diff --git a/Kaggle/Titanic/test_result.csv b/Kaggle/Titanic/test_result.csv new file mode 100644 index 0000000..7f4a2a4 --- /dev/null +++ b/Kaggle/Titanic/test_result.csv @@ -0,0 +1,419 @@ +PassengerId,Survived +892,0 +893,0 +894,0 +895,0 +896,0 +897,0 +898,1 +899,0 +900,0 +901,0 +902,0 +903,0 +904,1 +905,0 +906,1 +907,1 +908,0 +909,0 +910,1 +911,0 +912,0 +913,0 +914,1 +915,0 +916,1 +917,0 +918,1 +919,0 +920,0 +921,0 +922,0 +923,0 +924,0 +925,1 +926,0 +927,0 +928,1 +929,0 +930,0 +931,1 +932,0 +933,0 +934,0 +935,1 +936,1 +937,0 +938,0 +939,0 +940,1 +941,0 +942,1 +943,0 +944,1 +945,1 +946,0 +947,0 +948,0 +949,0 +950,0 +951,1 +952,0 +953,0 +954,0 +955,1 +956,0 +957,1 +958,1 +959,0 +960,0 +961,1 +962,1 +963,0 +964,0 +965,0 +966,1 +967,0 +968,0 +969,1 +970,0 +971,1 +972,1 +973,0 +974,0 +975,0 +976,0 +977,0 +978,0 +979,1 +980,0 +981,1 +982,0 +983,0 +984,1 +985,0 +986,0 +987,0 +988,1 +989,0 +990,1 +991,0 +992,1 +993,0 +994,0 +995,0 +996,0 +997,0 +998,0 +999,0 +1000,0 +1001,0 +1002,0 +1003,0 +1004,1 +1005,1 +1006,1 +1007,0 +1008,0 +1009,1 +1010,0 +1011,1 +1012,1 +1013,0 +1014,1 +1015,0 +1016,0 +1017,0 +1018,0 +1019,1 +1020,0 +1021,0 +1022,0 +1023,0 +1024,1 +1025,0 +1026,0 +1027,0 +1028,0 +1029,0 +1030,1 +1031,0 +1032,0 +1033,1 +1034,0 +1035,0 +1036,0 +1037,0 +1038,1 +1039,0 +1040,0 +1041,0 +1042,1 +1043,0 +1044,0 +1045,0 +1046,0 +1047,0 +1048,1 +1049,1 +1050,0 +1051,1 +1052,0 +1053,1 +1054,1 +1055,0 +1056,0 +1057,1 +1058,0 +1059,0 +1060,1 +1061,0 +1062,0 +1063,0 +1064,0 +1065,0 +1066,0 +1067,1 +1068,1 +1069,0 +1070,1 +1071,1 +1072,0 +1073,0 +1074,1 +1075,0 +1076,1 +1077,0 +1078,1 +1079,0 +1080,0 +1081,0 +1082,0 +1083,0 +1084,1 +1085,0 +1086,1 +1087,0 +1088,1 +1089,1 +1090,0 +1091,1 +1092,0 +1093,1 +1094,1 +1095,1 +1096,0 +1097,0 +1098,0 +1099,0 +1100,1 +1101,0 +1102,0 +1103,0 +1104,0 +1105,1 +1106,0 +1107,0 +1108,0 +1109,0 +1110,1 +1111,0 +1112,1 +1113,0 +1114,1 +1115,0 +1116,1 +1117,1 +1118,0 +1119,0 +1120,0 +1121,0 +1122,0 +1123,1 +1124,0 +1125,0 +1126,0 +1127,0 +1128,0 +1129,0 +1130,1 +1131,1 +1132,1 +1133,1 +1134,0 +1135,0 +1136,0 +1137,0 +1138,1 +1139,0 +1140,1 +1141,0 +1142,1 +1143,0 +1144,1 +1145,0 +1146,0 +1147,0 +1148,0 +1149,0 +1150,1 +1151,0 +1152,0 +1153,0 +1154,1 +1155,1 +1156,0 +1157,0 +1158,0 +1159,0 +1160,1 +1161,0 +1162,0 +1163,0 +1164,1 +1165,0 +1166,0 +1167,1 +1168,0 +1169,0 +1170,0 +1171,0 +1172,0 +1173,1 +1174,0 +1175,0 +1176,1 +1177,0 +1178,0 +1179,1 +1180,0 +1181,0 +1182,1 +1183,0 +1184,0 +1185,0 +1186,0 +1187,0 +1188,1 +1189,0 +1190,0 +1191,0 +1192,0 +1193,0 +1194,0 +1195,0 +1196,0 +1197,1 +1198,1 +1199,1 +1200,0 +1201,0 +1202,0 +1203,0 +1204,0 +1205,0 +1206,1 +1207,1 +1208,0 +1209,0 +1210,0 +1211,0 +1212,0 +1213,0 +1214,0 +1215,0 +1216,1 +1217,0 +1218,1 +1219,0 +1220,0 +1221,0 +1222,1 +1223,1 +1224,0 +1225,0 +1226,0 +1227,0 +1228,0 +1229,0 +1230,0 +1231,0 +1232,0 +1233,0 +1234,0 +1235,1 +1236,1 +1237,1 +1238,0 +1239,0 +1240,0 +1241,1 +1242,1 +1243,0 +1244,0 +1245,0 +1246,1 +1247,0 +1248,1 +1249,0 +1250,0 +1251,0 +1252,0 +1253,1 +1254,1 +1255,0 +1256,1 +1257,0 +1258,0 +1259,0 +1260,1 +1261,0 +1262,0 +1263,1 +1264,0 +1265,0 +1266,1 +1267,1 +1268,0 +1269,0 +1270,0 +1271,0 +1272,0 +1273,0 +1274,0 +1275,0 +1276,0 +1277,1 +1278,0 +1279,0 +1280,0 +1281,0 +1282,0 +1283,1 +1284,0 +1285,0 +1286,0 +1287,1 +1288,0 +1289,1 +1290,0 +1291,0 +1292,1 +1293,0 +1294,1 +1295,0 +1296,0 +1297,0 +1298,0 +1299,0 +1300,1 +1301,1 +1302,0 +1303,1 +1304,0 +1305,0 +1306,1 +1307,0 +1308,0 +1309,0 diff --git a/Kaggle/Titanic/titanic.py b/Kaggle/Titanic/titanic.py index 13f5caf..69f5162 100644 --- a/Kaggle/Titanic/titanic.py +++ b/Kaggle/Titanic/titanic.py @@ -116,4 +116,64 @@ def transform(self, X): passenger_train_var #%% passenger_prepared = full_pipeline.fit_transform(passenger_train_var) -passenger_prepared \ No newline at end of file +passenger_prepared + +#%% +from sklearn.ensemble import RandomForestClassifier +from sklearn.model_selection import cross_val_predict +forest_clf = RandomForestClassifier(random_state=42) +y_probas_forest = cross_val_predict(forest_clf, passenger_prepared, passenger_train_label, cv=3, +method="predict_proba") +y_probas_forest + +#%% +from sklearn.metrics import roc_auc_score +y_scores_forest = y_probas_forest[:, 1] +roc_auc_score(passenger_train_label, y_scores_forest) +#%% +forest_clf.fit(passenger_prepared,passenger_train_label) +forest_clf.predict(passenger_prepared[800]) + +#%% +passenger_test_var = passenger_test +passenger_test_var = passenger_test_var.drop("Name",axis = 1) +passenger_test_var = passenger_test_var.drop("Cabin",axis = 1) +passenger_test_var = passenger_test_var.drop("Ticket",axis = 1) +passenger_test_var = passenger_test_var.drop("PassengerId",axis = 1) +passenger_test_var = passenger_test_var.drop("Embarked",axis = 1) +passenger_test_var + +#%% +passenger_prepared_test = full_pipeline.fit_transform(passenger_test_var) + +final_result = forest_clf.predict(passenger_prepared_test) +final_result + +#%% +final_result_list = final_result.tolist() +final_result_list + +#%% +passenger_id = passenger_test["PassengerId"].copy() +passenger_id_list = passenger_id.tolist() +passenger_id_list + +#%% +final_result_combined_list = [] +for i,j in zip(passenger_id_list,final_result_list): + final_result_combined_list.append([i,j]) +final_result_combined_list + +#%% +import csv +csv_file = "/home/soumyajit/Codes/DL/100DaysOfML/Kaggle/Titanic/test_result.csv" +# with open(csv_file, "w") as output: +# writer = csv.writer(output) +with open(csv_file, "w" , newline='') as output: + writer = csv.writer(output) + writer.writerow(["PassengerId","Survived"]) + writer.writerows(final_result_combined_list) + +#the score is 0.73684 + +