From 5a6a48e6222e750c7ed06a262647d77b49cf4f4d Mon Sep 17 00:00:00 2001 From: Zakharov_Rostislav Date: Sat, 14 Dec 2024 10:14:47 +0400 Subject: [PATCH] feat(lab-4): add prediction output --- notebooks/lab4.ipynb | 965 +++++++++++++++++++++++++++++++++---------- 1 file changed, 744 insertions(+), 221 deletions(-) diff --git a/notebooks/lab4.ipynb b/notebooks/lab4.ipynb index 5895840..d1ad90e 100644 --- a/notebooks/lab4.ipynb +++ b/notebooks/lab4.ipynb @@ -13,7 +13,7 @@ }, { "cell_type": "code", - "execution_count": 732, + "execution_count": 30, "metadata": {}, "outputs": [ { @@ -325,7 +325,7 @@ "[19237 rows x 17 columns]" ] }, - "execution_count": 732, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -375,7 +375,7 @@ }, { "cell_type": "code", - "execution_count": 733, + "execution_count": 31, "metadata": {}, "outputs": [ { @@ -401,7 +401,7 @@ "dtype: object" ] }, - "execution_count": 733, + "execution_count": 31, "metadata": {}, "output_type": "execute_result" } @@ -412,7 +412,7 @@ }, { "cell_type": "code", - "execution_count": 734, + "execution_count": 32, "metadata": {}, "outputs": [ { @@ -426,7 +426,7 @@ " 6.8, 4.5, 7.3, 0.1, 3.1, 6.4, 3.9, 0.9, 5.2, 5.8])" ] }, - "execution_count": 734, + "execution_count": 32, "metadata": {}, "output_type": "execute_result" } @@ -439,7 +439,7 @@ }, { "cell_type": "code", - "execution_count": 735, + "execution_count": 33, "metadata": {}, "outputs": [ { @@ -448,7 +448,7 @@ "array([186005, 192000, 200000, ..., 140607, 307325, 186923])" ] }, - "execution_count": 735, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } @@ -461,7 +461,7 @@ }, { "cell_type": "code", - "execution_count": 736, + "execution_count": 34, "metadata": {}, "outputs": [ { @@ -532,7 +532,7 @@ " 1901])" ] }, - "execution_count": 736, + "execution_count": 34, "metadata": {}, "output_type": "execute_result" } @@ -545,7 +545,7 @@ }, { "cell_type": "code", - "execution_count": 737, + "execution_count": 35, "metadata": {}, "outputs": [ { @@ -554,7 +554,7 @@ "array([ 6, 4, 8, 1, 12, 3, 2, 16, 5, 7, 9, 10, 14])" ] }, - "execution_count": 737, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" } @@ -566,7 +566,7 @@ }, { "cell_type": "code", - "execution_count": 738, + "execution_count": 36, "metadata": {}, "outputs": [ { @@ -575,7 +575,7 @@ "array(['04-May', '02-Mar', '>5'], dtype=object)" ] }, - "execution_count": 738, + "execution_count": 36, "metadata": {}, "output_type": "execute_result" } @@ -586,7 +586,7 @@ }, { "cell_type": "code", - "execution_count": 739, + "execution_count": 37, "metadata": {}, "outputs": [ { @@ -595,7 +595,7 @@ "array(['Четырехдверный', 'Двухдверный', 'Многодверный'], dtype=object)" ] }, - "execution_count": 739, + "execution_count": 37, "metadata": {}, "output_type": "execute_result" } @@ -609,7 +609,7 @@ }, { "cell_type": "code", - "execution_count": 740, + "execution_count": 38, "metadata": {}, "outputs": [ { @@ -618,7 +618,7 @@ "array([ 1, 3, 6, ..., 627220, 872946, 26307500])" ] }, - "execution_count": 740, + "execution_count": 38, "metadata": {}, "output_type": "execute_result" } @@ -630,7 +630,7 @@ }, { "cell_type": "code", - "execution_count": 741, + "execution_count": 39, "metadata": {}, "outputs": [ { @@ -650,7 +650,7 @@ }, { "cell_type": "code", - "execution_count": 742, + "execution_count": 40, "metadata": {}, "outputs": [ { @@ -659,7 +659,7 @@ "array([ 500, 549, 600, ..., 627220, 872946, 26307500])" ] }, - "execution_count": 742, + "execution_count": 40, "metadata": {}, "output_type": "execute_result" } @@ -671,7 +671,7 @@ }, { "cell_type": "code", - "execution_count": 743, + "execution_count": 41, "metadata": {}, "outputs": [ { @@ -684,7 +684,7 @@ " 2014, 2015, 2016, 2017, 2018, 2019, 2020])" ] }, - "execution_count": 743, + "execution_count": 41, "metadata": {}, "output_type": "execute_result" } @@ -696,7 +696,7 @@ }, { "cell_type": "code", - "execution_count": 744, + "execution_count": 42, "metadata": {}, "outputs": [ { @@ -1021,7 +1021,7 @@ "[17574 rows x 17 columns]" ] }, - "execution_count": 744, + "execution_count": 42, "metadata": {}, "output_type": "execute_result" } @@ -1039,7 +1039,7 @@ }, { "cell_type": "code", - "execution_count": 745, + "execution_count": 43, "metadata": {}, "outputs": [ { @@ -1048,7 +1048,7 @@ "np.int64(2773)" ] }, - "execution_count": 745, + "execution_count": 43, "metadata": {}, "output_type": "execute_result" } @@ -1059,14 +1059,14 @@ }, { "cell_type": "code", - "execution_count": 746, + "execution_count": 44, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\user\\AppData\\Local\\Temp\\ipykernel_30576\\1689817098.py:1: SettingWithCopyWarning: \n", + "C:\\Users\\user\\AppData\\Local\\Temp\\ipykernel_18064\\1689817098.py:1: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", @@ -1081,7 +1081,7 @@ }, { "cell_type": "code", - "execution_count": 747, + "execution_count": 45, "metadata": {}, "outputs": [ { @@ -1107,7 +1107,7 @@ "dtype: int64" ] }, - "execution_count": 747, + "execution_count": 45, "metadata": {}, "output_type": "execute_result" } @@ -1125,7 +1125,7 @@ }, { "cell_type": "code", - "execution_count": 748, + "execution_count": 46, "metadata": {}, "outputs": [ { @@ -1151,7 +1151,7 @@ "dtype: object" ] }, - "execution_count": 748, + "execution_count": 46, "metadata": {}, "output_type": "execute_result" } @@ -1162,7 +1162,7 @@ }, { "cell_type": "code", - "execution_count": 749, + "execution_count": 47, "metadata": {}, "outputs": [ { @@ -1224,7 +1224,7 @@ }, { "cell_type": "code", - "execution_count": 750, + "execution_count": 48, "metadata": {}, "outputs": [ { @@ -1255,7 +1255,7 @@ }, { "cell_type": "code", - "execution_count": 751, + "execution_count": 49, "metadata": {}, "outputs": [ { @@ -1317,7 +1317,7 @@ }, { "cell_type": "code", - "execution_count": 752, + "execution_count": 50, "metadata": {}, "outputs": [ { @@ -1343,7 +1343,7 @@ "dtype: object" ] }, - "execution_count": 752, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } @@ -1354,13 +1354,13 @@ }, { "cell_type": "code", - "execution_count": 753, + "execution_count": 51, "metadata": {}, "outputs": [], "source": [ "columns_to_drop = [\n", " \"Model\",\n", - " \"Manufacturer\",\n", + " # \"Manufacturer\",\n", " \"Color\",\n", " \"Doors\",\n", " \"Cylinders\",\n", @@ -1387,6 +1387,7 @@ " \"Drive wheels\",\n", " # \"Doors\",\n", " \"Wheel\",\n", + " \"Manufacturer\",\n", "]\n", "\n", "cat_cols_for_num_enc = [\n", @@ -1457,7 +1458,7 @@ }, { "cell_type": "code", - "execution_count": 754, + "execution_count": 52, "metadata": {}, "outputs": [ { @@ -1492,11 +1493,11 @@ " Category_Pickup\n", " Category_Sedan\n", " ...\n", - " Gear box type_Tiptronic\n", - " Gear box type_Variator\n", - " Drive wheels_Front\n", - " Drive wheels_Rear\n", - " Wheel_Right-hand drive\n", + " Manufacturer_UAZ\n", + " Manufacturer_VAZ\n", + " Manufacturer_VOLKSWAGEN\n", + " Manufacturer_VOLVO\n", + " Manufacturer_სხვა\n", " Price\n", " Levy\n", " Prod. year\n", @@ -1542,7 +1543,7 @@ " 0.0\n", " 0.0\n", " ...\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 0.0\n", @@ -1567,10 +1568,10 @@ " 0.0\n", " ...\n", " 0.0\n", - " 1.0\n", - " 1.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", + " 0.0\n", + " 0.0\n", " -0.781060\n", " -1.187596\n", " -1.091356\n", @@ -1616,7 +1617,7 @@ " ...\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " -0.480485\n", @@ -1664,7 +1665,7 @@ " ...\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " -0.752100\n", @@ -1686,11 +1687,11 @@ " 0.0\n", " 1.0\n", " ...\n", - " 1.0\n", " 0.0\n", " 0.0\n", - " 1.0\n", - " 1.0\n", + " 0.0\n", + " 0.0\n", + " 0.0\n", " -0.838888\n", " -1.187596\n", " -1.741709\n", @@ -1713,7 +1714,7 @@ " 0.0\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " -0.781060\n", " -1.187596\n", @@ -1734,9 +1735,9 @@ " 0.0\n", " 1.0\n", " ...\n", - " 1.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " -0.115718\n", @@ -1760,7 +1761,7 @@ " ...\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 0.845956\n", @@ -1771,7 +1772,7 @@ " \n", " \n", "\n", - "

12597 rows × 28 columns

\n", + "

12597 rows × 83 columns

\n", "" ], "text/plain": [ @@ -1814,49 +1815,49 @@ "19233 0.0 0.0 0.0 1.0 \n", "19234 0.0 0.0 0.0 0.0 \n", "\n", - " ... Gear box type_Tiptronic Gear box type_Variator \\\n", - "0 ... 0.0 0.0 \n", - "1 ... 1.0 0.0 \n", - "2 ... 0.0 1.0 \n", - "3 ... 0.0 0.0 \n", - "4 ... 0.0 0.0 \n", - "... ... ... ... \n", - "19225 ... 0.0 0.0 \n", - "19226 ... 1.0 0.0 \n", - "19232 ... 0.0 0.0 \n", - "19233 ... 1.0 0.0 \n", - "19234 ... 0.0 0.0 \n", + " ... Manufacturer_UAZ Manufacturer_VAZ Manufacturer_VOLKSWAGEN \\\n", + "0 ... 0.0 0.0 0.0 \n", + "1 ... 0.0 0.0 0.0 \n", + "2 ... 0.0 0.0 0.0 \n", + "3 ... 0.0 0.0 0.0 \n", + "4 ... 0.0 0.0 0.0 \n", + "... ... ... ... ... \n", + "19225 ... 0.0 0.0 0.0 \n", + "19226 ... 0.0 0.0 0.0 \n", + "19232 ... 0.0 0.0 0.0 \n", + "19233 ... 0.0 0.0 0.0 \n", + "19234 ... 0.0 0.0 0.0 \n", "\n", - " Drive wheels_Front Drive wheels_Rear Wheel_Right-hand drive \\\n", - "0 0.0 0.0 0.0 \n", - "1 0.0 0.0 0.0 \n", - "2 1.0 0.0 1.0 \n", - "3 0.0 0.0 0.0 \n", - "4 1.0 0.0 0.0 \n", - "... ... ... ... \n", - "19225 1.0 0.0 0.0 \n", - "19226 0.0 1.0 1.0 \n", - "19232 0.0 1.0 0.0 \n", - "19233 1.0 0.0 0.0 \n", - "19234 1.0 0.0 0.0 \n", + " Manufacturer_VOLVO Manufacturer_სხვა Price Levy Prod. year \\\n", + "0 0.0 0.0 -0.332733 1.851925 -0.224219 \n", + "1 0.0 0.0 -0.029023 1.024150 -0.007434 \n", + "2 0.0 0.0 -0.781060 -1.187596 -1.091356 \n", + "3 0.0 0.0 -1.229294 0.685218 -0.007434 \n", + "4 0.0 0.0 -0.480485 -0.218599 0.642919 \n", + "... ... ... ... ... ... \n", + "19225 0.0 0.0 -0.752100 1.217515 -0.874572 \n", + "19226 0.0 0.0 -0.838888 -1.187596 -1.741709 \n", + "19232 0.0 0.0 -0.781060 -1.187596 -2.608847 \n", + "19233 0.0 0.0 -0.115718 0.617867 -0.007434 \n", + "19234 0.0 0.0 0.845956 0.628730 -0.224219 \n", "\n", - " Price Levy Prod. year Engine volume Airbags \n", - "0 -0.332733 1.851925 -0.224219 1.849443 1.353782 \n", - "1 -0.029023 1.024150 -0.007434 1.162057 0.340316 \n", - "2 -0.781060 -1.187596 -1.091356 -1.175055 -1.179883 \n", - "3 -1.229294 0.685218 -0.007434 0.474671 -1.686616 \n", - "4 -0.480485 -0.218599 0.642919 -1.175055 -0.673150 \n", - "... ... ... ... ... ... \n", - "19225 -0.752100 1.217515 -0.874572 -0.625146 -0.673150 \n", - "19226 -0.838888 -1.187596 -1.741709 1.162057 -1.686616 \n", - "19232 -0.781060 -1.187596 -2.608847 -0.212715 -0.419784 \n", - "19233 -0.115718 0.617867 -0.007434 0.337194 0.340316 \n", - "19234 0.845956 0.628730 -0.224219 -0.212715 -0.673150 \n", + " Engine volume Airbags \n", + "0 1.849443 1.353782 \n", + "1 1.162057 0.340316 \n", + "2 -1.175055 -1.179883 \n", + "3 0.474671 -1.686616 \n", + "4 -1.175055 -0.673150 \n", + "... ... ... \n", + "19225 -0.625146 -0.673150 \n", + "19226 1.162057 -1.686616 \n", + "19232 -0.212715 -0.419784 \n", + "19233 0.337194 0.340316 \n", + "19234 -0.212715 -0.673150 \n", "\n", - "[12597 rows x 28 columns]" + "[12597 rows x 83 columns]" ] }, - "execution_count": 754, + "execution_count": 52, "metadata": {}, "output_type": "execute_result" } @@ -1880,7 +1881,7 @@ }, { "cell_type": "code", - "execution_count": 755, + "execution_count": 53, "metadata": {}, "outputs": [ { @@ -1905,7 +1906,7 @@ }, { "cell_type": "code", - "execution_count": 756, + "execution_count": 54, "metadata": {}, "outputs": [ { @@ -1940,12 +1941,12 @@ " Category_Pickup\n", " Category_Sedan\n", " ...\n", - " Gear box type_Manual\n", - " Gear box type_Tiptronic\n", - " Gear box type_Variator\n", - " Drive wheels_Front\n", - " Drive wheels_Rear\n", - " Wheel_Right-hand drive\n", + " Manufacturer_TOYOTA\n", + " Manufacturer_UAZ\n", + " Manufacturer_VAZ\n", + " Manufacturer_VOLKSWAGEN\n", + " Manufacturer_VOLVO\n", + " Manufacturer_სხვა\n", " Levy\n", " Prod. year\n", " Engine volume\n", @@ -1966,12 +1967,12 @@ " 0.0\n", " 1.0\n", " ...\n", - " 0.0\n", - " 0.0\n", - " 0.0\n", " 1.0\n", " 0.0\n", " 0.0\n", + " 0.0\n", + " 0.0\n", + " 0.0\n", " -1.187596\n", " 1.943625\n", " -0.487669\n", @@ -1990,12 +1991,12 @@ " 0.0\n", " 1.0\n", " ...\n", - " 0.0\n", " 1.0\n", " 0.0\n", - " 1.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", + " 0.0\n", + " 0.0\n", " -1.187596\n", " -0.874572\n", " -0.900100\n", @@ -2015,9 +2016,9 @@ " 1.0\n", " ...\n", " 0.0\n", - " 1.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 0.081225\n", @@ -2065,7 +2066,7 @@ " 0.0\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 1.695495\n", @@ -2110,7 +2111,7 @@ " 0.0\n", " 1.0\n", " ...\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 0.0\n", @@ -2137,7 +2138,7 @@ " 0.0\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 0.474472\n", @@ -2158,10 +2159,10 @@ " 0.0\n", " 0.0\n", " ...\n", + " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", - " 1.0\n", - " 1.0\n", " 0.0\n", " 0.0\n", " 0.643938\n", @@ -2185,7 +2186,7 @@ " 0.0\n", " 0.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " -1.187596\n", @@ -2207,9 +2208,9 @@ " 1.0\n", " ...\n", " 0.0\n", - " 1.0\n", " 0.0\n", - " 1.0\n", + " 0.0\n", + " 0.0\n", " 0.0\n", " 0.0\n", " 0.444055\n", @@ -2219,7 +2220,7 @@ " \n", " \n", "\n", - "

8817 rows × 27 columns

\n", + "

8817 rows × 82 columns

\n", "" ], "text/plain": [ @@ -2262,49 +2263,49 @@ "1136 0.0 0.0 0.0 1.0 \n", "10640 0.0 0.0 0.0 1.0 \n", "\n", - " ... Gear box type_Manual Gear box type_Tiptronic \\\n", - "15146 ... 0.0 0.0 \n", - "14145 ... 0.0 1.0 \n", - "8943 ... 0.0 1.0 \n", - "17889 ... 0.0 0.0 \n", - "9515 ... 0.0 0.0 \n", - "... ... ... ... \n", - "18201 ... 1.0 0.0 \n", - "7436 ... 0.0 0.0 \n", - "7728 ... 0.0 0.0 \n", - "1136 ... 0.0 0.0 \n", - "10640 ... 0.0 1.0 \n", + " ... Manufacturer_TOYOTA Manufacturer_UAZ Manufacturer_VAZ \\\n", + "15146 ... 1.0 0.0 0.0 \n", + "14145 ... 1.0 0.0 0.0 \n", + "8943 ... 0.0 0.0 0.0 \n", + "17889 ... 0.0 0.0 0.0 \n", + "9515 ... 0.0 0.0 0.0 \n", + "... ... ... ... ... \n", + "18201 ... 0.0 0.0 0.0 \n", + "7436 ... 0.0 0.0 0.0 \n", + "7728 ... 1.0 0.0 0.0 \n", + "1136 ... 0.0 0.0 0.0 \n", + "10640 ... 0.0 0.0 0.0 \n", "\n", - " Gear box type_Variator Drive wheels_Front Drive wheels_Rear \\\n", - "15146 0.0 1.0 0.0 \n", - "14145 0.0 1.0 0.0 \n", - "8943 0.0 1.0 0.0 \n", - "17889 0.0 0.0 0.0 \n", - "9515 0.0 1.0 0.0 \n", - "... ... ... ... \n", - "18201 0.0 0.0 0.0 \n", - "7436 0.0 1.0 0.0 \n", - "7728 1.0 1.0 0.0 \n", - "1136 0.0 1.0 0.0 \n", - "10640 0.0 1.0 0.0 \n", + " Manufacturer_VOLKSWAGEN Manufacturer_VOLVO Manufacturer_სხვა \\\n", + "15146 0.0 0.0 0.0 \n", + "14145 0.0 0.0 0.0 \n", + "8943 0.0 0.0 0.0 \n", + "17889 0.0 0.0 0.0 \n", + "9515 0.0 0.0 0.0 \n", + "... ... ... ... \n", + "18201 0.0 0.0 0.0 \n", + "7436 0.0 0.0 0.0 \n", + "7728 0.0 0.0 0.0 \n", + "1136 0.0 0.0 0.0 \n", + "10640 0.0 0.0 0.0 \n", "\n", - " Wheel_Right-hand drive Levy Prod. year Engine volume Airbags \n", - "15146 0.0 -1.187596 1.943625 -0.487669 -0.673150 \n", - "14145 1.0 -1.187596 -0.874572 -0.900100 -1.179883 \n", - "8943 0.0 0.081225 0.642919 -0.487669 0.847049 \n", - "17889 0.0 -1.187596 -1.524925 0.474671 -0.419784 \n", - "9515 0.0 1.695495 1.510056 0.474671 -0.673150 \n", - "... ... ... ... ... ... \n", - "18201 0.0 -1.187596 -0.874572 0.337194 -0.673150 \n", - "7436 0.0 0.474472 0.859703 -0.212715 1.353782 \n", - "7728 0.0 0.643938 -0.657787 -0.900100 0.340316 \n", - "1136 0.0 -1.187596 1.076487 -0.762623 0.340316 \n", - "10640 0.0 0.444055 0.426134 0.337194 0.340316 \n", + " Levy Prod. year Engine volume Airbags \n", + "15146 -1.187596 1.943625 -0.487669 -0.673150 \n", + "14145 -1.187596 -0.874572 -0.900100 -1.179883 \n", + "8943 0.081225 0.642919 -0.487669 0.847049 \n", + "17889 -1.187596 -1.524925 0.474671 -0.419784 \n", + "9515 1.695495 1.510056 0.474671 -0.673150 \n", + "... ... ... ... ... \n", + "18201 -1.187596 -0.874572 0.337194 -0.673150 \n", + "7436 0.474472 0.859703 -0.212715 1.353782 \n", + "7728 0.643938 -0.657787 -0.900100 0.340316 \n", + "1136 -1.187596 1.076487 -0.762623 0.340316 \n", + "10640 0.444055 0.426134 0.337194 0.340316 \n", "\n", - "[8817 rows x 27 columns]" + "[8817 rows x 82 columns]" ] }, - "execution_count": 756, + "execution_count": 54, "metadata": {}, "output_type": "execute_result" } @@ -2327,7 +2328,7 @@ }, { "cell_type": "code", - "execution_count": 757, + "execution_count": 55, "metadata": {}, "outputs": [], "source": [ @@ -2367,17 +2368,14 @@ }, { "cell_type": "code", - "execution_count": 758, + "execution_count": 56, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Model: linear\n", - "Model: ridge\n", - "Model: decision_tree\n", - "Model: knn\n" + "Model: linear\n" ] }, { @@ -2387,7 +2385,20 @@ "c:\\Users\\user\\source\\repos\\mai_pi-33_zakharov\\.venv\\Lib\\site-packages\\sklearn\\base.py:486: UserWarning: X has feature names, but LinearRegression was fitted without feature names\n", " warnings.warn(\n", "c:\\Users\\user\\source\\repos\\mai_pi-33_zakharov\\.venv\\Lib\\site-packages\\sklearn\\base.py:486: UserWarning: X has feature names, but LinearRegression was fitted without feature names\n", - " warnings.warn(\n", + " warnings.warn(\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Model: ridge\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ "c:\\Users\\user\\source\\repos\\mai_pi-33_zakharov\\.venv\\Lib\\site-packages\\sklearn\\base.py:486: UserWarning: X has feature names, but RidgeCV was fitted without feature names\n", " warnings.warn(\n", "c:\\Users\\user\\source\\repos\\mai_pi-33_zakharov\\.venv\\Lib\\site-packages\\sklearn\\base.py:486: UserWarning: X has feature names, but RidgeCV was fitted without feature names\n", @@ -2406,6 +2417,8 @@ "name": "stdout", "output_type": "stream", "text": [ + "Model: decision_tree\n", + "Model: knn\n", "Model: random_forest\n" ] }, @@ -2456,116 +2469,116 @@ }, { "cell_type": "code", - "execution_count": 759, + "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", - "\n", + "
\n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", "
 RMSE_trainRMSE_testRMAE_testR2_testRMSE_trainRMSE_testRMAE_testR2_test
knn0.5367120.6023770.6436010.640894knn0.5293590.5943540.6351910.650397
random_forest0.6105110.6343210.6755240.601798random_forest0.6092100.6316180.6731730.605184
decision_tree0.6507040.6834370.7013930.537743decision_tree0.6470250.6743580.6965390.549944
ridge0.7791990.7880520.7763910.385397ridge0.7536370.7591540.7588690.429644
linear0.7791980.7880560.7763790.385390linear0.7525690.7593410.7587840.429364
\n" ], "text/plain": [ - "" + "" ] }, - "execution_count": 759, + "execution_count": 57, "metadata": {}, "output_type": "execute_result" } @@ -2578,6 +2591,516 @@ " cmap=\"viridis\", low=1, high=0.3, subset=[\"RMSE_train\", \"RMSE_test\"]\n", ").background_gradient(cmap=\"plasma\", low=0.3, high=1, subset=[\"RMAE_test\", \"R2_test\"])" ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'knn'" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "best_model = str(reg_metrics.sort_values(by=\"RMSE_test\").iloc[0].name)\n", + "\n", + "display(best_model)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Вывод предсказаний для выборок" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Leather interior_YesCategory_CoupeCategory_Goods wagonCategory_HatchbackCategory_JeepCategory_LimousineCategory_MicrobusCategory_MinivanCategory_PickupCategory_Sedan...Manufacturer_VAZManufacturer_VOLKSWAGENManufacturer_VOLVOManufacturer_სხვაLevyProd. yearEngine volumeAirbagsPricePricePred
151460.00.00.00.00.00.00.00.00.01.0...0.00.00.00.0-1.1875961.943625-0.487669-0.6731500.1445530.557766
141450.00.00.00.00.00.00.00.00.01.0...0.00.00.00.0-1.187596-0.874572-0.900100-1.179883-0.665312-0.603334
89430.00.00.00.00.00.00.00.00.01.0...0.00.00.00.00.0812250.642919-0.4876690.847049-0.144678-0.355422
178891.00.00.00.01.00.00.00.00.00.0...0.00.00.00.0-1.187596-1.5249250.474671-0.419784-0.462869-0.746737
95151.00.00.00.00.00.00.00.00.00.0...0.00.00.00.01.6954951.5100560.474671-0.6731502.7653392.375842
\n", + "

5 rows × 84 columns

\n", + "
" + ], + "text/plain": [ + " Leather interior_Yes Category_Coupe Category_Goods wagon \\\n", + "15146 0.0 0.0 0.0 \n", + "14145 0.0 0.0 0.0 \n", + "8943 0.0 0.0 0.0 \n", + "17889 1.0 0.0 0.0 \n", + "9515 1.0 0.0 0.0 \n", + "\n", + " Category_Hatchback Category_Jeep Category_Limousine \\\n", + "15146 0.0 0.0 0.0 \n", + "14145 0.0 0.0 0.0 \n", + "8943 0.0 0.0 0.0 \n", + "17889 0.0 1.0 0.0 \n", + "9515 0.0 0.0 0.0 \n", + "\n", + " Category_Microbus Category_Minivan Category_Pickup Category_Sedan \\\n", + "15146 0.0 0.0 0.0 1.0 \n", + "14145 0.0 0.0 0.0 1.0 \n", + "8943 0.0 0.0 0.0 1.0 \n", + "17889 0.0 0.0 0.0 0.0 \n", + "9515 0.0 0.0 0.0 0.0 \n", + "\n", + " ... Manufacturer_VAZ Manufacturer_VOLKSWAGEN Manufacturer_VOLVO \\\n", + "15146 ... 0.0 0.0 0.0 \n", + "14145 ... 0.0 0.0 0.0 \n", + "8943 ... 0.0 0.0 0.0 \n", + "17889 ... 0.0 0.0 0.0 \n", + "9515 ... 0.0 0.0 0.0 \n", + "\n", + " Manufacturer_სხვა Levy Prod. year Engine volume Airbags \\\n", + "15146 0.0 -1.187596 1.943625 -0.487669 -0.673150 \n", + "14145 0.0 -1.187596 -0.874572 -0.900100 -1.179883 \n", + "8943 0.0 0.081225 0.642919 -0.487669 0.847049 \n", + "17889 0.0 -1.187596 -1.524925 0.474671 -0.419784 \n", + "9515 0.0 1.695495 1.510056 0.474671 -0.673150 \n", + "\n", + " Price PricePred \n", + "15146 0.144553 0.557766 \n", + "14145 -0.665312 -0.603334 \n", + "8943 -0.144678 -0.355422 \n", + "17889 -0.462869 -0.746737 \n", + "9515 2.765339 2.375842 \n", + "\n", + "[5 rows x 84 columns]" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat(\n", + " [\n", + " train_df,\n", + " price_y_train,\n", + " pd.Series(\n", + " models[best_model][\"train_preds\"],\n", + " index=price_y_train.index,\n", + " name=\"PricePred\",\n", + " ),\n", + " ],\n", + " axis=1,\n", + ").head(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Leather interior_YesCategory_CoupeCategory_Goods wagonCategory_HatchbackCategory_JeepCategory_LimousineCategory_MicrobusCategory_MinivanCategory_PickupCategory_Sedan...Manufacturer_VAZManufacturer_VOLKSWAGENManufacturer_VOLVOManufacturer_სხვაLevyProd. yearEngine volumeAirbagsPricePricePred
109681.00.00.01.00.00.00.00.00.00.0...0.00.00.00.0-0.055651-0.007434-1.0375781.353782-1.316082-0.960788
11211.00.00.00.00.00.00.00.00.01.0...0.00.00.00.0-0.3315770.6429190.4746711.353782-1.489657-0.235577
43551.00.00.00.00.00.00.00.00.01.0...0.00.00.00.00.3984301.076487-0.762623-0.6731500.7713430.887499
177021.00.00.01.00.00.00.00.00.00.0...0.00.00.00.00.528788-0.441003-0.762623-0.673150-0.679792-0.579671
61670.00.00.00.00.00.00.00.00.01.0...0.00.00.00.00.719981-0.441003-0.4876690.340316-0.173638-0.471104
\n", + "

5 rows × 84 columns

\n", + "
" + ], + "text/plain": [ + " Leather interior_Yes Category_Coupe Category_Goods wagon \\\n", + "10968 1.0 0.0 0.0 \n", + "1121 1.0 0.0 0.0 \n", + "4355 1.0 0.0 0.0 \n", + "17702 1.0 0.0 0.0 \n", + "6167 0.0 0.0 0.0 \n", + "\n", + " Category_Hatchback Category_Jeep Category_Limousine \\\n", + "10968 1.0 0.0 0.0 \n", + "1121 0.0 0.0 0.0 \n", + "4355 0.0 0.0 0.0 \n", + "17702 1.0 0.0 0.0 \n", + "6167 0.0 0.0 0.0 \n", + "\n", + " Category_Microbus Category_Minivan Category_Pickup Category_Sedan \\\n", + "10968 0.0 0.0 0.0 0.0 \n", + "1121 0.0 0.0 0.0 1.0 \n", + "4355 0.0 0.0 0.0 1.0 \n", + "17702 0.0 0.0 0.0 0.0 \n", + "6167 0.0 0.0 0.0 1.0 \n", + "\n", + " ... Manufacturer_VAZ Manufacturer_VOLKSWAGEN Manufacturer_VOLVO \\\n", + "10968 ... 0.0 0.0 0.0 \n", + "1121 ... 0.0 0.0 0.0 \n", + "4355 ... 0.0 0.0 0.0 \n", + "17702 ... 0.0 0.0 0.0 \n", + "6167 ... 0.0 0.0 0.0 \n", + "\n", + " Manufacturer_სხვა Levy Prod. year Engine volume Airbags \\\n", + "10968 0.0 -0.055651 -0.007434 -1.037578 1.353782 \n", + "1121 0.0 -0.331577 0.642919 0.474671 1.353782 \n", + "4355 0.0 0.398430 1.076487 -0.762623 -0.673150 \n", + "17702 0.0 0.528788 -0.441003 -0.762623 -0.673150 \n", + "6167 0.0 0.719981 -0.441003 -0.487669 0.340316 \n", + "\n", + " Price PricePred \n", + "10968 -1.316082 -0.960788 \n", + "1121 -1.489657 -0.235577 \n", + "4355 0.771343 0.887499 \n", + "17702 -0.679792 -0.579671 \n", + "6167 -0.173638 -0.471104 \n", + "\n", + "[5 rows x 84 columns]" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat(\n", + " [\n", + " test_df,\n", + " price_y_test,\n", + " pd.Series(\n", + " models[best_model][\"preds\"],\n", + " index=price_y_test.index,\n", + " name=\"PricePred\",\n", + " ),\n", + " ],\n", + " axis=1,\n", + ").head(5)" + ] } ], "metadata": {