File size: 2,511 Bytes
cb96cf5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os\n",
"\n",
"DATA_DIR = os.path.join(\"..\", \"data\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/var/folders/v8/0hd98b512cn3ms2rz146k7jw0000gn/T/ipykernel_46104/712369024.py:1: DtypeWarning: Columns (481,482,483) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" games_df = pd.read_csv(os.path.join(DATA_DIR, \"AllSuperDetailedGames.csv\"))\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 377608 entries, 0 to 377607\n",
"Columns: 487 entries, Unnamed: 0 to ChalkSeed\n",
"dtypes: float64(347), int64(133), object(7)\n",
"memory usage: 1.4+ GB\n"
]
}
],
"source": [
"games_df = pd.read_csv(os.path.join(DATA_DIR, \"AllSuperDetailedGames.csv\"))\n",
"games_df.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# create baseline model that predicts the winner of the game only based on the team with the higher seed\n",
"# and if the seed is the same, have it be the winning percentage that determines the winner. We will compare\n",
"# our ML models to this one to decide if performance is actually good or not.\n",
"\n",
"def predict_baseline(row: pd.Series) -> int:\n",
" if row[\"ChalkSeed Team\"] > row[\"OppChalkSeed Opp\"]:\n",
" return 1\n",
" if row[\"Win mean reg\"] > row[\"OppWin mean reg\"]:\n",
" return 1\n",
" return 0\n",
"\n",
"games_df[\"BaselinePrediction\"] = games_df.apply(\n",
" lambda row: predict_baseline(row),\n",
" axis=1,\n",
")\n",
"\n",
"games_df[\"BaselinePrediction\"]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|