|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "id": "b4a01b39", |
| 6 | + "metadata": {}, |
| 7 | + "source": [ |
| 8 | + "# Project 1" |
| 9 | + ] |
| 10 | + }, |
| 11 | + { |
| 12 | + "cell_type": "markdown", |
| 13 | + "id": "1cc24e93", |
| 14 | + "metadata": {}, |
| 15 | + "source": [ |
| 16 | + "For this project, we will be looking at F1 team data. More specifically, team data. \n", |
| 17 | + "\n", |
| 18 | + "We will be looking at the mode, median and average age number of laps done during the qualifying sessions. \n", |
| 19 | + "\n", |
| 20 | + "We will looking at a solidifed dataset including qualifying session from 2022 to 2025" |
| 21 | + ] |
| 22 | + }, |
| 23 | + { |
| 24 | + "cell_type": "markdown", |
| 25 | + "id": "ed9d198c", |
| 26 | + "metadata": {}, |
| 27 | + "source": [ |
| 28 | + "# Let me merge the 4 years of data to have a big enough dataset" |
| 29 | + ] |
| 30 | + }, |
| 31 | + { |
| 32 | + "cell_type": "code", |
| 33 | + "execution_count": 1, |
| 34 | + "id": "2f86d349", |
| 35 | + "metadata": {}, |
| 36 | + "outputs": [], |
| 37 | + "source": [ |
| 38 | + "#step 1\n", |
| 39 | + "\n", |
| 40 | + "import pandas as pd\n", |
| 41 | + "years = [2022, 2023, 2024, 2025]\n", |
| 42 | + "qual = pd.concat((pd.read_csv(f\"{y}.csv\").assign(season=y) for y in years), ignore_index=True)\n", |
| 43 | + "qual.to_csv(\"f1_qualifying_2022_2025.csv\", index=False)\n" |
| 44 | + ] |
| 45 | + }, |
| 46 | + { |
| 47 | + "cell_type": "markdown", |
| 48 | + "id": "d858a645", |
| 49 | + "metadata": {}, |
| 50 | + "source": [ |
| 51 | + "# Average of laps done in qualifying across all seasons" |
| 52 | + ] |
| 53 | + }, |
| 54 | + { |
| 55 | + "cell_type": "code", |
| 56 | + "execution_count": 2, |
| 57 | + "id": "c8485d2d", |
| 58 | + "metadata": {}, |
| 59 | + "outputs": [ |
| 60 | + { |
| 61 | + "name": "stdout", |
| 62 | + "output_type": "stream", |
| 63 | + "text": [ |
| 64 | + "15.943181818181818\n" |
| 65 | + ] |
| 66 | + } |
| 67 | + ], |
| 68 | + "source": [ |
| 69 | + "# step 2\n", |
| 70 | + "import pandas as pd\n", |
| 71 | + "\n", |
| 72 | + "df = pd.read_csv(\"f1_qualifying_2022_2025.csv\")\n", |
| 73 | + "avg_laps = df[\"Laps\"].mean()\n", |
| 74 | + "print(avg_laps)" |
| 75 | + ] |
| 76 | + }, |
| 77 | + { |
| 78 | + "cell_type": "markdown", |
| 79 | + "id": "4ac17b31", |
| 80 | + "metadata": {}, |
| 81 | + "source": [ |
| 82 | + "# The median now" |
| 83 | + ] |
| 84 | + }, |
| 85 | + { |
| 86 | + "cell_type": "code", |
| 87 | + "execution_count": 3, |
| 88 | + "id": "61d744bd", |
| 89 | + "metadata": {}, |
| 90 | + "outputs": [ |
| 91 | + { |
| 92 | + "name": "stdout", |
| 93 | + "output_type": "stream", |
| 94 | + "text": [ |
| 95 | + "15.943181818181818\n" |
| 96 | + ] |
| 97 | + } |
| 98 | + ], |
| 99 | + "source": [ |
| 100 | + "# step 3\n", |
| 101 | + "import pandas as pd\n", |
| 102 | + "\n", |
| 103 | + "df = pd.read_csv(\"f1_qualifying_2022_2025.csv\")\n", |
| 104 | + "median_laps = df[\"Laps\"].mean()\n", |
| 105 | + "print(median_laps)\n", |
| 106 | + "\n", |
| 107 | + "# I think all entries in Laps are number. If not, to be sure, I could use \n", |
| 108 | + "\n", |
| 109 | + "#import pandas as pd\n", |
| 110 | + "\n", |
| 111 | + "#df = pd.read_csv(\"f1_qualifying_2022_2025.csv\")\n", |
| 112 | + "#median_laps = pd.to_numeric(df[\"Laps\"], errors=\"coerce\").median()\n", |
| 113 | + "#print(f\"Median laps (2022–2025): {median_laps}\")" |
| 114 | + ] |
| 115 | + }, |
| 116 | + { |
| 117 | + "cell_type": "markdown", |
| 118 | + "id": "15a68fe0", |
| 119 | + "metadata": {}, |
| 120 | + "source": [ |
| 121 | + "# Mode" |
| 122 | + ] |
| 123 | + }, |
| 124 | + { |
| 125 | + "cell_type": "code", |
| 126 | + "execution_count": 4, |
| 127 | + "id": "51205acc", |
| 128 | + "metadata": {}, |
| 129 | + "outputs": [ |
| 130 | + { |
| 131 | + "name": "stdout", |
| 132 | + "output_type": "stream", |
| 133 | + "text": [ |
| 134 | + "0 15.0\n", |
| 135 | + "Name: Laps, dtype: float64\n" |
| 136 | + ] |
| 137 | + } |
| 138 | + ], |
| 139 | + "source": [ |
| 140 | + "# step 4\n", |
| 141 | + "import pandas as pd\n", |
| 142 | + "\n", |
| 143 | + "df = pd.read_csv(\"f1_qualifying_2022_2025.csv\")\n", |
| 144 | + "mode_laps = df[\"Laps\"].mode()\n", |
| 145 | + "print(mode_laps)" |
| 146 | + ] |
| 147 | + }, |
| 148 | + { |
| 149 | + "cell_type": "markdown", |
| 150 | + "id": "87e45682", |
| 151 | + "metadata": {}, |
| 152 | + "source": [ |
| 153 | + "# Now the hardway: average, median, mode" |
| 154 | + ] |
| 155 | + }, |
| 156 | + { |
| 157 | + "cell_type": "code", |
| 158 | + "execution_count": null, |
| 159 | + "id": "08ee701f", |
| 160 | + "metadata": {}, |
| 161 | + "outputs": [], |
| 162 | + "source": [ |
| 163 | + "import csv\n", |
| 164 | + "\n", |
| 165 | + "with open(\"f1_qualifying_2022_2025.csv\", \"r\") as f1:\n" |
| 166 | + ] |
| 167 | + } |
| 168 | + ], |
| 169 | + "metadata": { |
| 170 | + "kernelspec": { |
| 171 | + "display_name": ".venv", |
| 172 | + "language": "python", |
| 173 | + "name": "python3" |
| 174 | + }, |
| 175 | + "language_info": { |
| 176 | + "codemirror_mode": { |
| 177 | + "name": "ipython", |
| 178 | + "version": 3 |
| 179 | + }, |
| 180 | + "file_extension": ".py", |
| 181 | + "mimetype": "text/x-python", |
| 182 | + "name": "python", |
| 183 | + "nbconvert_exporter": "python", |
| 184 | + "pygments_lexer": "ipython3", |
| 185 | + "version": "3.13.7" |
| 186 | + } |
| 187 | + }, |
| 188 | + "nbformat": 4, |
| 189 | + "nbformat_minor": 5 |
| 190 | +} |
0 commit comments