nuevoojoooo
BIN
__pycache__/preguntas.cpython-311.pyc
Normal file
BIN
mae_perf_method.png
Normal file
After Width: | Height: | Size: 13 KiB |
|
@ -7,4 +7,3 @@
|
|||
## ideas NAs
|
||||
- usar los voluntarios con ceros como training
|
||||
- probar todas las posibles combinaciones de retirar NAs en train
|
||||
|
||||
|
|
BIN
perf_metrics_summary.png
Normal file
After Width: | Height: | Size: 28 KiB |
12
preguntas.py
Normal file
|
@ -0,0 +1,12 @@
|
|||
import scrapy
|
||||
|
||||
class BlogSpider(scrapy.Spider):
|
||||
name = 'blogspider'
|
||||
start_urls = ['https://www.iata.csic.es/']
|
||||
|
||||
def parse(self, response):
|
||||
for title in response.css('.oxy-post-title'):
|
||||
yield {'title': title.css('::text').get()}
|
||||
|
||||
for next_page in response.css('a.next'):
|
||||
yield response.follow(next_page, self.parse)
|
BIN
r2_perf_method.png
Normal file
After Width: | Height: | Size: 14 KiB |
|
@ -0,0 +1,29 @@
|
|||
;DHPAA.GG_urine_post_pred;DHPAA.GG_urine_post_test
|
||||
135;0.028153156055213128;0.02306918427348137
|
||||
66;0.018361467996007543;0.02124183
|
||||
31;0.01845511186209114;0.011437908
|
||||
118;0.050374303744972336;0.049019608
|
||||
42;0.036810230067259544;0.02283056080341339
|
||||
12;0.05219072017192368;0.06341682374477386
|
||||
51;0.06314230449378826;0.081699346
|
||||
68;0.032156267227236364;0.013071895
|
||||
126;0.028153156055213128;0.03025123104453087
|
||||
55;0.017200176868291738;0.022875817
|
||||
112;0.028287330195368495;0.038646358996629715
|
||||
130;0.06512786516866897;0.058823529
|
||||
80;0.036769699793187775;0.02044045552611351
|
||||
19;0.0646236779087797;0.091503268
|
||||
86;0.06512786516866897;0.088235294
|
||||
69;0.03409086651673512;0.016339869
|
||||
11;0.031212544361196616;0.041303522884845734
|
||||
27;0.036461300354839396;0.032679739
|
||||
134;0.036810230067259544;0.031945351511240005
|
||||
109;0.036038730903312076;0.050144873559474945
|
||||
36;0.05406548222590799;0.021195339038968086
|
||||
117;0.018320937721935774;0.011437908
|
||||
78;0.04159588633530323;0.032308947294950485
|
||||
4;0.027259469129501897;0.006535948
|
||||
73;0.018320937721935774;0.019607843
|
||||
26;0.06757869907213537;0.109477124
|
||||
132;0.018320937721935774;0.004901961
|
||||
60;0.03125307463526839;0.05469038337469101
|
|
|
@ -0,0 +1,29 @@
|
|||
;VA.S_post_pred;VA.S_post_test
|
||||
135;0.3856540425219162;0.39814651012420654
|
||||
66;0.1820317685516569;0.179540709812109
|
||||
31;0.09500056013237226;0.103340292275574
|
||||
118;0.4109125647914376;0.536534446764092
|
||||
42;0.3856540425219162;0.39814651012420654
|
||||
12;0.18261806302989889;0.177800974251914
|
||||
51;0.10268324709709578;0.0723729993041058
|
||||
68;0.1796872094731296;0.17571329157968
|
||||
126;0.4477433077604814;1.0
|
||||
55;0.14072484000067353;0.159011830201809
|
||||
112;0.29733352042822303;0.283228949199722
|
||||
130;0.15674750982777283;0.0949895615866388
|
||||
80;0.28089946791987636;0.251913709116214
|
||||
19;0.30881229269932087;0.282533054975644
|
||||
86;0.26250097642533193;0.14294157922267914
|
||||
69;0.2070460948787779;0.211899791231733
|
||||
11;0.17120079373894959;0.178844815588031
|
||||
27;0.1924398089521744;0.17223382045929
|
||||
134;0.3856540425219162;0.39814651012420654
|
||||
109;0.24717340450649433;0.224425887265136
|
||||
36;0.3498188867479469;0.331593597773139
|
||||
117;0.15631651482067102;0.156576200417537
|
||||
78;0.40182931980868064;0.616910229645094
|
||||
4;0.3112146833258589;0.279053583855254
|
||||
73;0.142318495823758;0.157620041753653
|
||||
26;0.19001386932573935;0.203201113430759
|
||||
132;0.3723563099639571;0.26920539140701294
|
||||
60;0.3845162666647124;0.532707028531663
|
|
|
@ -0,0 +1,29 @@
|
|||
;DHPAA.GG_urine_post_pred;DHPAA.GG_urine_post_test
|
||||
135;0.031273110190910364;0.02306918427348137
|
||||
66;0.03145485430803648;0.02124183
|
||||
31;0.01765842710094761;0.011437908
|
||||
118;0.04195940158403984;0.049019608
|
||||
42;0.03142314200243451;0.02283056080341339
|
||||
12;0.0377685457829103;0.06341682374477386
|
||||
51;0.07098040480298232;0.081699346
|
||||
68;0.020870417506442494;0.013071895
|
||||
126;0.03283576057480141;0.03025123104453087
|
||||
55;0.022325100615161547;0.022875817
|
||||
112;0.03705067103943467;0.038646358996629715
|
||||
130;0.04507897043507233;0.058823529
|
||||
80;0.029334536335621445;0.02044045552611351
|
||||
19;0.07895820794032689;0.091503268
|
||||
86;0.07592136790440752;0.088235294
|
||||
69;0.05038106270314998;0.016339869
|
||||
11;0.0364069806867011;0.041303522884845734
|
||||
27;0.042261517999367705;0.032679739
|
||||
134;0.04181352141882766;0.031945351511240005
|
||||
109;0.029714568217147713;0.050144873559474945
|
||||
36;0.03668268442589102;0.021195339038968086
|
||||
117;0.024357621131988083;0.011437908
|
||||
78;0.04948888001872687;0.032308947294950485
|
||||
4;0.02368186276767989;0.006535948
|
||||
73;0.018124506751902702;0.019607843
|
||||
26;0.08721752947338282;0.109477124
|
||||
132;0.014476640958512664;0.004901961
|
||||
60;0.027154709682683038;0.05469038337469101
|
|
|
@ -0,0 +1,29 @@
|
|||
;VA.S_post_pred;VA.S_post_test
|
||||
135;0.3777733238510637;0.39814651012420654
|
||||
66;0.2295859566079087;0.179540709812109
|
||||
31;0.17085845085143272;0.103340292275574
|
||||
118;0.47819910002193927;0.536534446764092
|
||||
42;0.3920482403870007;0.39814651012420654
|
||||
12;0.18721629507048224;0.177800974251914
|
||||
51;0.14784595676779108;0.0723729993041058
|
||||
68;0.20366391781796678;0.17571329157968
|
||||
126;0.4627053571344643;1.0
|
||||
55;0.15880194207735832;0.159011830201809
|
||||
112;0.2782131437541021;0.283228949199722
|
||||
130;0.30317636237545054;0.0949895615866388
|
||||
80;0.289299486043098;0.251913709116214
|
||||
19;0.2407923468256168;0.282533054975644
|
||||
86;0.23815393602134982;0.14294157922267914
|
||||
69;0.2014224425325397;0.211899791231733
|
||||
11;0.21277665207793675;0.178844815588031
|
||||
27;0.2029479530718343;0.17223382045929
|
||||
134;0.3777733238510637;0.39814651012420654
|
||||
109;0.3156291944544935;0.224425887265136
|
||||
36;0.30806962701332347;0.331593597773139
|
||||
117;0.20823083572217962;0.156576200417537
|
||||
78;0.3983591457155721;0.616910229645094
|
||||
4;0.24678185142233666;0.279053583855254
|
||||
73;0.19202459194875676;0.157620041753653
|
||||
26;0.2262721234028612;0.203201113430759
|
||||
132;0.31789609961575716;0.26920539140701294
|
||||
60;0.39152947533099897;0.532707028531663
|
|
|
@ -0,0 +1,29 @@
|
|||
;DHPAA.GG_urine_post_pred;DHPAA.GG_urine_post_test
|
||||
135;0.031462133;0.02306918427348137
|
||||
66;0.02905063;0.02124183
|
||||
31;0.017424105;0.011437908
|
||||
118;0.04723146;0.049019608
|
||||
42;0.027945299;0.02283056080341339
|
||||
12;0.041838914;0.06341682374477386
|
||||
51;0.07040258;0.081699346
|
||||
68;0.029148411;0.013071895
|
||||
126;0.034234293;0.03025123104453087
|
||||
55;0.020864855;0.022875817
|
||||
112;0.04168502;0.038646358996629715
|
||||
130;0.04384079;0.058823529
|
||||
80;0.025912791;0.02044045552611351
|
||||
19;0.07090839;0.091503268
|
||||
86;0.07661374;0.088235294
|
||||
69;0.043188192;0.016339869
|
||||
11;0.021142017;0.041303522884845734
|
||||
27;0.049644094;0.032679739
|
||||
134;0.043581855;0.031945351511240005
|
||||
109;0.02959964;0.050144873559474945
|
||||
36;0.042403404;0.021195339038968086
|
||||
117;0.020200256;0.011437908
|
||||
78;0.04311989;0.032308947294950485
|
||||
4;0.028928952;0.006535948
|
||||
73;0.015874023;0.019607843
|
||||
26;0.08626201;0.109477124
|
||||
132;0.013017364;0.004901961
|
||||
60;0.020769069;0.05469038337469101
|
|
|
@ -0,0 +1,29 @@
|
|||
;VA.S_post_pred;VA.S_post_test
|
||||
135;0.39736453;0.39814651012420654
|
||||
66;0.17058298;0.179540709812109
|
||||
31;0.08955078;0.103340292275574
|
||||
118;0.48255712;0.536534446764092
|
||||
42;0.3974191;0.39814651012420654
|
||||
12;0.17535107;0.177800974251914
|
||||
51;0.082894;0.0723729993041058
|
||||
68;0.21463375;0.17571329157968
|
||||
126;0.5112201;1.0
|
||||
55;0.15372284;0.159011830201809
|
||||
112;0.26576737;0.283228949199722
|
||||
130;0.12122539;0.0949895615866388
|
||||
80;0.23488523;0.251913709116214
|
||||
19;0.28017506;0.282533054975644
|
||||
86;0.18157113;0.14294157922267914
|
||||
69;0.2018286;0.211899791231733
|
||||
11;0.17589235;0.178844815588031
|
||||
27;0.1840144;0.17223382045929
|
||||
134;0.39736453;0.39814651012420654
|
||||
109;0.2519063;0.224425887265136
|
||||
36;0.31645885;0.331593597773139
|
||||
117;0.16063862;0.156576200417537
|
||||
78;0.5179117;0.616910229645094
|
||||
4;0.21262856;0.279053583855254
|
||||
73;0.15488961;0.157620041753653
|
||||
26;0.22001734;0.203201113430759
|
||||
132;0.24209619;0.26920539140701294
|
||||
60;0.65157264;0.532707028531663
|
|
|
@ -0,0 +1,8 @@
|
|||
index;Value
|
||||
target;DHPAA.GG_urine_post
|
||||
method;lgbm_DHPAA.GG_urine_post
|
||||
r2;0.6321800511692435
|
||||
mae;0.01322630609274777
|
||||
mse;0.0002716411701154974
|
||||
mape;0.5937794803254899
|
||||
ev;0.6324661040098283
|
|
|
@ -0,0 +1,8 @@
|
|||
index;Value
|
||||
target;DHPAA.GG_urine_post
|
||||
method;rf_DHPAA.GG_urine_post
|
||||
r2;0.7153104415478325
|
||||
mae;0.01211031209267511
|
||||
mse;0.00021024798960317991
|
||||
mape;0.5389835080915979
|
||||
ev;0.7158407698133342
|
|
|
@ -0,0 +1,8 @@
|
|||
index;Value
|
||||
target;DHPAA.GG_urine_post
|
||||
method;xgb_DHPAA.GG_urine_post
|
||||
r2;0.672220639822841
|
||||
mae;0.01314507662885431
|
||||
mse;0.0002420705272274436
|
||||
mape;0.5725399904527851
|
||||
ev;0.6722345480353836
|
|
|
@ -0,0 +1,8 @@
|
|||
index;Value
|
||||
target;VA.S_post
|
||||
method;lgbm_VA.S_post
|
||||
r2;0.5942984537720181
|
||||
mae;0.05840252157288433
|
||||
mse;0.01514590421303627
|
||||
mape;0.17611546600375563
|
||||
ev;0.6090790308599667
|
|
|
@ -0,0 +1,8 @@
|
|||
index;Value
|
||||
target;VA.S_post
|
||||
method;rf_VA.S_post
|
||||
r2;0.5707264348940158
|
||||
mae;0.07143929096472698
|
||||
mse;0.01602590958485085
|
||||
mape;0.30699726553302753
|
||||
ev;0.5725430320175894
|
|
|
@ -0,0 +1,8 @@
|
|||
index;Value
|
||||
target;VA.S_post
|
||||
method;xgb_VA.S_post
|
||||
r2;0.734865384893162
|
||||
mae;0.040325589676149964
|
||||
mse;0.009898171503915842
|
||||
mape;0.1080470427189779
|
||||
ev;0.7449203977422081
|
|
After Width: | Height: | Size: 32 KiB |
After Width: | Height: | Size: 32 KiB |
After Width: | Height: | Size: 31 KiB |
After Width: | Height: | Size: 26 KiB |
After Width: | Height: | Size: 27 KiB |
After Width: | Height: | Size: 26 KiB |
After Width: | Height: | Size: 46 KiB |
After Width: | Height: | Size: 50 KiB |
After Width: | Height: | Size: 50 KiB |
After Width: | Height: | Size: 38 KiB |
After Width: | Height: | Size: 37 KiB |
After Width: | Height: | Size: 36 KiB |
|
@ -117,8 +117,6 @@ anthropometric_features = ["Weight_pre","Weight_post","Delta_Weight",
|
|||
"Bpmin_pre", "Bpmax_pre","Frec_post","Frec_pre"]
|
||||
#main_df[anthropometric_features] = main_df[anthropometric_features].apply(pd.to_numeric)
|
||||
|
||||
|
||||
|
||||
study_features = ["Sex", "Sweetener"]
|
||||
|
||||
urine_ant_features = ['CA_urine_pre', 'CA.G_urine_pre', 'CA.S_urine_pre',
|
||||
|
@ -159,16 +157,29 @@ plasm_ant_features = ['CA_plasm_pre', 'CA.G_plasm_pre', 'CA.S_plasm_pre', 'To
|
|||
'Total.VA_plasm_post']
|
||||
|
||||
|
||||
# Total VA, Total DHPAA, DHPAA_plasm -> Ok
|
||||
# VA_plasm -> =(
|
||||
directory = "../results/customStudy/custom_Ind"
|
||||
# Faltan VA.S, DHPAA.SS_plasm, DHPAA.GG_urine
|
||||
|
||||
targets = ['E.S_urine_post','Total.E_urine_post']
|
||||
features = ['E_urine_pre', 'E.S_urine_pre', 'EG.1_pre', 'Total.E_urine_pre']
|
||||
# VA.S
|
||||
|
||||
directory = "../results/customStudy/custom_Ind/specialCases"
|
||||
|
||||
print(" ----------------- STARTING "+ directory + "----------------- ")
|
||||
if not os.path.exists(directory):
|
||||
os.mkdir(directory)
|
||||
targets = ['VA.S_post']
|
||||
features = ['VA_plasm_pre','VA.GG_plasm_pre', 'VA.S_pre', 'VA.GS_plasm_pre', 'VA.SS_plasm_pre','Total.VA_plasm_pre'] + study_features
|
||||
exec_models(main_df, features=features, targets=targets, multiple=False, directory=directory+"/")
|
||||
|
||||
targets = ['DHPAA.GG_urine_post']
|
||||
features = ['DHPAA_urine_pre', 'DHPAA.G_urine_pre', 'DHPAA.GG_urine_pre', 'DHPAA.GS_urine_pre', 'DHPAA.SS_urine_pre', 'Total.DHPAA_urine_pre'] + study_features
|
||||
exec_models(main_df, features=features, targets=targets, multiple=False, directory=directory+"/")
|
||||
|
||||
|
||||
|
||||
|
||||
custom_Ind_Study = False
|
||||
if custom_Ind_Study:
|
||||
directory = "../results/customStudy/custom_Ind"
|
||||
|
||||
# TFA Family
|
||||
print(" ----------------- STARTING "+ directory + "----------------- ")
|
||||
|
@ -190,7 +201,6 @@ if custom_Ind_Study:
|
|||
'Total.VA_plasm_pre'] + study_features
|
||||
exec_models(main_df, features=features, targets=targets, multiple=False, directory=directory+"/")
|
||||
|
||||
|
||||
# DHPAA Family
|
||||
|
||||
print(" ----------------- STARTING "+ directory + "----------------- ")
|
||||
|
@ -219,7 +229,9 @@ if custom_Ind_Study:
|
|||
exec_models(main_df, features=features, targets=targets, multiple=False, directory=directory+"/")
|
||||
|
||||
|
||||
|
||||
targets = ['E.S_urine_post','Total.E_urine_post']
|
||||
features = ['E_urine_pre', 'E.S_urine_pre', 'EG.1_pre', 'Total.E_urine_pre']
|
||||
exec_models(main_df, features=features, targets=targets, multiple=False, directory=directory+"/")
|
||||
|
||||
|
||||
multipleStudy = False
|
||||
|
@ -281,7 +293,7 @@ if multipleStudy:
|
|||
os.mkdir("../results/multiple_targets/HomoeriodyctiolFamily")
|
||||
exec_models(main_df, features=features, targets=targets, multiple=True, directory="../results/multiple_targets/HomoeriodyctiolFamily/")
|
||||
|
||||
customStudy = True
|
||||
customStudy = False
|
||||
|
||||
if customStudy:
|
||||
|
||||
|
|
|
@ -2,7 +2,7 @@ import pandas as pd
|
|||
import numpy as np
|
||||
from sklearn.model_selection import RepeatedKFold, cross_val_score
|
||||
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error, mean_absolute_percentage_error, explained_variance_score
|
||||
import re
|
||||
|
||||
def scoringMulti(model, X_test, y_test):
|
||||
|
||||
scores = []
|
||||
|
@ -51,7 +51,7 @@ def modelMetrics (target, method, y_true, y_pred, multiple = False):
|
|||
result_metrics_list.append(result_metrics)
|
||||
result_metrics = pd.DataFrame.from_dict(result_metrics_list)
|
||||
else:
|
||||
r2 = r2_score(y_true, y_pred)
|
||||
r2 = r2_score(y_true, y_pred, )
|
||||
mae = mean_absolute_error(y_true, y_pred)
|
||||
mse = mean_squared_error(y_true, y_pred)
|
||||
mape = mean_absolute_percentage_error(y_true, y_pred)
|
||||
|
|
|
@ -6,3 +6,4 @@ Problema: desbalanceo de resultados debido a muchos ceros en algunas variables
|
|||
|
||||
Posibles soluciones:
|
||||
Hay que ver si hay implementación de MLP que maneje NAs
|
||||
|
||||
|
|