
tree_param_grid 
              
                =
              
              
                {
              
              
                'min_samples_split'
              
              
                :
              
              
                list
              
              
                (
              
              
                (
              
              
                2
              
              
                ,
              
              
                3
              
              
                ,
              
              
                4
              
              
                )
              
              
                )
              
              
                ,
              
              
                'n_estimators'
              
              
                :
              
              
                list
              
              
                (
              
              
                (
              
              
                3
              
              
                ,
              
              
                5
              
              
                ,
              
              
                10
              
              
                ,
              
              
                15
              
              
                ,
              
              
                20
              
              
                ,
              
              
                25
              
              
                ,
              
              
                30
              
              
                ,
              
              
                35
              
              
                ,
              
              
                40
              
              
                ,
              
              
                45
              
              
                ,
              
              
                50
              
              
                )
              
              
                )
              
              
                }
              
              
grid 
              
                =
              
               GridSearchCV
              
                (
              
              RandomForestClassifier
              
                (
              
              
                )
              
              
                ,
              
              param_grid
              
                =
              
              tree_param_grid
              
                ,
              
               cv
              
                =
              
              kf
              
                )
              
              
                #(算法，調節參數（用字典形式），交叉驗證次數)
              
              
grid
              
                .
              
              fit
              
                (
              
              data_train
              
                ,
              
               target_train
              
                )
              
              
                #訓練集
              
              
grid
              
                .
              
              cv_results_ 
              
                ,
              
               grid
              
                .
              
              best_params_
              
                ,
              
               grid
              
                .
              
              best_score_
              
                #得分，最優參數，最優得分

隨機森林

            
              
                from
              
               sklearn 
              
                import
              
               model_selection

              
                from
              
               sklearn
              
                .
              
              ensemble 
              
                import
              
               RandomForestClassifier
rf 
              
                =
              
               RandomForestClassifier
              
                (
              
              random_state
              
                =
              
              
                1
              
              
                ,
              
               n_estimators
              
                =
              
              
                35
              
              
                ,
              
               min_samples_split
              
                =
              
              
                2
              
              
                ,
              
               min_samples_leaf
              
                =
              
              
                2
              
              
                )
              
              
                #交叉驗證
              
              
kf 
              
                =
              
               model_selection
              
                .
              
              KFold
              
                (
              
              n_splits
              
                =
              
              
                3
              
              
                )
              
              
scores 
              
                =
              
               model_selection
              
                .
              
              cross_val_score
              
                (
              
              rf
              
                ,
              
               data_train
              
                ,
              
               target_train
              
                ,
              
               cv
              
                =
              
              kf
              
                )
              
              
                print
              
              
                (
              
              scores
              
                .
              
              mean
              
                (
              
              
                )
              
              
                )

樣本數據

sample	distance	duration	total_time	outdoor	angle	proportion	warning(1 yes 0 no)
1	20	72	344	148	11	81	1
2	34	68	263	135	7	50	1
3	25	98	357	32	12	64	1
4	37	65	291	157	8	89	0
5	34	151	162	169	18	63	1
6	30	178	259	146	32	50	1
7	20	35	134	37	23	68	0
8	39	111	169	87	4	52	0
9	22	44	265	136	14	76	1
10	39	151	219	140	2	55	0
11	21	179	184	64	18	60	1
12	25	41	241	71	16	72	1
13	18	171	286	131	35	89	1
14	32	33	236	102	29	50	1
15	20	133	226	124	17	81	1
16	17	148	236	66	32	75	1
17	34	111	214	57	5	88	0
18	24	85	163	155	14	32	1
19	32	165	276	146	33	52	1
20	25	124	359	171	33	70	0
21	31	51	167	47	25	47	0
22	31	63	352	58	22	44	1
23	16	58	164	45	13	73	0
24	29	37	326	104	33	68	1
25	34	47	197	59	5	66	0
26	36	123	185	165	26	70	0
27	25	126	171	45	23	33	1
28	31	84	98	37	30	51	1
29	30	92	153	114	14	48	0
30	29	178	278	146	27	45	1

更多文章、技術交流、商務合作、聯系博主

微信掃碼或搜索：z360901061

微信掃一掃加我為好友

QQ號聯系： 360901061

您的支持是博主寫作最大的動力，如果您喜歡我的文章，感覺我的文章對您有幫助，請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧，狠狠點擊下面給點支持吧，站長非常感激您！手機微信長按不能支付解決辦法：請將微信支付二維碼保存到相冊，切換到微信，然后點擊微信右上角掃一掃功能，選擇支付二維碼完成支付。

【本文對您有幫助就好】元

2元

5元

10元

20元

自定義

sample	distance	duration	total_time	outdoor	angle	proportion	warning(1 yes 0 no)
1	20	72	344	148	11	81	1
2	34	68	263	135	7	50	1
3	25	98	357	32	12	64	1
4	37	65	291	157	8	89	0
5	34	151	162	169	18	63	1
6	30	178	259	146	32	50	1
7	20	35	134	37	23	68	0
8	39	111	169	87	4	52	0
9	22	44	265	136	14	76	1
10	39	151	219	140	2	55	0
11	21	179	184	64	18	60	1
12	25	41	241	71	16	72	1
13	18	171	286	131	35	89	1
14	32	33	236	102	29	50	1
15	20	133	226	124	17	81	1
16	17	148	236	66	32	75	1
17	34	111	214	57	5	88	0
18	24	85	163	155	14	32	1
19	32	165	276	146	33	52	1
20	25	124	359	171	33	70	0
21	31	51	167	47	25	47	0
22	31	63	352	58	22	44	1
23	16	58	164	45	13	73	0
24	29	37	326	104	33	68	1
25	34	47	197	59	5	66	0
26	36	123	185	165	26	70	0
27	25	126	171	45	23	33	1
28	31	84	98	37	30	51	1
29	30	92	153	114	14	48	0
30	29	178	278	146	27	45	1

sample	distance	duration	total_time	outdoor	angle	proportion	warning(1 yes 0 no)
1	20	72	344	148	11	81	1
2	34	68	263	135	7	50	1
3	25	98	357	32	12	64	1
4	37	65	291	157	8	89	0
5	34	151	162	169	18	63	1
6	30	178	259	146	32	50	1
7	20	35	134	37	23	68	0
8	39	111	169	87	4	52	0
9	22	44	265	136	14	76	1
10	39	151	219	140	2	55	0
11	21	179	184	64	18	60	1
12	25	41	241	71	16	72	1
13	18	171	286	131	35	89	1
14	32	33	236	102	29	50	1
15	20	133	226	124	17	81	1
16	17	148	236	66	32	75	1
17	34	111	214	57	5	88	0
18	24	85	163	155	14	32	1
19	32	165	276	146	33	52	1
20	25	124	359	171	33	70	0
21	31	51	167	47	25	47	0
22	31	63	352	58	22	44	1
23	16	58	164	45	13	73	0
24	29	37	326	104	33	68	1
25	34	47	197	59	5	66	0
26	36	123	185	165	26	70	0
27	25	126	171	45	23	33	1
28	31	84	98	37	30	51	1
29	30	92	153	114	14	48	0
30	29	178	278	146	27	45	1

sample	distance	duration	total_time	outdoor	angle	proportion	warning(1 yes 0 no)
1	20	72	344	148	11	81	1
2	34	68	263	135	7	50	1
3	25	98	357	32	12	64	1
4	37	65	291	157	8	89	0
5	34	151	162	169	18	63	1
6	30	178	259	146	32	50	1
7	20	35	134	37	23	68	0
8	39	111	169	87	4	52	0
9	22	44	265	136	14	76	1
10	39	151	219	140	2	55	0
11	21	179	184	64	18	60	1
12	25	41	241	71	16	72	1
13	18	171	286	131	35	89	1
14	32	33	236	102	29	50	1
15	20	133	226	124	17	81	1
16	17	148	236	66	32	75	1
17	34	111	214	57	5	88	0
18	24	85	163	155	14	32	1
19	32	165	276	146	33	52	1
20	25	124	359	171	33	70	0
21	31	51	167	47	25	47	0
22	31	63	352	58	22	44	1
23	16	58	164	45	13	73	0
24	29	37	326	104	33	68	1
25	34	47	197	59	5	66	0
26	36	123	185	165	26	70	0
27	25	126	171	45	23	33	1
28	31	84	98	37	30	51	1
29	30	92	153	114	14	48	0
30	29	178	278	146	27	45	1