Yunusov_Niyaz/MII_Yunusov_Niyaz
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Lab3
MII_Yunusov_Niyaz/notebooks/lec1.ipynb

907 lines
213 KiB
Plaintext
Raw Permalink Normal View History

Lab1-2
2024-09-30 23:02:17 +04:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Работа с NumPy"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"matrix = \n",
" [[4 5 0]\n",
" [9 9 9]] \n",
"\n",
"tmatrix = \n",
" [[4 9]\n",
" [5 9]\n",
" [0 9]] \n",
"\n",
"vector = \n",
" [4 5 0 9 9 9] \n",
"\n",
"tvector = \n",
" [[4]\n",
" [5]\n",
" [0]\n",
" [9]\n",
" [9]\n",
" [9]] \n",
"\n",
"list_matrix = \n",
" [array([4, 5, 0]), array([9, 9, 9])] \n",
"\n",
"matrix as str = \n",
" [[4 5 0]\n",
" [9 9 9]] \n",
"\n",
"matrix type is <class 'numpy.ndarray'> \n",
"\n",
"vector type is <class 'numpy.ndarray'> \n",
"\n",
"list_matrix type is <class 'list'> \n",
"\n",
"str_matrix type is <class 'str'> \n",
"\n",
"formatted_vector = \n",
" 4; 5; 0; 9; 9; 9 \n",
"\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
"matrix = np.array([[4, 5, 0], [9, 9, 9]])\n",
"print(\"matrix = \\n\", matrix, \"\\n\")\n",
"\n",
"tmatrix = matrix.T\n",
"print(\"tmatrix = \\n\", tmatrix, \"\\n\")\n",
"\n",
"vector = np.ravel(matrix)\n",
"print(\"vector = \\n\", vector, \"\\n\")\n",
"\n",
"tvector = np.reshape(vector, (6, 1))\n",
"print(\"tvector = \\n\", tvector, \"\\n\")\n",
"\n",
"list_matrix = list(matrix)\n",
"print(\"list_matrix = \\n\", list_matrix, \"\\n\")\n",
"\n",
"str_matrix = str(matrix)\n",
"print(\"matrix as str = \\n\", str_matrix, \"\\n\")\n",
"\n",
"print(\"matrix type is\", type(matrix), \"\\n\")\n",
"\n",
"print(\"vector type is\", type(vector), \"\\n\")\n",
"\n",
"print(\"list_matrix type is\", type(list_matrix), \"\\n\")\n",
"\n",
"print(\"str_matrix type is\", type(str_matrix), \"\\n\")\n",
"\n",
"formatted_vector = \"; \".join(map(str, vector))\n",
"print(\"formatted_vector = \\n\", formatted_vector, \"\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Работа с Pandas DataFrame\n",
"\n",
"https://pandas.pydata.org/docs/user_guide/10min.html"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Работа с данными - чтение и запись CSV"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"df = pd.read_csv(\"../data/car_price_prediction.csv\")\n",
"\n",
"df.to_csv(\"../data/test.csv\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Работа с данными - основные команды"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 19237 entries, 0 to 19236\n",
"Data columns (total 18 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 ID 19237 non-null int64 \n",
" 1 Price 19237 non-null int64 \n",
" 2 Levy 19237 non-null object \n",
" 3 Manufacturer 19237 non-null object \n",
" 4 Model 19237 non-null object \n",
" 5 Prod. year 19237 non-null int64 \n",
" 6 Category 19237 non-null object \n",
" 7 Leather interior 19237 non-null object \n",
" 8 Fuel type 19237 non-null object \n",
" 9 Engine volume 19237 non-null object \n",
" 10 Mileage 19237 non-null object \n",
" 11 Cylinders 19237 non-null float64\n",
" 12 Gear box type 19237 non-null object \n",
" 13 Drive wheels 19237 non-null object \n",
" 14 Doors 19237 non-null object \n",
" 15 Wheel 19237 non-null object \n",
" 16 Color 19237 non-null object \n",
" 17 Airbags 19237 non-null int64 \n",
"dtypes: float64(1), int64(4), object(13)\n",
"memory usage: 2.6+ MB\n",
" count mean std min 25% \\\n",
"ID 19237.0 4.557654e+07 936591.422799 20746880.0 45698374.0 \n",
"Price 19237.0 1.855593e+04 190581.269684 1.0 5331.0 \n",
"Prod. year 19237.0 2.010913e+03 5.668673 1939.0 2009.0 \n",
"Cylinders 19237.0 4.582991e+00 1.199933 1.0 4.0 \n",
"Airbags 19237.0 6.582627e+00 4.320168 0.0 4.0 \n",
"\n",
" 50% 75% max \n",
"ID 45772308.0 45802036.0 45816654.0 \n",
"Price 13172.0 22075.0 26307500.0 \n",
"Prod. year 2012.0 2015.0 2020.0 \n",
"Cylinders 4.0 4.0 16.0 \n",
"Airbags 6.0 12.0 16.0 \n",
" ID Price Levy Manufacturer Model Prod. year Category \\\n",
"0 45654403 13328 1399 LEXUS RX 450 2010 Jeep \n",
"1 44731507 16621 1018 CHEVROLET Equinox 2011 Jeep \n",
"2 45774419 8467 - HONDA FIT 2006 Hatchback \n",
"3 45769185 3607 862 FORD Escape 2011 Jeep \n",
"4 45809263 11726 446 HONDA FIT 2014 Hatchback \n",
"\n",
" Fuel type Engine volume Mileage Cylinders Gear box type Drive wheels \\\n",
"0 Hybrid 3.5 186005 km 6.0 Automatic 4x4 \n",
"1 Petrol 3 192000 km 6.0 Tiptronic 4x4 \n",
"2 Petrol 1.3 200000 km 4.0 Variator Front \n",
"3 Hybrid 2.5 168966 km 4.0 Automatic 4x4 \n",
"4 Petrol 1.3 91901 km 4.0 Automatic Front \n",
"\n",
" Doors Wheel Airbags \n",
"0 04-May Left wheel 12 \n",
"1 04-May Left wheel 8 \n",
"2 04-May Right-hand drive 2 \n",
"3 04-May Left wheel 0 \n",
"4 04-May Left wheel 4 \n",
" ID Price Levy Manufacturer Model Prod. year Category \\\n",
"19232 45798355 8467 - MERCEDES-BENZ CLK 200 1999 Coupe \n",
"19233 45778856 15681 831 HYUNDAI Sonata 2011 Sedan \n",
"19234 45804997 26108 836 HYUNDAI Tucson 2010 Jeep \n",
"19235 45793526 5331 1288 CHEVROLET Captiva 2007 Jeep \n",
"19236 45813273 470 753 HYUNDAI Sonata 2012 Sedan \n",
"\n",
" Fuel type Engine volume Mileage Cylinders Gear box type \\\n",
"19232 CNG 2.0 Turbo 300000 km 4.0 Manual \n",
"19233 Petrol 2.4 161600 km 4.0 Tiptronic \n",
"19234 Diesel 2 116365 km 4.0 Automatic \n",
"19235 Diesel 2 51258 km 4.0 Automatic \n",
"19236 Hybrid 2.4 186923 km 4.0 Automatic \n",
"\n",
" Drive wheels Doors Wheel Airbags \n",
"19232 Rear 02-Mar Left wheel 5 \n",
"19233 Front 04-May Left wheel 8 \n",
"19234 Front 04-May Left wheel 4 \n",
"19235 Front 04-May Left wheel 4 \n",
"19236 Front 04-May Left wheel 12 \n",
" ID Price Levy Manufacturer Model Prod. year Category \\\n",
"7815 45765530 1 - OPEL Astra 1999 Sedan \n",
"16992 45772201 1 1202 CHEVROLET Lacetti 2006 Hatchback \n",
"4776 45687380 3 810 VOLKSWAGEN Jetta 2016 Sedan \n",
"13419 45816352 3 503 TOYOTA Prius C 2012 Hatchback \n",
"14642 45816369 3 87 PORSCHE Panamera 2011 Sedan \n",
"\n",
" Fuel type Engine volume Mileage Cylinders Gear box type \\\n",
"7815 Petrol 1.6 122231 km 4.0 Manual \n",
"16992 Petrol 1.6 200000 km 4.0 Manual \n",
"4776 Petrol 1.8 Turbo 41000 km 4.0 Automatic \n",
"13419 Petrol 1.5 172800 km 4.0 Automatic \n",
"14642 Petrol 0 196800 km 6.0 Automatic \n",
"\n",
" Drive wheels Doors Wheel Airbags \n",
"7815 Front 04-May Left wheel 4 \n",
"16992 Front 04-May Left wheel 2 \n",
"4776 Front 04-May Left wheel 8 \n",
"13419 Front 04-May Left wheel 12 \n",
"14642 Rear 04-May Left wheel 12 \n",
" ID Price Levy Manufacturer Model Prod. year \\\n",
"14839 45792307 297930 - LAND ROVER Range Rover Vogue 2019 \n",
"5008 45810285 308906 1694 PORSCHE 911 2016 \n",
"1225 45795524 627220 - MERCEDES-BENZ G 65 AMG 63AMG 2020 \n",
"8541 45761204 872946 2067 LAMBORGHINI Urus 2019 \n",
"16983 45812886 26307500 - OPEL Combo 1999 \n",
"\n",
" Category Fuel type Engine volume Mileage Cylinders Gear box type \\\n",
"14839 Jeep Diesel 3.0 Turbo 4500 km 8.0 Tiptronic \n",
"5008 Coupe Petrol 4 8690 km 6.0 Automatic \n",
"1225 Jeep Petrol 6.3 Turbo 0 km 8.0 Tiptronic \n",
"8541 Universal Petrol 4 2531 km 8.0 Tiptronic \n",
"16983 Goods wagon Diesel 1.7 99999 km 4.0 Manual \n",
"\n",
" Drive wheels Doors Wheel Airbags \n",
"14839 4x4 04-May Left wheel 12 \n",
"5008 Rear 02-Mar Left wheel 12 \n",
"1225 4x4 04-May Left wheel 12 \n",
"8541 4x4 04-May Left wheel 0 \n",
"16983 Front 02-Mar Left wheel 0 \n"
]
}
],
"source": [
"df.info()\n",
"\n",
"print(df.describe().transpose())\n",
"\n",
"cleared_df = df.drop([\"Color\", \"Leather interior\"], axis=1)\n",
"print(cleared_df.head())\n",
"print(cleared_df.tail())\n",
"\n",
"sorted_df = cleared_df.sort_values(by=\"Price\")\n",
"print(sorted_df.head())\n",
"print(sorted_df.tail())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Работа с данными - работа с элементами"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0 RX 450\n",
"1 Equinox\n",
"2 FIT\n",
"3 Escape\n",
"4 FIT\n",
" ... \n",
"19232 CLK 200\n",
"19233 Sonata\n",
"19234 Tucson\n",
"19235 Captiva\n",
"19236 Sonata\n",
"Name: Model, Length: 19237, dtype: object\n",
"ID 45809760\n",
"Price 2901\n",
"Levy 473\n",
"Manufacturer CHEVROLET\n",
"Model Cruze\n",
"Prod. year 2014\n",
"Category Sedan\n",
"Leather interior Yes\n",
"Fuel type Petrol\n",
"Engine volume 1.4\n",
"Mileage 80827 km\n",
"Cylinders 4.0\n",
"Gear box type Automatic\n",
"Drive wheels Front\n",
"Doors 04-May\n",
"Wheel Left wheel\n",
"Color Green\n",
"Airbags 12\n",
"Name: 100, dtype: object\n",
"2901\n",
" Model Price\n",
"100 Cruze 2901\n",
"101 911 706\n",
"102 Fusion 314\n",
"103 GX 460 15681\n",
"104 Sprinter 26657\n",
".. ... ...\n",
"196 Sonata 706\n",
"197 E 350 5802\n",
"198 Camry 25716\n",
"199 Orlando 14426\n",
"200 RAV 4 10820\n",
"\n",
"[101 rows x 2 columns]\n",
" ID Price Levy Manufacturer Model Prod. year Category \\\n",
"0 45654403 13328 1399 LEXUS RX 450 2010 Jeep \n",
"1 44731507 16621 1018 CHEVROLET Equinox 2011 Jeep \n",
"2 45774419 8467 - HONDA FIT 2006 Hatchback \n",
"\n",
" Leather interior Fuel type Engine volume Mileage Cylinders \\\n",
"0 Yes Hybrid 3.5 186005 km 6.0 \n",
"1 No Petrol 3 192000 km 6.0 \n",
"2 No Petrol 1.3 200000 km 4.0 \n",
"\n",
" Gear box type Drive wheels Doors Wheel Color Airbags \n",
"0 Automatic 4x4 04-May Left wheel Silver 12 \n",
"1 Tiptronic 4x4 04-May Left wheel Black 8 \n",
"2 Variator Front 04-May Right-hand drive Black 2 \n",
"ID 45654403\n",
"Price 13328\n",
"Levy 1399\n",
"Manufacturer LEXUS\n",
"Model RX 450\n",
"Prod. year 2010\n",
"Category Jeep\n",
"Leather interior Yes\n",
"Fuel type Hybrid\n",
"Engine volume 3.5\n",
"Mileage 186005 km\n",
"Cylinders 6.0\n",
"Gear box type Automatic\n",
"Drive wheels 4x4\n",
"Doors 04-May\n",
"Wheel Left wheel\n",
"Color Silver\n",
"Airbags 12\n",
"Name: 0, dtype: object\n",
" ID Price\n",
"3 45769185 3607\n",
"4 45809263 11726\n",
" ID Price\n",
"3 45769185 3607\n",
"4 45809263 11726\n"
]
}
],
"source": [
"print(df[\"Model\"])\n",
"\n",
"print(df.loc[100])\n",
"\n",
"print(df.loc[100, \"Price\"])\n",
"\n",
"print(df.loc[100:200, [\"Model\", \"Price\"]])\n",
"\n",
"print(df[0:3])\n",
"\n",
"print(df.iloc[0])\n",
"\n",
"print(df.iloc[3:5, 0:2])\n",
"\n",
"print(df.iloc[[3, 4], [0, 1]])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Работа с данными - отбор и группировка"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['LEXUS' 'CHEVROLET' 'HONDA' 'FORD' 'HYUNDAI' 'TOYOTA' 'MERCEDES-BENZ'\n",
" 'OPEL' 'PORSCHE' 'BMW' 'JEEP' 'VOLKSWAGEN' 'AUDI' 'RENAULT' 'NISSAN'\n",
" 'SUBARU' 'DAEWOO' 'KIA' 'MITSUBISHI' 'SSANGYONG' 'MAZDA' 'GMC' 'FIAT'\n",
" 'INFINITI' 'ALFA ROMEO' 'SUZUKI' 'ACURA' 'LINCOLN' 'VAZ' 'GAZ' 'CITROEN'\n",
" 'LAND ROVER' 'MINI' 'DODGE' 'CHRYSLER' 'JAGUAR' 'ISUZU' 'SKODA'\n",
" 'DAIHATSU' 'BUICK' 'TESLA' 'CADILLAC' 'PEUGEOT' 'BENTLEY' 'VOLVO' 'სხვა'\n",
" 'HAVAL' 'HUMMER' 'SCION' 'UAZ' 'MERCURY' 'ZAZ' 'ROVER' 'SEAT' 'LANCIA'\n",
" 'MOSKVICH' 'MASERATI' 'FERRARI' 'SAAB' 'LAMBORGHINI' 'ROLLS-ROYCE'\n",
" 'PONTIAC' 'SATURN' 'ASTON MARTIN' 'GREATWALL']\n",
"LEXUS count = 982\n",
"CHEVROLET count = 1069\n",
"HONDA count = 977\n",
"FORD count = 1111\n",
"HYUNDAI count = 3769\n",
"TOYOTA count = 3662\n",
"MERCEDES-BENZ count = 2076\n",
"OPEL count = 397\n",
"PORSCHE count = 54\n",
"BMW count = 1049\n",
"JEEP count = 138\n",
"VOLKSWAGEN count = 579\n",
"AUDI count = 255\n",
"RENAULT count = 37\n",
"NISSAN count = 660\n",
"SUBARU count = 275\n",
"DAEWOO count = 91\n",
"KIA count = 421\n",
"MITSUBISHI count = 289\n",
"SSANGYONG count = 441\n",
"MAZDA count = 183\n",
"GMC count = 15\n",
"FIAT count = 78\n",
"INFINITI count = 30\n",
"ALFA ROMEO count = 4\n",
"SUZUKI count = 76\n",
"ACURA count = 15\n",
"LINCOLN count = 15\n",
"VAZ count = 48\n",
"GAZ count = 12\n",
"CITROEN count = 9\n",
"LAND ROVER count = 49\n",
"MINI count = 48\n",
"DODGE count = 91\n",
"CHRYSLER count = 26\n",
"JAGUAR count = 42\n",
"ISUZU count = 4\n",
"SKODA count = 20\n",
"DAIHATSU count = 13\n",
"BUICK count = 16\n",
"TESLA count = 1\n",
"CADILLAC count = 14\n",
"PEUGEOT count = 17\n",
"BENTLEY count = 2\n",
"VOLVO count = 19\n",
"სხვა count = 2\n",
"HAVAL count = 1\n",
"HUMMER count = 5\n",
"SCION count = 7\n",
"UAZ count = 12\n",
"MERCURY count = 4\n",
"ZAZ count = 2\n",
"ROVER count = 3\n",
"SEAT count = 2\n",
"LANCIA count = 1\n",
"MOSKVICH count = 4\n",
"MASERATI count = 4\n",
"FERRARI count = 2\n",
"SAAB count = 2\n",
"LAMBORGHINI count = 1\n",
"ROLLS-ROYCE count = 2\n",
"PONTIAC count = 1\n",
"SATURN count = 1\n",
"ASTON MARTIN count = 1\n",
"GREATWALL count = 1\n",
"Total count = 19237\n",
" Model Category Count\n",
"0 09-Mar Sedan 2\n",
"1 100 Jeep 2\n",
"2 100 NX Sedan 1\n",
"3 1000 Jeep 6\n",
"4 1000 Sedan 11\n",
"... ... ... ...\n",
"2053 macan Jeep 1\n",
"2054 macan Sedan 1\n",
"2055 macan S Jeep 1\n",
"2056 tC Coupe 3\n",
"2057 xD Hatchback 3\n",
"\n",
"[2058 rows x 3 columns]\n"
]
}
],
"source": [
"s_values = df[\"Manufacturer\"].unique()\n",
"print(s_values)\n",
"\n",
"s_total = 0\n",
"for s_value in s_values:\n",
" count = df[df[\"Manufacturer\"] == s_value].shape[0]\n",
" s_total += count\n",
" print(s_value, \"count =\", count)\n",
"print(\"Total count = \", s_total)\n",
"\n",
"print(df.groupby([\"Model\", \"Category\"]).size().reset_index(name=\"Count\")) # type: ignore"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Визуализация - Исходные данные"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Manufacturer Model Levy\n",
"0 LEXUS RX 450 1399\n",
"1 CHEVROLET Equinox 1018\n",
"2 HONDA FIT -\n",
"3 FORD Escape 862\n",
"4 HONDA FIT 446\n",
"... ... ... ...\n",
"19232 MERCEDES-BENZ CLK 200 -\n",
"19233 HYUNDAI Sonata 831\n",
"19234 HYUNDAI Tucson 836\n",
"19235 CHEVROLET Captiva 1288\n",
"19236 HYUNDAI Sonata 753\n",
"\n",
"[19237 rows x 3 columns]\n"
]
}
],
"source": [
"data = df[[\"Manufacturer\", \"Model\", \"Levy\"]].copy()\n",
"data.dropna(subset=[\"Levy\"], inplace=True)\n",
"print(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Визуализация - Сводка пяти чисел\n",
"\n",
"<img src=\"assets/quantile.png\" width=\"400\" style=\"background-color: white\">"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Prod. year \n",
" min q1 q2 median q3 max\n",
"Manufacturer \n",
"ACURA 2001 2010.00 2012.0 2012.0 2014.00 2015\n",
"ALFA ROMEO 2001 2001.00 2003.0 2003.0 2007.00 2013\n",
"ASTON MARTIN 2007 2007.00 2007.0 2007.0 2007.00 2007\n",
"AUDI 1995 2010.00 2013.0 2013.0 2014.00 2018\n",
"BENTLEY 2012 2013.00 2014.0 2014.0 2015.00 2016\n",
"... ... ... ... ... ... ...\n",
"VAZ 1974 1986.00 1995.5 1995.5 2004.25 2018\n",
"VOLKSWAGEN 1980 2003.00 2012.0 2012.0 2014.00 2019\n",
"VOLVO 1993 2000.50 2006.0 2006.0 2010.50 2014\n",
"ZAZ 1989 1989.25 1989.5 1989.5 1989.75 1990\n",
"სხვა 2005 2005.50 2006.0 2006.0 2006.50 2007\n",
"\n",
"[65 rows x 6 columns]\n",
" Prod. year \n",
" low_iqr iqr high_iqr\n",
"Manufacturer \n",
"ACURA 2004.000 4.00 2020.000\n",
"ALFA ROMEO 1992.000 6.00 2016.000\n",
"ASTON MARTIN 2007.000 0.00 2007.000\n",
"AUDI 2004.000 4.00 2020.000\n",
"BENTLEY 2010.000 2.00 2018.000\n",
"... ... ... ...\n",
"VAZ 1958.625 18.25 2031.625\n",
"VOLKSWAGEN 1986.500 11.00 2030.500\n",
"VOLVO 1985.500 10.00 2025.500\n",
"ZAZ 1988.500 0.50 1990.500\n",
"სხვა 2004.000 1.00 2008.000\n",
"\n",
"[65 rows x 3 columns]\n"
]
},
{
"data": {
"text/plain": [
"<Axes: title={'center': 'Prod. year'}, xlabel='Manufacturer'>"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAAHOCAYAAABaeEesAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAADW8UlEQVR4nOydd1wUx/vHPwcHCEixUESkROwSa8QSQaKiFIUgSZTYa0RFBSTRGHv0GwSxxJLERP2qmESDh0FMREXACIkaMWCHgF2agnogx8H8/uC3++W4gzu4fs779eLF3czs7LOzs7tzM599Hg4hhIBCoVAoFAqFIjd66jaAQqFQKBQKRVegAysKhUKhUCgUBUEHVhQKhUKhUCgKgg6sKBQKhUKhUBQEHVhRKBQKhUKhKAg6sKJQKBQKhUJREHRgRaFQKBQKhaIg6MCKQqFQKBQKRUHQgRWFQqFQKBSKgqADKwpFSXA4HKxZs0bdZug858+fB4fDwfnz55sst2bNGnA4HJSUlKjGMC3j7t278PLygoWFBTgcDng8nrpNolC0Ejqwomgd+/fvB4fDEfmztraGp6cnTp06pW7z5ObGjRtYs2YNCgoK1G0KpQWMGDECHA4HXbp0kZifnJzM9ttjx46p2LrGmTZtGrKzs/Hll1/i4MGDGDhwoELrf/z4MdasWYOsrCyF1kuhaBpcdRtAobSUdevWwdnZGYQQFBYWYv/+/fDx8cGvv/4KPz8/dZvXYm7cuIG1a9dixIgRcHJyUrc5lBbQqlUr5Obm4q+//sKgQYNE8g4fPoxWrVrh9evXarJOnMrKSmRkZODzzz/HwoULlbKPx48fY+3atXByckLfvn2Vsg8KRROgM1YUrcXb2xuTJ0/GlClTEBERgfT0dBgYGODIkSPqNk1rEAqFEAgE6jZD5+jcuTO6desm1hdfv36N48ePw9fXV02WSaa4uBgAYGlpqV5DWsDr169RW1srVx18Pl9B1lAodGBF0SEsLS1hbGwMLld0IpbP5yM8PBydOnWCkZERunXrhujoaBBCANT9Wu/evTu6d++OyspKdrtnz56hQ4cOGDp0KGpqagAA06dPR+vWrfHvv/9izJgxMDU1hZ2dHdatW8fW1xRXr16Ft7c3zM3N0bp1a4wcORKZmZls/v79+/HBBx8AADw9PdklI2n6oaNHj6Jnz55o1aoVevfujePHj2P69OkiM14FBQXgcDiIjo7G1q1b0blzZxgZGeHGjRsAgHPnzmH48OEwNTWFpaUl/P39cfPmTZH9NKyTgdEv1YfD4WDhwoU4fPgwunXrhlatWmHAgAFIS0sT2/7Ro0eYOXMmbGxsYGRkhF69euGHH34QK/fw4UMEBATA1NQU1tbWWLp0Kaqqqppsm4aUlJTgww8/hLm5Odq1a4fFixeLzB55eHigT58+Erft1q0bxowZI9N+Jk2ahJ9++knkof/rr7+ioqICH374oVj5e/fuISQkBN26dYOxsTHatWuHDz74QGxJmFkK/+OPPxAWFgYrKyuYmpri/fffZwdIDI3p/JycnDB9+nQAdefO0dERALBs2TJwOBz2HMtqEwCUlZVh6dKlcHJygpGREezt7TF16lSUlJTg/PnzeOeddwAAM2bMYPv1/v37xeypz4gRIzBixAj2O6On+/HHH7Fy5Up07NgRJiYmePHiBQDgzz//xNixY2FhYQETExN4eHjgjz/+EKmT6as3btxAcHAw2rRpg3fffVds3xRKS6FLgRStpby8HCUlJSCEoKioCDt27MCrV68wefJktgwhBOPHj0dKSgpmzZqFvn374vfff8eyZcvw6NEjxMbGwtjYGAcOHMCwYcPw+eefY8uWLQCABQsWoLy8HPv374e+vj5bZ01NDcaOHYvBgwcjKioKv/32G1avXg2hUIh169Y1au/169cxfPhwmJubIzIyEgYGBvjmm28wYsQIpKamws3NDe7u7ggNDcX27duxYsUK9OjRAwDY/5I4efIkPvroI7i6umLTpk14/vw5Zs2ahY4dO0osv2/fPrx+/Rpz586FkZER2rZtizNnzsDb2xtvvfUW1qxZg8rKSuzYsQPDhg3D33//3eIlydTUVPz0008IDQ2FkZERdu3ahbFjx+Kvv/5C7969AQCFhYUYPHgwOxCzsrLCqVOnMGvWLLx48QJLliwBUDcAHjlyJO7fv4/Q0FDY2dnh4MGDOHfuXLNs+vDDD+Hk5IRNmzYhMzMT27dvx/Pnz/Hf//4XADBlyhTMmTMHOTk5rI0AcOnSJdy5cwcrV66UaT/BwcFYs2YNzp8/j/feew8AEBcXh5EjR8La2lqs/KVLl3Dx4kVMnDgR9vb2KCgowO7duzFixAjcuHEDJiYmIuUXLVqENm3aYPXq1SgoKMDWrVuxcOFC/PTTT81qj8DAQFhaWmLp0qWYNGkSfHx80Lp162bZ9OrVKwwfPhw3b97EzJkz0b9/f5SUlODEiRN4+PAhevTogXXr1mHVqlWYO3cuhg8fDgAYOnRos2xlWL9+PQwNDREREYGqqioYGhri3Llz8Pb2xoABA7B69Wro6elh3759eO+995Ceni62JPvBBx+gS5cu2Lhxo0w/iigUmSEUipaxb98+AkDsz8jIiOzfv1+kLI/HIwDIhg0bRNKDgoIIh8Mhubm5bNry5cuJnp4eSUtLI0ePHiUAyNatW0W2mzZtGgFAFi1axKbV1tYSX19fYmhoSIqLi9l0AGT16tXs94CAAGJoaEjy8vLYtMePHxMzMzPi7u7OpjH7TklJkak9XF1dib29PXn58iWbdv78eQKAODo6smn5+fkEADE3NydFRUUidfTt25dYW1uT0tJSNu3atWtET0+PTJ06VeT469fJsHr1atLwdsKcl8uXL7Np9+7dI61atSLvv/8+mzZr1izSoUMHUlJSIrL9xIkTiYWFBamoqCCEELJ161YCgPz8889sGT6fT1xcXGRqL8bG8ePHi6SHhIQQAOTatWuEEELKyspIq1atyKeffipSLjQ0lJiampJXr141uR8PDw/Sq1cvQgghAwcOJLNmzSKEEPL8+XNiaGhIDhw4QFJSUggAcvToUXY75jjrk5GRQQCQ//73v2wa0/9HjRpFamtr2fSlS5cSfX19UlZWxqY17IMMjo6OZNq0aex3pm9s3rxZpJysNq1atYoAIPHx8WLlGRsvXbpEAJB9+/ZJtYfBw8ODeHh4sN+ZdnvrrbdEbKutrSVdunQhY8aMEWmTiooK4uzsTEaPHs2mMf1g0qRJYvujUBQBXQqkaC07d+5EcnIykpOTcejQIXh6emL27NmIj49nyyQlJUFfXx+hoaEi24aHh4MQIvIW4Zo1a9CrVy9MmzYNISEh8PDwENuOob7Al5lpEQgEOHPmjMTyNTU1OH36NAICAvDWW2+x6R06dEBwcDAuXLjALmc0h8ePHyM7OxtTp05lZxmAuuUsV1dXidtMmDABVlZW7PcnT54gKysL06dPR9u2bdn0t99+G6NHj0ZSUlKz7WIYMmQIBgwYwH53cHCAv78/fv/9d9TU1IAQgl9++QXjxo0DIQQlJSXs35gxY1BeXo6///4bQN257NChA4KCgtj6TExMMHfu3GbZtGDBApHvixYtYusHAAsLC/j7++PIkSPsTEZNTQ1++ukndhlSVoKDgxEfHw+BQIBjx45BX18f77//vsSyxsbG7Ofq6mqUlpbCxcUFlpaWbBvUZ+7cuSLLr8OHD0dNTQ3u3bsns33SkNWmX375BX369JF4bA2XiBXBtGnTRGzLysrC3bt3ERwcjNLSUrYP8fl8jBw5EmlpaWI6rE8++UThdlEoANVYUbSYQYMGYdSoURg1ahQ+/vhjnDx5Ej179mQHOUCdRsTOzg5mZmYi2zJLa/UfQoaGhvjhhx+Qn5+Ply9fYt++fRIfCnp6eiKDIwDo2rUrADTqIqG4uBgVFRXo1q2bWF6PHj1QW1uLBw8eyH7w/w9jv4uLi1iepDQAcHZ2llhHY7YxD6iWIMnlQNeuXVFRUYHi4mIUFxejrKwM3377LaysrET+ZsyYAQAoKipi7XRxcRE7J5L
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"def q1(x):\n",
" return x.quantile(0.25)\n",
"\n",
"\n",
"# median = quantile(0.5)\n",
"def q2(x):\n",
" return x.quantile(0.5)\n",
"\n",
"\n",
"def q3(x):\n",
" return x.quantile(0.75)\n",
"\n",
"\n",
"def iqr(x):\n",
" return q3(x) - q1(x)\n",
"\n",
"\n",
"def low_iqr(x):\n",
" return max(0, q1(x) - 1.5 * iqr(x))\n",
"\n",
"\n",
"def high_iqr(x):\n",
" return q3(x) + 1.5 * iqr(x)\n",
"\n",
"quantiles = df[[\"Manufacturer\", \"Prod. year\"]].groupby([\"Manufacturer\"]).aggregate([\"min\", q1, q2, \"median\", q3, \"max\"])\n",
"print(quantiles)\n",
"\n",
"iqrs = (\n",
" df[[\"Manufacturer\", \"Prod. year\"]].groupby([\"Manufacturer\"]).aggregate([low_iqr, iqr, high_iqr])\n",
")\n",
"print(iqrs)\n",
"\n",
"df.boxplot(column=\"Prod. year\", by=\"Manufacturer\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Визуализация - Гистограмма"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: ylabel='Frequency'>"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df.plot.hist(column=[\"Prod. year\"], bins=80)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Визуализация - Точечная диаграмма"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: xlabel='Fuel type', ylabel='Category'>"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df.plot.scatter(x=\"Fuel type\", y=\"Category\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Визуализация - Столбчатая диаграмма"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.legend.Legend at 0x173840b6240>"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plot = df.groupby([\"Category\", \"Gear box type\"]).size().unstack().plot.bar(color=[\"pink\", \"green\"])\n",
"plot.legend([\"Automatic\",\"Not automatic\"])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Визуализация - Временные ряды"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 19237 entries, 0 to 19236\n",
"Data columns (total 4 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Manufacturer 19237 non-null object \n",
" 1 Price 19237 non-null int64 \n",
" 2 Prod. year 19237 non-null int64 \n",
" 3 date 19237 non-null datetime64[ns]\n",
"dtypes: datetime64[ns](1), int64(2), object(1)\n",
"memory usage: 601.3+ KB\n",
" Manufacturer Price Prod. year date\n",
"0 LEXUS 13328 2010 2010-01-01\n",
"1 CHEVROLET 16621 2011 2011-01-01\n",
"2 HONDA 8467 2006 2006-01-01\n",
"3 FORD 3607 2011 2011-01-01\n",
"4 HONDA 11726 2014 2014-01-01\n",
"... ... ... ... ...\n",
"19232 MERCEDES-BENZ 8467 1999 1999-01-01\n",
"19233 HYUNDAI 15681 2011 2011-01-01\n",
"19234 HYUNDAI 26108 2010 2010-01-01\n",
"19235 CHEVROLET 5331 2007 2007-01-01\n",
"19236 HYUNDAI 470 2012 2012-01-01\n",
"\n",
"[19237 rows x 4 columns]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n",
"Locator attempting to generate 32544 ticks ([-12802.0, ..., 19741.0]), which exceeds Locator.MAXTICKS (1000).\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from datetime import datetime\n",
"import matplotlib.dates as md\n",
"\n",
"dt = pd.read_csv(\"../data/car_price_prediction.csv\")\n",
"ts = dt[[\"Manufacturer\",\"Price\",\"Prod. year\"]].copy()\n",
"tf = ts[\"Manufacturer\"].unique()\n",
"ts[\"date\"] = ts[\"Prod. year\"].astype(str)\n",
"ts[\"date\"] = ts.apply(lambda row: datetime.strptime(row[\"date\"], \"%Y\"), axis=1)\n",
"ts.info()\n",
"\n",
"print(ts)\n",
"\n",
"plot = ts.plot.line(x=\"date\", y=\"Price\")\n",
"plot.xaxis.set_major_locator(md.DayLocator(interval=1))\n",
"plot.xaxis.set_major_formatter(md.DateFormatter(\"%Y\"))\n",
"plot.tick_params(axis=\"x\", labelrotation=90)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.12.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink