Skip to content

Commit 4a61fb9

Browse files
vinodvr81vinodvr81
committed
changed the train notebook file
1 parent 0246100 commit 4a61fb9

File tree

1 file changed

+367
-0
lines changed

1 file changed

+367
-0
lines changed

‎TrainProject.ipynb

+367
Original file line numberDiff line numberDiff line change
@@ -965,6 +965,373 @@
965965
"pd.crosstab(data[\"Embarked\"],data[\"Sex\"],margins=True)"
966966
]
967967
},
968+
{
969+
"cell_type": "code",
970+
"execution_count": 49,
971+
"metadata": {},
972+
"outputs": [
973+
{
974+
"name": "stdout",
975+
"output_type": "stream",
976+
"text": [
977+
"<class 'pandas.core.frame.DataFrame'>\n",
978+
"RangeIndex: 891 entries, 0 to 890\n",
979+
"Data columns (total 12 columns):\n",
980+
"PassengerId 891 non-null int64\n",
981+
"Survived 891 non-null int64\n",
982+
"Pclass 891 non-null int64\n",
983+
"Name 891 non-null object\n",
984+
"Sex 891 non-null object\n",
985+
"Age 714 non-null float64\n",
986+
"SibSp 891 non-null int64\n",
987+
"Parch 891 non-null int64\n",
988+
"Ticket 891 non-null object\n",
989+
"Fare 891 non-null float64\n",
990+
"Cabin 204 non-null object\n",
991+
"Embarked 889 non-null object\n",
992+
"dtypes: float64(2), int64(5), object(5)\n",
993+
"memory usage: 83.6+ KB\n"
994+
]
995+
}
996+
],
997+
"source": [
998+
"data.info()"
999+
]
1000+
},
1001+
{
1002+
"cell_type": "code",
1003+
"execution_count": 50,
1004+
"metadata": {},
1005+
"outputs": [
1006+
{
1007+
"data": {
1008+
"text/plain": [
1009+
"12"
1010+
]
1011+
},
1012+
"execution_count": 50,
1013+
"metadata": {},
1014+
"output_type": "execute_result"
1015+
}
1016+
],
1017+
"source": [
1018+
"data.shape[1] # gives number of columns"
1019+
]
1020+
},
1021+
{
1022+
"cell_type": "markdown",
1023+
"metadata": {},
1024+
"source": [
1025+
"# who was the oldest person"
1026+
]
1027+
},
1028+
{
1029+
"cell_type": "code",
1030+
"execution_count": 62,
1031+
"metadata": {},
1032+
"outputs": [
1033+
{
1034+
"data": {
1035+
"text/html": [
1036+
"<div>\n",
1037+
"<style scoped>\n",
1038+
" .dataframe tbody tr th:only-of-type {\n",
1039+
" vertical-align: middle;\n",
1040+
" }\n",
1041+
"\n",
1042+
" .dataframe tbody tr th {\n",
1043+
" vertical-align: top;\n",
1044+
" }\n",
1045+
"\n",
1046+
" .dataframe thead th {\n",
1047+
" text-align: right;\n",
1048+
" }\n",
1049+
"</style>\n",
1050+
"<table border=\"1\" class=\"dataframe\">\n",
1051+
" <thead>\n",
1052+
" <tr style=\"text-align: right;\">\n",
1053+
" <th></th>\n",
1054+
" <th>PassengerId</th>\n",
1055+
" <th>Survived</th>\n",
1056+
" <th>Pclass</th>\n",
1057+
" <th>Age</th>\n",
1058+
" <th>SibSp</th>\n",
1059+
" <th>Parch</th>\n",
1060+
" <th>Fare</th>\n",
1061+
" </tr>\n",
1062+
" <tr>\n",
1063+
" <th>Name</th>\n",
1064+
" <th></th>\n",
1065+
" <th></th>\n",
1066+
" <th></th>\n",
1067+
" <th></th>\n",
1068+
" <th></th>\n",
1069+
" <th></th>\n",
1070+
" <th></th>\n",
1071+
" </tr>\n",
1072+
" </thead>\n",
1073+
" <tbody>\n",
1074+
" <tr>\n",
1075+
" <th>Barkworth, Mr. Algernon Henry Wilson</th>\n",
1076+
" <td>631</td>\n",
1077+
" <td>1</td>\n",
1078+
" <td>1</td>\n",
1079+
" <td>80.0</td>\n",
1080+
" <td>0</td>\n",
1081+
" <td>0</td>\n",
1082+
" <td>30.0</td>\n",
1083+
" </tr>\n",
1084+
" </tbody>\n",
1085+
"</table>\n",
1086+
"</div>"
1087+
],
1088+
"text/plain": [
1089+
" PassengerId Survived Pclass Age \\\n",
1090+
"Name \n",
1091+
"Barkworth, Mr. Algernon Henry Wilson 631 1 1 80.0 \n",
1092+
"\n",
1093+
" SibSp Parch Fare \n",
1094+
"Name \n",
1095+
"Barkworth, Mr. Algernon Henry Wilson 0 0 30.0 "
1096+
]
1097+
},
1098+
"execution_count": 62,
1099+
"metadata": {},
1100+
"output_type": "execute_result"
1101+
}
1102+
],
1103+
"source": [
1104+
"c = data.groupby('Name')\n",
1105+
"c = c.sum()\n",
1106+
"c = c.sort_values(['Age'], ascending=False)\n",
1107+
"c.head(1)"
1108+
]
1109+
},
1110+
{
1111+
"cell_type": "markdown",
1112+
"metadata": {},
1113+
"source": [
1114+
"# list five oldest persons"
1115+
]
1116+
},
1117+
{
1118+
"cell_type": "code",
1119+
"execution_count": 63,
1120+
"metadata": {},
1121+
"outputs": [
1122+
{
1123+
"data": {
1124+
"text/html": [
1125+
"<div>\n",
1126+
"<style scoped>\n",
1127+
" .dataframe tbody tr th:only-of-type {\n",
1128+
" vertical-align: middle;\n",
1129+
" }\n",
1130+
"\n",
1131+
" .dataframe tbody tr th {\n",
1132+
" vertical-align: top;\n",
1133+
" }\n",
1134+
"\n",
1135+
" .dataframe thead th {\n",
1136+
" text-align: right;\n",
1137+
" }\n",
1138+
"</style>\n",
1139+
"<table border=\"1\" class=\"dataframe\">\n",
1140+
" <thead>\n",
1141+
" <tr style=\"text-align: right;\">\n",
1142+
" <th></th>\n",
1143+
" <th>PassengerId</th>\n",
1144+
" <th>Survived</th>\n",
1145+
" <th>Pclass</th>\n",
1146+
" <th>Age</th>\n",
1147+
" <th>SibSp</th>\n",
1148+
" <th>Parch</th>\n",
1149+
" <th>Fare</th>\n",
1150+
" </tr>\n",
1151+
" <tr>\n",
1152+
" <th>Name</th>\n",
1153+
" <th></th>\n",
1154+
" <th></th>\n",
1155+
" <th></th>\n",
1156+
" <th></th>\n",
1157+
" <th></th>\n",
1158+
" <th></th>\n",
1159+
" <th></th>\n",
1160+
" </tr>\n",
1161+
" </thead>\n",
1162+
" <tbody>\n",
1163+
" <tr>\n",
1164+
" <th>Barkworth, Mr. Algernon Henry Wilson</th>\n",
1165+
" <td>631</td>\n",
1166+
" <td>1</td>\n",
1167+
" <td>1</td>\n",
1168+
" <td>80.0</td>\n",
1169+
" <td>0</td>\n",
1170+
" <td>0</td>\n",
1171+
" <td>30.0000</td>\n",
1172+
" </tr>\n",
1173+
" <tr>\n",
1174+
" <th>Svensson, Mr. Johan</th>\n",
1175+
" <td>852</td>\n",
1176+
" <td>0</td>\n",
1177+
" <td>3</td>\n",
1178+
" <td>74.0</td>\n",
1179+
" <td>0</td>\n",
1180+
" <td>0</td>\n",
1181+
" <td>7.7750</td>\n",
1182+
" </tr>\n",
1183+
" <tr>\n",
1184+
" <th>Goldschmidt, Mr. George B</th>\n",
1185+
" <td>97</td>\n",
1186+
" <td>0</td>\n",
1187+
" <td>1</td>\n",
1188+
" <td>71.0</td>\n",
1189+
" <td>0</td>\n",
1190+
" <td>0</td>\n",
1191+
" <td>34.6542</td>\n",
1192+
" </tr>\n",
1193+
" <tr>\n",
1194+
" <th>Artagaveytia, Mr. Ramon</th>\n",
1195+
" <td>494</td>\n",
1196+
" <td>0</td>\n",
1197+
" <td>1</td>\n",
1198+
" <td>71.0</td>\n",
1199+
" <td>0</td>\n",
1200+
" <td>0</td>\n",
1201+
" <td>49.5042</td>\n",
1202+
" </tr>\n",
1203+
" <tr>\n",
1204+
" <th>Connors, Mr. Patrick</th>\n",
1205+
" <td>117</td>\n",
1206+
" <td>0</td>\n",
1207+
" <td>3</td>\n",
1208+
" <td>70.5</td>\n",
1209+
" <td>0</td>\n",
1210+
" <td>0</td>\n",
1211+
" <td>7.7500</td>\n",
1212+
" </tr>\n",
1213+
" </tbody>\n",
1214+
"</table>\n",
1215+
"</div>"
1216+
],
1217+
"text/plain": [
1218+
" PassengerId Survived Pclass Age \\\n",
1219+
"Name \n",
1220+
"Barkworth, Mr. Algernon Henry Wilson 631 1 1 80.0 \n",
1221+
"Svensson, Mr. Johan 852 0 3 74.0 \n",
1222+
"Goldschmidt, Mr. George B 97 0 1 71.0 \n",
1223+
"Artagaveytia, Mr. Ramon 494 0 1 71.0 \n",
1224+
"Connors, Mr. Patrick 117 0 3 70.5 \n",
1225+
"\n",
1226+
" SibSp Parch Fare \n",
1227+
"Name \n",
1228+
"Barkworth, Mr. Algernon Henry Wilson 0 0 30.0000 \n",
1229+
"Svensson, Mr. Johan 0 0 7.7750 \n",
1230+
"Goldschmidt, Mr. George B 0 0 34.6542 \n",
1231+
"Artagaveytia, Mr. Ramon 0 0 49.5042 \n",
1232+
"Connors, Mr. Patrick 0 0 7.7500 "
1233+
]
1234+
},
1235+
"execution_count": 63,
1236+
"metadata": {},
1237+
"output_type": "execute_result"
1238+
}
1239+
],
1240+
"source": [
1241+
"c.head(5)"
1242+
]
1243+
},
1244+
{
1245+
"cell_type": "markdown",
1246+
"metadata": {},
1247+
"source": [
1248+
"# Multi Index Tables"
1249+
]
1250+
},
1251+
{
1252+
"cell_type": "code",
1253+
"execution_count": 68,
1254+
"metadata": {},
1255+
"outputs": [
1256+
{
1257+
"data": {
1258+
"text/html": [
1259+
"<div>\n",
1260+
"<style scoped>\n",
1261+
" .dataframe tbody tr th:only-of-type {\n",
1262+
" vertical-align: middle;\n",
1263+
" }\n",
1264+
"\n",
1265+
" .dataframe tbody tr th {\n",
1266+
" vertical-align: top;\n",
1267+
" }\n",
1268+
"\n",
1269+
" .dataframe thead th {\n",
1270+
" text-align: right;\n",
1271+
" }\n",
1272+
"</style>\n",
1273+
"<table border=\"1\" class=\"dataframe\">\n",
1274+
" <thead>\n",
1275+
" <tr style=\"text-align: right;\">\n",
1276+
" <th></th>\n",
1277+
" <th></th>\n",
1278+
" <th>a</th>\n",
1279+
" <th>b</th>\n",
1280+
" <th>c</th>\n",
1281+
" </tr>\n",
1282+
" <tr>\n",
1283+
" <th>n</th>\n",
1284+
" <th>v</th>\n",
1285+
" <th></th>\n",
1286+
" <th></th>\n",
1287+
" <th></th>\n",
1288+
" </tr>\n",
1289+
" </thead>\n",
1290+
" <tbody>\n",
1291+
" <tr>\n",
1292+
" <th>d</th>\n",
1293+
" <th>1</th>\n",
1294+
" <td>4</td>\n",
1295+
" <td>7</td>\n",
1296+
" <td>10</td>\n",
1297+
" </tr>\n",
1298+
" <tr>\n",
1299+
" <th>f</th>\n",
1300+
" <th>2</th>\n",
1301+
" <td>5</td>\n",
1302+
" <td>8</td>\n",
1303+
" <td>11</td>\n",
1304+
" </tr>\n",
1305+
" <tr>\n",
1306+
" <th>e</th>\n",
1307+
" <th>2</th>\n",
1308+
" <td>6</td>\n",
1309+
" <td>9</td>\n",
1310+
" <td>12</td>\n",
1311+
" </tr>\n",
1312+
" </tbody>\n",
1313+
"</table>\n",
1314+
"</div>"
1315+
],
1316+
"text/plain": [
1317+
" a b c\n",
1318+
"n v \n",
1319+
"d 1 4 7 10\n",
1320+
"f 2 5 8 11\n",
1321+
"e 2 6 9 12"
1322+
]
1323+
},
1324+
"execution_count": 68,
1325+
"metadata": {},
1326+
"output_type": "execute_result"
1327+
}
1328+
],
1329+
"source": [
1330+
"df = pd.DataFrame({\"a\" : [4 ,5, 6],\"b\" : [7, 8, 9],\"c\" : [10, 11, 12]}, index = pd.MultiIndex.from_tuples([('d',1),('f',2),('e',2)],\n",
1331+
"names=['n','v']))\n",
1332+
"df"
1333+
]
1334+
},
9681335
{
9691336
"cell_type": "code",
9701337
"execution_count": null,

0 commit comments

Comments
 (0)