{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Evolution of NBA Player Salary Determinants Over the Last 30 Years" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As a longtime NBA fan, I have been curious for a while as to how NBA player contracts are determined, and which factors play the biggest part in determining the size of a contract that a player will get. Specifically in the modern NBA, 3-point shooting has become much more common, and most of the current highest-payed players are excellent 3-point shooters. For this project, I decided to take a look at how the NBA has evolved in the last 30 years in regards to determinants for a player's contract, with a focus on 3-point shooting." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: chart-studio in /opt/conda/lib/python3.8/site-packages (1.1.0)\r\n", "Requirement already satisfied: requests in /opt/conda/lib/python3.8/site-packages (from chart-studio) (2.25.0)\r\n", "Requirement already satisfied: plotly in /opt/conda/lib/python3.8/site-packages (from chart-studio) (4.14.1)\r\n", "Requirement already satisfied: retrying>=1.3.3 in /opt/conda/lib/python3.8/site-packages (from chart-studio) (1.3.3)\r\n", "Requirement already satisfied: six in /opt/conda/lib/python3.8/site-packages (from chart-studio) (1.15.0)\r\n", "Requirement already satisfied: retrying>=1.3.3 in /opt/conda/lib/python3.8/site-packages (from chart-studio) (1.3.3)\r\n", "Requirement already satisfied: six in /opt/conda/lib/python3.8/site-packages (from chart-studio) (1.15.0)\r\n", "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.8/site-packages (from requests->chart-studio) (2020.12.5)\r\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /opt/conda/lib/python3.8/site-packages (from requests->chart-studio) (1.25.11)\r\n", "Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.8/site-packages (from requests->chart-studio) (2.10)\r\n", "Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/lib/python3.8/site-packages (from requests->chart-studio) (3.0.4)\r\n", "Requirement already satisfied: six in /opt/conda/lib/python3.8/site-packages (from chart-studio) (1.15.0)\r\n" ] } ], "source": [ "# import packages and set themes\n", "! pip install chart-studio\n", "\n", "import numpy as np\n", "import pandas as pd\n", "import qeds\n", "import requests\n", "\n", "import plotly as pt\n", "import plotly.express as px\n", "from chart_studio.plotly import plot, iplot as py\n", "import plotly.graph_objects as go\n", "from plotly.offline import iplot, init_notebook_mode\n", "\n", "import seaborn as sns\n", "import matplotlib.colors as mplc\n", "import matplotlib.pyplot as plt\n", "\n", "from sklearn import (\n", " linear_model, metrics, neural_network, pipeline, model_selection\n", ")\n", "\n", "%matplotlib inline\n", "# activate plot theme\n", "qeds.themes.mpl_style();\n", "colors = qeds.themes.COLOR_CYCLE" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The first dataset contains all basketball statistics for all NBA players through each season." ] }, { "cell_type": "code", "execution_count": 2, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
seas_idseasonplayer_idplayerbirth_yearhofposageexperiencelg...ft_percentorb_per_gamedrb_per_gametrb_per_gameast_per_gamestl_per_gameblk_per_gametov_per_gamepf_per_gamepts_per_game
02894320214219Aaron GordonNaNFalsePF25.07NBA...0.6461.54.56.03.70.70.82.21.913.6
12894420214219Aaron GordonNaNFalsePF25.07NBA...0.6291.65.16.64.20.60.82.72.014.6
22894520214219Aaron GordonNaNFalsePF25.07NBA...0.7271.33.34.52.50.80.61.11.611.5
32894620214582Aaron HolidayNaNFalsePG24.03NBA...0.7830.21.11.21.60.60.20.91.67.3
42894720214805Aaron NesmithNaNFalseSF21.01NBA...0.6880.51.62.10.30.30.20.51.43.3
..................................................................
296072001947157Walt MillerNaNFalseF31.01BAA...0.500NaNNaNNaN0.5NaNNaNNaN1.31.9
296082011947158Warren FenleyNaNFalseF24.01BAA...0.511NaNNaNNaN0.5NaNNaNNaN1.82.6
296092021947159Wilbert KautzNaNFalseG-F31.01BAA...0.534NaNNaNNaN0.7NaNNaNNaN2.35.1
296102031947160Woody GrimshawNaNFalseG27.01BAA...0.477NaNNaNNaN0.0NaNNaNNaN1.22.9
296112041947161Wyndol GrayNaNFalseG-F24.01BAA...0.581NaNNaNNaN0.9NaNNaNNaN1.96.4
\n", "

29612 rows × 36 columns

\n", "
" ], "text/plain": [ " seas_id season player_id player birth_year hof pos \\\n", "0 28943 2021 4219 Aaron Gordon NaN False PF \n", "1 28944 2021 4219 Aaron Gordon NaN False PF \n", "2 28945 2021 4219 Aaron Gordon NaN False PF \n", "3 28946 2021 4582 Aaron Holiday NaN False PG \n", "4 28947 2021 4805 Aaron Nesmith NaN False SF \n", "... ... ... ... ... ... ... ... \n", "29607 200 1947 157 Walt Miller NaN False F \n", "29608 201 1947 158 Warren Fenley NaN False F \n", "29609 202 1947 159 Wilbert Kautz NaN False G-F \n", "29610 203 1947 160 Woody Grimshaw NaN False G \n", "29611 204 1947 161 Wyndol Gray NaN False G-F \n", "\n", " age experience lg ... ft_percent orb_per_game drb_per_game \\\n", "0 25.0 7 NBA ... 0.646 1.5 4.5 \n", "1 25.0 7 NBA ... 0.629 1.6 5.1 \n", "2 25.0 7 NBA ... 0.727 1.3 3.3 \n", "3 24.0 3 NBA ... 0.783 0.2 1.1 \n", "4 21.0 1 NBA ... 0.688 0.5 1.6 \n", "... ... ... ... ... ... ... ... \n", "29607 31.0 1 BAA ... 0.500 NaN NaN \n", "29608 24.0 1 BAA ... 0.511 NaN NaN \n", "29609 31.0 1 BAA ... 0.534 NaN NaN \n", "29610 27.0 1 BAA ... 0.477 NaN NaN \n", "29611 24.0 1 BAA ... 0.581 NaN NaN \n", "\n", " trb_per_game ast_per_game stl_per_game blk_per_game tov_per_game \\\n", "0 6.0 3.7 0.7 0.8 2.2 \n", "1 6.6 4.2 0.6 0.8 2.7 \n", "2 4.5 2.5 0.8 0.6 1.1 \n", "3 1.2 1.6 0.6 0.2 0.9 \n", "4 2.1 0.3 0.3 0.2 0.5 \n", "... ... ... ... ... ... \n", "29607 NaN 0.5 NaN NaN NaN \n", "29608 NaN 0.5 NaN NaN NaN \n", "29609 NaN 0.7 NaN NaN NaN \n", "29610 NaN 0.0 NaN NaN NaN \n", "29611 NaN 0.9 NaN NaN NaN \n", "\n", " pf_per_game pts_per_game \n", "0 1.9 13.6 \n", "1 2.0 14.6 \n", "2 1.6 11.5 \n", "3 1.6 7.3 \n", "4 1.4 3.3 \n", "... ... ... \n", "29607 1.3 1.9 \n", "29608 1.8 2.6 \n", "29609 2.3 5.1 \n", "29610 1.2 2.9 \n", "29611 1.9 6.4 \n", "\n", "[29612 rows x 36 columns]" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(\"nba_player_data.csv\")\n", "\n", "df" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This doesn't include any player salaries or salary cap information, so I will need to combine a few more datasets to add in that information." ] }, { "cell_type": "code", "execution_count": 3, "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", "
YearSalary CapAdjusted
01985$3,600,000$8,557,797
11986$4,233,000$9,873,144
21987$4,945,000$11,128,422
31988$6,164,000$13,325,270
41989$7,232,000$14,916,364
\n", "
" ], "text/plain": [ " Year Salary Cap Adjusted\n", "0 1985 $3,600,000 $8,557,797 \n", "1 1986 $4,233,000 $9,873,144 \n", "2 1987 $4,945,000 $11,128,422 \n", "3 1988 $6,164,000 $13,325,270 \n", "4 1989 $7,232,000 $14,916,364 " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "salary_cap_df = pd.read_csv(\"nba_historical_salary_cap.csv\")\n", "salary_cap_df.head()" ] }, { "cell_type": "code", "execution_count": 4, "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", "
YearEndTeamPlayerSalaryBelowMinUnnamed: 5
02017Atlanta HawksDwight Howard23,180,275NaN1
12017Atlanta HawksPaul Millsap20,072,033NaN2
22017Atlanta HawksKent Bazemore15,730,338NaN0
32017Atlanta HawksTiago Splitter8,550,000NaN0
42017Atlanta HawksKyle Korver5,239,437NaN0
.....................
127101991Washington BulletsHarvey Grant475,000NaN0
127111991Washington BulletsByron Irvin375,000NaN0
127121991Washington BulletsA.J. English275,000NaN0
127131991Washington BulletsGreg Foster275,000NaN0
127141991Washington BulletsHaywoode Workman120,000NaN0
\n", "

12715 rows × 6 columns

\n", "
" ], "text/plain": [ " YearEnd Team Player Salary BelowMin \\\n", "0 2017 Atlanta Hawks Dwight Howard 23,180,275 NaN \n", "1 2017 Atlanta Hawks Paul Millsap 20,072,033 NaN \n", "2 2017 Atlanta Hawks Kent Bazemore 15,730,338 NaN \n", "3 2017 Atlanta Hawks Tiago Splitter 8,550,000 NaN \n", "4 2017 Atlanta Hawks Kyle Korver 5,239,437 NaN \n", "... ... ... ... ... ... \n", "12710 1991 Washington Bullets Harvey Grant 475,000 NaN \n", "12711 1991 Washington Bullets Byron Irvin 375,000 NaN \n", "12712 1991 Washington Bullets A.J. English 275,000 NaN \n", "12713 1991 Washington Bullets Greg Foster 275,000 NaN \n", "12714 1991 Washington Bullets Haywoode Workman 120,000 NaN \n", "\n", " Unnamed: 5 \n", "0 1 \n", "1 2 \n", "2 0 \n", "3 0 \n", "4 0 \n", "... ... \n", "12710 0 \n", "12711 0 \n", "12712 0 \n", "12713 0 \n", "12714 0 \n", "\n", "[12715 rows x 6 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "big_salary_data = pd.read_csv('player_salary_history.csv')\n", "big_salary_data" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "salary2018 = pd.read_csv('salary2018.csv')\n", "salary2019 = pd.read_csv('salary2019.csv')\n", "salary2020 = pd.read_csv('salary2020.csv')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It looks like we have a lot of data cleaning and merging ahead of us to combine these datasets, so let's get started." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Year object\n", "Salary Cap object\n", "dtype: object" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Data cleaning #\n", "\n", "clean_cap = salary_cap_df.drop('Adjusted', axis = 1)\n", "clean_cap['Salary Cap'] = clean_cap['Salary Cap'].str.replace(',', '')\n", "clean_cap['Salary Cap'] = clean_cap['Salary Cap'].str.replace('$', '')\n", "clean_cap['Year'] = clean_cap['Year'].str.replace(\"'\", '')\n", "\n", "clean_cap.dtypes" ] }, { "cell_type": "code", "execution_count": 7, "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", "
YearSalary Cap
019853600000
119864233000
219874945000
319886164000
419897232000
519909802000
6199111871000
7199212500000
8199314000000
9199415175000
\n", "
" ], "text/plain": [ " Year Salary Cap\n", "0 1985 3600000\n", "1 1986 4233000\n", "2 1987 4945000\n", "3 1988 6164000\n", "4 1989 7232000\n", "5 1990 9802000\n", "6 1991 11871000\n", "7 1992 12500000\n", "8 1993 14000000\n", "9 1994 15175000" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clean_cap['Year'] = pd.to_numeric(clean_cap['Year'])\n", "clean_cap['Salary Cap'] = pd.to_numeric(clean_cap['Salary Cap'])\n", "clean_cap.head(10)" ] }, { "cell_type": "code", "execution_count": 8, "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", "
YearPlayerSalary
02017Dwight Howard23180275
12017Paul Millsap20072033
22017Kent Bazemore15730338
32017Tiago Splitter8550000
42017Kyle Korver5239437
............
127101991Harvey Grant475000
127111991Byron Irvin375000
127121991A.J. English275000
127131991Greg Foster275000
127141991Haywoode Workman120000
\n", "

12715 rows × 3 columns

\n", "
" ], "text/plain": [ " Year Player Salary\n", "0 2017 Dwight Howard 23180275 \n", "1 2017 Paul Millsap 20072033 \n", "2 2017 Kent Bazemore 15730338 \n", "3 2017 Tiago Splitter 8550000 \n", "4 2017 Kyle Korver 5239437 \n", "... ... ... ...\n", "12710 1991 Harvey Grant 475000 \n", "12711 1991 Byron Irvin 375000 \n", "12712 1991 A.J. English 275000 \n", "12713 1991 Greg Foster 275000 \n", "12714 1991 Haywoode Workman 120000 \n", "\n", "[12715 rows x 3 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clean_bigsalary = big_salary_data.drop(['Team', 'BelowMin', 'Unnamed: 5'], axis=1)\n", "cleaned = clean_bigsalary.rename(columns = {'YearEnd': 'Year', ' Salary ': 'Salary'})\n", "cleaned['Salary'] = cleaned['Salary'].str.replace(',', '')\n", "cleaned" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Year int64\n", "Player object\n", "Salary int64\n", "dtype: object" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cleaned['Salary'] = cleaned['Salary'].str.replace('Unknown', '0')\n", "cleaned['Salary'] = pd.to_numeric(cleaned['Salary'])\n", "cleaned.dtypes" ] }, { "cell_type": "code", "execution_count": 10, "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", "
PlayerSalaryYear
0Stephen Curry346825502018
1LeBron James332857092018
2Paul Millsap307692312018
3Gordon Hayward297279002018
4Blake Griffin295129002018
............
581Andre Ingram460792018
582Trey McKinney-Jones460792018
583Aaron Jackson460792018
584Jameel Warney460792018
585Marcus Thornton II460792018
\n", "

586 rows × 3 columns

\n", "
" ], "text/plain": [ " Player Salary Year\n", "0 Stephen Curry 34682550 2018\n", "1 LeBron James 33285709 2018\n", "2 Paul Millsap 30769231 2018\n", "3 Gordon Hayward 29727900 2018\n", "4 Blake Griffin 29512900 2018\n", ".. ... ... ...\n", "581 Andre Ingram 46079 2018\n", "582 Trey McKinney-Jones 46079 2018\n", "583 Aaron Jackson 46079 2018\n", "584 Jameel Warney 46079 2018\n", "585 Marcus Thornton II 46079 2018\n", "\n", "[586 rows x 3 columns]" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clean_salary2018 = salary2018.drop('Unnamed: 0', axis=1)\n", "clean_salary2018['Salary'] = clean_salary2018['Salary'].str.replace(',', '')\n", "clean_salary2018['Salary'] = clean_salary2018['Salary'].str.replace('$', '')\n", "clean_salary2018_v2 = clean_salary2018.rename(columns = {'Season': 'Year'})\n", "clean_salary2018_v2['Salary'] = pd.to_numeric(clean_salary2018_v2['Salary'])\n", "clean_salary2018_v2" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "clean_salary2019 = salary2019.drop('Unnamed: 0', axis=1)\n", "clean_salary2019['Salary'] = clean_salary2019['Salary'].str.replace(',', '')\n", "clean_salary2019['Salary'] = clean_salary2019['Salary'].str.replace('$', '')\n", "clean_salary2019['Salary'] = pd.to_numeric(clean_salary2019['Salary'])" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "clean_salary2020 = salary2020.drop('Unnamed: 0', axis=1)\n", "clean_salary2020['Salary'] = clean_salary2020['Salary'].str.replace(',', '')\n", "clean_salary2020['Salary'] = clean_salary2020['Salary'].str.replace('$', '')\n", "clean_salary2020['Salary'] = pd.to_numeric(clean_salary2020['Salary'])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now that the five salary data frames are cleaned and have the same column names, I can combine them together." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Year int64\n", "Salary Cap int64\n", "Player object\n", "Salary int64\n", "dtype: object\n" ] }, { "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", "
YearSalary CapPlayerSalary
0199111871000Moses Malone2406000
1199111871000Dominique Wilkins2065000
2199111871000Jon Koncak1550000
3199111871000Doc Rivers895000
4199111871000Rumeal Robinson800000
...............
143842020109140000Jeremiah Martin79568
143852020109140000Tremont Waters79568
143862020109140000Tacko Fall79568
143872020109140000Charlie Brown79568
143882020109140000Malik Newman65978
\n", "

14389 rows × 4 columns

\n", "
" ], "text/plain": [ " Year Salary Cap Player Salary\n", "0 1991 11871000 Moses Malone 2406000\n", "1 1991 11871000 Dominique Wilkins 2065000\n", "2 1991 11871000 Jon Koncak 1550000\n", "3 1991 11871000 Doc Rivers 895000\n", "4 1991 11871000 Rumeal Robinson 800000\n", "... ... ... ... ...\n", "14384 2020 109140000 Jeremiah Martin 79568\n", "14385 2020 109140000 Tremont Waters 79568\n", "14386 2020 109140000 Tacko Fall 79568\n", "14387 2020 109140000 Charlie Brown 79568\n", "14388 2020 109140000 Malik Newman 65978\n", "\n", "[14389 rows x 4 columns]" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Combine all salary and salary cap dataframes\n", "merge1 = pd.concat([clean_salary2018_v2, cleaned], axis=0)\n", "merge1\n", "\n", "merge2 = pd.concat([clean_salary2019, merge1], axis=0)\n", "merge2\n", "\n", "merge3 = pd.concat([clean_salary2020, merge2], axis=0)\n", "merge3\n", "\n", "merge4 = pd.merge(clean_cap, merge3, on='Year')\n", "merge4\n", "\n", "print(merge4.dtypes)\n", "merge4" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For our purposes, most of these columns won't be used in our calculations and can be dropped from the data. Additionally, a lot of data from 1947-1979 is fragmented and includes players from the ABA and BAA, so I will limit my data from seasons after 1991." ] }, { "cell_type": "code", "execution_count": 14, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Yearplayer_idPlayerageexperiencetmgmp_per_gamex3p_per_gamex3pa_per_gametrb_per_gameast_per_gamestl_per_gameblk_per_gametov_per_gamepf_per_gamepts_per_gameSalary CapSalary
020204219Aaron Gordon24.06ORL62.032.51.23.87.73.70.80.61.62.014.410914000019863636
120204582Aaron Holiday23.02IND66.024.51.33.32.43.40.80.21.31.89.51091400002239200
220204463Abdel Nader26.03OKC55.015.80.92.31.80.70.40.40.81.46.31091400001618520
320204687Adam Mokoka21.01CHI11.010.20.51.40.90.40.40.00.21.52.910914000079568
420204688Admiral Schofield22.01WAS33.011.20.61.81.40.50.20.10.21.53.01091400001000000
............................................................
1590219912558Winston Bennett25.02CLE27.012.40.00.02.41.00.30.10.71.94.311871000525000
1590319912401Winston Garland26.04LAC69.024.70.10.42.94.61.40.11.72.78.211871000450000
1590419912278Xavier McDaniel27.06TOT81.032.50.00.16.92.30.90.62.33.317.0118710001400000
1590519912278Xavier McDaniel27.06SEA15.035.30.00.25.42.51.70.32.73.321.8118710001400000
1590619912278Xavier McDaniel27.06PHO66.031.90.00.17.22.30.80.62.23.215.8118710001400000
\n", "

15907 rows × 19 columns

\n", "
" ], "text/plain": [ " Year player_id Player age experience tm g \\\n", "0 2020 4219 Aaron Gordon 24.0 6 ORL 62.0 \n", "1 2020 4582 Aaron Holiday 23.0 2 IND 66.0 \n", "2 2020 4463 Abdel Nader 26.0 3 OKC 55.0 \n", "3 2020 4687 Adam Mokoka 21.0 1 CHI 11.0 \n", "4 2020 4688 Admiral Schofield 22.0 1 WAS 33.0 \n", "... ... ... ... ... ... ... ... \n", "15902 1991 2558 Winston Bennett 25.0 2 CLE 27.0 \n", "15903 1991 2401 Winston Garland 26.0 4 LAC 69.0 \n", "15904 1991 2278 Xavier McDaniel 27.0 6 TOT 81.0 \n", "15905 1991 2278 Xavier McDaniel 27.0 6 SEA 15.0 \n", "15906 1991 2278 Xavier McDaniel 27.0 6 PHO 66.0 \n", "\n", " mp_per_game x3p_per_game x3pa_per_game trb_per_game ast_per_game \\\n", "0 32.5 1.2 3.8 7.7 3.7 \n", "1 24.5 1.3 3.3 2.4 3.4 \n", "2 15.8 0.9 2.3 1.8 0.7 \n", "3 10.2 0.5 1.4 0.9 0.4 \n", "4 11.2 0.6 1.8 1.4 0.5 \n", "... ... ... ... ... ... \n", "15902 12.4 0.0 0.0 2.4 1.0 \n", "15903 24.7 0.1 0.4 2.9 4.6 \n", "15904 32.5 0.0 0.1 6.9 2.3 \n", "15905 35.3 0.0 0.2 5.4 2.5 \n", "15906 31.9 0.0 0.1 7.2 2.3 \n", "\n", " stl_per_game blk_per_game tov_per_game pf_per_game pts_per_game \\\n", "0 0.8 0.6 1.6 2.0 14.4 \n", "1 0.8 0.2 1.3 1.8 9.5 \n", "2 0.4 0.4 0.8 1.4 6.3 \n", "3 0.4 0.0 0.2 1.5 2.9 \n", "4 0.2 0.1 0.2 1.5 3.0 \n", "... ... ... ... ... ... \n", "15902 0.3 0.1 0.7 1.9 4.3 \n", "15903 1.4 0.1 1.7 2.7 8.2 \n", "15904 0.9 0.6 2.3 3.3 17.0 \n", "15905 1.7 0.3 2.7 3.3 21.8 \n", "15906 0.8 0.6 2.2 3.2 15.8 \n", "\n", " Salary Cap Salary \n", "0 109140000 19863636 \n", "1 109140000 2239200 \n", "2 109140000 1618520 \n", "3 109140000 79568 \n", "4 109140000 1000000 \n", "... ... ... \n", "15902 11871000 525000 \n", "15903 11871000 450000 \n", "15904 11871000 1400000 \n", "15905 11871000 1400000 \n", "15906 11871000 1400000 \n", "\n", "[15907 rows x 19 columns]" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Drop rows and combine player and salary data\n", "clean_data = df.drop(['seas_id', 'hof', 'lg', 'pos', 'birth_year', 'gs', 'fg_per_game', 'fga_per_game', 'fg_percent'], axis=1) \n", "clean_data2 = clean_data.drop(['x2p_per_game', 'x2pa_per_game', 'x2p_percent', 'x3p_percent', 'e_fg_percent', 'ft_per_game', 'fta_per_game', 'ft_percent', 'orb_per_game', 'drb_per_game'], axis=1)\n", "capitalized = clean_data2.rename(columns = {'season' : 'Year', 'player' : 'Player'})\n", "modern_data = capitalized.loc[capitalized[\"Year\"] > 1990]\n", "\n", "merge5 = pd.merge(modern_data, merge4, on=['Year', 'Player'])\n", "merge5" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It looks like a few players have multiple entries in the data due to changing teams partway through the season. In order to not have the presence of multiple players for each traded player, I will combine the multiple team players into one entry for each season. I will also add a column including the percentage of team salary cap that a player holds, and I will remove players who play less than 10 games, less than 5 minutes per game, or do not sign full-year contracts. In this way, the data is not influenced by players who play an arbitrary amount of time in the NBA or who play a very short season due to injury." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Int64Index: 8585 entries, 0 to 12312\n", "Data columns (total 18 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 Year 8585 non-null int64 \n", " 1 Player 8585 non-null int64 \n", " 2 Age 8585 non-null float64\n", " 3 Experience 8585 non-null float64\n", " 4 Games 8585 non-null float64\n", " 5 Minutes 8585 non-null float64\n", " 6 3P Makes 8585 non-null float64\n", " 7 3P Attempts 8585 non-null float64\n", " 8 Rebounds 8585 non-null float64\n", " 9 Assists 8585 non-null float64\n", " 10 Steals 8585 non-null float64\n", " 11 Blocks 8585 non-null float64\n", " 12 Turnovers 8585 non-null float64\n", " 13 Fouls 8585 non-null float64\n", " 14 Points 8585 non-null float64\n", " 15 Salary Cap 8585 non-null float64\n", " 16 Salary 8585 non-null float64\n", " 17 Salary Percent 8585 non-null float64\n", "dtypes: float64(16), int64(2)\n", "memory usage: 1.2 MB\n" ] } ], "source": [ "# Combine rows of players who played for multiple seasons in one year\n", "\n", "grouped = merge5.groupby(['Year', 'player_id']).mean()\n", "trade_df = grouped.reset_index()\n", "\n", "# Add row of salary percentage\n", "salary_percent = pd.DataFrame(data = (trade_df['Salary'] / trade_df['Salary Cap']), columns = ['Salary Percent'])\n", "\n", "new_df = pd.concat([trade_df, salary_percent], axis=1)\n", "new_df\n", "\n", "# Filter out unnecessary rows and rename columns\n", "trade_df_games = new_df.loc[new_df['g'] > 10]\n", "trade_df_mins = trade_df_games.loc[trade_df_games['mp_per_game'] > 5]\n", "trade_df_adjusted = trade_df_mins[trade_df_mins['Salary Percent'] > 0.02]\n", "clean_df1 = trade_df_adjusted[trade_df_adjusted['Salary Percent'] < 0.6]\n", "clean_df = clean_df1.rename(columns = {'player_id': 'Player', 'age': 'Age', 'experience': 'Experience', \n", " 'g': 'Games', 'mp_per_game': 'Minutes','x3p_per_game' : '3P Makes', \n", " 'x3pa_per_game': '3P Attempts', 'trb_per_game': 'Rebounds', \n", " 'ast_per_game': 'Assists', 'stl_per_game': 'Steals', \n", " 'blk_per_game': 'Blocks', 'tov_per_game': 'Turnovers', \n", " 'pf_per_game': 'Fouls', 'pts_per_game': 'Points'})\n", "# Check for non-number columns\n", "clean_df.info()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can finally get to some visualizations. First let's take a look at how the average 3-point attempts and makes has changed in the past 40 years in the NBA." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/html": [ " \n", " " ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "line": { "color": "orange", "width": 2 }, "mode": "lines+markers", "name": "3P Attempts", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 0.7164887307236055, 0.7684272300469481, 0.8828605200945624, 0.9780092592592587, 1.5706293706293715, 1.6653846153846152, 1.6982779827798284, 1.2766666666666664, 1.3191812865497081, 1.370666666666667, 1.3526984126984134, 1.495906432748538, 1.4265046296296295, 1.4861409796893676, 1.5941580756013751, 1.595108077360637, 1.6823129251700695, 1.7840206185567018, 1.8098173515981748, 1.7829908675799102, 1.752551020408165, 1.8323497267759574, 1.9588996763754059, 2.044491525423729, 2.215824915824917, 2.352133794694348, 2.8233397190293736, 2.9542592592592585, 3.1987203495630454, 3.454098360655737 ] }, { "line": { "color": "red", "width": 2 }, "mode": "lines+markers", "name": "3P Misses", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 0.48873072360616754, 0.5167840375586851, 0.589125295508274, 0.6559027777777774, 1.0069638694638705, 1.0645687645687651, 1.09258917589176, 0.8427380952380951, 0.8701754385964915, 0.8874444444444445, 0.8769312169312176, 0.9700584795321643, 0.9275462962962961, 0.9781660692951027, 1.0310423825887751, 1.0245733788395905, 1.081292517006804, 1.1488831615120287, 1.1444063926940655, 1.158418949771691, 1.12559523809524, 1.1920218579234985, 1.262351672060412, 1.3117231638418079, 1.4374859708193053, 1.5220876585928487, 1.8014687100893998, 1.8871008939974447, 2.062109862671659, 2.2185792349726765 ] }, { "line": { "color": "green", "width": 2 }, "mode": "lines+markers", "name": "3P Makes", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 0.227758007117438, 0.25164319248826306, 0.2937352245862884, 0.32210648148148135, 0.5636655011655011, 0.6008158508158502, 0.6056888068880685, 0.43392857142857133, 0.4490058479532166, 0.4832222222222225, 0.4757671957671958, 0.5258479532163738, 0.4989583333333334, 0.5079749103942649, 0.5631156930126, 0.5705346985210465, 0.6010204081632654, 0.6351374570446731, 0.6654109589041093, 0.6245719178082192, 0.6269557823129248, 0.6403278688524591, 0.696548004314994, 0.732768361581921, 0.7783389450056115, 0.8300461361014994, 1.0218710089399738, 1.0671583652618137, 1.1366104868913862, 1.2355191256830604 ] } ], "layout": { "height": 750, "template": { "data": { "bar": [ { "error_x": { "color": "#2a3f5f" }, "error_y": { "color": "#2a3f5f" }, "marker": { "line": { "color": "#E5ECF6", "width": 0.5 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "#E5ECF6", "width": 0.5 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "baxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "#EBF0F8" }, "line": { "color": "white" } }, "header": { "fill": { "color": "#C8D4E3" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowcolor": "#2a3f5f", "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "colorscale": { "diverging": [ [ 0, "#8e0152" ], [ 0.1, "#c51b7d" ], [ 0.2, "#de77ae" ], [ 0.3, "#f1b6da" ], [ 0.4, "#fde0ef" ], [ 0.5, "#f7f7f7" ], [ 0.6, "#e6f5d0" ], [ 0.7, "#b8e186" ], [ 0.8, "#7fbc41" ], [ 0.9, "#4d9221" ], [ 1, "#276419" ] ], "sequential": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "sequentialminus": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ] }, "colorway": [ "#636efa", "#EF553B", "#00cc96", "#ab63fa", "#FFA15A", "#19d3f3", "#FF6692", "#B6E880", "#FF97FF", "#FECB52" ], "font": { "color": "#2a3f5f" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "#E5ECF6", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "paper_bgcolor": "white", "plot_bgcolor": "#E5ECF6", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "radialaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "scene": { "xaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" } }, "shapedefaults": { "line": { "color": "#2a3f5f" } }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "baxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "caxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "title": { "x": 0.05 }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 } } }, "title": { "text": "Average 3-point attempts and makes of NBA players by season", "x": 0.5, "xanchor": "center", "y": 0.9, "yanchor": "top" }, "xaxis": { "title": { "text": "Year" } }, "yaxis": { "title": { "text": "3P" } } } }, "text/html": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Generate yearly averages\n", "seasonal = clean_df.groupby('Year').mean()\n", "averages = seasonal.reset_index()\n", "averages['3P Misses'] = averages['3P Attempts'] - averages['3P Makes']\n", "\n", "# Create plot\n", "fig = go.Figure([\n", " go.Scatter(x = averages['Year'], y = averages['3P Attempts'],line=dict(color='orange', width=2),mode='lines+markers', name = \"3P Attempts\"),\n", " go.Scatter(x = averages['Year'], y = averages['3P Misses'],line=dict(color='red', width=2),mode='lines+markers', name = \"3P Misses\"),\n", " go.Scatter(x = averages['Year'], y = averages['3P Makes'],line=dict(color='green', width=2),mode='lines+markers', name = \"3P Makes\")])\n", "fig.update_layout(\n", " height = 750,\n", " title={\n", " 'text': \"Average 3-point attempts and makes of NBA players by season\",\n", " 'y':0.9,\n", " 'x':0.5,\n", " 'xanchor': 'center',\n", " 'yanchor': 'top'},\n", " xaxis_title=\"Year\",\n", " yaxis_title=\"3P\"\n", " \n", ")\n", "fig.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The eye test shows a very strong positive correlation between season and 3-pointers, with averages approximately quadruping since 1991. There is growth almost year-by-year, with the exception of 1995-1997 when the league implemented a shorter 3-point line.\n", "\n", "Let's take a look at if the results are similar for if we isolate our data to elite players only (> 20 points per game)." ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "line": { "color": "orange", "width": 2 }, "mode": "lines+markers", "name": "3P Attempts", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 1.591304347826087, 1.842857142857143, 1.8799999999999997, 2.097916666666667, 3.102666666666667, 2.515, 3.504166666666667, 1.9312500000000001, 1.361904761904762, 2.2950000000000004, 2.845833333333333, 3.221333333333334, 3.404166666666667, 3.310526315789473, 3.3507246376811595, 3.4296296296296305, 3.326388888888889, 3.276666666666666, 3.1346153846153846, 2.988888888888889, 2.8183333333333325, 2.857142857142857, 3.936363636363637, 3.738888888888889, 3.961111111111111, 4.823809523809523, 5.366666666666666, 5.57361111111111, 6.093103448275862, 6.192473118279569 ] }, { "line": { "color": "red", "width": 2 }, "mode": "lines+markers", "name": "3P Misses", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 1.0797101449275364, 1.204761904761905, 1.2149999999999996, 1.385416666666667, 2.002666666666667, 1.58, 2.2333333333333334, 1.3, 0.9547619047619047, 1.4900000000000002, 1.8333333333333328, 2.073333333333334, 2.2236111111111114, 2.23157894736842, 2.1811594202898554, 2.174074074074075, 2.1416666666666666, 2.1166666666666654, 1.9846153846153844, 1.9814814814814816, 1.816666666666666, 1.8928571428571428, 2.436363636363637, 2.344444444444444, 2.4999999999999996, 3.0047619047619034, 3.3612903225806448, 3.5069444444444438, 3.875862068965517, 3.9043010752688163 ] }, { "line": { "color": "green", "width": 2 }, "mode": "lines+markers", "name": "3P Makes", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 0.5115942028985507, 0.638095238095238, 0.665, 0.7125, 1.1, 0.9350000000000002, 1.2708333333333333, 0.6312500000000001, 0.4071428571428572, 0.805, 1.0125000000000004, 1.148, 1.1805555555555556, 1.0789473684210529, 1.1695652173913043, 1.2555555555555558, 1.1847222222222222, 1.1600000000000004, 1.1500000000000001, 1.0074074074074073, 1.0016666666666665, 0.9642857142857144, 1.5, 1.3944444444444446, 1.4611111111111112, 1.8190476190476192, 2.0053763440860215, 2.0666666666666664, 2.217241379310345, 2.2881720430107526 ] } ], "layout": { "height": 750, "template": { "data": { "bar": [ { "error_x": { "color": "#2a3f5f" }, "error_y": { "color": "#2a3f5f" }, "marker": { "line": { "color": "#E5ECF6", "width": 0.5 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "#E5ECF6", "width": 0.5 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "baxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "#EBF0F8" }, "line": { "color": "white" } }, "header": { "fill": { "color": "#C8D4E3" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowcolor": "#2a3f5f", "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "colorscale": { "diverging": [ [ 0, "#8e0152" ], [ 0.1, "#c51b7d" ], [ 0.2, "#de77ae" ], [ 0.3, "#f1b6da" ], [ 0.4, "#fde0ef" ], [ 0.5, "#f7f7f7" ], [ 0.6, "#e6f5d0" ], [ 0.7, "#b8e186" ], [ 0.8, "#7fbc41" ], [ 0.9, "#4d9221" ], [ 1, "#276419" ] ], "sequential": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "sequentialminus": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ] }, "colorway": [ "#636efa", "#EF553B", "#00cc96", "#ab63fa", "#FFA15A", "#19d3f3", "#FF6692", "#B6E880", "#FF97FF", "#FECB52" ], "font": { "color": "#2a3f5f" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "#E5ECF6", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "paper_bgcolor": "white", "plot_bgcolor": "#E5ECF6", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "radialaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "scene": { "xaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" } }, "shapedefaults": { "line": { "color": "#2a3f5f" } }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "baxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "caxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "title": { "x": 0.05 }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 } } }, "title": { "text": "Average 3-point attempts and makes of elite NBA players by season", "x": 0.5, "xanchor": "center", "y": 0.9, "yanchor": "top" }, "xaxis": { "title": { "text": "Year" } }, "yaxis": { "title": { "text": "3P" } } } }, "text/html": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Create a dataset of elite players\n", "elite_players = clean_df.loc[clean_df[\"Points\"] > 20]\n", "\n", "# Generate yearly averages for elite players\n", "e_seasonal = elite_players.groupby('Year').mean()\n", "e_averages = e_seasonal.reset_index()\n", "e_averages['3P Misses'] = e_averages['3P Attempts'] - e_averages['3P Makes']\n", "\n", "# Create plot\n", "fig = go.Figure([\n", " go.Scatter(x = e_averages['Year'], y = e_averages['3P Attempts'],line=dict(color='orange', width=2),mode='lines+markers', name = \"3P Attempts\"),\n", " go.Scatter(x = e_averages['Year'], y = e_averages['3P Misses'],line=dict(color='red', width=2),mode='lines+markers', name = \"3P Misses\"),\n", " go.Scatter(x = e_averages['Year'], y = e_averages['3P Makes'],line=dict(color='green', width=2),mode='lines+markers', name = \"3P Makes\")])\n", "fig.update_layout(\n", " height = 750,\n", " title={\n", " 'text': \"Average 3-point attempts and makes of elite NBA players by season\",\n", " 'y':0.9,\n", " 'x':0.5,\n", " 'xanchor': 'center',\n", " 'yanchor': 'top'},\n", " xaxis_title=\"Year\",\n", " yaxis_title=\"3P\"\n", " \n", ")\n", "fig.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The 3-point attempts and makes for elite players follows a similar trend with strong positive correlation with season, however with around double the attempts and makes per-year, likely explained by the higher usage rate of elite players.\n", "\n", "It is worth noting that 3-point attempts and makes per game have reached approximately quadrupled since 1991." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now lets take a look at how the salary cap has changed during the same period." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "line": { "color": "green", "width": 2 }, "mode": "lines+markers", "name": "Cap", "type": "scatter", "x": [ 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 ], "y": [ 11871000, 12500000, 14000000, 15175000, 15964000, 23000000, 24363000, 26900000, 30000000, 34000000, 35500000, 42500000, 40271000, 43840000, 43870000, 49500000, 53135000, 55630000, 58680000, 57700000, 58044000, 58044000, 58044000, 58679000, 63065000, 70000000, 94143000, 99093000, 101869000, 109140000 ] } ], "layout": { "height": 750, "template": { "data": { "bar": [ { "error_x": { "color": "#2a3f5f" }, "error_y": { "color": "#2a3f5f" }, "marker": { "line": { "color": "#E5ECF6", "width": 0.5 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "#E5ECF6", "width": 0.5 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "baxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "#EBF0F8" }, "line": { "color": "white" } }, "header": { "fill": { "color": "#C8D4E3" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowcolor": "#2a3f5f", "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "colorscale": { "diverging": [ [ 0, "#8e0152" ], [ 0.1, "#c51b7d" ], [ 0.2, "#de77ae" ], [ 0.3, "#f1b6da" ], [ 0.4, "#fde0ef" ], [ 0.5, "#f7f7f7" ], [ 0.6, "#e6f5d0" ], [ 0.7, "#b8e186" ], [ 0.8, "#7fbc41" ], [ 0.9, "#4d9221" ], [ 1, "#276419" ] ], "sequential": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "sequentialminus": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ] }, "colorway": [ "#636efa", "#EF553B", "#00cc96", "#ab63fa", "#FFA15A", "#19d3f3", "#FF6692", "#B6E880", "#FF97FF", "#FECB52" ], "font": { "color": "#2a3f5f" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "#E5ECF6", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "paper_bgcolor": "white", "plot_bgcolor": "#E5ECF6", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "radialaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "scene": { "xaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" } }, "shapedefaults": { "line": { "color": "#2a3f5f" } }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "baxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "caxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "title": { "x": 0.05 }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 } } }, "title": { "text": "NBA Team Salary Cap by Year (Nominal Dollars)", "x": 0.5, "xanchor": "center", "y": 0.9, "yanchor": "top" }, "xaxis": { "title": { "text": "Year" } }, "yaxis": { "title": { "text": "Dollars" } } } }, "text/html": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Create plot\n", "fig = go.Figure([\n", " go.Scatter(x = averages['Year'], y = averages['Salary Cap'],line=dict(color='green', width=2),mode='lines+markers', name = \"Cap\")])\n", "fig.update_layout(\n", " height = 750,\n", " title={\n", " 'text': \"NBA Team Salary Cap by Year (Nominal Dollars)\",\n", " 'y':0.9,\n", " 'x':0.5,\n", " 'xanchor': 'center',\n", " 'yanchor': 'top'},\n", " xaxis_title=\"Year\",\n", " yaxis_title=\"Dollars\"\n", " \n", ")\n", "fig.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The salary cap has increased tenfold in the last 30 years, likely due to inflation and the increase in popularity of the NBA. To adjust for varying salary caps, I will use the percentage of the team salary cap that a player earns.\n", "\n", "Let's do a preliminary analysis of the correlation between the variables we would like to look at. First we will split our data into two equal time frames: 1991-2005 and 2006-2020." ] }, { "cell_type": "code", "execution_count": 19, "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", "
Salary Percent3P Makes
Salary Percent1.0000000.167274
3P Makes0.1672741.000000
\n", "
" ], "text/plain": [ " Salary Percent 3P Makes\n", "Salary Percent 1.000000 0.167274\n", "3P Makes 0.167274 1.000000" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "older_df = clean_df[clean_df['Year'] < 2006]\n", "newer_df = clean_df[clean_df['Year'] > 2005]\n", "\n", "# Combined dataframe 3P correlation\n", "clean_df[['Salary Percent', '3P Makes']].corr()" ] }, { "cell_type": "code", "execution_count": 20, "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", "
Salary Percent3P Makes
Salary Percent1.0000000.143388
3P Makes0.1433881.000000
\n", "
" ], "text/plain": [ " Salary Percent 3P Makes\n", "Salary Percent 1.000000 0.143388\n", "3P Makes 0.143388 1.000000" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Older data 3P correlation\n", "older_df[['Salary Percent', '3P Makes']].corr()" ] }, { "cell_type": "code", "execution_count": 21, "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", "
Salary Percent3P Makes
Salary Percent1.0000000.208503
3P Makes0.2085031.000000
\n", "
" ], "text/plain": [ " Salary Percent 3P Makes\n", "Salary Percent 1.000000 0.208503\n", "3P Makes 0.208503 1.000000" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Newer data 3P correlation\n", "newer_df[['Salary Percent', '3P Makes']].corr()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This is a promising start. There is positive correlation between salary percent and 3-points per game in both time frames, and about a 0.06 increase from the older to newer data.\n", "\n", "Let's start with a simple linear regression on our filtered dataframe." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Simple Linear Regression" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Simple linear model: Salary Percent = 0.0907 + 0.0193 3P Makes\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from sklearn import linear_model\n", "\n", "\n", "X = clean_df.copy()\n", "y = clean_df['Salary Percent']\n", "\n", "# construct the model instance\n", "simple_lr_model = linear_model.LinearRegression()\n", "\n", "# fit the model\n", "simple_lr_model.fit(X[[\"3P Makes\"]], y)\n", "\n", "# print the coefficients\n", "beta_0 = simple_lr_model.intercept_\n", "beta_1 = simple_lr_model.coef_[0]\n", "\n", "print(f\"Simple linear model: Salary Percent = {beta_0:.4f} + {beta_1:.4f} 3P Makes\")\n", "\n", "sns.lmplot(\n", " data=clean_df, x=\"3P Makes\", y=\"Salary Percent\", height=6,\n", " scatter_kws=dict(s=5, alpha=0.5),\n", " line_kws={'color': 'orange'}\n", ");" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "While here we can see positive correlation between 3-points made and salary, the data is not a great fit, and we are still looking at our time period as a whole.\n", "\n", "The same regression will be run with our data split between older and newer data to see if beta_1 increases as 3-pointers become more common in the modern era." ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Old simple linear model: Salary Percent = 0.0958 + 0.0197 3P Makes\n", "Mean squared error is 0.006662360293839116\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "X = older_df.copy()\n", "y = older_df['Salary Percent']\n", "\n", "oldsimple_lr_model = linear_model.LinearRegression()\n", "\n", "oldsimple_lr_model.fit(X[[\"3P Makes\"]], y)\n", "\n", "oldbeta_0 = oldsimple_lr_model.intercept_\n", "oldbeta_1 = oldsimple_lr_model.coef_[0]\n", "\n", "print(f\"Old simple linear model: Salary Percent = {oldbeta_0:.4f} + {oldbeta_1:.4f} 3P Makes\")\n", "\n", "sns.lmplot(\n", " data=older_df, x=\"3P Makes\", y=\"Salary Percent\", height=6,\n", " scatter_kws=dict(s=5, alpha=0.5),\n", " line_kws={'color': 'orange'}\n", ");\n", "\n", "old_mse = metrics.mean_squared_error(y, oldsimple_lr_model.predict(X[['3P Makes']]))\n", "print('Mean squared error is', old_mse) " ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "New simple linear model: Salary Percent = 0.0833 + 0.0219 3P Makes\n", "Mean squared error is 0.006293510029486172\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "X = newer_df.copy()\n", "y = newer_df['Salary Percent']\n", "\n", "newsimple_lr_model = linear_model.LinearRegression()\n", "\n", "newsimple_lr_model.fit(X[[\"3P Makes\"]], y)\n", "\n", "newbeta_0 = newsimple_lr_model.intercept_\n", "newbeta_1 = newsimple_lr_model.coef_[0]\n", "\n", "print(f\"New simple linear model: Salary Percent = {newbeta_0:.4f} + {newbeta_1:.4f} 3P Makes\")\n", "\n", "sns.lmplot(\n", " data=newer_df, x=\"3P Makes\", y=\"Salary Percent\", height=8,\n", " scatter_kws=dict(s=5, alpha=0.5),\n", " line_kws={'color': 'orange'}\n", ");\n", "\n", "new_mse = metrics.mean_squared_error(y, newsimple_lr_model.predict(X[['3P Makes']]))\n", "print('Mean squared error is', new_mse)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Unfortunately the data is still not a great fit for this simple linear regression. However, it looks like our beta_1 is about 12% higher in our newer data compared to the older data. That is a good sign. Let's see how they fare when we include our other variables as well.\n", "\n", "Before we generate some multivariate linear regressions, it is a good idea to check the correlation between each of our predictor variables, in order to eliminate variables that show signs of multicollinearity." ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.subplots(figsize=(10,10))\n", "sns.heatmap(clean_df.corr(), linewidths = 2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "I will remove all salary information as we are using salary percentage as our dependent variable. I'll also remove Player, as player_id is an arbitrary number, and Year, as it is already factored into our two datasets. Finally, I'll remove Age for its high correlation with Experience, and 3P Attempts for its high correlation with 3P Makes." ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "newindep_variables = newer_df.drop(['Salary', 'Salary Cap', 'Salary Percent', 'Year', 'Player', 'Age', '3P Attempts', 'Points'], axis=1)\n", "oldindep_variables = older_df.drop(['Salary', 'Salary Cap', 'Salary Percent', 'Year', 'Player', 'Age', '3P Attempts', 'Points'], axis=1)\n", "plt.subplots(figsize=(10,5))\n", "sns.heatmap(newindep_variables.corr(), linewidths = 2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Multiple Linear Regression" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now that the predictor variables have been filtered, I will run a multiple linear regression on each of the old and new data." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Old Intercept: -0.01083027981862214\n", "Experience : 0.006356229149073229\n", "Games : -0.00035442506394580287\n", "Minutes Played : 0.0017468426427601413\n", "3P Made : 0.010412184611248551\n", "Rebounds : 0.006054133896862581\n", "Assists : 0.002317022298807209\n", "Steals : -0.01885485384063002\n", "Blocks : 0.02910799228369434\n", "Turnovers : 0.026474773398563668\n", "Fouls : -0.009810582336634172\n" ] } ], "source": [ "X = oldindep_variables.copy()\n", "y = older_df['Salary Percent']\n", "\n", "categories = ['Experience', 'Games', 'Minutes Played', '3P Made', \n", " 'Rebounds', 'Assists', 'Steals', 'Blocks', 'Turnovers', 'Fouls']\n", "\n", "oldmulti_regr = linear_model.LinearRegression()\n", "oldmulti_regr.fit(X, y)\n", "\n", "pairs = zip(categories, oldmulti_regr.coef_)\n", "\n", "print('Old Intercept:', oldmulti_regr.intercept_)\n", "for (category, coef) in pairs:\n", " print(category, ': ', coef)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "New Intercept: -0.03617121782411255\n", "Experience : 0.007216528291439452\n", "Games : -0.0004742823454764643\n", "Minutes Played : 0.0028959302451106697\n", "3P Made : 0.004759857038476971\n", "Rebounds : 0.007801379347796547\n", "Assists : 0.00036986302927898517\n", "Steals : -0.010678000581346946\n", "Blocks : 0.010584607766033583\n", "Turnovers : 0.02724818053296039\n", "Fouls : -0.01403652911810434\n" ] } ], "source": [ "X = newindep_variables.copy()\n", "y = newer_df['Salary Percent']\n", "\n", "newmulti_regr = linear_model.LinearRegression()\n", "newmulti_regr.fit(X, y)\n", "\n", "pairs = zip(categories, newmulti_regr.coef_)\n", "\n", "print('New Intercept:', newmulti_regr.intercept_)\n", "for (category, coef) in pairs:\n", " print(category, ': ', coef)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Interestingly, turnovers (a negative stat) have a positive coefficient. This likely can be explained by the high turnover count of elite players, as only top players handle the ball enough to generate a high turnover count.\n", "\n", "3-points made are positive in both regressions, which is a good sign, however the coefficient is smaller in our newer data.\n", "\n", "Let's compare our multivariate linear regressions with lasso regressions." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Lasso Regression" ] }, { "cell_type": "code", "execution_count": 29, "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", "
lassolinreg
Experience0.0050690.006356
Games-0.000397-0.000354
Minutes0.0034910.001747
3P Makes0.0000000.010412
Rebounds0.0061000.006054
Assists0.0000000.002317
Steals-0.000000-0.018855
Blocks0.0000000.029108
Turnovers0.0000000.026475
Fouls-0.000000-0.009811
\n", "
" ], "text/plain": [ " lasso linreg\n", "Experience 0.005069 0.006356\n", "Games -0.000397 -0.000354\n", "Minutes 0.003491 0.001747\n", "3P Makes 0.000000 0.010412\n", "Rebounds 0.006100 0.006054\n", "Assists 0.000000 0.002317\n", "Steals -0.000000 -0.018855\n", "Blocks 0.000000 0.029108\n", "Turnovers 0.000000 0.026475\n", "Fouls -0.000000 -0.009811" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X = oldindep_variables.copy()\n", "y = older_df['Salary Percent']\n", "\n", "oldlasso_model = linear_model.Lasso(alpha = 0.01)\n", "oldlasso_model.fit(X, y)\n", "\n", "oldlasso_coefs = pd.Series(dict(zip(list(X), oldlasso_model.coef_)))\n", "oldlr_coefs = pd.Series(dict(zip(list(X), oldmulti_regr.coef_)))\n", "oldlasso_vs_linreg = pd.DataFrame(dict(lasso=oldlasso_coefs, linreg=oldlr_coefs))\n", "oldlasso_vs_linreg" ] }, { "cell_type": "code", "execution_count": 30, "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", "
lassolinreg
Experience0.0066470.007217
Games-0.000560-0.000474
Minutes0.0044960.002896
3P Makes0.0000000.004760
Rebounds0.0055500.007801
Assists0.0008120.000370
Steals-0.000000-0.010678
Blocks0.0000000.010585
Turnovers0.0000000.027248
Fouls-0.000000-0.014037
\n", "
" ], "text/plain": [ " lasso linreg\n", "Experience 0.006647 0.007217\n", "Games -0.000560 -0.000474\n", "Minutes 0.004496 0.002896\n", "3P Makes 0.000000 0.004760\n", "Rebounds 0.005550 0.007801\n", "Assists 0.000812 0.000370\n", "Steals -0.000000 -0.010678\n", "Blocks 0.000000 0.010585\n", "Turnovers 0.000000 0.027248\n", "Fouls -0.000000 -0.014037" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X = newindep_variables.copy()\n", "y = newer_df['Salary Percent']\n", "\n", "newlasso_model = linear_model.Lasso(alpha = 0.01)\n", "newlasso_model.fit(X, y)\n", "\n", "newlasso_coefs = pd.Series(dict(zip(list(X), newlasso_model.coef_)))\n", "newlr_coefs = pd.Series(dict(zip(list(X), newmulti_regr.coef_)))\n", "newlasso_vs_linreg = pd.DataFrame(dict(lasso=newlasso_coefs, linreg=newlr_coefs))\n", "newlasso_vs_linreg" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Even with a low alpha regularization parameter of 0.01, the '3P Makes' column is thrown out in both the older and newer data. This is due to either a lack of prediction power in '3P Makes', or still too much multicollinearity between predictor variables.\n", "\n", "Let's generate training and testing data to see how the mean squared error compares in our linear and lasso regressions." ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Old linear MSE train: 0.0034287730803641498 , MSE test: 0.010252713402191525\n" ] } ], "source": [ "# Compute MSE values for all 4 regressions\n", "\n", "n_test = 75\n", "X_train = X.iloc[:n_test, :]\n", "X_test = X.iloc[n_test:, :]\n", "y_train = y.iloc[:n_test]\n", "y_test = y.iloc[n_test:]\n", "\n", "oldmulti_regr.fit(X_train, y_train)\n", "print('Old linear MSE train:', metrics.mean_squared_error(y_train, oldmulti_regr.predict(X_train)), ', '\n", " 'MSE test:', metrics.mean_squared_error(y_test, oldmulti_regr.predict(X_test)))" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Old lasso MSE train: 0.004165405010664216 , MSE test: 0.007019333696622415\n" ] } ], "source": [ "oldlasso_model.fit(X_train, y_train)\n", "print('Old lasso MSE train:', metrics.mean_squared_error(y_train, oldlasso_model.predict(X_train)), ', '\n", " 'MSE test:', metrics.mean_squared_error(y_test, oldlasso_model.predict(X_test)))" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "New linear MSE train: 0.0034287730803641498 , MSE test: 0.010252713402191525\n" ] } ], "source": [ "newmulti_regr.fit(X_train, y_train)\n", "print('New linear MSE train:', metrics.mean_squared_error(y_train, newmulti_regr.predict(X_train)), ', '\n", " 'MSE test:', metrics.mean_squared_error(y_test, newmulti_regr.predict(X_test)))" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "New lasso MSE train: 0.004165405010664216 , MSE test: 0.007019333696622415\n" ] } ], "source": [ "newlasso_model.fit(X_train, y_train)\n", "print('New lasso MSE train:', metrics.mean_squared_error(y_train, newlasso_model.predict(X_train)), ', '\n", " 'MSE test:', metrics.mean_squared_error(y_test, newlasso_model.predict(X_test)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Test MSE improves in the lasso models, which mean they are a more accurate measurement of the data." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Conclusion" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "\n", "I had a few interesting takeaways from this project.\n", "\n", "1. The increase in 3-point shooting by year is evident, and the increase in both attempts and makes has been positive almost every year since 1990.\n", "\n", "2. Stronger correlation and a higher beta_1 coefficient in the newer data of the simple linear regression point towards an increase in value for 3-point shooting when determining player contracts.\n", "\n", "3. The relationship between 3-point shooting and player salary is hard to determine in the multiple linear and lasso regressions, likely due in part to the multicollinearity of predictor variables.\n", "\n", "\n", "While I enjoyed analyzing NBA data on this project, I will have to continue to experiment with different predictor variables and time frames to see if more evidence of the relationship between 3-point shooting and player salary exists." ] } ], "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": "3.8.6" } }, "nbformat": 4, "nbformat_minor": 4 }