Merge pull request 'lab5 done' (#8) from lab_5 into main

Reviewed-on: #8

lab_2/datasetlab2/Stores.csv

@@ -0,0 +1,897 @@
+Store ID ,Store_Area,Items_Available,Daily_Customer_Count,Store_Sales
+1,1659,1961,530,66490
+2,1461,1752,210,39820
+3,1340,1609,720,54010
+4,1451,1748,620,53730
+5,1770,2111,450,46620
+6,1442,1733,760,45260
+7,1542,1858,1030,72240
+8,1261,1507,1020,37720
+9,1090,1321,680,46310
+10,1030,1235,1130,44150
+11,1187,1439,1090,71280
+12,1751,2098,720,57620
+13,1746,2064,1050,60470
+14,1615,1931,1160,59130
+15,1469,1756,770,66360
+16,1644,1950,790,78870
+17,1578,1907,1440,77250
+18,1703,2045,670,38170
+19,1438,1731,1030,63540
+20,1940,2340,980,40190
+21,1421,1700,370,43460
+22,1458,1746,690,68890
+23,1719,2065,950,52780
+24,1449,1752,620,50680
+25,1234,1488,840,41880
+26,1732,2073,820,70050
+27,1475,1777,1100,25820
+28,1390,1648,980,60530
+29,1642,1943,710,78100
+30,1715,2071,650,84860
+31,1439,1746,990,80140
+32,1250,1508,990,14920
+33,1331,1608,880,60460
+34,1784,2163,620,74560
+35,1375,1648,1020,72430
+36,1871,2230,700,45460
+37,1442,1744,610,41570
+38,1174,1411,1080,62870
+39,1839,2204,1010,55170
+40,1270,1516,10,45480
+41,1435,1725,1250,49550
+42,965,1152,600,48140
+43,1665,2001,730,67640
+44,1780,2117,780,39730
+45,1009,1194,520,35800
+46,1227,1471,870,49270
+47,1769,2087,690,66510
+48,1660,1982,910,62530
+49,1472,1776,1260,59980
+50,1408,1688,1040,76350
+51,1514,1820,910,81820
+52,1565,1880,1300,57830
+53,1074,1288,320,70450
+54,1864,2240,530,67000
+55,1570,1898,980,64090
+56,1417,1701,740,48670
+57,1734,2060,1240,66210
+58,1470,1763,1080,83660
+59,1761,2104,1080,70770
+60,1756,2070,460,53870
+61,1704,2045,300,71300
+62,2011,2391,530,46100
+63,1472,1748,600,49100
+64,1310,1561,860,65920
+65,1544,1821,590,58660
+66,1707,2052,920,69130
+67,1881,2262,570,49080
+68,1416,1681,290,72710
+69,1631,1941,650,33430
+70,1318,1576,710,42430
+71,1692,2019,850,56650
+72,1152,1380,530,33580
+73,891,1073,630,67370
+74,1468,1749,700,71780
+75,1539,1833,650,84840
+76,1635,1956,720,82070
+77,1267,1520,450,26770
+78,1250,1475,1390,65560
+79,1720,2044,960,38660
+80,1462,1761,600,65660
+81,1431,1711,620,40700
+82,1539,1858,1020,88910
+83,1441,1723,330,57860
+84,1572,1884,1410,42670
+85,1287,1525,1200,90180
+86,1468,1760,280,51280
+87,1931,2342,940,97260
+88,1252,1506,850,39650
+89,1238,1468,960,45720
+90,1479,1758,420,42060
+91,1590,1912,830,65350
+92,2169,2617,600,67080
+93,1838,2205,400,54030
+94,1385,1655,760,56360
+95,1921,2305,1470,77120
+96,1975,2385,500,50810
+97,1853,2235,1120,60960
+98,1816,2171,1160,61180
+99,1785,2147,820,63660
+100,1579,1899,1140,41190
+101,1096,1321,900,78420
+102,1919,2294,760,65580
+103,1262,1500,1170,89080
+104,1374,1655,1080,94170
+105,1309,1587,1000,50950
+106,1207,1434,690,65180
+107,1692,2031,810,69310
+108,1929,2311,630,79210
+109,1573,1878,650,23740
+110,1415,1700,920,36330
+111,1162,1382,1260,51700
+112,1485,1787,800,62950
+113,1897,2248,1330,56010
+114,1607,1927,940,45080
+115,1909,2287,1210,46830
+116,1274,1503,660,64750
+117,1157,1379,770,80780
+118,1712,2046,460,31180
+119,1500,1798,860,56710
+120,1682,2017,780,49390
+121,1441,1727,890,66000
+122,1525,1835,900,32770
+123,1408,1669,530,46580
+124,1947,2333,790,79780
+125,1164,1390,370,35510
+126,1787,2137,610,80970
+127,1871,2241,500,61150
+128,1718,2051,750,49210
+129,1365,1636,980,79950
+130,1368,1654,530,68740
+131,1342,1595,910,57480
+132,1076,1270,620,72630
+133,1396,1672,1170,50070
+134,1713,2071,900,40490
+135,1370,1638,980,51850
+136,1667,1993,740,42840
+137,1638,1972,810,60940
+138,1581,1905,810,62280
+139,1795,2187,300,76530
+140,1179,1412,790,85130
+141,1978,2374,800,48590
+142,1688,2042,760,73080
+143,1214,1456,530,48950
+144,1504,1805,540,48560
+145,1498,1770,620,59380
+146,1462,1762,1010,51190
+147,1442,1750,130,58920
+148,1250,1486,730,50360
+149,1229,1480,830,38070
+150,1936,2300,1060,49170
+151,1369,1629,770,39740
+152,1662,1986,70,63730
+153,1548,1855,670,85330
+154,1649,1963,490,27410
+155,1393,1663,670,37320
+156,1450,1734,380,71120
+157,1613,1921,1200,72800
+158,1408,1696,350,34410
+159,775,932,1090,42530
+160,1275,1534,1230,54300
+161,1740,2078,680,50780
+162,1372,1657,580,45020
+163,1414,1723,680,69600
+164,2044,2474,340,80340
+165,1823,2176,700,37810
+166,955,1133,580,46140
+167,1465,1763,680,99570
+168,1331,1606,630,38650
+169,1232,1487,860,49800
+170,1481,1765,490,69910
+171,1343,1599,870,44910
+172,1539,1837,990,78470
+173,1007,1207,670,47460
+174,1762,2145,490,33460
+175,1527,1832,580,44090
+176,1356,1619,700,42620
+177,1536,1848,670,69450
+178,1605,1902,390,73120
+179,1704,2032,590,48300
+180,1626,1941,1350,58090
+181,1612,1939,840,74250
+182,1174,1396,1100,40930
+183,1923,2339,950,70930
+184,1702,2053,950,64670
+185,1398,1692,650,77420
+186,1437,1717,230,32330
+187,1524,1796,1060,41080
+188,1660,1985,1180,42860
+189,1302,1569,710,68450
+190,1666,2000,480,39730
+191,1391,1649,810,83750
+192,1778,2148,1140,69940
+193,1462,1770,1070,67710
+194,1751,2115,790,67360
+195,1652,1982,690,52460
+196,1841,2215,610,88760
+197,1496,1791,1240,67030
+198,1504,1827,840,78230
+199,1524,1808,460,62270
+200,1148,1371,940,49760
+201,1468,1744,590,73660
+202,1310,1558,890,72320
+203,1321,1579,770,68890
+204,992,1192,900,34180
+205,1540,1857,1020,58260
+206,1807,2149,910,38120
+207,1526,1853,660,49070
+208,1406,1677,480,61660
+209,1703,2055,1080,37830
+210,1575,1872,690,52270
+211,1309,1572,510,52280
+212,1488,1807,1030,70810
+213,1658,1988,370,71530
+214,1863,2245,640,77260
+215,1458,1725,750,75550
+216,1604,1909,370,33730
+217,1575,1899,840,66270
+218,1525,1829,840,55820
+219,1451,1737,890,68430
+220,1390,1687,620,73990
+221,1442,1742,310,62800
+222,1620,1922,550,33740
+223,1251,1527,380,63830
+224,1318,1606,1200,24410
+225,1647,1962,800,70020
+226,1829,2175,870,92240
+227,1852,2227,1220,68230
+228,1699,2053,1080,81870
+229,1325,1595,540,73860
+230,1350,1634,880,77120
+231,1347,1628,120,72350
+232,1397,1661,1410,49160
+233,1245,1499,570,45650
+234,1366,1649,940,52780
+235,1378,1658,760,90960
+236,1767,2110,1200,64950
+237,1184,1434,670,47230
+238,1257,1505,950,83250
+239,1863,2247,480,51950
+240,1881,2244,920,66030
+241,1329,1609,1150,68590
+242,1539,1848,750,47140
+243,1557,1861,370,69940
+244,2007,2397,610,65890
+245,1185,1418,1150,89310
+246,1657,2003,1070,58540
+247,1294,1539,790,78130
+248,1296,1559,1070,92300
+249,1733,2097,730,56170
+250,1641,1976,620,46050
+251,1373,1648,530,43390
+252,1550,1845,700,61750
+253,1583,1907,680,21830
+254,1428,1719,1060,39800
+255,1604,1925,670,54370
+256,1439,1735,400,62470
+257,1648,2003,910,82930
+258,1025,1231,760,63720
+259,2001,2394,540,79180
+260,1145,1370,350,38210
+261,1174,1426,980,25950
+262,913,1106,860,56610
+263,1199,1433,1020,73710
+264,1875,2254,1120,70400
+265,1153,1397,1020,50440
+266,1240,1492,940,66840
+267,1381,1660,970,50170
+268,1701,2030,830,60140
+269,1206,1456,920,37130
+270,1476,1777,660,42890
+271,1189,1439,780,26220
+272,1837,2220,340,50840
+273,1319,1571,1190,25630
+274,1617,1901,490,60770
+275,1631,1967,1090,69600
+276,1517,1805,1040,41740
+277,1764,2109,1210,50130
+278,1572,1869,1030,21750
+279,1855,2197,1170,80490
+280,1327,1571,730,34020
+281,1270,1515,720,60240
+282,1734,2073,500,39460
+283,1533,1848,1070,56440
+284,1390,1646,800,46840
+285,1856,2216,1020,64820
+286,1000,1215,1070,52520
+287,1313,1586,420,45940
+288,1494,1799,510,38970
+289,1386,1674,1210,58610
+290,1979,2364,660,30810
+291,1057,1264,360,47730
+292,902,1093,1210,64640
+293,1347,1622,560,44860
+294,1314,1576,360,55660
+295,1513,1803,970,57530
+296,1305,1548,480,75200
+297,1180,1436,690,37330
+298,1142,1352,710,35280
+299,1471,1768,780,70610
+300,1075,1288,630,49720
+301,1578,1885,220,68850
+302,1585,1916,1110,50740
+303,1391,1648,720,77070
+304,1577,1892,560,74730
+305,1092,1314,600,76530
+306,1375,1681,440,68900
+307,1523,1813,520,44960
+308,1373,1654,410,41490
+309,1550,1871,590,74320
+310,1614,1946,740,73800
+311,1566,1889,610,56400
+312,2019,2396,540,71570
+313,1494,1806,1450,43640
+314,1659,2008,620,35120
+315,1766,2131,340,58670
+316,1293,1554,970,75800
+317,1375,1659,1080,76640
+318,1236,1484,560,31890
+319,1332,1586,630,61670
+320,1513,1825,980,75950
+321,1208,1459,930,41490
+322,1190,1429,470,66170
+323,1448,1734,680,37980
+324,1771,2147,430,62710
+325,1365,1645,830,60470
+326,1510,1810,950,35230
+327,1458,1736,870,48550
+328,1808,2157,730,56810
+329,1615,1954,760,41080
+330,1640,1948,960,51270
+331,1060,1273,860,57500
+332,1633,1968,330,81470
+333,1222,1473,630,49570
+334,1619,1957,1280,45580
+335,1624,1973,1440,44660
+336,1887,2278,570,76240
+337,1320,1583,540,43720
+338,1450,1750,480,46700
+339,1455,1764,390,84690
+340,966,1172,900,85470
+341,1922,2290,290,80410
+342,1678,1999,740,46650
+343,1638,1952,690,81840
+344,1145,1375,950,63590
+345,2004,2390,930,50130
+346,1954,2378,810,45820
+347,1577,1879,760,86710
+348,1766,2138,580,49980
+349,1362,1634,770,82940
+350,1886,2228,1530,40350
+351,1291,1546,420,93950
+352,1584,1897,1210,47310
+353,1397,1686,850,21300
+354,1445,1709,1340,62180
+355,1433,1707,1160,61460
+356,1269,1511,500,54360
+357,1798,2134,820,72050
+358,1514,1822,670,48090
+359,1015,1216,460,27310
+360,1495,1799,950,57160
+361,1759,2095,980,34190
+362,1219,1468,850,35600
+363,1571,1877,580,54670
+364,1404,1670,620,76730
+365,1124,1369,650,63540
+366,1514,1837,1130,36690
+367,1207,1476,720,87370
+368,1484,1774,940,59800
+369,1398,1678,920,48030
+370,1769,2112,660,96650
+371,1111,1322,610,65500
+372,1078,1305,1190,55530
+373,1876,2254,1340,21650
+374,1909,2306,820,31940
+375,1940,2343,1130,84690
+376,1391,1683,890,68390
+377,1496,1774,810,75490
+378,1412,1699,680,39200
+379,1121,1345,320,85670
+380,1691,2026,700,60530
+381,1599,1946,940,78090
+382,1208,1467,910,50720
+383,1454,1737,870,23090
+384,1555,1881,1260,91360
+385,1554,1852,440,48120
+386,1491,1800,980,75620
+387,1415,1697,1200,39420
+388,1487,1801,890,51130
+389,1339,1589,1050,33890
+390,1320,1562,610,87170
+391,1509,1799,960,38600
+392,1406,1680,860,60980
+393,1264,1502,800,79410
+394,1905,2280,1060,82350
+395,1209,1464,600,36740
+396,1546,1829,380,27720
+397,1689,2044,1140,32260
+398,1153,1381,730,53270
+399,2063,2493,810,51480
+400,1848,2254,1000,59970
+401,1718,2056,1220,83600
+402,1480,1773,360,63020
+403,1439,1724,900,50920
+404,1576,1896,750,56450
+405,1948,2374,930,89540
+406,1613,1893,1180,46030
+407,896,1059,870,75110
+408,1625,1943,680,74520
+409,1303,1587,1310,102310
+410,1340,1605,1000,53400
+411,1410,1704,1130,59760
+412,1432,1719,990,49540
+413,1891,2280,360,51560
+414,1322,1583,720,49510
+415,1378,1670,950,58610
+416,1462,1732,840,68260
+417,1440,1733,1120,65310
+418,1421,1724,920,52090
+419,1280,1530,1240,43860
+420,1431,1710,840,74170
+421,1161,1404,430,58380
+422,1175,1405,810,91200
+423,1395,1662,920,90940
+424,1443,1755,880,49330
+425,1247,1523,1350,53500
+426,1788,2133,1000,54590
+427,1138,1375,1220,57450
+428,1709,2042,430,33240
+429,1777,2145,520,80790
+430,1612,1918,580,61000
+431,1618,1943,460,47620
+432,1311,1571,470,72090
+433,1365,1638,680,102920
+434,1249,1503,950,61970
+435,1373,1635,840,61040
+436,1536,1836,990,52060
+437,1744,2101,520,69570
+438,1513,1820,520,66020
+439,1297,1561,1070,40000
+440,1908,2304,990,79500
+441,1721,2076,710,76300
+442,1243,1491,430,69030
+443,1472,1766,1290,57140
+444,1307,1570,1080,41710
+445,1628,1959,890,71480
+446,1556,1869,1000,33010
+447,1179,1428,1290,74570
+448,1768,2123,860,49590
+449,1378,1656,1010,73170
+450,1685,2015,1160,79220
+451,1474,1759,880,75880
+452,1794,2137,670,67610
+453,1086,1291,930,69090
+454,1808,2154,990,35220
+455,1501,1790,450,53940
+456,1353,1598,690,56660
+457,1455,1757,650,67520
+458,1165,1411,1020,38620
+459,1332,1610,880,38890
+460,1396,1668,760,79270
+461,1513,1821,690,42880
+462,1618,1940,630,44240
+463,1845,2233,370,43190
+464,1172,1411,460,74550
+465,1436,1737,770,57090
+466,1738,2065,750,56480
+467,2229,2667,660,87410
+468,1490,1783,730,81370
+469,1060,1279,670,97360
+470,2015,2436,680,77960
+471,1611,1919,960,71240
+472,1187,1417,1230,58940
+473,1430,1690,800,78950
+474,1543,1840,450,36380
+475,1836,2195,940,45160
+476,1463,1764,1060,69050
+477,1213,1462,560,56830
+478,1244,1480,860,93530
+479,1745,2108,730,46920
+480,933,1121,940,55990
+481,1764,2132,920,40840
+482,1675,2002,1050,64990
+483,1688,2046,380,53550
+484,1842,2204,930,51320
+485,1316,1597,980,36560
+486,1440,1719,580,66050
+487,1760,2111,680,52400
+488,1323,1571,850,27970
+489,1230,1466,730,67100
+490,1540,1838,570,43710
+491,1167,1388,620,38600
+492,1429,1695,890,53890
+493,1491,1770,800,52610
+494,1313,1574,920,43130
+495,1609,1943,920,40300
+496,1109,1342,760,49750
+497,1207,1440,500,43840
+498,902,1087,680,56820
+499,1191,1422,770,36350
+500,1335,1601,460,50820
+501,1382,1660,1070,83720
+502,1588,1906,450,46970
+503,1918,2284,310,78020
+504,1484,1774,880,45080
+505,1334,1607,370,55160
+506,1556,1846,760,72020
+507,1784,2142,950,64010
+508,1244,1477,890,27840
+509,1496,1787,800,58070
+510,1719,2058,700,51760
+511,1678,2022,1050,66050
+512,1247,1490,330,65750
+513,1191,1421,980,65820
+514,1832,2208,1090,46760
+515,1271,1523,1140,50940
+516,1735,2084,820,56440
+517,1627,1948,890,32610
+518,1351,1616,650,62770
+519,1520,1817,850,63600
+520,1490,1788,360,45840
+521,1777,2117,780,38280
+522,1688,2037,590,50960
+523,1537,1836,670,39480
+524,1622,1968,340,69610
+525,1148,1384,730,47800
+526,1001,1194,1210,44890
+527,1857,2236,1280,67420
+528,1552,1869,710,78870
+529,1700,2064,940,70310
+530,1554,1844,670,38530
+531,1482,1777,800,77570
+532,1275,1517,790,59920
+533,1642,1981,720,54450
+534,1381,1633,1270,50250
+535,1381,1634,930,30790
+536,1057,1262,1490,35420
+537,1192,1445,810,43470
+538,1601,1920,600,61000
+539,1622,1968,210,64780
+540,1607,1909,460,39030
+541,2214,2647,740,65900
+542,1633,1936,1320,46050
+543,1546,1845,760,59070
+544,1475,1753,920,44670
+545,1270,1519,920,58390
+546,1185,1420,880,80370
+547,1614,1938,1110,53230
+548,1141,1353,1370,72000
+549,1244,1481,410,84040
+550,869,1050,850,52540
+551,2049,2465,720,63510
+552,1883,2262,570,42240
+553,1526,1842,690,39580
+554,1165,1390,1220,54610
+555,1832,2185,840,87330
+556,1723,2072,560,88410
+557,932,1138,820,89760
+558,1137,1374,700,101780
+559,1231,1472,810,70290
+560,1237,1512,1070,88210
+561,1371,1650,540,87160
+562,1767,2158,530,41540
+563,1748,2092,580,49170
+564,1212,1440,500,63950
+565,1466,1743,1200,70810
+566,1152,1386,980,49590
+567,1439,1703,1000,67290
+568,2026,2400,720,51240
+569,1772,2146,1030,48540
+570,1511,1822,420,72410
+571,1199,1461,1070,54370
+572,1834,2184,830,94460
+573,1143,1375,940,85160
+574,1494,1794,550,52130
+575,1770,2131,1140,54650
+576,1455,1747,750,69320
+577,1141,1372,620,51480
+578,1586,1886,660,50060
+579,1701,2034,660,62180
+580,1860,2246,410,79780
+581,1167,1406,440,42860
+582,1424,1716,630,54410
+583,1710,2053,730,69390
+584,1408,1708,220,42810
+585,1517,1831,610,30840
+586,1227,1476,720,56260
+587,1609,1930,740,76470
+588,1553,1831,740,35680
+589,1814,2174,770,90070
+590,1240,1493,590,33120
+591,1206,1437,1330,54060
+592,1847,2186,910,75120
+593,1009,1202,330,41600
+594,1624,1946,870,20270
+595,1612,1931,790,60060
+596,1498,1805,1270,82270
+597,946,1125,590,29170
+598,1563,1872,1080,68420
+599,1664,2016,830,59130
+600,1619,1947,910,74330
+601,1433,1722,830,77080
+602,1241,1489,1380,76250
+603,1429,1720,1180,59540
+604,1241,1488,770,54690
+605,1078,1306,680,84360
+606,1690,2065,910,51420
+607,1289,1536,540,65120
+608,1581,1894,760,49380
+609,1608,1945,760,37830
+610,1344,1608,730,35980
+611,1513,1804,430,69190
+612,1529,1839,1000,50590
+613,1677,2014,660,60800
+614,1015,1229,930,31180
+615,1438,1751,760,77790
+616,1426,1718,370,47570
+617,1412,1701,630,69130
+618,1622,1944,360,75970
+619,1503,1791,630,68350
+620,1501,1789,670,41680
+621,1971,2342,690,86560
+622,1383,1687,830,81390
+623,1371,1635,720,50730
+624,1508,1823,520,71290
+625,1057,1284,750,70110
+626,1411,1680,1070,61590
+627,1466,1746,590,69370
+628,1545,1888,600,67110
+629,2044,2408,380,82020
+630,1887,2264,830,62050
+631,1505,1836,940,61730
+632,1422,1722,560,58660
+633,1564,1869,1030,53370
+634,1510,1810,730,39700
+635,1568,1920,890,53750
+636,1933,2338,1140,44730
+637,1501,1822,590,49350
+638,1593,1911,580,43340
+639,1812,2189,310,78090
+640,1580,1895,720,54950
+641,1440,1749,490,75530
+642,1100,1331,1010,57330
+643,1534,1841,680,87930
+644,1299,1555,1020,56850
+645,1767,2121,1050,78430
+646,1368,1649,740,63660
+647,1393,1670,410,62960
+648,1327,1590,770,81870
+649,1514,1794,1400,54820
+650,1989,2414,860,116320
+651,1334,1584,840,57200
+652,1533,1817,950,84360
+653,1809,2145,940,36530
+654,1607,1933,930,81260
+655,1165,1387,1060,82350
+656,1193,1430,560,80830
+657,1709,2065,670,30610
+658,1525,1839,540,51310
+659,1348,1623,1010,72940
+660,1132,1366,1340,52450
+661,1667,2020,980,66070
+662,1427,1720,630,43190
+663,1211,1447,1110,40730
+664,1717,2048,700,78530
+665,1766,2111,580,94690
+666,1086,1299,1050,44400
+667,1410,1692,790,73800
+668,1476,1760,600,37390
+669,1068,1278,440,64120
+670,1485,1785,1340,66160
+671,1461,1739,1250,22310
+672,1685,2010,990,62380
+673,1624,1958,290,63850
+674,1658,2000,350,36210
+675,1427,1677,210,54590
+676,1755,2072,810,69610
+677,1211,1472,790,65390
+678,1591,1896,780,78130
+679,1797,2126,730,55710
+680,1519,1823,1040,69210
+681,1637,1958,760,59940
+682,1451,1750,570,72550
+683,1203,1446,620,44260
+684,1884,2262,310,56910
+685,1540,1820,310,82390
+686,1121,1332,790,54590
+687,1307,1562,490,69990
+688,1475,1775,230,72740
+689,1160,1401,900,35360
+690,1078,1276,640,94370
+691,1191,1436,840,43520
+692,1317,1569,780,36000
+693,1548,1858,480,99480
+694,1560,1883,1040,83220
+695,1297,1529,870,52940
+696,1645,1958,530,93360
+697,1225,1455,750,73590
+698,1421,1704,840,53840
+699,1655,1956,800,47350
+700,1615,1928,660,65080
+701,1872,2262,560,62050
+702,1317,1581,910,30020
+703,1434,1729,480,49510
+704,1791,2167,700,64320
+705,932,1120,660,35590
+706,1609,1924,1170,63050
+707,1495,1793,1020,65300
+708,1769,2153,580,69560
+709,1693,2032,610,41910
+710,1247,1497,590,28330
+711,1502,1815,190,55980
+712,1360,1612,490,61080
+713,1542,1844,680,51380
+714,1631,1947,670,84410
+715,1246,1482,1070,60680
+716,1990,2384,1110,64690
+717,967,1154,560,45780
+718,1582,1894,1100,41800
+719,1430,1743,970,53230
+720,1827,2160,930,36160
+721,1118,1338,1040,40450
+722,1766,2109,1120,57910
+723,1799,2173,910,36280
+724,1167,1411,440,39190
+725,1493,1795,530,62380
+726,1445,1734,900,21470
+727,1033,1237,740,34610
+728,1440,1711,1020,88120
+729,1487,1773,970,59190
+730,1854,2205,890,36290
+731,1748,2086,550,53760
+732,1937,2310,520,66300
+733,1641,1999,950,93000
+734,1659,1999,650,65660
+735,1743,2061,860,81930
+736,1449,1733,320,60060
+737,1098,1309,860,59530
+738,1121,1351,900,46380
+739,1526,1858,550,76200
+740,1358,1645,770,56860
+741,1336,1616,710,86620
+742,1502,1802,840,49730
+743,1534,1858,860,88370
+744,1418,1699,870,49160
+745,854,1018,660,77740
+746,1450,1728,930,38560
+747,1474,1776,1020,51990
+748,1524,1819,1190,39970
+749,1361,1638,1140,46040
+750,1398,1683,490,49500
+751,1085,1308,1170,76670
+752,1660,1979,480,75800
+753,1648,2017,930,81720
+754,1453,1749,890,58440
+755,1323,1591,680,85720
+756,1385,1643,740,70940
+757,1250,1506,990,62420
+758,1389,1683,680,56880
+759,1486,1758,820,101820
+760,1655,1993,440,86890
+761,1645,1963,900,47300
+762,1464,1771,1080,31270
+763,1197,1428,830,65410
+764,1878,2264,310,54200
+765,1150,1378,730,67390
+766,1562,1881,740,54530
+767,1596,1939,960,79760
+768,1119,1345,790,78060
+769,1116,1347,700,74080
+770,1934,2349,750,52990
+771,1299,1540,590,70580
+772,1417,1689,570,34310
+773,1235,1503,660,74160
+774,1497,1815,700,59190
+775,1430,1704,1070,43370
+776,1537,1877,660,17670
+777,1444,1742,840,56710
+778,1477,1798,850,59820
+779,1041,1246,600,36190
+780,1226,1472,710,60440
+781,1489,1783,450,75300
+782,1549,1871,740,74080
+783,1073,1280,1240,60440
+784,1473,1785,570,80720
+785,2013,2396,580,47060
+786,1975,2368,450,86830
+787,1561,1877,790,56790
+788,1427,1723,1040,67090
+789,1441,1747,670,44370
+790,1275,1548,370,82970
+791,1574,1876,620,56230
+792,1511,1791,1010,53760
+793,1428,1713,550,55390
+794,1388,1672,800,73500
+795,1057,1280,610,41050
+796,1440,1747,1090,67320
+797,1349,1610,700,65890
+798,1536,1808,830,56380
+799,2019,2420,850,85670
+800,1236,1508,1260,70830
+801,1436,1715,1030,48180
+802,1862,2248,1160,51910
+803,1200,1442,880,44320
+804,1360,1650,420,58940
+805,1722,2078,770,73610
+806,1577,1902,910,54060
+807,1850,2214,1110,85000
+808,1447,1730,510,49030
+809,1496,1800,780,63300
+810,1679,2008,790,84300
+811,994,1194,1090,81390
+812,1354,1635,1270,95900
+813,1597,1918,1260,71830
+814,1873,2252,330,79310
+815,1218,1459,540,87890
+816,1458,1746,720,48610
+817,1546,1860,670,73160
+818,1608,1962,770,36280
+819,1822,2160,860,49720
+820,1716,2038,410,44400
+821,1072,1296,900,47590
+822,1330,1604,480,51460
+823,1588,1892,540,57750
+824,1425,1733,760,66000
+825,1778,2133,280,45950
+826,1363,1630,1120,53900
+827,1609,1928,160,37920
+828,1671,2024,620,63100
+829,1379,1636,440,36770
+830,1218,1452,870,43910
+831,1724,2101,900,66390
+832,986,1179,710,59160
+833,1330,1606,590,38510
+834,1437,1725,910,46220
+835,1327,1609,1320,41500
+836,1651,2009,1000,58160
+837,1211,1462,670,38530
+838,1916,2277,610,55880
+839,1638,1937,1050,70940
+840,1172,1413,480,53940
+841,1350,1606,770,43030
+842,1528,1843,340,59820
+843,1305,1557,580,55500
+844,1463,1751,900,49990
+845,1409,1727,700,42980
+846,1419,1743,860,65970
+847,1535,1819,540,59290
+848,1474,1745,970,63020
+849,919,1099,1560,73810
+850,2067,2492,790,70230
+851,1977,2362,1020,59950
+852,1293,1558,790,78100
+853,1477,1790,880,16370
+854,1582,1906,550,92640
+855,1481,1789,550,63540
+856,1214,1455,950,87220
+857,1206,1460,810,41990
+858,1653,1982,390,79410
+859,1152,1393,860,54380
+860,1458,1757,850,58600
+861,1249,1510,660,48950
+862,1939,2333,830,40670
+863,1591,1919,640,52340
+864,1180,1397,750,39140
+865,1846,2195,1170,41090
+866,780,951,790,25600
+867,1565,1854,900,100900
+868,1648,1959,370,77080
+869,1775,2104,980,105150
+870,1439,1732,1170,80580
+871,1487,1776,800,46230
+872,1800,2158,1100,98260
+873,1690,2024,1070,75930
+874,1209,1452,830,52050
+875,1859,2222,1210,87000
+876,1691,2023,540,60270
+877,1259,1493,100,88270
+878,1771,2138,820,57820
+879,1205,1468,1210,61210
+880,1792,2131,810,76420
+881,1263,1516,780,70980
+882,1344,1605,1160,76740
+883,1819,2187,590,47920
+884,1357,1625,1140,52160
+885,1396,1673,690,32740
+886,1118,1337,560,72270
+887,1655,1986,1150,77430
+888,1156,1398,140,92370
+889,1451,1734,670,34880
+890,1539,1829,650,46580
+891,1549,1851,1220,70620
+892,1582,1910,1080,66390
+893,1387,1663,850,82080
+894,1200,1436,1060,76440
+895,1299,1560,770,96610
+896,1174,1429,1110,54340

lab_2/lab2.ipynb

@@ -0,0 +1,599 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Lab2 Pibd-31 Malafeev**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "*Загрузка трёх других датасетов(не своего варианта)*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "df = pd.read_csv(\".//datasetlab2//kc_house_data.csv\", sep=\",\")\n",
+    "df2 = pd.read_csv(\".//datasetlab2//Stores.csv\", sep=\",\")\n",
+    "df3 = pd.read_csv(\".//datasetlab2//Forbes Billionaires.csv\", sep=\",\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Далее будут выполнены в Markdown пукнты лабораторной 2-8 с пометкой каждого пункта."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "2.Проблемной областью явлются: датасет stores.csv - магазины, kc_house_data.csv - датасет продажи домов и Forber Billionares.csv - датасет миллионеров."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "3.Объектами наблюдениями явлются магазины, дома и миллионеры. Связи между объектами нет, единственная схожесть - магазин и дом являются зданиями."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "4.Датасет миллионеров нужны например для сайта forbes - чтобы составить тир лист. В целом, другие датасеты тоже подходят для составления тир листа)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "5.Технический проект - тир лист, на входе датасет"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "6.Пункт будем выполнять в коде, оставлю к каждому комменты:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "id               0\n",
+      "date             0\n",
+      "price            0\n",
+      "bedrooms         0\n",
+      "bathrooms        0\n",
+      "sqft_living      0\n",
+      "sqft_lot         0\n",
+      "floors           0\n",
+      "waterfront       0\n",
+      "view             0\n",
+      "condition        0\n",
+      "grade            0\n",
+      "sqft_above       0\n",
+      "sqft_basement    0\n",
+      "yr_built         0\n",
+      "yr_renovated     0\n",
+      "zipcode          0\n",
+      "lat              0\n",
+      "long             0\n",
+      "sqft_living15    0\n",
+      "sqft_lot15       0\n",
+      "dtype: int64\n",
+      "Store ID                0\n",
+      "Store_Area              0\n",
+      "Items_Available         0\n",
+      "Daily_Customer_Count    0\n",
+      "Store_Sales             0\n",
+      "dtype: int64\n",
+      "Rank        0\n",
+      "Name        0\n",
+      "Networth    0\n",
+      "Age         0\n",
+      "Country     0\n",
+      "Source      0\n",
+      "Industry    0\n",
+      "dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Проверка на пропущенные значения\n",
+    "print(df.isnull().sum())\n",
+    "print(df2.isnull().sum())\n",
+    "print(df3.isnull().sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                 id         price      bedrooms     bathrooms   sqft_living  \\\n",
+      "count  2.161300e+04  2.161300e+04  21613.000000  21613.000000  21613.000000   \n",
+      "mean   4.580302e+09  5.400881e+05      3.370842      2.114757   2079.899736   \n",
+      "std    2.876566e+09  3.671272e+05      0.930062      0.770163    918.440897   \n",
+      "min    1.000102e+06  7.500000e+04      0.000000      0.000000    290.000000   \n",
+      "25%    2.123049e+09  3.219500e+05      3.000000      1.750000   1427.000000   \n",
+      "50%    3.904930e+09  4.500000e+05      3.000000      2.250000   1910.000000   \n",
+      "75%    7.308900e+09  6.450000e+05      4.000000      2.500000   2550.000000   \n",
+      "max    9.900000e+09  7.700000e+06     33.000000      8.000000  13540.000000   \n",
+      "\n",
+      "           sqft_lot        floors    waterfront          view     condition  \\\n",
+      "count  2.161300e+04  21613.000000  21613.000000  21613.000000  21613.000000   \n",
+      "mean   1.510697e+04      1.494309      0.007542      0.234303      3.409430   \n",
+      "std    4.142051e+04      0.539989      0.086517      0.766318      0.650743   \n",
+      "min    5.200000e+02      1.000000      0.000000      0.000000      1.000000   \n",
+      "25%    5.040000e+03      1.000000      0.000000      0.000000      3.000000   \n",
+      "50%    7.618000e+03      1.500000      0.000000      0.000000      3.000000   \n",
+      "75%    1.068800e+04      2.000000      0.000000      0.000000      4.000000   \n",
+      "max    1.651359e+06      3.500000      1.000000      4.000000      5.000000   \n",
+      "\n",
+      "              grade    sqft_above  sqft_basement      yr_built  yr_renovated  \\\n",
+      "count  21613.000000  21613.000000   21613.000000  21613.000000  21613.000000   \n",
+      "mean       7.656873   1788.390691     291.509045   1971.005136     84.402258   \n",
+      "std        1.175459    828.090978     442.575043     29.373411    401.679240   \n",
+      "min        1.000000    290.000000       0.000000   1900.000000      0.000000   \n",
+      "25%        7.000000   1190.000000       0.000000   1951.000000      0.000000   \n",
+      "50%        7.000000   1560.000000       0.000000   1975.000000      0.000000   \n",
+      "75%        8.000000   2210.000000     560.000000   1997.000000      0.000000   \n",
+      "max       13.000000   9410.000000    4820.000000   2015.000000   2015.000000   \n",
+      "\n",
+      "            zipcode           lat          long  sqft_living15     sqft_lot15  \n",
+      "count  21613.000000  21613.000000  21613.000000   21613.000000   21613.000000  \n",
+      "mean   98077.939805     47.560053   -122.213896    1986.552492   12768.455652  \n",
+      "std       53.505026      0.138564      0.140828     685.391304   27304.179631  \n",
+      "min    98001.000000     47.155900   -122.519000     399.000000     651.000000  \n",
+      "25%    98033.000000     47.471000   -122.328000    1490.000000    5100.000000  \n",
+      "50%    98065.000000     47.571800   -122.230000    1840.000000    7620.000000  \n",
+      "75%    98118.000000     47.678000   -122.125000    2360.000000   10083.000000  \n",
+      "max    98199.000000     47.777600   -121.315000    6210.000000  871200.000000  \n",
+      "        Store ID    Store_Area  Items_Available  Daily_Customer_Count  \\\n",
+      "count  896.000000   896.000000       896.000000            896.000000   \n",
+      "mean   448.500000  1485.409598      1782.035714            786.350446   \n",
+      "std    258.797218   250.237011       299.872053            265.389281   \n",
+      "min      1.000000   775.000000       932.000000             10.000000   \n",
+      "25%    224.750000  1316.750000      1575.500000            600.000000   \n",
+      "50%    448.500000  1477.000000      1773.500000            780.000000   \n",
+      "75%    672.250000  1653.500000      1982.750000            970.000000   \n",
+      "max    896.000000  2229.000000      2667.000000           1560.000000   \n",
+      "\n",
+      "         Store_Sales  \n",
+      "count     896.000000  \n",
+      "mean    59351.305804  \n",
+      "std     17190.741895  \n",
+      "min     14920.000000  \n",
+      "25%     46530.000000  \n",
+      "50%     58605.000000  \n",
+      "75%     71872.500000  \n",
+      "max    116320.000000  \n",
+      "             Rank      Networth          Age\n",
+      "count  2600.000000  2600.000000  2600.000000\n",
+      "mean   1269.570769     4.860750    64.271923\n",
+      "std     728.146364    10.659671    13.220607\n",
+      "min       1.000000     1.000000    19.000000\n",
+      "25%     637.000000     1.500000    55.000000\n",
+      "50%    1292.000000     2.400000    64.000000\n",
+      "75%    1929.000000     4.500000    74.000000\n",
+      "max    2578.000000   219.000000   100.000000\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Статистика по числовым данным для выявления аномальных распределений\n",
+    "print(df.describe())\n",
+    "print(df2.describe())\n",
+    "print(df3.describe())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "7.По перым трём строкам кода, т.е после проверки на пропущенные значения выявлено, что их нет. А дальше я обнаружил аномалию: в датасете миллионеров есть столбец networth - чистое количество денег во всех формах ( в миллиардах ), в этом солбце минимальное значение является единицей, медиана в районе 2.4, а максимальное - 219. В ЭТОМ СТОЛБЦЕ АНОМАЛИЯ"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "8.Наши датасеты довольно информационные. Например у миллионер датасета можно посмотреть фио, сколько денег, что он сделал. Датасет по продаже домов гораздо информационнее, является лидером по наполненности и соответствует реальности. А вот датасет магазинов слабоват, можно например добавить: количество филлиалов, работников, прибыль"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "9.Возьмём датасет магазинов, будем удалять столбцы, где площадь ниже 1500 (по тз надо)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     Store ID   Store_Area  Items_Available  Daily_Customer_Count  Store_Sales\n",
+      "0            1        1659             1961                   530        66490\n",
+      "4            5        1770             2111                   450        46620\n",
+      "6            7        1542             1858                  1030        72240\n",
+      "11          12        1751             2098                   720        57620\n",
+      "12          13        1746             2064                  1050        60470\n",
+      "..         ...         ...              ...                   ...          ...\n",
+      "882        883        1819             2187                   590        47920\n",
+      "886        887        1655             1986                  1150        77430\n",
+      "889        890        1539             1829                   650        46580\n",
+      "890        891        1549             1851                  1220        70620\n",
+      "891        892        1582             1910                  1080        66390\n",
+      "\n",
+      "[415 rows x 5 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "df2_filtered = df2[df2['Store_Area'] >= 1500]\n",
+    "print(df2_filtered)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Теперь в датасете магазнов price заменим у всех на константное значение - 1 500 000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "               id             date    price  bedrooms  bathrooms  sqft_living  \\\n",
+      "0      7129300520  20141013T000000  1500000         3       1.00         1180   \n",
+      "1      6414100192  20141209T000000  1500000         3       2.25         2570   \n",
+      "2      5631500400  20150225T000000  1500000         2       1.00          770   \n",
+      "3      2487200875  20141209T000000  1500000         4       3.00         1960   \n",
+      "4      1954400510  20150218T000000  1500000         3       2.00         1680   \n",
+      "...           ...              ...      ...       ...        ...          ...   \n",
+      "21608   263000018  20140521T000000  1500000         3       2.50         1530   \n",
+      "21609  6600060120  20150223T000000  1500000         4       2.50         2310   \n",
+      "21610  1523300141  20140623T000000  1500000         2       0.75         1020   \n",
+      "21611   291310100  20150116T000000  1500000         3       2.50         1600   \n",
+      "21612  1523300157  20141015T000000  1500000         2       0.75         1020   \n",
+      "\n",
+      "       sqft_lot  floors  waterfront  view  ...  grade  sqft_above  \\\n",
+      "0          5650     1.0           0     0  ...      7        1180   \n",
+      "1          7242     2.0           0     0  ...      7        2170   \n",
+      "2         10000     1.0           0     0  ...      6         770   \n",
+      "3          5000     1.0           0     0  ...      7        1050   \n",
+      "4          8080     1.0           0     0  ...      8        1680   \n",
+      "...         ...     ...         ...   ...  ...    ...         ...   \n",
+      "21608      1131     3.0           0     0  ...      8        1530   \n",
+      "21609      5813     2.0           0     0  ...      8        2310   \n",
+      "21610      1350     2.0           0     0  ...      7        1020   \n",
+      "21611      2388     2.0           0     0  ...      8        1600   \n",
+      "21612      1076     2.0           0     0  ...      7        1020   \n",
+      "\n",
+      "       sqft_basement  yr_built  yr_renovated  zipcode      lat     long  \\\n",
+      "0                  0      1955             0    98178  47.5112 -122.257   \n",
+      "1                400      1951          1991    98125  47.7210 -122.319   \n",
+      "2                  0      1933             0    98028  47.7379 -122.233   \n",
+      "3                910      1965             0    98136  47.5208 -122.393   \n",
+      "4                  0      1987             0    98074  47.6168 -122.045   \n",
+      "...              ...       ...           ...      ...      ...      ...   \n",
+      "21608              0      2009             0    98103  47.6993 -122.346   \n",
+      "21609              0      2014             0    98146  47.5107 -122.362   \n",
+      "21610              0      2009             0    98144  47.5944 -122.299   \n",
+      "21611              0      2004             0    98027  47.5345 -122.069   \n",
+      "21612              0      2008             0    98144  47.5941 -122.299   \n",
+      "\n",
+      "       sqft_living15  sqft_lot15  \n",
+      "0               1340        5650  \n",
+      "1               1690        7639  \n",
+      "2               2720        8062  \n",
+      "3               1360        5000  \n",
+      "4               1800        7503  \n",
+      "...              ...         ...  \n",
+      "21608           1530        1509  \n",
+      "21609           1830        7200  \n",
+      "21610           1020        2007  \n",
+      "21611           1410        1287  \n",
+      "21612           1020        1357  \n",
+      "\n",
+      "[21613 rows x 21 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "df['price'] = 1500000\n",
+    "print(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Теперь у миллионеров в networth подставим среднее по  столбцу:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "      Networth\n",
+      "0      4.86075\n",
+      "1      4.86075\n",
+      "2      4.86075\n",
+      "3      4.86075\n",
+      "4      4.86075\n",
+      "...        ...\n",
+      "2595   4.86075\n",
+      "2596   4.86075\n",
+      "2597   4.86075\n",
+      "2598   4.86075\n",
+      "2599   4.86075\n",
+      "\n",
+      "[2600 rows x 1 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "networth_mean = df3['Networth'].mean()\n",
+    "df3['Networth'] = networth_mean\n",
+    "print(df3[['Networth']])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "10.КОД"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train df: (15129, 21), Validation df: (3242, 21), Test df: (3242, 21)\n",
+      "Train df2: (627, 5), Validation df2: (134, 5), Test df2: (135, 5)\n",
+      "Train df3: (1820, 7), Validation df3: (390, 7), Test df3: (390, 7)\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "train_df, temp_df = train_test_split(df, test_size=0.3, random_state=42)\n",
+    "val_df, test_df = train_test_split(temp_df, test_size=0.5, random_state=42) \n",
+    "\n",
+    "train_df2, temp_df2 = train_test_split(df2, test_size=0.3, random_state=42)\n",
+    "val_df2, test_df2 = train_test_split(temp_df2, test_size=0.5, random_state=42)\n",
+    "\n",
+    "train_df3, temp_df3 = train_test_split(df3, test_size=0.3, random_state=42)\n",
+    "val_df3, test_df3 = train_test_split(temp_df3, test_size=0.5, random_state=42)\n",
+    "print(f\"Train df: {train_df.shape}, Validation df: {val_df.shape}, Test df: {test_df.shape}\")\n",
+    "print(f\"Train df2: {train_df2.shape}, Validation df2: {val_df2.shape}, Test df2: {test_df2.shape}\")\n",
+    "print(f\"Train df3: {train_df3.shape}, Validation df3: {val_df3.shape}, Test df3: {test_df3.shape}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Было сделаное разбиение на три выборки: 70%, 15% и 15%. Подключена была библиотека scikit-learn и функция train_test_split , как сказано в пункте 15. Вполне сбалансированные"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "12.Качаем библиотеку imbalanced-learn, достаём нужные функции и погнали"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Class distribution after oversampling (df):\n",
+      "price_category\n",
+      "Low       10787\n",
+      "Medium    10787\n",
+      "High      10787\n",
+      "Luxury    10787\n",
+      "Name: count, dtype: int64\n",
+      "Class distribution after undersampling (df):\n",
+      "price_category\n",
+      "Low       1465\n",
+      "Medium    1465\n",
+      "High      1465\n",
+      "Luxury    1465\n",
+      "Name: count, dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "from imblearn.over_sampling import RandomOverSampler\n",
+    "from imblearn.under_sampling import RandomUnderSampler\n",
+    "df = pd.read_csv(\".//datasetlab2//kc_house_data.csv\", sep=\",\")\n",
+    "df['price_category'] = pd.cut(df['price'], bins=[0, 300000, 600000, 1000000, float('inf')],\n",
+    "                              labels=['Low', 'Medium', 'High', 'Luxury'])\n",
+    "\n",
+    "y = df['price_category']\n",
+    "X = df.drop(columns=['price', 'price_category'])\n",
+    "\n",
+    "oversampler = RandomOverSampler(random_state=42)\n",
+    "X_resampled, y_resampled = oversampler.fit_resample(X, y)\n",
+    "\n",
+    "undersampler = RandomUnderSampler(random_state=42)\n",
+    "X_resampled_under, y_resampled_under = undersampler.fit_resample(X, y)\n",
+    "\n",
+    "print(\"Class distribution after oversampling (df):\")\n",
+    "print(pd.Series(y_resampled).value_counts())\n",
+    "\n",
+    "print(\"Class distribution after undersampling (df):\")\n",
+    "print(pd.Series(y_resampled_under).value_counts())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Class distribution after oversampling (df3):\n",
+      "AGE_category\n",
+      "Young          1401\n",
+      "Middle-aged    1401\n",
+      "Senior         1401\n",
+      "Elderly        1401\n",
+      "Name: count, dtype: int64\n",
+      "Class distribution after undersampling (df3):\n",
+      "AGE_category\n",
+      "Young          15\n",
+      "Middle-aged    15\n",
+      "Senior         15\n",
+      "Elderly        15\n",
+      "Name: count, dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "df3 = pd.read_csv(\".//datasetlab2//Forbes Billionaires.csv\", sep=\",\")\n",
+    "\n",
+    "df3['AGE_category'] = pd.cut(df3['Age'], bins=[0, 30, 50, 70, float('inf')],\n",
+    "                              labels=['Young', 'Middle-aged', 'Senior', 'Elderly'])\n",
+    "\n",
+    "y3 = df3['AGE_category']\n",
+    "X3 = df3.drop(columns=['Age', 'AGE_category'])\n",
+    "\n",
+    "oversampler3 = RandomOverSampler(random_state=42)\n",
+    "X_resampled_3, y_resampled_3 = oversampler3.fit_resample(X3, y3)\n",
+    "\n",
+    "undersampler3 = RandomUnderSampler(random_state=42)\n",
+    "X_resampled_3_under, y_resampled_3_under = undersampler3.fit_resample(X3, y3)\n",
+    "\n",
+    "print(\"Class distribution after oversampling (df3):\")\n",
+    "print(pd.Series(y_resampled_3).value_counts())\n",
+    "\n",
+    "print(\"Class distribution after undersampling (df3):\")\n",
+    "print(pd.Series(y_resampled_3_under).value_counts())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Class distribution after oversampling (df2):\n",
+      "Sales_category\n",
+      "Low       598\n",
+      "Medium    598\n",
+      "High      598\n",
+      "Luxury      0\n",
+      "Name: count, dtype: int64\n",
+      "Class distribution after undersampling (df2):\n",
+      "Sales_category\n",
+      "Low       7\n",
+      "Medium    7\n",
+      "High      7\n",
+      "Luxury    0\n",
+      "Name: count, dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "df2 = pd.read_csv(\".//datasetlab2//Stores.csv\", sep=\",\")\n",
+    "\n",
+    "df2['Sales_category'] = pd.cut(df2['Store_Sales'], bins=[0, 50000, 100000, 200000, float('inf')],\n",
+    "                                labels=['Low', 'Medium', 'High', 'Luxury'])\n",
+    "\n",
+    "y2 = df2['Sales_category']\n",
+    "X2 = df2.drop(columns=['Store_Sales', 'Sales_category'])\n",
+    "\n",
+    "oversampler2 = RandomOverSampler(random_state=42)\n",
+    "X_resampled_2, y_resampled_2 = oversampler2.fit_resample(X2, y2)\n",
+    "\n",
+    "undersampler2 = RandomUnderSampler(random_state=42)\n",
+    "X_resampled_2_under, y_resampled_2_under = undersampler2.fit_resample(X2, y2)\n",
+    "\n",
+    "print(\"Class distribution after oversampling (df2):\")\n",
+    "print(pd.Series(y_resampled_2).value_counts())\n",
+    "\n",
+    "print(\"Class distribution after undersampling (df2):\")\n",
+    "print(pd.Series(y_resampled_2_under).value_counts())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "miivenv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

lab_4/lab4.ipynb

@@ -0,0 +1,496 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Lab 4 Malafeev PIbd-31**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "1.Для начала выберем бизнес-цели для задач регрессии и классификации."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Классификация. Цель: определить, откликнется ли клиент на маркетинговую кампанию. Столбец целевой переменной - Response, 1 - откликнулся, 0 - нет. Признаки - Возраст, Уровень дохода. (Age, Income)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Регрессия. Цель: прогноз расходов клиента. Столбец целевой переменной: Total_Spending - общие расходы, будут считаться по всем расходам. Признаки такие же."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "2.Достижимый уровень качества:\n",
+    "Классификация:\n",
+    "Оценка метрики accuracy: ориентир 70-80% (с учетом ограниченных признаков).\n",
+    "Регрессия:\n",
+    "MSE (среднеквадратичная ошибка): минимизация, ориентир в зависимости от разброса целевой переменной.\n",
+    "R^2 > 0.6"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "3.Ориентир. Классификация:\n",
+    "DummyClassifier, предсказывающий самый частый класс, даст accuracy ~50-60%.\n",
+    "Регрессия:\n",
+    "Прогноз среднего значения целевой переменной."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "X_class_train: (1568, 2), y_class_train: (1568,)\n",
+      "X_reg_train: (1568, 2), y_reg_train: (1568,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "data = pd.read_csv(\".//datasetlab1//marketing_campaign.csv\", sep=\"\\t\")\n",
+    "data2 = pd.read_csv(\".//datasetlab1//marketing_campaign2.csv\", sep=\"\\t\")\n",
+    "\n",
+    "# Преобразуем данные для классификации (дата для отклика на кампанию)\n",
+    "data['Age'] = 2024 - data['Year_Birth'] \n",
+    "data = data[['Age', 'Income', 'Response']] \n",
+    "\n",
+    "X_class = data[['Age', 'Income']]\n",
+    "y_class = data['Response']\n",
+    "\n",
+    "# Преобразуем данные для регрессии (прогноз расходов)\n",
+    "data2['Age'] = 2024 - data2['Year_Birth']  \n",
+    "data2['Total_Spending'] = (data2['MntWines'] + data2['MntFruits'] + data2['MntMeatProducts'] +\n",
+    "                           data2['MntFishProducts'] + data2['MntSweetProducts'] + data2['MntGoldProds'])\n",
+    "data2 = data2[['Age', 'Income', 'Total_Spending']]  \n",
+    "\n",
+    "# Разделение на признаки и целевую переменную для регрессии\n",
+    "X_reg = data2[['Age', 'Income']]\n",
+    "y_reg = data2['Total_Spending']\n",
+    "\n",
+    "# Масштабирование данных\n",
+    "scaler = StandardScaler()\n",
+    "X_class_scaled = scaler.fit_transform(X_class)\n",
+    "X_reg_scaled = scaler.fit_transform(X_reg)\n",
+    "\n",
+    "# Разделение на тренировочные и тестовые выборки\n",
+    "X_train_class, X_test_class, y_train_class, y_test_class = train_test_split(X_class_scaled, y_class, test_size=0.3, random_state=42)\n",
+    "X_train_reg, X_test_reg, y_train_reg, y_test_reg = train_test_split(X_reg_scaled, y_reg, test_size=0.3, random_state=42)\n",
+    "\n",
+    "# Проверим, что все выглядит правильно\n",
+    "print(f\"X_class_train: {X_train_class.shape}, y_class_train: {y_train_class.shape}\")\n",
+    "print(f\"X_reg_train: {X_train_reg.shape}, y_reg_train: {y_train_reg.shape}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "5-6.Выбор трёх моделей и построение конвейера"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Logistic Regression - Средняя точность модели: 0.8475 ± 0.0027\n",
+      "Random Forest - Средняя точность модели: 0.8258 ± 0.0099\n",
+      "SVM - Средняя точность модели: 0.8529 ± 0.0027\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.model_selection import train_test_split, cross_val_score\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "from sklearn.svm import SVC\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "\n",
+    "# Удаляем строки с пропущенными значениями\n",
+    "X_class_scaled = X_class.dropna()\n",
+    "y_class = y_class[X_class_scaled.index]\n",
+    "\n",
+    "models = [\n",
+    "    ('Logistic Regression', LogisticRegression(max_iter=1000)),\n",
+    "    ('Random Forest', RandomForestClassifier(n_estimators=100)),\n",
+    "    ('SVM', SVC())\n",
+    "]\n",
+    "\n",
+    "# Создаем конвейер\n",
+    "imputer = SimpleImputer(strategy='mean') \n",
+    "scaler = StandardScaler()\n",
+    "\n",
+    "for name, model in models:\n",
+    "    pipe = Pipeline([\n",
+    "        ('imputer', imputer),\n",
+    "        ('scaler', scaler),\n",
+    "        ('classifier', model)\n",
+    "    ])\n",
+    "    \n",
+    "    scores = cross_val_score(pipe, X_class_scaled, y_class, cv=5, scoring='accuracy')\n",
+    "    print(f\"{name} - Средняя точность модели: {scores.mean():.4f} ± {scores.std():.4f}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Вот такие модели и конвейр я выбрал: Imputer: Заполняет пропущенные значения средним (если они есть).\n",
+    "Scaler: Масштабирует данные с помощью StandardScaler.\n",
+    "Classifier: Используются три модели:\n",
+    "LogisticRegression: Логистическая регрессия.\n",
+    "RandomForestClassifier: Случайный лес.\n",
+    "SVC: Метод опорных векторов (SVM)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "7.Теперь сделаем настройку гиперпараметров."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fitting 5 folds for each of 6 candidates, totalling 30 fits\n",
+      "Logistic Regression - Лучшие гиперпараметры: {'classifier__C': 0.1, 'classifier__solver': 'lbfgs'}\n",
+      "Logistic Regression - Лучшая точность: 0.8484\n",
+      "--------------------------------------------------\n",
+      "Fitting 5 folds for each of 9 candidates, totalling 45 fits\n",
+      "Random Forest - Лучшие гиперпараметры: {'classifier__max_depth': 10, 'classifier__n_estimators': 100}\n",
+      "Random Forest - Лучшая точность: 0.8520\n",
+      "--------------------------------------------------\n",
+      "Fitting 5 folds for each of 6 candidates, totalling 30 fits\n",
+      "SVM - Лучшие гиперпараметры: {'classifier__C': 1, 'classifier__kernel': 'rbf'}\n",
+      "SVM - Лучшая точность: 0.8529\n",
+      "--------------------------------------------------\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import GridSearchCV\n",
+    "models = [\n",
+    "    ('Logistic Regression', LogisticRegression(max_iter=1000), {'classifier__C': [0.1, 1, 10], 'classifier__solver': ['lbfgs', 'liblinear']}),\n",
+    "    ('Random Forest', RandomForestClassifier(n_estimators=100), {'classifier__n_estimators': [50, 100, 200], 'classifier__max_depth': [10, 20, None]}),\n",
+    "    ('SVM', SVC(), {'classifier__C': [0.1, 1, 10], 'classifier__kernel': ['linear', 'rbf']})\n",
+    "]\n",
+    "\n",
+    "for name, model, param_grid in models:\n",
+    "    pipe = Pipeline([\n",
+    "        ('imputer', imputer),\n",
+    "        ('scaler', scaler),\n",
+    "        ('classifier', model)\n",
+    "    ])\n",
+    "    \n",
+    "    grid_search = GridSearchCV(pipe, param_grid, cv=5, scoring='accuracy', n_jobs=-1, verbose=1)\n",
+    "    grid_search.fit(X_class_scaled, y_class)\n",
+    "\n",
+    "    print(f\"{name} - Лучшие гиперпараметры: {grid_search.best_params_}\")\n",
+    "    print(f\"{name} - Лучшая точность: {grid_search.best_score_:.4f}\")\n",
+    "    print(\"-\" * 50)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Тут мы проходим по моделям и настраиваем гиперпараметры с помощью GridSearchCV с помощью кросс-валидации. Параметры: cv=5: 5 фолдов для кросс-валидации.\n",
+    "scoring='accuracy': Мы используем точность как метрику.\n",
+    "n_jobs=-1: Используем все доступные процессоры для ускорения вычислений.\n",
+    "verbose=1: Подробный вывод процесса."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "8.Обучим модели"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fitting 5 folds for each of 6 candidates, totalling 30 fits\n",
+      "Fitting 5 folds for each of 6 candidates, totalling 30 fits\n",
+      "Fitting 5 folds for each of 6 candidates, totalling 30 fits\n"
+     ]
+    }
+   ],
+   "source": [
+    "best_models = {} \n",
+    "for name, model, param_grid in models: \n",
+    "    grid_search.fit(X_class_scaled, y_class)\n",
+    "    best_models[name] = grid_search.best_estimator_ \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "9.Оценим модели."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score\n",
+    "from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score\n",
+    "\n",
+    "# Оценка качества классификации\n",
+    "for name, model in best_models.items():\n",
+    "    y_pred_class = model.predict(X_class_scaled)  # Предсказание для классификации\n",
+    "\n",
+    "# Оценка качества регрессии\n",
+    "for name, model in best_models.items():\n",
+    "    y_pred_reg = model.predict(X_reg_scaled)  # Предсказание для регрессии\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Т.к. вывод слишком длинный, приложу его тут(вылазит Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...):<br>Оценка качества для модели Logistic Regression:<br>\n",
+    "Accuracy: 0.8528880866425993<br>\n",
+    "Precision: 0.8181818181818182<br>\n",
+    "Recall: 0.02702702702702703<br>\n",
+    "F1-Score: 0.05232558139534884<br>\n",
+    "ROC AUC: Не поддерживается для этой модели<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "Оценка качества для модели Random Forest:<br>\n",
+    "Accuracy: 0.8528880866425993<br>\n",
+    "Precision: 0.8181818181818182<br>\n",
+    "Recall: 0.02702702702702703<br>\n",
+    "F1-Score: 0.05232558139534884<br>\n",
+    "ROC AUC: Не поддерживается для этой модели<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "Оценка качества для модели SVM:<br>\n",
+    "Accuracy: 0.8528880866425993<br>\n",
+    "Precision: 0.8181818181818182<br>\n",
+    "Recall: 0.02702702702702703<br>\n",
+    "F1-Score: 0.05232558139534884<br>\n",
+    "ROC AUC: Не поддерживается для этой модели<br>\n",
+    "<br>\n",
+    "<br>Задача регрессии: <br>\n",
+    "Оценка качества для модели Logistic Regression:<br>\n",
+    "MAE: 605.7982142857143<br>\n",
+    "MSE: 729533.7598214286<br>\n",
+    "RMSE: 854.1274845252485<br>\n",
+    "R²: -1.0122722045012051<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "Оценка качества для модели Random Forest:<br>\n",
+    "MAE: 605.7982142857143<br>\n",
+    "MSE: 729533.7598214286<br>\n",
+    "RMSE: 854.1274845252485<br>\n",
+    "R²: -1.0122722045012051<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "Оценка качества для модели SVM:<br>\n",
+    "MAE: 605.7982142857143<br>\n",
+    "MSE: 729533.7598214286<br>\n",
+    "RMSE: 854.1274845252485<br>\n",
+    "R²: -1.0122722045012051<br>\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Почему выбрал эти метирки:<br>Классификация (Отклик на предложение)<br>\n",
+    "Целевая переменная — бинарная (0 и 1), где 1 — откликнулся, а 0 — не откликнулся. Для классификации подходящими метриками являются:<br>\n",
+    "<br>\n",
+    "Accuracy (Точность):\n",
+    "Это доля правильно классифицированных объектов среди всех. \n",
+    "Подходит для оценки общей эффективности модели. Однако важно учитывать, что если классы несбалансированы, точность может быть обманчивой.<br>\n",
+    "Precision (Точность):\n",
+    "\n",
+    "Это доля истинных положительных случаев среди всех предсказанных положительных случаев.\n",
+    "Важна для задач, где важно минимизировать количество ложных срабатываний, например, когда модель ошибочно классифицирует клиента как откликнувшегося (True Positive).<br>\n",
+    "Recall (Полнота):\n",
+    "\n",
+    "Это доля истинных положительных случаев среди всех истинных положительных случаев.\n",
+    "Важно для задач, где важно не пропустить откликнувшихся клиентов (False Negatives).<br>\n",
+    "F1-Score:\n",
+    "\n",
+    "Это гармоническое среднее между точностью и полнотой.\n",
+    "Подходит для оценки моделей в случаях, когда важно иметь баланс между точностью и полнотой, особенно в ситуациях с несбалансированными классами.<br>\n",
+    "ROC AUC:\n",
+    "Площадь под кривой ROC, которая отображает способность модели различать положительные и отрицательные классы.\n",
+    "Чем выше значение AUC, тем лучше модель справляется с разделением классов."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Регрессия (Прогноз расходов)<br>\n",
+    "Целевая переменная — это числовое значение (расходы клиента). Для задач регрессии используются другие метрики:<br>\n",
+    "\n",
+    "Mean Absolute Error (MAE):\n",
+    "\n",
+    "Это средняя абсолютная ошибка предсказания.\n",
+    "Простой и интерпретируемый показатель, который описывает среднее отклонение предсказанных значений от фактических.<br>\n",
+    "Mean Squared Error (MSE):\n",
+    "\n",
+    "Это средняя квадратичная ошибка.\n",
+    "Чувствителен к большим ошибкам, так как квадратичный штраф увеличивает вес больших отклонений, что полезно, если вы хотите минимизировать большие ошибки.<br>\n",
+    "Root Mean Squared Error (RMSE):\n",
+    "\n",
+    "Это квадратный корень из MSE.\n",
+    "Подходит для задач, где важно учитывать большие ошибки, так как более чувствителен к выбросам.<br>\n",
+    "R-squared (R²):\n",
+    "\n",
+    "Это коэффициент детерминации, который показывает, какая доля дисперсии целевой переменной объясняется моделью.\n",
+    "R² может быть полезен для оценки того, насколько хорошо модель объясняет вариацию целевой переменной, но не всегда подходит, если модель имеет много выбросов или некорректно подогнана.<br>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "9.Оценка"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Evaluating model: Logistic Regression\n",
+      "Train Accuracy: 0.8476, Test Accuracy: 0.8586\n",
+      "Bias: 0.0000, Variance: 0.0000\n",
+      "Train Error (MSE): 732205.3240, Test Error (MSE): 723300.1101\n",
+      "Bias: 0.0000, Variance: 0.0000\n",
+      "Evaluating model: Random Forest\n",
+      "Train Accuracy: 0.8476, Test Accuracy: 0.8586\n",
+      "Bias: 0.0000, Variance: 0.0000\n",
+      "Train Error (MSE): 732205.3240, Test Error (MSE): 723300.1101\n",
+      "Bias: 0.0000, Variance: 0.0000\n",
+      "Evaluating model: SVM\n",
+      "Train Accuracy: 0.8476, Test Accuracy: 0.8586\n",
+      "Bias: 0.0000, Variance: 0.0000\n",
+      "Train Error (MSE): 732205.3240, Test Error (MSE): 723300.1101\n",
+      "Bias: 0.0000, Variance: 0.0000\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.metrics import mean_squared_error, accuracy_score\n",
+    "\n",
+    "# Оценка смещения и дисперсии для классификации и регрессии\n",
+    "def evaluate_bias_variance(model, X_train, y_train, X_test, y_test, task='classification'):\n",
+    "    # Прогнозы на обучающих и тестовых данных\n",
+    "    y_train_pred = model.predict(X_train)\n",
+    "    y_test_pred = model.predict(X_test)\n",
+    "\n",
+    "    if task == 'classification':\n",
+    "        # Для классификации считаем точность\n",
+    "        train_accuracy = accuracy_score(y_train, y_train_pred)\n",
+    "        test_accuracy = accuracy_score(y_test, y_test_pred)\n",
+    "        print(f\"Train Accuracy: {train_accuracy:.4f}, Test Accuracy: {test_accuracy:.4f}\")\n",
+    "    elif task == 'regression':\n",
+    "        # Для регрессии считаем среднеквадратичную ошибку (MSE)\n",
+    "        train_error = mean_squared_error(y_train, y_train_pred)\n",
+    "        test_error = mean_squared_error(y_test, y_test_pred)\n",
+    "        print(f\"Train Error (MSE): {train_error:.4f}, Test Error (MSE): {test_error:.4f}\")\n",
+    "\n",
+    "    # Для оценки смещения и дисперсии на тестовых данных\n",
+    "    bias = np.mean(y_test_pred - y_train_pred[:len(y_test_pred)])  # Смещение: разница между тестом и обучением\n",
+    "    variance = np.var(y_test_pred - y_train_pred[:len(y_test_pred)])  # Дисперсия: варьирование прогнозов\n",
+    "\n",
+    "    print(f\"Bias: {bias:.4f}, Variance: {variance:.4f}\")\n",
+    "\n",
+    "# Оценим для каждой из моделей\n",
+    "for name, model in best_models.items():\n",
+    "    print(f\"Evaluating model: {name}\")\n",
+    "    # Для классификации\n",
+    "    evaluate_bias_variance(model, X_train_class, y_train_class, X_test_class, y_test_class, task='classification')  \n",
+    "    # Для регрессии\n",
+    "    evaluate_bias_variance(model, X_train_reg, y_train_reg, X_test_reg, y_test_reg, task='regression')  \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Конец"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "miivenv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}