Predição de Preços de Imóveis

#!pip install kaggle

#!cp -i /work/kaggle.json /root/.kaggle/kaggle.json

#!kaggle competitions download -c house-prices-advanced-regression-techniques

#!unzip house-prices-advanced-regression-techniques.zip -d /work/dados/

import pandas as pd data = pd.read_csv("/work/dados/train.csv") test_kaggle = pd.read_csv("/work/dados/test.csv") data.head()

print(len(data))

data.describe()

Engenharia de Atributos

Tratamento dos Nans

null_columns = data.columns[data.isna().any()].tolist() null_columns_data = data[null_columns].isnull().sum() null_columns_data

null_columns = test_kaggle.columns[test_kaggle.isna().any()].tolist() null_columns_data = test_kaggle[null_columns].isnull().sum() null_columns_data

# remover atributos com muitas entradas em branco (NaN > 100) threshold = 100 for column in null_columns_data.index: if null_columns_data[column] >= threshold: print(column, null_columns_data[column]) data.drop(column, axis='columns', inplace=True) # drop test as well test_kaggle.drop(column, axis='columns', inplace=True)

LotFrontage 227
Alley 1352
FireplaceQu 730
PoolQC 1456
Fence 1169
MiscFeature 1408

all_cat_cols = data.select_dtypes(include=['object']).columns.to_list() all_num_cols = data.select_dtypes(exclude=['object']).columns.to_list() null_cat_cols = [] for col in all_cat_cols: if col in null_columns: null_cat_cols.append(col) nul_num_cols = [] for col in all_num_cols: if col in null_columns: nul_num_cols.append(col)

data.head()

for col in all_cat_cols: mode = data[col].mode()[0] data[col].fillna(mode, inplace=True) # preenche as colunas do test test_kaggle[col].fillna(mode, inplace=True)

def fillna_num_col(cols, type): for col in cols: if type == "mode": mode = data[col].mode()[0] data[col].fillna(mode, inplace=True) test_kaggle[col].fillna(mode, inplace=True) elif type == "median": median = data[col].median() data[col].fillna(median, inplace=True) test_kaggle[col].fillna(median, inplace=True) elif type == "mean": mean = data[col].mean() data[col].fillna(mean, inplace=True) if col != "SalePrice": test_kaggle[col].fillna(mean, inplace=True)

# inputação dos valores faltantes (NaN < 100) #fillna_num_col(cols=["BsmtFullBath", "BsmtHalfBath"], type="mode") #fillna_num_col(cols=["GarageCars"], type="median") fillna_num_col(cols=all_num_cols, type="mean")

all_cat_cols = data.select_dtypes(include=['object']).columns.to_list() all_cat_cols

data.shape

test_kaggle.shape

null_columns = data.columns[data.isna().any()].tolist() null_columns_data = data[null_columns].isnull().sum() null_columns_data

null_columns = test_kaggle.columns[test_kaggle.isna().any()].tolist() null_columns_data = test_kaggle[null_columns].isnull().sum() null_columns_data

Mapeamento dos Atributos Categóricos Ordinais

from sklearn.preprocessing import LabelEncoder label = LabelEncoder() data["GarageType"] = label.fit_transform(data["GarageType"]) dict(zip(label.classes_, range(1, len(label.classes_)+1))) test_kaggle["GarageType"] = label.fit_transform(test_kaggle["GarageType"])

data["GarageCond"] = data["GarageCond"].astype("str") test_kaggle["GarageCond"] = test_kaggle["GarageCond"].astype("str")

pd.set_option('display.max_rows', data["GarageCond"].shape[0]+1) print(data["GarageCond"])

0       TA
1       TA
2       TA
3       TA
4       TA
5       TA
6       TA
7       TA
8       TA
9       TA
10      TA
11      TA
12      TA
13      TA
14      TA
15      TA
16      TA
17      TA
18      TA
19      TA
20      TA
21      TA
22      TA
23      TA
24      TA
25      TA
26      TA
27      TA
28      TA
29      TA
30      Fa
31      TA
32      TA
33      TA
34      TA
35      TA
36      TA
37      TA
38      TA
39      TA
40      TA
41      TA
42      Gd
43      TA
44      TA
45      TA
46      TA
47      TA
48      TA
49      TA
50      TA
51      TA
52      TA
53      TA
54      TA
55      TA
56      TA
57      TA
58      TA
59      TA
60      TA
61      TA
62      TA
63      TA
64      TA
65      TA
66      TA
67      TA
68      TA
69      TA
70      TA
71      TA
72      TA
73      TA
74      TA
75      TA
76      TA
77      TA
78      TA
79      TA
80      TA
81      TA
82      TA
83      TA
84      TA
85      TA
86      TA
87      TA
88      TA
89      TA
90      TA
91      TA
92      TA
93      TA
94      TA
95      TA
96      TA
97      TA
98      TA
99      TA
100     TA
101     TA
102     TA
103     TA
104     TA
105     TA
106     Fa
107     TA
108     TA
109     TA
110     TA
111     TA
112     TA
113     TA
114     TA
115     TA
116     TA
117     TA
118     TA
119     TA
120     TA
121     TA
122     TA
123     TA
124     TA
125     TA
126     TA
127     TA
128     TA
129     TA
130     TA
131     TA
132     TA
133     TA
134     TA
135     TA
136     TA
137     TA
138     TA
139     TA
140     TA
141     TA
142     TA
143     TA
144     TA
145     TA
146     TA
147     TA
148     TA
149     TA
150     TA
151     TA
152     TA
153     TA
154     Fa
155     TA
156     TA
157     TA
158     TA
159     TA
160     TA
161     TA
162     TA
163     TA
164     TA
165     TA
166     TA
167     TA
168     TA
169     TA
170     TA
171     TA
172     TA
173     TA
174     TA
175     TA
176     TA
177     TA
178     TA
179     TA
180     TA
181     TA
182     TA
183     TA
184     TA
185     TA
186     TA
187     Fa
188     TA
189     TA
190     TA
191     TA
192     TA
193     TA
194     TA
195     TA
196     TA
197     TA
198     TA
199     TA
200     TA
201     TA
202     TA
203     TA
204     TA
205     TA
206     TA
207     TA
208     TA
209     Gd
210     TA
211     TA
212     TA
213     TA
214     TA
215     TA
216     TA
217     TA
218     TA
219     TA
220     TA
221     TA
222     TA
223     TA
224     TA
225     TA
226     TA
227     TA
228     TA
229     TA
230     TA
231     TA
232     TA
233     TA
234     TA
235     TA
236     TA
237     TA
238     TA
239     TA
240     TA
241     TA
242     TA
243     TA
244     TA
245     TA
246     Po
247     TA
248     TA
249     TA
250     TA
251     TA
252     TA
253     TA
254     TA
255     TA
256     TA
257     TA
258     TA
259     TA
260     TA
261     TA
262     TA
263     TA
264     TA
265     TA
266     TA
267     TA
268     Ex
269     Gd
270     TA
271     TA
272     TA
273     TA
274     TA
275     TA
276     TA
277     TA
278     TA
279     TA
280     TA
281     TA
282     TA
283     TA
284     TA
285     TA
286     TA
287     TA
288     TA
289     TA
290     TA
291     TA
292     TA
293     TA
294     TA
295     TA
296     TA
297     TA
298     TA
299     TA
300     TA
301     TA
302     TA
303     TA
304     TA
305     TA
306     TA
307     TA
308     TA
309     TA
310     TA
311     TA
312     TA
313     TA
314     TA
315     TA
316     TA
317     TA
318     TA
319     TA
320     TA
321     TA
322     TA
323     TA
324     TA
325     TA
326     TA
327     TA
328     TA
329     Fa
330     TA
331     TA
332     TA
333     TA
334     TA
335     TA
336     TA
337     TA
338     TA
339     TA
340     TA
341     TA
342     TA
343     TA
344     TA
345     TA
346     TA
347     TA
348     TA
349     TA
350     TA
351     TA
352     Fa
353     TA
354     TA
355     TA
356     TA
357     TA
358     TA
359     TA
360     TA
361     TA
362     TA
363     TA
364     TA
365     Fa
366     TA
367     TA
368     TA
369     TA
370     TA
371     TA
372     TA
373     TA
374     TA
375     TA
376     TA
377     TA
378     TA
379     TA
380     TA
381     TA
382     TA
383     Fa
384     TA
385     TA
386     TA
387     TA
388     TA
389     TA
390     TA
391     TA
392     TA
393     TA
394     TA
395     TA
396     TA
397     TA
398     Po
399     TA
400     TA
401     TA
402     TA
403     TA
404     TA
405     TA
406     TA
407     TA
408     TA
409     TA
410     TA
411     TA
412     TA
413     TA
414     TA
415     TA
416     TA
417     TA
418     TA
419     TA
420     TA
421     TA
422     TA
423     TA
424     TA
425     TA
426     TA
427     TA
428     TA
429     TA
430     TA
431     TA
432     TA
433     TA
434     TA
435     TA
436     TA
437     TA
438     TA
439     TA
440     TA
441     TA
442     TA
443     TA
444     TA
445     TA
446     TA
447     TA
448     TA
449     TA
450     Fa
451     TA
452     TA
453     TA
454     TA
455     TA
456     Fa
457     TA
458     TA
459     TA
460     TA
461     TA
462     TA
463     TA
464     TA
465     TA
466     TA
467     TA
468     TA
469     TA
470     TA
471     TA
472     TA
473     TA
474     TA
475     TA
476     TA
477     TA
478     TA
479     TA
480     TA
481     TA
482     Fa
483     TA
484     TA
485     TA
486     TA
487     TA
488     Fa
489     TA
490     TA
491     TA
492     TA
493     TA
494     TA
495     TA
496     TA
497     TA
498     TA
499     TA
500     TA
501     TA
502     Fa
503     TA
504     TA
505     TA
506     TA
507     TA
508     TA
509     TA
510     TA
511     TA
512     TA
513     TA
514     Po
515     TA
516     TA
517     TA
518     TA
519     TA
520     TA
521     TA
522     TA
523     TA
524     TA
525     TA
526     TA
527     TA
528     TA
529     TA
530     TA
531     Fa
532     TA
533     TA
534     TA
535     TA
536     TA
537     TA
538     TA
539     TA
540     TA
541     TA
542     TA
543     TA
544     TA
545     TA
546     TA
547     TA
548     TA
549     TA
550     TA
551     TA
552     TA
553     TA
554     TA
555     TA
556     TA
557     TA
558     TA
559     TA
560     TA
561     TA
562     TA
563     TA
564     TA
565     TA
566     TA
567     TA
568     TA
569     TA
570     TA
571     TA
572     TA
573     TA
574     TA
575     TA
576     TA
577     TA
578     TA
579     TA
580     TA
581     TA
582     TA
583     TA
584     TA
585     TA
586     TA
587     TA
588     TA
589     TA
590     TA
591     TA
592     TA
593     TA
594     TA
595     TA
596     Fa
597     TA
598     TA
599     TA
600     TA
601     TA
602     TA
603     TA
604     TA
605     TA
606     TA
607     TA
608     TA
609     TA
610     TA
611     TA
612     TA
613     TA
614     TA
615     TA
616     TA
617     TA
618     TA
619     TA
620     TA
621     TA
622     TA
623     TA
624     TA
625     TA
626     TA
627     TA
628     TA
629     TA
630     Po
631     TA
632     TA
633     TA
634     TA
635     TA
636     TA
637     TA
638     TA
639     TA
640     TA
641     TA
642     TA
643     TA
644     TA
645     TA
646     TA
647     TA
648     TA
649     TA
650     TA
651     Po
652     TA
653     TA
654     TA
655     TA
656     TA
657     TA
658     TA
659     TA
660     TA
661     TA
662     TA
663     TA
664     TA
665     TA
666     TA
667     TA
668     TA
669     Fa
670     TA
671     TA
672     TA
673     TA
674     TA
675     TA
676     Fa
677     Fa
678     TA
679     TA
680     TA
681     TA
682     TA
683     TA
684     TA
685     TA
686     TA
687     TA
688     TA
689     TA
690     TA
691     TA
692     TA
693     TA
694     TA
695     TA
696     TA
697     TA
698     TA
699     TA
700     TA
701     TA
702     TA
703     TA
704     TA
705     TA
706     TA
707     TA
708     TA
709     TA
710     TA
711     TA
712     TA
713     TA
714     TA
715     TA
716     TA
717     TA
718     TA
719     TA
720     TA
721     TA
722     TA
723     TA
724     TA
725     TA
726     TA
727     TA
728     TA
729     TA
730     TA
731     TA
732     TA
733     TA
734     TA
735     TA
736     TA
737     TA
738     TA
739     TA
740     Gd
741     TA
742     TA
743     TA
744     TA
745     TA
746     TA
747     TA
748     TA
749     TA
750     TA
751     TA
752     TA
753     TA
754     TA
755     TA
756     TA
757     TA
758     TA
759     TA
760     Ex
761     TA
762     TA
763     TA
764     TA
765     TA
766     TA
767     TA
768     TA
769     TA
770     TA
771     TA
772     TA
773     TA
774     TA
775     TA
776     TA
777     TA
778     TA
779     TA
780     TA
781     TA
782     TA
783     TA
784     TA
785     TA
786     TA
787     TA
788     TA
789     TA
790     TA
791     TA
792     TA
793     TA
794     TA
795     TA
796     TA
797     TA
798     TA
799     TA
800     TA
801     TA
802     TA
803     TA
804     TA
805     TA
806     TA
807     TA
808     TA
809     Po
810     TA
811     TA
812     TA
813     TA
814     TA
815     TA
816     TA
817     TA
818     TA
819     TA
820     TA
821     TA
822     TA
823     TA
824     TA
825     TA
826     TA
827     TA
828     TA
829     TA
830     TA
831     TA
832     TA
833     TA
834     TA
835     TA
836     TA
837     TA
838     TA
839     TA
840     TA
841     TA
842     Gd
843     TA
844     TA
845     TA
846     TA
847     TA
848     TA
849     TA
850     TA
851     TA
852     TA
853     TA
854     TA
855     TA
856     Fa
857     TA
858     TA
859     TA
860     TA
861     TA
862     TA
863     TA
864     TA
865     TA
866     TA
867     TA
868     TA
869     TA
870     TA
871     TA
872     TA
873     TA
874     TA
875     TA
876     TA
877     TA
878     TA
879     TA
880     TA
881     TA
882     TA
883     Gd
884     TA
885     TA
886     TA
887     TA
888     TA
889     TA
890     TA
891     TA
892     TA
893     TA
894     TA
895     TA
896     TA
897     TA
898     TA
899     TA
900     TA
901     TA
902     TA
903     TA
904     TA
905     TA
906     TA
907     TA
908     TA
909     TA
910     TA
911     TA
912     TA
913     TA
914     TA
915     TA
916     TA
917     TA
918     TA
919     TA
920     TA
921     TA
922     TA
923     TA
924     TA
925     TA
926     TA
927     TA
928     TA
929     TA
930     TA
931     TA
932     TA
933     TA
934     TA
935     TA
936     TA
937     TA
938     TA
939     TA
940     TA
941     TA
942     TA
943     TA
944     TA
945     TA
946     TA
947     TA
948     TA
949     TA
950     TA
951     TA
952     TA
953     TA
954     TA
955     TA
956     TA
957     TA
958     TA
959     TA
960     TA
961     TA
962     TA
963     TA
964     TA
965     TA
966     TA
967     TA
968     TA
969     TA
970     TA
971     TA
972     TA
973     TA
974     TA
975     TA
976     TA
977     TA
978     TA
979     TA
980     TA
981     TA
982     TA
983     TA
984     TA
985     TA
986     TA
987     TA
988     TA
989     TA
990     TA
991     TA
992     TA
993     TA
994     TA
995     TA
996     TA
997     TA
998     Fa
999     TA
1000    Fa
1001    TA
1002    TA
1003    TA
1004    TA
1005    TA
1006    TA
1007    TA
1008    TA
1009    TA
1010    TA
1011    TA
1012    TA
1013    TA
1014    TA
1015    TA
1016    TA
1017    TA
1018    TA
1019    TA
1020    TA
1021    TA
1022    Fa
1023    TA
1024    TA
1025    TA
1026    TA
1027    TA
1028    TA
1029    TA
1030    TA
1031    TA
1032    TA
1033    TA
1034    TA
1035    TA
1036    TA
1037    TA
1038    TA
1039    TA
1040    TA
1041    TA
1042    TA
1043    TA
1044    TA
1045    TA
1046    TA
1047    TA
1048    TA
1049    TA
1050    TA
1051    TA
1052    TA
1053    TA
1054    TA
1055    TA
1056    TA
1057    TA
1058    TA
1059    Fa
1060    TA
1061    TA
1062    TA
1063    TA
1064    TA
1065    TA
1066    TA
1067    TA
1068    TA
1069    TA
1070    TA
1071    TA
1072    TA
1073    TA
1074    TA
1075    TA
1076    TA
1077    TA
1078    TA
1079    TA
1080    TA
1081    TA
1082    TA
1083    TA
1084    TA
1085    TA
1086    TA
1087    TA
1088    TA
1089    TA
1090    TA
1091    TA
1092    TA
1093    TA
1094    TA
1095    TA
1096    TA
1097    TA
1098    TA
1099    TA
1100    TA
1101    TA
1102    TA
1103    TA
1104    TA
1105    TA
1106    TA
1107    TA
1108    TA
1109    TA
1110    TA
1111    TA
1112    TA
1113    TA
1114    TA
1115    TA
1116    TA
1117    TA
1118    TA
1119    TA
1120    TA
1121    TA
1122    TA
1123    TA
1124    TA
1125    Fa
1126    TA
1127    TA
1128    TA
1129    TA
1130    TA
1131    TA
1132    TA
1133    TA
1134    TA
1135    TA
1136    TA
1137    TA
1138    TA
1139    TA
1140    TA
1141    TA
1142    TA
1143    TA
1144    TA
1145    TA
1146    TA
1147    TA
1148    TA
1149    TA
1150    TA
1151    TA
1152    TA
1153    TA
1154    TA
1155    TA
1156    TA
1157    TA
1158    TA
1159    TA
1160    TA
1161    TA
1162    TA
1163    TA
1164    TA
1165    TA
1166    TA
1167    TA
1168    TA
1169    TA
1170    TA
1171    TA
1172    TA
1173    TA
1174    TA
1175    TA
1176    TA
1177    TA
1178    TA
1179    TA
1180    TA
1181    TA
1182    TA
1183    TA
1184    TA
1185    TA
1186    Fa
1187    TA
1188    TA
1189    TA
1190    TA
1191    TA
1192    Fa
1193    TA
1194    TA
1195    TA
1196    TA
1197    TA
1198    TA
1199    TA
1200    TA
1201    TA
1202    TA
1203    TA
1204    TA
1205    TA
1206    TA
1207    TA
1208    TA
1209    TA
1210    TA
1211    TA
1212    TA
1213    TA
1214    TA
1215    TA
1216    TA
1217    TA
1218    TA
1219    TA
1220    TA
1221    TA
1222    TA
1223    TA
1224    TA
1225    TA
1226    TA
1227    TA
1228    TA
1229    TA
1230    TA
1231    TA
1232    TA
1233    TA
1234    TA
1235    Fa
1236    TA
1237    TA
1238    TA
1239    TA
1240    TA
1241    TA
1242    TA
1243    TA
1244    TA
1245    TA
1246    TA
1247    TA
1248    Fa
1249    TA
1250    TA
1251    TA
1252    TA
1253    TA
1254    TA
1255    TA
1256    TA
1257    TA
1258    TA
1259    TA
1260    TA
1261    TA
1262    TA
1263    TA
1264    TA
1265    TA
1266    TA
1267    TA
1268    TA
1269    TA
1270    TA
1271    TA
1272    TA
1273    TA
1274    TA
1275    Fa
1276    TA
1277    TA
1278    TA
1279    TA
1280    TA
1281    Gd
1282    TA
1283    TA
1284    TA
1285    TA
1286    TA
1287    TA
1288    TA
1289    TA
1290    TA
1291    TA
1292    TA
1293    TA
1294    TA
1295    TA
1296    TA
1297    TA
1298    TA
1299    TA
1300    TA
1301    TA
1302    TA
1303    TA
1304    TA
1305    TA
1306    TA
1307    TA
1308    TA
1309    TA
1310    TA
1311    TA
1312    Gd
1313    TA
1314    TA
1315    TA
1316    TA
1317    TA
1318    TA
1319    TA
1320    TA
1321    Fa
1322    TA
1323    TA
1324    TA
1325    TA
1326    TA
1327    TA
1328    TA
1329    TA
1330    TA
1331    TA
1332    Fa
1333    TA
1334    TA
1335    TA
1336    TA
1337    TA
1338    TA
1339    TA
1340    TA
1341    TA
1342    TA
1343    Fa
1344    TA
1345    TA
1346    TA
1347    TA
1348    TA
1349    TA
1350    TA
1351    TA
1352    TA
1353    TA
1354    TA
1355    TA
1356    TA
1357    TA
1358    TA
1359    TA
1360    TA
1361    TA
1362    TA
1363    TA
1364    TA
1365    TA
1366    TA
1367    TA
1368    TA
1369    TA
1370    TA
1371    TA
1372    TA
1373    TA
1374    TA
1375    TA
1376    TA
1377    TA
1378    TA
1379    TA
1380    Fa
1381    TA
1382    TA
1383    TA
1384    TA
1385    TA
1386    TA
1387    TA
1388    TA
1389    TA
1390    TA
1391    TA
1392    TA
1393    TA
1394    TA
1395    TA
1396    TA
1397    Fa
1398    TA
1399    TA
1400    TA
1401    TA
1402    TA
1403    TA
1404    TA
1405    TA
1406    TA
1407    TA
1408    TA
1409    TA
1410    TA
1411    TA
1412    TA
1413    TA
1414    TA
1415    TA
1416    TA
1417    TA
1418    TA
1419    TA
1420    TA
1421    TA
1422    TA
1423    Gd
1424    TA
1425    TA
1426    TA
1427    TA
1428    TA
1429    TA
1430    TA
1431    TA
1432    Fa
1433    TA
1434    TA
1435    TA
1436    TA
1437    TA
1438    TA
1439    TA
1440    TA
1441    TA
1442    TA
1443    Po
1444    TA
1445    TA
1446    TA
1447    TA
1448    TA
1449    TA
1450    TA
1451    TA
1452    TA
1453    TA
1454    TA
1455    TA
1456    TA
1457    TA
1458    TA
1459    TA
Name: GarageCond, dtype: object

print(data["GarageCond"])

0       TA
1       TA
2       TA
3       TA
4       TA
5       TA
6       TA
7       TA
8       TA
9       TA
10      TA
11      TA
12      TA
13      TA
14      TA
15      TA
16      TA
17      TA
18      TA
19      TA
20      TA
21      TA
22      TA
23      TA
24      TA
25      TA
26      TA
27      TA
28      TA
29      TA
30      Fa
31      TA
32      TA
33      TA
34      TA
35      TA
36      TA
37      TA
38      TA
39      TA
40      TA
41      TA
42      Gd
43      TA
44      TA
45      TA
46      TA
47      TA
48      TA
49      TA
50      TA
51      TA
52      TA
53      TA
54      TA
55      TA
56      TA
57      TA
58      TA
59      TA
60      TA
61      TA
62      TA
63      TA
64      TA
65      TA
66      TA
67      TA
68      TA
69      TA
70      TA
71      TA
72      TA
73      TA
74      TA
75      TA
76      TA
77      TA
78      TA
79      TA
80      TA
81      TA
82      TA
83      TA
84      TA
85      TA
86      TA
87      TA
88      TA
89      TA
90      TA
91      TA
92      TA
93      TA
94      TA
95      TA
96      TA
97      TA
98      TA
99      TA
100     TA
101     TA
102     TA
103     TA
104     TA
105     TA
106     Fa
107     TA
108     TA
109     TA
110     TA
111     TA
112     TA
113     TA
114     TA
115     TA
116     TA
117     TA
118     TA
119     TA
120     TA
121     TA
122     TA
123     TA
124     TA
125     TA
126     TA
127     TA
128     TA
129     TA
130     TA
131     TA
132     TA
133     TA
134     TA
135     TA
136     TA
137     TA
138     TA
139     TA
140     TA
141     TA
142     TA
143     TA
144     TA
145     TA
146     TA
147     TA
148     TA
149     TA
150     TA
151     TA
152     TA
153     TA
154     Fa
155     TA
156     TA
157     TA
158     TA
159     TA
160     TA
161     TA
162     TA
163     TA
164     TA
165     TA
166     TA
167     TA
168     TA
169     TA
170     TA
171     TA
172     TA
173     TA
174     TA
175     TA
176     TA
177     TA
178     TA
179     TA
180     TA
181     TA
182     TA
183     TA
184     TA
185     TA
186     TA
187     Fa
188     TA
189     TA
190     TA
191     TA
192     TA
193     TA
194     TA
195     TA
196     TA
197     TA
198     TA
199     TA
200     TA
201     TA
202     TA
203     TA
204     TA
205     TA
206     TA
207     TA
208     TA
209     Gd
210     TA
211     TA
212     TA
213     TA
214     TA
215     TA
216     TA
217     TA
218     TA
219     TA
220     TA
221     TA
222     TA
223     TA
224     TA
225     TA
226     TA
227     TA
228     TA
229     TA
230     TA
231     TA
232     TA
233     TA
234     TA
235     TA
236     TA
237     TA
238     TA
239     TA
240     TA
241     TA
242     TA
243     TA
244     TA
245     TA
246     Po
247     TA
248     TA
249     TA
250     TA
251     TA
252     TA
253     TA
254     TA
255     TA
256     TA
257     TA
258     TA
259     TA
260     TA
261     TA
262     TA
263     TA
264     TA
265     TA
266     TA
267     TA
268     Ex
269     Gd
270     TA
271     TA
272     TA
273     TA
274     TA
275     TA
276     TA
277     TA
278     TA
279     TA
280     TA
281     TA
282     TA
283     TA
284     TA
285     TA
286     TA
287     TA
288     TA
289     TA
290     TA
291     TA
292     TA
293     TA
294     TA
295     TA
296     TA
297     TA
298     TA
299     TA
300     TA
301     TA
302     TA
303     TA
304     TA
305     TA
306     TA
307     TA
308     TA
309     TA
310     TA
311     TA
312     TA
313     TA
314     TA
315     TA
316     TA
317     TA
318     TA
319     TA
320     TA
321     TA
322     TA
323     TA
324     TA
325     TA
326     TA
327     TA
328     TA
329     Fa
330     TA
331     TA
332     TA
333     TA
334     TA
335     TA
336     TA
337     TA
338     TA
339     TA
340     TA
341     TA
342     TA
343     TA
344     TA
345     TA
346     TA
347     TA
348     TA
349     TA
350     TA
351     TA
352     Fa
353     TA
354     TA
355     TA
356     TA
357     TA
358     TA
359     TA
360     TA
361     TA
362     TA
363     TA
364     TA
365     Fa
366     TA
367     TA
368     TA
369     TA
370     TA
371     TA
372     TA
373     TA
374     TA
375     TA
376     TA
377     TA
378     TA
379     TA
380     TA
381     TA
382     TA
383     Fa
384     TA
385     TA
386     TA
387     TA
388     TA
389     TA
390     TA
391     TA
392     TA
393     TA
394     TA
395     TA
396     TA
397     TA
398     Po
399     TA
400     TA
401     TA
402     TA
403     TA
404     TA
405     TA
406     TA
407     TA
408     TA
409     TA
410     TA
411     TA
412     TA
413     TA
414     TA
415     TA
416     TA
417     TA
418     TA
419     TA
420     TA
421     TA
422     TA
423     TA
424     TA
425     TA
426     TA
427     TA
428     TA
429     TA
430     TA
431     TA
432     TA
433     TA
434     TA
435     TA
436     TA
437     TA
438     TA
439     TA
440     TA
441     TA
442     TA
443     TA
444     TA
445     TA
446     TA
447     TA
448     TA
449     TA
450     Fa
451     TA
452     TA
453     TA
454     TA
455     TA
456     Fa
457     TA
458     TA
459     TA
460     TA
461     TA
462     TA
463     TA
464     TA
465     TA
466     TA
467     TA
468     TA
469     TA
470     TA
471     TA
472     TA
473     TA
474     TA
475     TA
476     TA
477     TA
478     TA
479     TA
480     TA
481     TA
482     Fa
483     TA
484     TA
485     TA
486     TA
487     TA
488     Fa
489     TA
490     TA
491     TA
492     TA
493     TA
494     TA
495     TA
496     TA
497     TA
498     TA
499     TA
500     TA
501     TA
502     Fa
503     TA
504     TA
505     TA
506     TA
507     TA
508     TA
509     TA
510     TA
511     TA
512     TA
513     TA
514     Po
515     TA
516     TA
517     TA
518     TA
519     TA
520     TA
521     TA
522     TA
523     TA
524     TA
525     TA
526     TA
527     TA
528     TA
529     TA
530     TA
531     Fa
532     TA
533     TA
534     TA
535     TA
536     TA
537     TA
538     TA
539     TA
540     TA
541     TA
542     TA
543     TA
544     TA
545     TA
546     TA
547     TA
548     TA
549     TA
550     TA
551     TA
552     TA
553     TA
554     TA
555     TA
556     TA
557     TA
558     TA
559     TA
560     TA
561     TA
562     TA
563     TA
564     TA
565     TA
566     TA
567     TA
568     TA
569     TA
570     TA
571     TA
572     TA
573     TA
574     TA
575     TA
576     TA
577     TA
578     TA
579     TA
580     TA
581     TA
582     TA
583     TA
584     TA
585     TA
586     TA
587     TA
588     TA
589     TA
590     TA
591     TA
592     TA
593     TA
594     TA
595     TA
596     Fa
597     TA
598     TA
599     TA
600     TA
601     TA
602     TA
603     TA
604     TA
605     TA
606     TA
607     TA
608     TA
609     TA
610     TA
611     TA
612     TA
613     TA
614     TA
615     TA
616     TA
617     TA
618     TA
619     TA
620     TA
621     TA
622     TA
623     TA
624     TA
625     TA
626     TA
627     TA
628     TA
629     TA
630     Po
631     TA
632     TA
633     TA
634     TA
635     TA
636     TA
637     TA
638     TA
639     TA
640     TA
641     TA
642     TA
643     TA
644     TA
645     TA
646     TA
647     TA
648     TA
649     TA
650     TA
651     Po
652     TA
653     TA
654     TA
655     TA
656     TA
657     TA
658     TA
659     TA
660     TA
661     TA
662     TA
663     TA
664     TA
665     TA
666     TA
667     TA
668     TA
669     Fa
670     TA
671     TA
672     TA
673     TA
674     TA
675     TA
676     Fa
677     Fa
678     TA
679     TA
680     TA
681     TA
682     TA
683     TA
684     TA
685     TA
686     TA
687     TA
688     TA
689     TA
690     TA
691     TA
692     TA
693     TA
694     TA
695     TA
696     TA
697     TA
698     TA
699     TA
700     TA
701     TA
702     TA
703     TA
704     TA
705     TA
706     TA
707     TA
708     TA
709     TA
710     TA
711     TA
712     TA
713     TA
714     TA
715     TA
716     TA
717     TA
718     TA
719     TA
720     TA
721     TA
722     TA
723     TA
724     TA
725     TA
726     TA
727     TA
728     TA
729     TA
730     TA
731     TA
732     TA
733     TA
734     TA
735     TA
736     TA
737     TA
738     TA
739     TA
740     Gd
741     TA
742     TA
743     TA
744     TA
745     TA
746     TA
747     TA
748     TA
749     TA
750     TA
751     TA
752     TA
753     TA
754     TA
755     TA
756     TA
757     TA
758     TA
759     TA
760     Ex
761     TA
762     TA
763     TA
764     TA
765     TA
766     TA
767     TA
768     TA
769     TA
770     TA
771     TA
772     TA
773     TA
774     TA
775     TA
776     TA
777     TA
778     TA
779     TA
780     TA
781     TA
782     TA
783     TA
784     TA
785     TA
786     TA
787     TA
788     TA
789     TA
790     TA
791     TA
792     TA
793     TA
794     TA
795     TA
796     TA
797     TA
798     TA
799     TA
800     TA
801     TA
802     TA
803     TA
804     TA
805     TA
806     TA
807     TA
808     TA
809     Po
810     TA
811     TA
812     TA
813     TA
814     TA
815     TA
816     TA
817     TA
818     TA
819     TA
820     TA
821     TA
822     TA
823     TA
824     TA
825     TA
826     TA
827     TA
828     TA
829     TA
830     TA
831     TA
832     TA
833     TA
834     TA
835     TA
836     TA
837     TA
838     TA
839     TA
840     TA
841     TA
842     Gd
843     TA
844     TA
845     TA
846     TA
847     TA
848     TA
849     TA
850     TA
851     TA
852     TA
853     TA
854     TA
855     TA
856     Fa
857     TA
858     TA
859     TA
860     TA
861     TA
862     TA
863     TA
864     TA
865     TA
866     TA
867     TA
868     TA
869     TA
870     TA
871     TA
872     TA
873     TA
874     TA
875     TA
876     TA
877     TA
878     TA
879     TA
880     TA
881     TA
882     TA
883     Gd
884     TA
885     TA
886     TA
887     TA
888     TA
889     TA
890     TA
891     TA
892     TA
893     TA
894     TA
895     TA
896     TA
897     TA
898     TA
899     TA
900     TA
901     TA
902     TA
903     TA
904     TA
905     TA
906     TA
907     TA
908     TA
909     TA
910     TA
911     TA
912     TA
913     TA
914     TA
915     TA
916     TA
917     TA
918     TA
919     TA
920     TA
921     TA
922     TA
923     TA
924     TA
925     TA
926     TA
927     TA
928     TA
929     TA
930     TA
931     TA
932     TA
933     TA
934     TA
935     TA
936     TA
937     TA
938     TA
939     TA
940     TA
941     TA
942     TA
943     TA
944     TA
945     TA
946     TA
947     TA
948     TA
949     TA
950     TA
951     TA
952     TA
953     TA
954     TA
955     TA
956     TA
957     TA
958     TA
959     TA
960     TA
961     TA
962     TA
963     TA
964     TA
965     TA
966     TA
967     TA
968     TA
969     TA
970     TA
971     TA
972     TA
973     TA
974     TA
975     TA
976     TA
977     TA
978     TA
979     TA
980     TA
981     TA
982     TA
983     TA
984     TA
985     TA
986     TA
987     TA
988     TA
989     TA
990     TA
991     TA
992     TA
993     TA
994     TA
995     TA
996     TA
997     TA
998     Fa
999     TA
1000    Fa
1001    TA
1002    TA
1003    TA
1004    TA
1005    TA
1006    TA
1007    TA
1008    TA
1009    TA
1010    TA
1011    TA
1012    TA
1013    TA
1014    TA
1015    TA
1016    TA
1017    TA
1018    TA
1019    TA
1020    TA
1021    TA
1022    Fa
1023    TA
1024    TA
1025    TA
1026    TA
1027    TA
1028    TA
1029    TA
1030    TA
1031    TA
1032    TA
1033    TA
1034    TA
1035    TA
1036    TA
1037    TA
1038    TA
1039    TA
1040    TA
1041    TA
1042    TA
1043    TA
1044    TA
1045    TA
1046    TA
1047    TA
1048    TA
1049    TA
1050    TA
1051    TA
1052    TA
1053    TA
1054    TA
1055    TA
1056    TA
1057    TA
1058    TA
1059    Fa
1060    TA
1061    TA
1062    TA
1063    TA
1064    TA
1065    TA
1066    TA
1067    TA
1068    TA
1069    TA
1070    TA
1071    TA
1072    TA
1073    TA
1074    TA
1075    TA
1076    TA
1077    TA
1078    TA
1079    TA
1080    TA
1081    TA
1082    TA
1083    TA
1084    TA
1085    TA
1086    TA
1087    TA
1088    TA
1089    TA
1090    TA
1091    TA
1092    TA
1093    TA
1094    TA
1095    TA
1096    TA
1097    TA
1098    TA
1099    TA
1100    TA
1101    TA
1102    TA
1103    TA
1104    TA
1105    TA
1106    TA
1107    TA
1108    TA
1109    TA
1110    TA
1111    TA
1112    TA
1113    TA
1114    TA
1115    TA
1116    TA
1117    TA
1118    TA
1119    TA
1120    TA
1121    TA
1122    TA
1123    TA
1124    TA
1125    Fa
1126    TA
1127    TA
1128    TA
1129    TA
1130    TA
1131    TA
1132    TA
1133    TA
1134    TA
1135    TA
1136    TA
1137    TA
1138    TA
1139    TA
1140    TA
1141    TA
1142    TA
1143    TA
1144    TA
1145    TA
1146    TA
1147    TA
1148    TA
1149    TA
1150    TA
1151    TA
1152    TA
1153    TA
1154    TA
1155    TA
1156    TA
1157    TA
1158    TA
1159    TA
1160    TA
1161    TA
1162    TA
1163    TA
1164    TA
1165    TA
1166    TA
1167    TA
1168    TA
1169    TA
1170    TA
1171    TA
1172    TA
1173    TA
1174    TA
1175    TA
1176    TA
1177    TA
1178    TA
1179    TA
1180    TA
1181    TA
1182    TA
1183    TA
1184    TA
1185    TA
1186    Fa
1187    TA
1188    TA
1189    TA
1190    TA
1191    TA
1192    Fa
1193    TA
1194    TA
1195    TA
1196    TA
1197    TA
1198    TA
1199    TA
1200    TA
1201    TA
1202    TA
1203    TA
1204    TA
1205    TA
1206    TA
1207    TA
1208    TA
1209    TA
1210    TA
1211    TA
1212    TA
1213    TA
1214    TA
1215    TA
1216    TA
1217    TA
1218    TA
1219    TA
1220    TA
1221    TA
1222    TA
1223    TA
1224    TA
1225    TA
1226    TA
1227    TA
1228    TA
1229    TA
1230    TA
1231    TA
1232    TA
1233    TA
1234    TA
1235    Fa
1236    TA
1237    TA
1238    TA
1239    TA
1240    TA
1241    TA
1242    TA
1243    TA
1244    TA
1245    TA
1246    TA
1247    TA
1248    Fa
1249    TA
1250    TA
1251    TA
1252    TA
1253    TA
1254    TA
1255    TA
1256    TA
1257    TA
1258    TA
1259    TA
1260    TA
1261    TA
1262    TA
1263    TA
1264    TA
1265    TA
1266    TA
1267    TA
1268    TA
1269    TA
1270    TA
1271    TA
1272    TA
1273    TA
1274    TA
1275    Fa
1276    TA
1277    TA
1278    TA
1279    TA
1280    TA
1281    Gd
1282    TA
1283    TA
1284    TA
1285    TA
1286    TA
1287    TA
1288    TA
1289    TA
1290    TA
1291    TA
1292    TA
1293    TA
1294    TA
1295    TA
1296    TA
1297    TA
1298    TA
1299    TA
1300    TA
1301    TA
1302    TA
1303    TA
1304    TA
1305    TA
1306    TA
1307    TA
1308    TA
1309    TA
1310    TA
1311    TA
1312    Gd
1313    TA
1314    TA
1315    TA
1316    TA
1317    TA
1318    TA
1319    TA
1320    TA
1321    Fa
1322    TA
1323    TA
1324    TA
1325    TA
1326    TA
1327    TA
1328    TA
1329    TA
1330    TA
1331    TA
1332    Fa
1333    TA
1334    TA
1335    TA
1336    TA
1337    TA
1338    TA
1339    TA
1340    TA
1341    TA
1342    TA
1343    Fa
1344    TA
1345    TA
1346    TA
1347    TA
1348    TA
1349    TA
1350    TA
1351    TA
1352    TA
1353    TA
1354    TA
1355    TA
1356    TA
1357    TA
1358    TA
1359    TA
1360    TA
1361    TA
1362    TA
1363    TA
1364    TA
1365    TA
1366    TA
1367    TA
1368    TA
1369    TA
1370    TA
1371    TA
1372    TA
1373    TA
1374    TA
1375    TA
1376    TA
1377    TA
1378    TA
1379    TA
1380    Fa
1381    TA
1382    TA
1383    TA
1384    TA
1385    TA
1386    TA
1387    TA
1388    TA
1389    TA
1390    TA
1391    TA
1392    TA
1393    TA
1394    TA
1395    TA
1396    TA
1397    Fa
1398    TA
1399    TA
1400    TA
1401    TA
1402    TA
1403    TA
1404    TA
1405    TA
1406    TA
1407    TA
1408    TA
1409    TA
1410    TA
1411    TA
1412    TA
1413    TA
1414    TA
1415    TA
1416    TA
1417    TA
1418    TA
1419    TA
1420    TA
1421    TA
1422    TA
1423    Gd
1424    TA
1425    TA
1426    TA
1427    TA
1428    TA
1429    TA
1430    TA
1431    TA
1432    Fa
1433    TA
1434    TA
1435    TA
1436    TA
1437    TA
1438    TA
1439    TA
1440    TA
1441    TA
1442    TA
1443    Po
1444    TA
1445    TA
1446    TA
1447    TA
1448    TA
1449    TA
1450    TA
1451    TA
1452    TA
1453    TA
1454    TA
1455    TA
1456    TA
1457    TA
1458    TA
1459    TA
Name: GarageCond, dtype: object

mapping = {"Ex":6, "Gd":5, "TA":4, "Fa":3, "Po":2, "nan":1} data["GarageCond"] = data["GarageCond"].astype("str") data["GarageCond"] = data["GarageCond"].apply(lambda x : mapping[x]) test_kaggle["GarageCond"] = test_kaggle["GarageCond"].apply(lambda x : mapping[x])

mapping = {"Fin":4, "RFn":3, "Unf":2, "nan":1} data["GarageFinish"] = data["GarageFinish"].astype("str") data["GarageFinish"] = data["GarageFinish"].apply(lambda x : mapping[x]) test_kaggle["GarageFinish"] = test_kaggle["GarageFinish"].apply(lambda x : mapping[x])

mapping = {"Ex":6, "Gd":5, "TA":4, "Fa":3, "Po":2, "nan":1} data["GarageQual"] = data["GarageQual"].astype("str") data["GarageQual"] = data["GarageQual"].apply(lambda x : mapping[x]) test_kaggle["GarageQual"] = test_kaggle["GarageQual"].apply(lambda x : mapping[x])

mapping = {"GLQ":7, "ALQ":6, "BLQ":5, "Rec":4, "LwQ":3, "Unf":2, "nan":1} data["BsmtFinType2"] = data["BsmtFinType2"].astype("str") data["BsmtFinType2"] = data["BsmtFinType2"].apply(lambda x : mapping[x]) test_kaggle["BsmtFinType2"] = test_kaggle["BsmtFinType2"].apply(lambda x : mapping[x])

mapping = {"Gd":5, "Av":4, "Mn":3, "No":2, "nan":1} data["BsmtExposure"] = data["BsmtExposure"].astype("str") data["BsmtExposure"] = data["BsmtExposure"].apply(lambda x : mapping[x]) test_kaggle["BsmtExposure"] = test_kaggle["BsmtExposure"].apply(lambda x : mapping[x])

mapping = {"GLQ":7, "ALQ":6, "BLQ":5, "Rec":4, "LwQ":3, "Unf":2, "nan":1} data["BsmtFinType1"] = data["BsmtFinType1"].astype("str") data["BsmtFinType1"] = data["BsmtFinType1"].apply(lambda x : mapping[x]) test_kaggle["BsmtFinType1"] = test_kaggle["BsmtFinType1"].apply(lambda x : mapping[x])

mapping = {"Ex":6, "Gd":5, "TA":4, "Fa":3, "Po":2, "nan":1} data["BsmtCond"] = data["BsmtCond"].astype("str") data["BsmtCond"] = data["BsmtCond"].apply(lambda x : mapping[x]) test_kaggle["BsmtCond"] = test_kaggle["BsmtCond"].apply(lambda x : mapping[x])

mapping = {"Ex":6, "Gd":5, "TA":4, "Fa":3, "Po":2, "nan":1} data["BsmtQual"] = data["BsmtQual"].astype("str") data["BsmtQual"] = data["BsmtQual"].apply(lambda x : mapping[x]) test_kaggle["BsmtQual"] = test_kaggle["BsmtQual"].apply(lambda x : mapping[x])

print(data.shape, test_kaggle.shape)

(1460, 75) (1459, 74)

data

price = data["SalePrice"] data.drop('SalePrice', axis='columns', inplace=True) data = pd.concat([data, price], axis=1) #deploy_data = data.copy(deep=True) X = data.iloc[:, :-1] y = data.iloc[:, -1].tolist()

from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

X_train

Análise das Matrizes de Correlação

df_garage = X_train[["GarageType","GarageCond","GarageYrBlt","GarageFinish","GarageQual","GarageCars","GarageArea"]] df_basement = X_train[["BsmtFinType2","BsmtExposure","BsmtFinType1","BsmtCond","BsmtQual","BsmtFinSF1","BsmtFinSF2","BsmtUnfSF","TotalBsmtSF"]]

import matplotlib.pyplot as plt import seaborn as sns plt.figure(figsize=(16,10)) corr = df_basement.corr() ax = sns.heatmap( corr, vmin=-1, vmax=1, center=0, cmap=sns.diverging_palette(20, 220, n=200), square=True ) ax.set_xticklabels( ax.get_xticklabels(), rotation=45, horizontalalignment='right' ) plt.show()

# bsmt types e square feet têm correlação alta, então removeremos bsmt square feet (1 e 2) X_train.drop(columns = ["BsmtFinSF1","BsmtFinSF2", "BsmtUnfSF"], axis = 1, inplace=True) X_test.drop(columns = ["BsmtFinSF1","BsmtFinSF2", "BsmtUnfSF"], axis = 1, inplace=True) test_kaggle.drop(columns = ["BsmtFinSF1","BsmtFinSF2", "BsmtUnfSF"], axis = 1, inplace=True) # unfinished square feet possuem uma correlação alta (embora inversa) com o termo removido, # portanto será removido também, visto que já está representado pelo basement type # e.g. um porão com score de tipo ruim provavelmente terá um unfinished square feet alto

plt.figure(figsize=(16,10)) corr = df_garage.corr() ax = sns.heatmap( corr, vmin=-1, vmax=1, center=0, cmap=sns.diverging_palette(20, 220, n=200), square=True ) ax.set_xticklabels( ax.get_xticklabels(), rotation=45, horizontalalignment='right' ) plt.show()

# ano da garagem não é tão relevante, e é compreendido pelo finish # qual é redundante em relação ao finish # garagecars é completamente equivalente ao garage area X_train.drop(columns = ["GarageYrBlt", "GarageQual", "GarageCars"], axis = 1, inplace=True) X_test.drop(columns = ["GarageYrBlt", "GarageQual", "GarageCars"], axis = 1, inplace=True) test_kaggle.drop(columns = ["GarageYrBlt", "GarageQual", "GarageCars"], axis = 1, inplace=True)

X_test.shape

X_train

y_train

train_data = X_train.copy(deep=True) train_data['SalePrice'] = pd.Series(y_train).values

X_train.columns

X_train

#train_data = pd.concat([X_train, pd.DataFrame(y_train)], axis=1) # colocar título sale price train_data

import numpy as np # taken from: https://www.kaggle.com/pmarcelino/comprehensive-data-exploration-with-python #saleprice correlation matrix plt.figure(figsize=(10,10)) k = 10 #number of variables for heatmap corrmat = train_data.corr() cols = corrmat.nlargest(k, 'SalePrice')['SalePrice'].index cm = np.corrcoef(train_data[cols].values.T) sns.set(font_scale=1.25) hm = sns.heatmap(cm, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 10}, yticklabels=cols.values, xticklabels=cols.values) plt.show()

X_train.columns

# tamanho total do porão é muito correlacionado com o tamanho do primeiro andar # (afinal porões geralmente são uma extensão do primeiro andar só que pra baixo) X_train.drop(columns = ["TotalBsmtSF"], axis = 1, inplace=True) X_test.drop(columns = ["TotalBsmtSF"], axis = 1, inplace=True) test_kaggle.drop(columns = ["TotalBsmtSF"], axis = 1, inplace=True)

Continuação dos Mapeamentos nos Atributos Categóricos Ordinais

X_train["MSSubClass"] = X_train["MSSubClass"].astype("str") X_test["MSSubClass"] = X_train["MSSubClass"].astype("str") test_kaggle["MSSubClass"] = test_kaggle["MSSubClass"].astype("str")

mapping = {"Reg":4,"IR1":3,"IR2":2,"IR3":1} X_train["LotShape"] = X_train["LotShape"].apply(lambda x : mapping[x]) X_test["LotShape"] = X_test["LotShape"].apply(lambda x : mapping[x]) test_kaggle["LotShape"] = test_kaggle["LotShape"].apply(lambda x : mapping[x])

#df_test["Utilities"].fillna("AllPub")

mapping = {"AllPub":4,"NoSewr":3,"NoSeWa":2,"ELO":1,np.nan:0} X_train["Utilities"] = X_train["Utilities"].apply(lambda x : mapping[x]) X_test["Utilities"] = X_test["Utilities"].apply(lambda x : mapping[x]) test_kaggle["Utilities"] = test_kaggle["Utilities"].apply(lambda x : mapping[x])

mapping = {"Gtl":3,"Mod":2,"Sev":1} X_train["LandSlope"] = X_train["LandSlope"].apply(lambda x : mapping[x]) X_test["LandSlope"] = X_test["LandSlope"].apply(lambda x : mapping[x]) test_kaggle["LandSlope"] = test_kaggle["LandSlope"].apply(lambda x : mapping[x])

mapping = {"Ex":5,"Gd":4,"TA":3,"Fa":2,"Po":1} X_train["ExterQual"] = X_train["ExterQual"].apply(lambda x : mapping[x]) X_test["ExterQual"] = X_test["ExterQual"].apply(lambda x : mapping[x]) test_kaggle["ExterQual"] = test_kaggle["ExterQual"].apply(lambda x : mapping[x])

mapping = {"Ex":5,"Gd":4,"TA":3,"Fa":2,"Po":1} X_train["ExterCond"] = X_train["ExterCond"].apply(lambda x : mapping[x]) X_test["ExterCond"] = X_test["ExterCond"].apply(lambda x : mapping[x]) test_kaggle["ExterCond"] = test_kaggle["ExterCond"].apply(lambda x : mapping[x])

mapping = {"Ex":5,"Gd":4,"TA":3,"Fa":2,"Po":1} X_train["KitchenQual"] = X_train["KitchenQual"].apply(lambda x : mapping[x]) X_test["KitchenQual"] = X_test["KitchenQual"].apply(lambda x : mapping[x]) test_kaggle["KitchenQual"] = test_kaggle["KitchenQual"].apply(lambda x : mapping[x])

mapping = {"Typ":8,"Min1":7,"Min2":6,"Mod":5,"Maj1":4,"Maj2":3,"Sev":2,"Sal":1} X_train["Functional"] = X_train["Functional"].apply(lambda x : mapping[x]) X_test["Functional"] = X_test["Functional"].apply(lambda x : mapping[x]) test_kaggle["Functional"] = test_kaggle["Functional"].apply(lambda x : mapping[x])

mapping = {"Y":3,"P":2,"N":1} X_train["PavedDrive"] = X_train["PavedDrive"].apply(lambda x : mapping[x]) X_test["PavedDrive"] = X_test["PavedDrive"].apply(lambda x : mapping[x]) test_kaggle["PavedDrive"] = test_kaggle["PavedDrive"].apply(lambda x : mapping[x])

Mapeamento dos Atributos Categóricos Nominais

X_train["MSSubClass"] = label.fit_transform(X_train["MSSubClass"]) X_train["MSZoning"] = label.fit_transform(X_train["MSZoning"]) X_train["Street"] = label.fit_transform(X_train["Street"]) X_train["LandContour"] = label.fit_transform(X_train["LandContour"]) X_train["LotConfig"] = label.fit_transform(X_train["LotConfig"]) X_train["Neighborhood"] = label.fit_transform(X_train["Neighborhood"]) X_train["Condition1"] = label.fit_transform(X_train["Condition1"]) X_train["Condition2"] = label.fit_transform(X_train["Condition2"]) X_train["BldgType"] = label.fit_transform(X_train["BldgType"]) X_train["HouseStyle"] = label.fit_transform(X_train["HouseStyle"]) X_train["RoofStyle"] = label.fit_transform(X_train["RoofStyle"]) X_train["RoofMatl"] = label.fit_transform(X_train["RoofMatl"]) X_train["Exterior1st"] = label.fit_transform(X_train["Exterior1st"]) X_train["Exterior2nd"] = label.fit_transform(X_train["Exterior2nd"]) X_train["MasVnrType"] = label.fit_transform(X_train["MasVnrType"]) X_train["HeatingQC"] = label.fit_transform(X_train["HeatingQC"]) X_train["Foundation"] = label.fit_transform(X_train["Foundation"]) X_train["Heating"] = label.fit_transform(X_train["Heating"]) X_train["CentralAir"] = label.fit_transform(X_train["CentralAir"]) X_train["Electrical"] = label.fit_transform(X_train["Electrical"]) X_train["SaleType"] = label.fit_transform(X_train["SaleType"]) X_train["SaleCondition"] = label.fit_transform(X_train["SaleCondition"])

X_test["MSSubClass"] = label.fit_transform(X_test["MSSubClass"]) X_test["MSZoning"] = label.fit_transform(X_test["MSZoning"]) X_test["Street"] = label.fit_transform(X_test["Street"]) X_test["LandContour"] = label.fit_transform(X_test["LandContour"]) X_test["LotConfig"] = label.fit_transform(X_test["LotConfig"]) X_test["Neighborhood"] = label.fit_transform(X_test["Neighborhood"]) X_test["Condition1"] = label.fit_transform(X_test["Condition1"]) X_test["Condition2"] = label.fit_transform(X_test["Condition2"]) X_test["BldgType"] = label.fit_transform(X_test["BldgType"]) X_test["HouseStyle"] = label.fit_transform(X_test["HouseStyle"]) X_test["RoofStyle"] = label.fit_transform(X_test["RoofStyle"]) X_test["RoofMatl"] = label.fit_transform(X_test["RoofMatl"]) X_test["Exterior1st"] = label.fit_transform(X_test["Exterior1st"]) X_test["Exterior2nd"] = label.fit_transform(X_test["Exterior2nd"]) X_test["MasVnrType"] = label.fit_transform(X_test["MasVnrType"]) X_test["HeatingQC"] = label.fit_transform(X_test["HeatingQC"]) X_test["Foundation"] = label.fit_transform(X_test["Foundation"]) X_test["Heating"] = label.fit_transform(X_test["Heating"]) X_test["CentralAir"] = label.fit_transform(X_test["CentralAir"]) X_test["Electrical"] = label.fit_transform(X_test["Electrical"]) X_test["SaleType"] = label.fit_transform(X_test["SaleType"]) X_test["SaleCondition"] = label.fit_transform(X_test["SaleCondition"])

test_kaggle["MSSubClass"] = label.fit_transform(test_kaggle["MSSubClass"]) test_kaggle["MSZoning"] = label.fit_transform(test_kaggle["MSZoning"]) test_kaggle["Street"] = label.fit_transform(test_kaggle["Street"]) test_kaggle["LandContour"] = label.fit_transform(test_kaggle["LandContour"]) test_kaggle["LotConfig"] = label.fit_transform(test_kaggle["LotConfig"]) test_kaggle["Neighborhood"] = label.fit_transform(test_kaggle["Neighborhood"]) test_kaggle["Condition1"] = label.fit_transform(test_kaggle["Condition1"]) test_kaggle["Condition2"] = label.fit_transform(test_kaggle["Condition2"]) test_kaggle["BldgType"] = label.fit_transform(test_kaggle["BldgType"]) test_kaggle["HouseStyle"] = label.fit_transform(test_kaggle["HouseStyle"]) test_kaggle["RoofStyle"] = label.fit_transform(test_kaggle["RoofStyle"]) test_kaggle["RoofMatl"] = label.fit_transform(test_kaggle["RoofMatl"]) test_kaggle["Exterior1st"] = label.fit_transform(test_kaggle["Exterior1st"]) test_kaggle["Exterior2nd"] = label.fit_transform(test_kaggle["Exterior2nd"]) test_kaggle["MasVnrType"] = label.fit_transform(test_kaggle["MasVnrType"]) test_kaggle["HeatingQC"] = label.fit_transform(test_kaggle["HeatingQC"]) test_kaggle["Foundation"] = label.fit_transform(test_kaggle["Foundation"]) test_kaggle["Heating"] = label.fit_transform(test_kaggle["Heating"]) test_kaggle["CentralAir"] = label.fit_transform(test_kaggle["CentralAir"]) test_kaggle["Electrical"] = label.fit_transform(test_kaggle["Electrical"]) test_kaggle["SaleType"] = label.fit_transform(test_kaggle["SaleType"]) test_kaggle["SaleCondition"] = label.fit_transform(test_kaggle["SaleCondition"])

X_train.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1168 entries, 618 to 684
Data columns (total 67 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Id             1168 non-null   int64  
 1   MSSubClass     1168 non-null   int64  
 2   MSZoning       1168 non-null   int64  
 3   LotArea        1168 non-null   int64  
 4   Street         1168 non-null   int64  
 5   LotShape       1168 non-null   int64  
 6   LandContour    1168 non-null   int64  
 7   Utilities      1168 non-null   int64  
 8   LotConfig      1168 non-null   int64  
 9   LandSlope      1168 non-null   int64  
 10  Neighborhood   1168 non-null   int64  
 11  Condition1     1168 non-null   int64  
 12  Condition2     1168 non-null   int64  
 13  BldgType       1168 non-null   int64  
 14  HouseStyle     1168 non-null   int64  
 15  OverallQual    1168 non-null   int64  
 16  OverallCond    1168 non-null   int64  
 17  YearBuilt      1168 non-null   int64  
 18  YearRemodAdd   1168 non-null   int64  
 19  RoofStyle      1168 non-null   int64  
 20  RoofMatl       1168 non-null   int64  
 21  Exterior1st    1168 non-null   int64  
 22  Exterior2nd    1168 non-null   int64  
 23  MasVnrType     1168 non-null   int64  
 24  MasVnrArea     1168 non-null   float64
 25  ExterQual      1168 non-null   int64  
 26  ExterCond      1168 non-null   int64  
 27  Foundation     1168 non-null   int64  
 28  BsmtQual       1168 non-null   int64  
 29  BsmtCond       1168 non-null   int64  
 30  BsmtExposure   1168 non-null   int64  
 31  BsmtFinType1   1168 non-null   int64  
 32  BsmtFinType2   1168 non-null   int64  
 33  Heating        1168 non-null   int64  
 34  HeatingQC      1168 non-null   int64  
 35  CentralAir     1168 non-null   int64  
 36  Electrical     1168 non-null   int64  
 37  1stFlrSF       1168 non-null   int64  
 38  2ndFlrSF       1168 non-null   int64  
 39  LowQualFinSF   1168 non-null   int64  
 40  GrLivArea      1168 non-null   int64  
 41  BsmtFullBath   1168 non-null   int64  
 42  BsmtHalfBath   1168 non-null   int64  
 43  FullBath       1168 non-null   int64  
 44  HalfBath       1168 non-null   int64  
 45  BedroomAbvGr   1168 non-null   int64  
 46  KitchenAbvGr   1168 non-null   int64  
 47  KitchenQual    1168 non-null   int64  
 48  TotRmsAbvGrd   1168 non-null   int64  
 49  Functional     1168 non-null   int64  
 50  Fireplaces     1168 non-null   int64  
 51  GarageType     1168 non-null   int64  
 52  GarageFinish   1168 non-null   int64  
 53  GarageArea     1168 non-null   int64  
 54  GarageCond     1168 non-null   int64  
 55  PavedDrive     1168 non-null   int64  
 56  WoodDeckSF     1168 non-null   int64  
 57  OpenPorchSF    1168 non-null   int64  
 58  EnclosedPorch  1168 non-null   int64  
 59  3SsnPorch      1168 non-null   int64  
 60  ScreenPorch    1168 non-null   int64  
 61  PoolArea       1168 non-null   int64  
 62  MiscVal        1168 non-null   int64  
 63  MoSold         1168 non-null   int64  
 64  YrSold         1168 non-null   int64  
 65  SaleType       1168 non-null   int64  
 66  SaleCondition  1168 non-null   int64  
dtypes: float64(1), int64(66)
memory usage: 652.8 KB

#data = data.reset_index()

Codificação One-Hot

X_train.columns

X_train.drop(columns = [ "Id"], axis = 1, inplace=True) X_test.drop(columns = ["Id"], axis = 1, inplace=True) test_kaggle.drop(columns = ["Id"], axis = 1, inplace=True)

X_train.head()

X_train['isTest'] = 0 X_test['isTest'] = 1 train_and_test = pd.concat([X_train, X_test], ignore_index=True) train_and_test

print(train_and_test.shape, test_kaggle.shape)

(1460, 67) (1459, 66)

test_kaggle['isTest'] = 2 train_and_test = pd.concat([train_and_test, test_kaggle], ignore_index=True)

train_and_test = pd.get_dummies(train_and_test, columns=["MSSubClass", "MSZoning", "Street", "LandContour", "LotConfig", "Neighborhood", "Condition1", "Condition2", "BldgType", "HouseStyle", "RoofStyle", "RoofMatl", "Exterior1st", "Exterior2nd", "MasVnrType", "Foundation", "Heating", "Electrical", "GarageType", "SaleType", "SaleCondition"]) # sem noção de ordem, converter para one-hotX_

#test_kaggle = pd.get_dummies(test_kaggle, columns=["MSSubClass", "MSZoning", "Street", "LandContour", "LotConfig", "Neighborhood", "Condition1", "Condition2", "BldgType", #"HouseStyle", "RoofStyle", "RoofMatl", "Exterior1st", "Exterior2nd", "MasVnrType", "Foundation", "Heating", "Electrical", #"GarageType", "SaleType", "SaleCondition"]) # sem noção de ordem, converter para one-hot

X_train = train_and_test[train_and_test['isTest'] == 0] X_test = train_and_test[train_and_test['isTest'] == 1] test_kaggle = train_and_test[train_and_test['isTest'] == 2] X_train.drop(columns = ["isTest"], axis = 1, inplace=True) X_test.drop(columns = ["isTest"], axis = 1, inplace=True) test_kaggle.drop(columns = ["isTest"], axis = 1, inplace=True)

/shared-libs/python3.7/py/lib/python3.7/site-packages/pandas/core/frame.py:4315: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  errors=errors,

train_and_test = train_and_test[train_and_test['isTest'] != 2] train_and_test.drop(columns = ["isTest"], axis = 1, inplace=True)

print(train_and_test.shape, test_kaggle.shape)

(1460, 216) (1459, 216)

# remover atributos com mais de 90% de zeros total = X_train.shape[0] threshold = 0.9 drop_list = [] for column in X_train.columns: zeroes = len(X_train[X_train[column] == 0]) ratio = zeroes / total if ratio > threshold: drop_list.append(column)

X_train.drop(columns = drop_list, axis = 1, inplace=True) X_test.drop(columns = drop_list, axis = 1, inplace=True) test_kaggle.drop(columns = drop_list, axis = 1, inplace=True) train_and_test.drop(columns = drop_list, axis = 1, inplace=True)

X_test.head()

X_train.head()

X_train["GarageCond"] = X_train["GarageCond"].astype("uint8") X_test["GarageCond"] = X_test["GarageCond"].astype("uint8") test_kaggle["GarageCond"] = test_kaggle["GarageCond"].astype("uint8")

Experimentos com Modelos

X_train.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1168 entries, 0 to 1167
Data columns (total 77 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   LotArea          1168 non-null   int64  
 1   LotShape         1168 non-null   int64  
 2   Utilities        1168 non-null   int64  
 3   LandSlope        1168 non-null   int64  
 4   OverallQual      1168 non-null   int64  
 5   OverallCond      1168 non-null   int64  
 6   YearBuilt        1168 non-null   int64  
 7   YearRemodAdd     1168 non-null   int64  
 8   MasVnrArea       1168 non-null   float64
 9   ExterQual        1168 non-null   int64  
 10  ExterCond        1168 non-null   int64  
 11  BsmtQual         1168 non-null   int64  
 12  BsmtCond         1168 non-null   int64  
 13  BsmtExposure     1168 non-null   int64  
 14  BsmtFinType1     1168 non-null   int64  
 15  BsmtFinType2     1168 non-null   int64  
 16  HeatingQC        1168 non-null   int64  
 17  CentralAir       1168 non-null   int64  
 18  1stFlrSF         1168 non-null   int64  
 19  2ndFlrSF         1168 non-null   int64  
 20  GrLivArea        1168 non-null   int64  
 21  BsmtFullBath     1168 non-null   float64
 22  FullBath         1168 non-null   int64  
 23  HalfBath         1168 non-null   int64  
 24  BedroomAbvGr     1168 non-null   int64  
 25  KitchenAbvGr     1168 non-null   int64  
 26  KitchenQual      1168 non-null   int64  
 27  TotRmsAbvGrd     1168 non-null   int64  
 28  Functional       1168 non-null   int64  
 29  Fireplaces       1168 non-null   int64  
 30  GarageFinish     1168 non-null   int64  
 31  GarageArea       1168 non-null   float64
 32  GarageCond       1168 non-null   uint8  
 33  PavedDrive       1168 non-null   int64  
 34  WoodDeckSF       1168 non-null   int64  
 35  OpenPorchSF      1168 non-null   int64  
 36  EnclosedPorch    1168 non-null   int64  
 37  MoSold           1168 non-null   int64  
 38  YrSold           1168 non-null   int64  
 39  MSSubClass_4     1168 non-null   uint8  
 40  MSSubClass_9     1168 non-null   uint8  
 41  MSZoning_3       1168 non-null   uint8  
 42  MSZoning_4       1168 non-null   uint8  
 43  Street_1         1168 non-null   uint8  
 44  LandContour_3    1168 non-null   uint8  
 45  LotConfig_0      1168 non-null   uint8  
 46  LotConfig_4      1168 non-null   uint8  
 47  Neighborhood_12  1168 non-null   uint8  
 48  Condition1_2     1168 non-null   uint8  
 49  Condition2_2     1168 non-null   uint8  
 50  BldgType_0       1168 non-null   uint8  
 51  HouseStyle_0     1168 non-null   uint8  
 52  HouseStyle_2     1168 non-null   uint8  
 53  HouseStyle_5     1168 non-null   uint8  
 54  RoofStyle_1      1168 non-null   uint8  
 55  RoofStyle_3      1168 non-null   uint8  
 56  RoofMatl_0       1168 non-null   uint8  
 57  Exterior1st_6    1168 non-null   uint8  
 58  Exterior1st_8    1168 non-null   uint8  
 59  Exterior1st_12   1168 non-null   uint8  
 60  Exterior1st_13   1168 non-null   uint8  
 61  Exterior2nd_6    1168 non-null   uint8  
 62  Exterior2nd_8    1168 non-null   uint8  
 63  Exterior2nd_10   1168 non-null   uint8  
 64  Exterior2nd_13   1168 non-null   uint8  
 65  Exterior2nd_14   1168 non-null   uint8  
 66  MasVnrType_1     1168 non-null   uint8  
 67  MasVnrType_2     1168 non-null   uint8  
 68  Foundation_0     1168 non-null   uint8  
 69  Foundation_1     1168 non-null   uint8  
 70  Foundation_2     1168 non-null   uint8  
 71  Heating_1        1168 non-null   uint8  
 72  Electrical_4     1168 non-null   uint8  
 73  GarageType_1     1168 non-null   uint8  
 74  GarageType_5     1168 non-null   uint8  
 75  SaleType_8       1168 non-null   uint8  
 76  SaleCondition_4  1168 non-null   uint8  
dtypes: float64(3), int64(35), uint8(39)
memory usage: 400.4 KB

X_train

X_train.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1168 entries, 0 to 1167
Data columns (total 77 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   LotArea          1168 non-null   int64  
 1   LotShape         1168 non-null   int64  
 2   Utilities        1168 non-null   int64  
 3   LandSlope        1168 non-null   int64  
 4   OverallQual      1168 non-null   int64  
 5   OverallCond      1168 non-null   int64  
 6   YearBuilt        1168 non-null   int64  
 7   YearRemodAdd     1168 non-null   int64  
 8   MasVnrArea       1168 non-null   float64
 9   ExterQual        1168 non-null   int64  
 10  ExterCond        1168 non-null   int64  
 11  BsmtQual         1168 non-null   int64  
 12  BsmtCond         1168 non-null   int64  
 13  BsmtExposure     1168 non-null   int64  
 14  BsmtFinType1     1168 non-null   int64  
 15  BsmtFinType2     1168 non-null   int64  
 16  HeatingQC        1168 non-null   int64  
 17  CentralAir       1168 non-null   int64  
 18  1stFlrSF         1168 non-null   int64  
 19  2ndFlrSF         1168 non-null   int64  
 20  GrLivArea        1168 non-null   int64  
 21  BsmtFullBath     1168 non-null   float64
 22  FullBath         1168 non-null   int64  
 23  HalfBath         1168 non-null   int64  
 24  BedroomAbvGr     1168 non-null   int64  
 25  KitchenAbvGr     1168 non-null   int64  
 26  KitchenQual      1168 non-null   int64  
 27  TotRmsAbvGrd     1168 non-null   int64  
 28  Functional       1168 non-null   int64  
 29  Fireplaces       1168 non-null   int64  
 30  GarageFinish     1168 non-null   int64  
 31  GarageArea       1168 non-null   float64
 32  GarageCond       1168 non-null   uint8  
 33  PavedDrive       1168 non-null   int64  
 34  WoodDeckSF       1168 non-null   int64  
 35  OpenPorchSF      1168 non-null   int64  
 36  EnclosedPorch    1168 non-null   int64  
 37  MoSold           1168 non-null   int64  
 38  YrSold           1168 non-null   int64  
 39  MSSubClass_4     1168 non-null   uint8  
 40  MSSubClass_9     1168 non-null   uint8  
 41  MSZoning_3       1168 non-null   uint8  
 42  MSZoning_4       1168 non-null   uint8  
 43  Street_1         1168 non-null   uint8  
 44  LandContour_3    1168 non-null   uint8  
 45  LotConfig_0      1168 non-null   uint8  
 46  LotConfig_4      1168 non-null   uint8  
 47  Neighborhood_12  1168 non-null   uint8  
 48  Condition1_2     1168 non-null   uint8  
 49  Condition2_2     1168 non-null   uint8  
 50  BldgType_0       1168 non-null   uint8  
 51  HouseStyle_0     1168 non-null   uint8  
 52  HouseStyle_2     1168 non-null   uint8  
 53  HouseStyle_5     1168 non-null   uint8  
 54  RoofStyle_1      1168 non-null   uint8  
 55  RoofStyle_3      1168 non-null   uint8  
 56  RoofMatl_0       1168 non-null   uint8  
 57  Exterior1st_6    1168 non-null   uint8  
 58  Exterior1st_8    1168 non-null   uint8  
 59  Exterior1st_12   1168 non-null   uint8  
 60  Exterior1st_13   1168 non-null   uint8  
 61  Exterior2nd_6    1168 non-null   uint8  
 62  Exterior2nd_8    1168 non-null   uint8  
 63  Exterior2nd_10   1168 non-null   uint8  
 64  Exterior2nd_13   1168 non-null   uint8  
 65  Exterior2nd_14   1168 non-null   uint8  
 66  MasVnrType_1     1168 non-null   uint8  
 67  MasVnrType_2     1168 non-null   uint8  
 68  Foundation_0     1168 non-null   uint8  
 69  Foundation_1     1168 non-null   uint8  
 70  Foundation_2     1168 non-null   uint8  
 71  Heating_1        1168 non-null   uint8  
 72  Electrical_4     1168 non-null   uint8  
 73  GarageType_1     1168 non-null   uint8  
 74  GarageType_5     1168 non-null   uint8  
 75  SaleType_8       1168 non-null   uint8  
 76  SaleCondition_4  1168 non-null   uint8  
dtypes: float64(3), int64(35), uint8(39)
memory usage: 400.4 KB

Modelos Candidatos

!pip install xgboost

Collecting xgboost
  Downloading xgboost-1.4.2-py3-none-manylinux2010_x86_64.whl (166.7 MB)
     |████████████████████████████████| 166.7 MB 27 kB/s 
Requirement already satisfied: scipy in /shared-libs/python3.7/py/lib/python3.7/site-packages (from xgboost) (1.7.1)
Requirement already satisfied: numpy in /shared-libs/python3.7/py/lib/python3.7/site-packages (from xgboost) (1.19.5)
Installing collected packages: xgboost
Successfully installed xgboost-1.4.2
WARNING: You are using pip version 21.2.4; however, version 21.3 is available.
You should consider upgrading via the '/root/venv/bin/python -m pip install --upgrade pip' command.

X_train.columns

X_test.columns

from sklearn.tree import DecisionTreeRegressor from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_absolute_error from sklearn.metrics import mean_squared_error from sklearn.ensemble import RandomForestRegressor from sklearn.datasets import make_regression from sklearn.metrics import mean_squared_log_error from sklearn.metrics import r2_score from xgboost import XGBRegressor import xgboost as xgb from sklearn.neural_network import MLPRegressor from sklearn.datasets import make_regression from sklearn.model_selection import train_test_split from sklearn import linear_model MLA = [ DecisionTreeRegressor(), LinearRegression(), XGBRegressor(), RandomForestRegressor(), MLPRegressor(random_state=1, max_iter=500), linear_model.SGDRegressor( max_iter = 1000,penalty = "elasticnet",loss = 'huber',tol = 1e-3, average = True) ] row_index = 0 MLA_compare = pd.DataFrame() model_names = [] r2_scores = [] for model in MLA: model.fit(X_train, y_train) y_pred = model.predict(X_test) model_r2_score = r2_score(y_test, y_pred) mse = mean_squared_error(y_test, y_pred) mae = mean_absolute_error(y_test, y_pred) msl = mean_squared_log_error(y_test, abs(y_pred)) MLA_name = model.__class__.__name__ MLA_compare.loc[row_index, 'MLA Name'] = MLA_name MLA_compare.loc[row_index, 'R2 Score'] = model_r2_score MLA_compare.loc[row_index, 'MSL'] = msl MLA_compare.loc[row_index, 'MSE'] = mse MLA_compare.loc[row_index, 'MAE'] = mae row_index+=1

/shared-libs/python3.7/py/lib/python3.7/site-packages/sklearn/neural_network/_multilayer_perceptron.py:696: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.
  ConvergenceWarning,

MLA_compare

# grid search comentado para não executar todas as vezes. ''' from sklearn.model_selection import GridSearchCV xgb1 = XGBRegressor() parameters = {'nthread':[4], #when use hyperthread, xgboost may become slower 'objective':['reg:linear'], 'learning_rate': [.03, 0.05, .07], #so called `eta` value 'max_depth': [5, 6, 7], 'min_child_weight': [4], 'silent': [1], 'subsample': [0.7], 'colsample_bytree': [0.7], 'n_estimators': [500]} xgb_grid = GridSearchCV(xgb1, parameters, cv = 2, n_jobs = 5, verbose=True) xgb_grid.fit(X_train, y_train) print(xgb_grid.best_score_) print(xgb_grid.best_params_) ''' #0.8616263070651717 #{'colsample_bytree': 0.7, 'learning_rate': 0.03, 'max_depth': 5, 'min_child_weight': 4, 'n_estimators': 500, 'nthread': 4, 'objective': 'reg:linear', 'silent': 1, 'subsample': 0.7}

grid_result = XGBRegressor(colsample_bytree=0.7, learning_rate=0.03, max_depth=5, min_child_weight=4, n_estimators=500, nthread=4, objective='reg:linear', silent=1, subsample=0.7) grid_result.fit(X_train, y_train) y_pred = grid_result.predict(X_test) print(r2_score(y_test, y_pred)) print(mean_squared_error(y_test, y_pred)) print(mean_absolute_error(y_test, y_pred)) print(mean_squared_log_error(y_test, abs(y_pred)))

[00:21:53] WARNING: ../src/objective/regression_obj.cu:171: reg:linear is now deprecated in favor of reg:squarederror.
[00:21:53] WARNING: ../src/learner.cc:573: 
Parameters: { "silent" } might not be used.

  This may not be accurate due to some parameters are only used in language bindings but
  passed down to XGBoost core.  Or some parameters are not used but slip through this
  verification. Please open an issue if you find above cases.


0.8648175138924725
933549966.8195812
17277.501110338184
0.018904495252256553

y_all = y_train + y_test X_train = train_and_test y_train = y_all

train_and_test.shape

len(y_train)

### Production optimal_model = XGBRegressor(colsample_bytree=0.7, learning_rate=0.03, max_depth=5, min_child_weight=4, n_estimators=500, nthread=4, objective='reg:linear', silent=1, subsample=0.7) optimal_model.fit(X_train, y_train) y_pred = optimal_model.predict(test_kaggle)

[00:21:58] WARNING: ../src/objective/regression_obj.cu:171: reg:linear is now deprecated in favor of reg:squarederror.
[00:21:58] WARNING: ../src/learner.cc:573: 
Parameters: { "silent" } might not be used.

  This may not be accurate due to some parameters are only used in language bindings but
  passed down to XGBoost core.  Or some parameters are not used but slip through this
  verification. Please open an issue if you find above cases.

test_kaggle.head(1)

test_pred = optimal_model.predict(test_kaggle.head(1)) test_pred

test_kaggle.tail(1)

test_pred = optimal_model.predict(test_kaggle.tail(1)) test_pred

test_csv = pd.read_csv("/work/dados/test.csv") submission = pd.DataFrame({ 'Id': np.asarray(test_csv.Id), 'SalePrice': y_pred.astype(int) }) submission.to_csv('my_submission.csv', index=False)

Engenharia de Atributos

Tratamento dos Nans

Mapeamento dos Atributos Categóricos Ordinais

Análise das Matrizes de Correlação

Continuação dos Mapeamentos nos Atributos Categóricos Ordinais

Mapeamento dos Atributos Categóricos Nominais

Codificação One-Hot

Experimentos com Modelos

Modelos Candidatos

Discussão