{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport ipywidgets as wg\nfrom IPython.core.display import HTML\nimport matplotlib.animation as anim\nimport matplotlib.pyplot as plt\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-01-23T21:52:30.388039Z","iopub.execute_input":"2022-01-23T21:52:30.388869Z","iopub.status.idle":"2022-01-23T21:52:30.463502Z","shell.execute_reply.started":"2022-01-23T21:52:30.388826Z","shell.execute_reply":"2022-01-23T21:52:30.462418Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"scouting_df = pd.read_csv('/kaggle/input/nfl-big-data-bowl-2022/PFFScoutingData.csv')\nscouting_df.head()\n#list(scouting_df.columns)","metadata":{"execution":{"iopub.status.busy":"2022-01-23T21:49:43.783876Z","iopub.execute_input":"2022-01-23T21:49:43.784166Z","iopub.status.idle":"2022-01-23T21:49:43.897597Z","shell.execute_reply.started":"2022-01-23T21:49:43.784137Z","shell.execute_reply":"2022-01-23T21:49:43.896745Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Keep the columns that are related to kickoffs\nkickoff_cols = ['gameId', 'playId', 'hangTime', 'kickType', 'kickDirectionIntended', 'kickDirectionActual', 'missedTackler',\n                'returnDirectionIntended', 'returnDirectionActual', 'kickoffReturnFormation', 'specialTeamsSafeties']\nkickoff_scouting_df = scouting_df[kickoff_cols]\nkickoff_scouting_df","metadata":{"execution":{"iopub.status.busy":"2022-01-23T21:49:43.898729Z","iopub.execute_input":"2022-01-23T21:49:43.899225Z","iopub.status.idle":"2022-01-23T21:49:43.928718Z","shell.execute_reply.started":"2022-01-23T21:49:43.899188Z","shell.execute_reply":"2022-01-23T21:49:43.927815Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plays_df = pd.read_csv('/kaggle/input/nfl-big-data-bowl-2022/plays.csv')\nkickoffs_df = plays_df.loc[plays_df['specialTeamsPlayType'] == 'Kickoff']\nkickoff_returns_df = kickoffs_df.loc[kickoffs_df['specialTeamsResult'] == 'Return']\nkickoff_returns_df","metadata":{"execution":{"iopub.status.busy":"2022-01-23T21:49:43.930362Z","iopub.execute_input":"2022-01-23T21:49:43.930619Z","iopub.status.idle":"2022-01-23T21:49:44.094474Z","shell.execute_reply.started":"2022-01-23T21:49:43.930593Z","shell.execute_reply":"2022-01-23T21:49:44.093612Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Merge the scouting data with the kickoffs that were returned.\nkickoff_returns_df = kickoff_returns_df.merge(kickoff_scouting_df, how='inner', on=['gameId', 'playId'])\nkickoff_returns_df\n#list(kickoff_returns_df.columns)","metadata":{"execution":{"iopub.status.busy":"2022-01-23T21:49:44.095753Z","iopub.execute_input":"2022-01-23T21:49:44.095972Z","iopub.status.idle":"2022-01-23T21:49:44.140904Z","shell.execute_reply.started":"2022-01-23T21:49:44.095946Z","shell.execute_reply":"2022-01-23T21:49:44.140081Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tracking2018 = pd.read_csv('/kaggle/input/nfl-big-data-bowl-2022/tracking2018.csv')\ntracking2019  = pd.read_csv('/kaggle/input/nfl-big-data-bowl-2022/tracking2019.csv')\ntracking2020 = pd.read_csv('/kaggle/input/nfl-big-data-bowl-2022/tracking2020.csv')","metadata":{"execution":{"iopub.status.busy":"2022-01-23T21:56:23.125333Z","iopub.execute_input":"2022-01-23T21:56:23.126017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tracking_data = tracking2018.append(tracking2019).append(tracking2020)\ntracking_cols = ['s', 'a', 'nflId', 'gameId','playId', 'frameId', 'event', \"x\", \"y\", \"time\", \"team\", \"dis\"]\ntracking_data = tracking_data[tracking_cols]\ntracking_data ","metadata":{"execution":{"iopub.status.busy":"2022-01-23T21:56:01.035656Z","iopub.execute_input":"2022-01-23T21:56:01.036817Z","iopub.status.idle":"2022-01-23T21:56:07.294814Z","shell.execute_reply.started":"2022-01-23T21:56:01.036764Z","shell.execute_reply":"2022-01-23T21:56:07.293845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tracking = tracking[tracking['nflId'].isin(list(punt_return['returnerId'].unique()))]","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"players_df = pd.read_csv('/kaggle/input/nfl-big-data-bowl-2022/players.csv') \npositions = ['WR','RB','DB']\nsub_players_df = pd.DataFrame(players_df[players_df.Position.isin(positions)])\n\nsub_players_df['nflId'] = sub_players_df['nflId'].astype(int)\nsub_players_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dropped_returns = kickoff_returns_df.loc[kickoff_returns_df['returnerId'].str.contains(';', na = False)]\nkickoff_returns_df = kickoff_returns_df[~kickoff_returns_df.isin(dropped_returns)]\nkickoff_returns_df['returnerId'] = pd.to_numeric(kickoff_returns_df['returnerId'])\nkickoff_returns_df = kickoff_returns_df.dropna(subset=['returnerId'])\nkickoff_returns_df['returnerId'] = kickoff_returns_df['returnerId'].astype(int)\nkickoff_returns_players_df = pd.merge(kickoff_returns_df,sub_players_df,\n                             how='left',left_on ='returnerId',right_on ='nflId')\nkickoff_returns_players_df = kickoff_returns_players_df.loc[:,~kickoff_returns_players_df.columns.duplicated()]\nkickoff_returns_players_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n1. Analyze whether teams that featured receivers most often scored more touchdowns or gained more yards. (ID average number of receivers)\n2. Examine kickoffs that went for greater than 50 yds (2018-2020) and see what position group achieved the most\n3. Analyze which position group performed the best in TDs, YPR, Total Yardage\n4. Analyze which players per position group performed the best in TDs, YPR, Total Yardage\n","metadata":{}},{"cell_type":"code","source":"no_na_kickoff_returns_players_df = kickoff_returns_players_df.loc[kickoff_returns_players_df['possessionTeam'] > 'NaN']\nno_na_kickoff_returns_players_df\n\nno_na_kickoff_returns_players_df['Position'].value_counts().plot.barh(figsize=(9,3), title=\"Postition Count\")\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"td_returns = no_na_kickoff_returns_players_df.loc[no_na_kickoff_returns_players_df['playDescription'].str.contains('TOUCHDOWN')]\ntd_returns\ntd_returns['Position'].value_counts().plot.barh(figsize=(9,3), title=\"Postition Count by touchdowns\")\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fifty_kickoff_returns_players_df = no_na_kickoff_returns_players_df.loc[kickoff_returns_players_df['kickReturnYardage'] >= 50.0]\nfifty_kickoff_returns_players_df.head()\n\nfifty_kickoff_returns_players_df['Position'].value_counts().plot.barh(figsize=(9,3), title=\"Postition Count by greater than 50 yards\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fifty_kickoff_returns_players_df['Year'] = fifty_kickoff_returns_players_df['gameId'].astype(str).str[0:4]\nfifty_kickoff_returns_players_df.head()\n\nax = fifty_kickoff_returns_players_df.groupby(['Position','Year']).size().plot.barh(figsize=(14,6), title=\"Kickoff returns greater than 50 yards by Position Group\")\nax.set_ylabel('Kicking Position')\n\ntest = fifty_kickoff_returns_players_df.groupby(['Year','Position'])\ntest.first()\n\n#fifty_kickoff_returns_players_df['Position'].value_counts().plot.barh(figsize=(9,3), title=\"Postition Count by greater than 50 yards\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"no_na_kickoff_returns_players_df.groupby(['Position','displayName'])['kickReturnYardage'].mean()\nno_na_kickoff_returns_players_df.groupby(['Position','displayName']).nunique()\n#td_returns['Position'].count()\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"no_na_kickoff_returns_players_df.groupby(['Position','displayName'])['kickReturnYardage'].mean()","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}