diff --git a/04_Linear_Regression_3_Notebook.ipynb b/04_Linear_Regression_3_Notebook.ipynb new file mode 100644 index 0000000..6f474c1 --- /dev/null +++ b/04_Linear_Regression_3_Notebook.ipynb @@ -0,0 +1,1095 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d974e538", + "metadata": { + "id": "d974e538" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d6c6296a", + "metadata": { + "id": "d6c6296a" + }, + "outputs": [], + "source": [ + "!gdown 1bwRmKkPwmLKiqOgQ_LnKH0Vsc3mJKmVR" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6ab99b71", + "metadata": { + "id": "6ab99b71" + }, + "outputs": [], + "source": [ + "df = pd.read_csv('cars24-car-price-cleaned.csv')\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "62b5ef95", + "metadata": { + "id": "62b5ef95" + }, + "outputs": [], + "source": [ + "from sklearn.preprocessing import MinMaxScaler\n", + "min_max_scaler = MinMaxScaler()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "158155bb", + "metadata": { + "id": "158155bb" + }, + "outputs": [], + "source": [ + "df1=pd.DataFrame(min_max_scaler.fit_transform(df[['year', 'km_driven', 'mileage', 'engine', 'max_power',\n", + " 'age', 'make', 'model', 'Individual', 'Trustmark Dealer', 'Diesel',\n", + " 'Electric', 'LPG', 'Petrol', 'Manual', '5', '>5']]),columns= ['year', 'km_driven', 'mileage', 'engine', 'max_power',\n", + " 'age', 'make', 'model', 'Individual', 'Trustmark Dealer', 'Diesel',\n", + " 'Electric', 'LPG', 'Petrol', 'Manual', '5', '>5'])\n", + "df1" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8d8db6e2", + "metadata": { + "id": "8d8db6e2" + }, + "outputs": [], + "source": [ + "y = df[\"selling_price\"]\n", + "y" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8c1d4c27", + "metadata": { + "id": "8c1d4c27" + }, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "\n", + "X_train, X_test, y_train, y_test = train_test_split(df1,y,test_size=0.2,random_state= 10)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8ce5de82", + "metadata": { + "id": "8ce5de82" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "dac2ff6c", + "metadata": { + "id": "dac2ff6c" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1f489187", + "metadata": { + "id": "1f489187" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fc256ae7", + "metadata": { + "id": "fc256ae7" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d1d540cc", + "metadata": { + "id": "d1d540cc" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4c1af6a6", + "metadata": { + "id": "4c1af6a6" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9ce90110", + "metadata": { + "id": "9ce90110" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "121ca3cc", + "metadata": { + "id": "121ca3cc" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "31490203", + "metadata": { + "id": "31490203" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e7ad96e9", + "metadata": { + "id": "e7ad96e9" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "81f35e84", + "metadata": { + "id": "81f35e84" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e2ba7e40", + "metadata": { + "id": "e2ba7e40" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f99ed52b", + "metadata": { + "id": "f99ed52b" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e4961c69", + "metadata": { + "id": "e4961c69" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "47142627", + "metadata": { + "id": "47142627" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "92524f4d", + "metadata": { + "id": "92524f4d" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2bf53579", + "metadata": { + "id": "2bf53579" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "05aa9dd7", + "metadata": { + "id": "05aa9dd7" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b338bd97", + "metadata": { + "id": "b338bd97", + "outputId": "dd086497-1d7a-41c1-e4ee-5f42a5ee840d" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8499699909972992" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.85)*(9999))/9997))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6636fef1", + "metadata": { + "id": "6636fef1", + "outputId": "f4e41315-b37c-4bc7-a174-c652d156c477" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8899669867947179" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.89)*(9999))/9996))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9df85f42", + "metadata": { + "id": "9df85f42", + "outputId": "47dfc49a-a34e-4411-9cb8-9101def7a5f9" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8500049969987995" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.85005)*(9999))/9996))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3c3485bc", + "metadata": { + "id": "3c3485bc" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c5c7739d", + "metadata": { + "id": "c5c7739d", + "outputId": "e56dfde5-3796-463c-bbc6-51d973f245c9" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.775075" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.85005)*(9))/6))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5cafad39", + "metadata": { + "id": "5cafad39" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c2340b03", + "metadata": { + "id": "c2340b03" + }, + "outputs": [], + "source": [ + "# original r2 --> 0.85\n", + "# k=2\n", + "# N=10" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "56ae52b6", + "metadata": { + "id": "56ae52b6", + "outputId": "dea9c3f0-d549-4f03-868b-2c35b16a06aa" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8071428571428572" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.85)*(9))/7))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "aed81332", + "metadata": { + "id": "aed81332" + }, + "outputs": [], + "source": [ + "# 0.85 --> 0.807" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "07a69afa", + "metadata": { + "id": "07a69afa" + }, + "outputs": [], + "source": [ + "# Relevant Features\n", + "# New r2 --> 0.89" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fbfe2cee", + "metadata": { + "id": "fbfe2cee", + "outputId": "d409ad66-bd90-4b68-8175-97189cc7c4b3" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.835" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.89)*(9))/6))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d069168b", + "metadata": { + "id": "d069168b" + }, + "outputs": [], + "source": [ + "0.89 --> 0.835" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "387d683a", + "metadata": { + "id": "387d683a" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "7de6ba0d", + "metadata": { + "id": "7de6ba0d" + }, + "outputs": [], + "source": [ + "# Irrelevant Features\n", + "# New r2 --> 0.855" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3d848172", + "metadata": { + "id": "3d848172", + "outputId": "a67ebef4-8a90-4643-f6a3-6872c458ee1d" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.7825" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-0.855)*(9))/6))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6672a08c", + "metadata": { + "id": "6672a08c" + }, + "outputs": [], + "source": [ + "0.855 --> 0.7825" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3d52f98a", + "metadata": { + "id": "3d52f98a" + }, + "outputs": [], + "source": [ + "N=1000000\n", + "k=10000\n", + "R2=0.85" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "97dbe442", + "metadata": { + "id": "97dbe442", + "outputId": "6ad33b1e-51ab-4027-bde5-f446a881d2e7" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8484848469543909" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-R2)*(N-1))/(N-k-1)))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8cc50f20", + "metadata": { + "id": "8cc50f20" + }, + "outputs": [], + "source": [ + "# Relevant Feature\n", + "N=1000000\n", + "k=12000\n", + "R2=0.89" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0c39698f", + "metadata": { + "id": "0c39698f", + "outputId": "1a50fcf9-614b-4aa5-e7b3-42a39c03c482" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8886639662590752" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-R2)*(N-1))/(N-k-1)))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c4835857", + "metadata": { + "id": "c4835857" + }, + "outputs": [], + "source": [ + "# Irrelevant Feature\n", + "N=1000000\n", + "k=12000\n", + "R2=0.85000005" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "caf35bc0", + "metadata": { + "id": "caf35bc0", + "outputId": "50ad4e9e-4fd8-492e-af62-5c97965c6740" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8481781864151179" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(1-(((1-R2)*(N-1))/(N-k-1)))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8c3c792d", + "metadata": { + "id": "8c3c792d" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9ea0e69b", + "metadata": { + "id": "9ea0e69b" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3174d66f", + "metadata": { + "id": "3174d66f" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3b68cfb5", + "metadata": { + "id": "3b68cfb5" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "faa95393", + "metadata": { + "id": "faa95393" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "865b841a", + "metadata": { + "id": "865b841a" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bd9b4539", + "metadata": { + "id": "bd9b4539" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "31b9a97d", + "metadata": { + "id": "31b9a97d" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e83de3a9", + "metadata": { + "id": "e83de3a9" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5c43d7cc", + "metadata": { + "id": "5c43d7cc" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "91f58501", + "metadata": { + "id": "91f58501" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e1d57bdb", + "metadata": { + "id": "e1d57bdb" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bfb888be", + "metadata": { + "id": "bfb888be" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b23680f8", + "metadata": { + "id": "b23680f8" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "134225fe", + "metadata": { + "id": "134225fe" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d294da4c", + "metadata": { + "id": "d294da4c" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "cb1dc66f", + "metadata": { + "id": "cb1dc66f" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e1dffb9b", + "metadata": { + "id": "e1dffb9b" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "51387bba", + "metadata": { + "id": "51387bba" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2a0915aa", + "metadata": { + "id": "2a0915aa" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f6b4ffb5", + "metadata": { + "id": "f6b4ffb5" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "716ba734", + "metadata": { + "id": "716ba734" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a01b1e11", + "metadata": { + "id": "a01b1e11" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1bd0afc5", + "metadata": { + "id": "1bd0afc5" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9fa0c6f1", + "metadata": { + "id": "9fa0c6f1" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "7faa4548", + "metadata": { + "id": "7faa4548" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "320f43b5", + "metadata": { + "id": "320f43b5" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fcc8f82c", + "metadata": { + "id": "fcc8f82c" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "65716ea8", + "metadata": { + "id": "65716ea8" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f9710600", + "metadata": { + "id": "f9710600" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "66f422ab", + "metadata": { + "id": "66f422ab" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "08ae4172", + "metadata": { + "id": "08ae4172" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2c5ea6bd", + "metadata": { + "id": "2c5ea6bd" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2d9f74ae", + "metadata": { + "id": "2d9f74ae" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "41e84ff8", + "metadata": { + "id": "41e84ff8" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3fc0567e", + "metadata": { + "id": "3fc0567e" + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "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": "3.9.7" + }, + "varInspector": { + "cols": { + "lenName": 16, + "lenType": 16, + "lenVar": 40 + }, + "kernels_config": { + "python": { + "delete_cmd_postfix": "", + "delete_cmd_prefix": "del ", + "library": "var_list.py", + "varRefreshCmd": "print(var_dic_list())" + }, + "r": { + "delete_cmd_postfix": ") ", + "delete_cmd_prefix": "rm(", + "library": "var_list.r", + "varRefreshCmd": "cat(var_dic_list()) " + } + }, + "types_to_exclude": [ + "module", + "function", + "builtin_function_or_method", + "instance", + "_Feature" + ], + "window_display": false + }, + "colab": { + "provenance": [], + "include_colab_link": true + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} \ No newline at end of file diff --git a/shubh.py b/shubh.py new file mode 100644 index 0000000..54cacc6 --- /dev/null +++ b/shubh.py @@ -0,0 +1 @@ +print('hi') \ No newline at end of file