{"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\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":"2021-09-25T14:22:05.037256Z","iopub.execute_input":"2021-09-25T14:22:05.037562Z","iopub.status.idle":"2021-09-25T14:22:05.136727Z","shell.execute_reply.started":"2021-09-25T14:22:05.037486Z","shell.execute_reply":"2021-09-25T14:22:05.135915Z"}},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\nfrom pandas_profiling import ProfileReport\npd.set_option('display.max_columns', None)","metadata":{"execution":{"iopub.status.busy":"2021-09-25T14:43:02.777950Z","iopub.execute_input":"2021-09-25T14:43:02.778351Z","iopub.status.idle":"2021-09-25T14:43:04.016770Z","shell.execute_reply.started":"2021-09-25T14:43:02.778314Z","shell.execute_reply":"2021-09-25T14:43:04.015990Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Read data to understand about data","metadata":{}},{"cell_type":"markdown","source":"# 1. PFFScoutingData\n\ngameId: Game identifier, unique, numeric\n\nplayId: Play identifier, not unique, numeric\n\nsnapDetail: \n\nsnapTime:\n\noperationTime:\n\nhangTime:\n\nkickType:\n\nkickDirectionIntended:\n\nkickDirectionActual:\n\nreturnDirectionIntended:\n\nreturnDirectionActual:\n\nmissedTackler:\n\nassistTackler:\n\ntackler:\n\nkickoffReturnFormation:\n\ngunners:\n\npuntRushers:\n\nspecialTeamSafeies:\n\nvises:\n\nkickContactType:\n\n\n\n\n","metadata":{}},{"cell_type":"code","source":"PFF_Scouting = pd.read_csv('../input/nfl-big-data-bowl-2022/PFFScoutingData.csv')\nPFF_Scouting.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T14:30:13.997942Z","iopub.execute_input":"2021-09-25T14:30:13.998286Z","iopub.status.idle":"2021-09-25T14:30:14.120210Z","shell.execute_reply.started":"2021-09-25T14:30:13.998253Z","shell.execute_reply":"2021-09-25T14:30:14.119284Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"PFF_Scouting.info()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T14:43:21.711652Z","iopub.execute_input":"2021-09-25T14:43:21.711917Z","iopub.status.idle":"2021-09-25T14:43:21.739293Z","shell.execute_reply.started":"2021-09-25T14:43:21.711891Z","shell.execute_reply":"2021-09-25T14:43:21.738029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"PFF_Scouting.describe()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:05:54.837659Z","iopub.execute_input":"2021-09-25T15:05:54.838296Z","iopub.status.idle":"2021-09-25T15:05:54.866803Z","shell.execute_reply.started":"2021-09-25T15:05:54.838252Z","shell.execute_reply":"2021-09-25T15:05:54.865878Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%matplotlib inline\nPFF_Scouting.hist(bins=50, figsize=(20, 15));","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:08:36.306266Z","iopub.execute_input":"2021-09-25T15:08:36.306553Z","iopub.status.idle":"2021-09-25T15:08:37.649015Z","shell.execute_reply.started":"2021-09-25T15:08:36.306527Z","shell.execute_reply":"2021-09-25T15:08:37.648082Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"profile_PFF_Scouting = ProfileReport(\n    PFF_Scouting, title=\"Pandas Profiling Report for NFL-big-data-bowl-2022\"\n)\nprofile_PFF_Scouting","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:10:55.379892Z","iopub.execute_input":"2021-09-25T15:10:55.380192Z","iopub.status.idle":"2021-09-25T15:11:17.961828Z","shell.execute_reply.started":"2021-09-25T15:10:55.380163Z","shell.execute_reply":"2021-09-25T15:11:17.961235Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2. Games\n\n","metadata":{}},{"cell_type":"code","source":"games = pd.read_csv(\"../input/nfl-big-data-bowl-2022/games.csv\")\ngames.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:02:51.268719Z","iopub.execute_input":"2021-09-25T15:02:51.268982Z","iopub.status.idle":"2021-09-25T15:02:51.286609Z","shell.execute_reply.started":"2021-09-25T15:02:51.268947Z","shell.execute_reply":"2021-09-25T15:02:51.286113Z"},"jupyter":{"source_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"games.info()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:03:08.661547Z","iopub.execute_input":"2021-09-25T15:03:08.662393Z","iopub.status.idle":"2021-09-25T15:03:08.675468Z","shell.execute_reply.started":"2021-09-25T15:03:08.662353Z","shell.execute_reply":"2021-09-25T15:03:08.674452Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"games.describe()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:09:43.137251Z","iopub.execute_input":"2021-09-25T15:09:43.137568Z","iopub.status.idle":"2021-09-25T15:09:43.156818Z","shell.execute_reply.started":"2021-09-25T15:09:43.137533Z","shell.execute_reply":"2021-09-25T15:09:43.156205Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"games.hist(bins=50, figsize=(20,15))","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:13:38.263781Z","iopub.execute_input":"2021-09-25T15:13:38.264822Z","iopub.status.idle":"2021-09-25T15:13:39.087717Z","shell.execute_reply.started":"2021-09-25T15:13:38.264771Z","shell.execute_reply":"2021-09-25T15:13:39.086888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"profile_games = ProfileReport(\n    games, title=\"Pandas Profiling Report for NFL-big-data-bowl-2022\"\n)\nprofile_games","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:11:25.203573Z","iopub.execute_input":"2021-09-25T15:11:25.203780Z","iopub.status.idle":"2021-09-25T15:11:32.249199Z","shell.execute_reply.started":"2021-09-25T15:11:25.203757Z","shell.execute_reply":"2021-09-25T15:11:32.248421Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3. Players","metadata":{}},{"cell_type":"code","source":"players = pd.read_csv('../input/nfl-big-data-bowl-2022/players.csv')\nplayers.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:15:09.670221Z","iopub.execute_input":"2021-09-25T15:15:09.670508Z","iopub.status.idle":"2021-09-25T15:15:09.703587Z","shell.execute_reply.started":"2021-09-25T15:15:09.670483Z","shell.execute_reply":"2021-09-25T15:15:09.702813Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"players.info()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:15:21.799141Z","iopub.execute_input":"2021-09-25T15:15:21.799448Z","iopub.status.idle":"2021-09-25T15:15:21.812950Z","shell.execute_reply.started":"2021-09-25T15:15:21.799417Z","shell.execute_reply":"2021-09-25T15:15:21.812295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"players.hist(bins=50, figsize=(20,15))","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:16:52.395526Z","iopub.execute_input":"2021-09-25T15:16:52.395818Z","iopub.status.idle":"2021-09-25T15:16:52.979428Z","shell.execute_reply.started":"2021-09-25T15:16:52.395785Z","shell.execute_reply":"2021-09-25T15:16:52.978563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"profile_players = ProfileReport(\n    players, title=\"Pandas Profiling Report for NFL-big-data-bowl-2022\"\n)\nprofile_players","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:18:55.084941Z","iopub.execute_input":"2021-09-25T15:18:55.085411Z","iopub.status.idle":"2021-09-25T15:19:03.379976Z","shell.execute_reply.started":"2021-09-25T15:18:55.085382Z","shell.execute_reply":"2021-09-25T15:19:03.379137Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. Plays","metadata":{}},{"cell_type":"code","source":"plays = pd.read_csv('../input/nfl-big-data-bowl-2022/plays.csv')\nplays.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:21:45.204719Z","iopub.execute_input":"2021-09-25T15:21:45.204980Z","iopub.status.idle":"2021-09-25T15:21:45.338364Z","shell.execute_reply.started":"2021-09-25T15:21:45.204953Z","shell.execute_reply":"2021-09-25T15:21:45.337383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plays.info()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:22:09.412955Z","iopub.execute_input":"2021-09-25T15:22:09.413260Z","iopub.status.idle":"2021-09-25T15:22:09.438723Z","shell.execute_reply.started":"2021-09-25T15:22:09.413230Z","shell.execute_reply":"2021-09-25T15:22:09.437848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plays.describe()","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:22:30.564441Z","iopub.execute_input":"2021-09-25T15:22:30.564755Z","iopub.status.idle":"2021-09-25T15:22:30.621551Z","shell.execute_reply.started":"2021-09-25T15:22:30.564724Z","shell.execute_reply":"2021-09-25T15:22:30.620747Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plays.hist(bins=50, figsize=(20,15))","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:23:03.699647Z","iopub.execute_input":"2021-09-25T15:23:03.699950Z","iopub.status.idle":"2021-09-25T15:23:07.394874Z","shell.execute_reply.started":"2021-09-25T15:23:03.699918Z","shell.execute_reply":"2021-09-25T15:23:07.394064Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"profile_plays = ProfileReport(\n    plays, title=\"Pandas Profiling Report for NFL-big-data-bowl-2022\"\n)\nprofile_plays","metadata":{"execution":{"iopub.status.busy":"2021-09-25T15:24:23.938346Z","iopub.execute_input":"2021-09-25T15:24:23.939011Z","iopub.status.idle":"2021-09-25T15:26:19.090613Z","shell.execute_reply.started":"2021-09-25T15:24:23.938964Z","shell.execute_reply":"2021-09-25T15:26:19.089589Z"},"trusted":true},"execution_count":null,"outputs":[]}]}