{"cells":[{"metadata":{"_uuid":"7296ec05f46c876ffa020f24ca67f9761d746e26"},"cell_type":"markdown","source":"# NFL Punt Player Data Analysis with New Rules Modification\n\n## Table of Content\n###### 1) Import all important Python Packages\n###### 2) Import all Datasets\n###### 3) Rename fields for all Datasets\n###### 4) Update missing values for all Datasets\n###### 5) Change data type for Video review Dataset\n###### 6) Date Types for all Datasets\n###### 7) Rename field values with proper text\n###### 8) Basic graphs for few Datasets\n###### 9) Data Analysis for all Datasets\n###### 10) Summary of Game Start Time\n###### 11) Summary of the Stadium\n###### 12) Summary of Punt Player Position"},{"metadata":{"_uuid":"3d2016f93ffa0824fbb2a082bbd084b6cfb22721"},"cell_type":"markdown","source":"# 1) Import all important Python Packages"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"dfb1463199089ad6340230f78cbc2bcbc7f83b08"},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport warnings\nwarnings.filterwarnings('ignore')\nimport plotly.figure_factory as ff \nimport  plotly.offline as py\nimport plotly.graph_objs as go \nfrom plotly.offline  import download_plotlyjs,init_notebook_mode,plot, iplot, plot\nimport cufflinks as cf\nfrom plotly import tools \npy.init_notebook_mode(connected = True)\nimport cufflinks as cf \ncf.go_offline()\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"abb1f4d8ee7a39fd3be7fd9672a41b9397ae1e9d"},"cell_type":"markdown","source":"# 2) Import all Datasets"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"205dfe61c357b76726e3635699d1f6743be43258"},"cell_type":"code","source":"Game_Data_Set = pd.read_csv('../input/game_data.csv')\nPlay_Information_Data_Set = pd.read_csv('../input/play_information.csv')\nPlayer_Punt_Data_Set = pd.read_csv('../input/player_punt_data.csv')\nPlay_Player_Role_Data_Set = pd.read_csv('../input/play_player_role_data.csv')\nVideo_Review_Data_Set = pd.read_csv('../input/video_review.csv')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"de2e15866fba5b48cbf854aeca359bb1071f94a7"},"cell_type":"markdown","source":"# 3) Rename fields for all Datasets"},{"metadata":{"_uuid":"9877cc63d0bbee4b8d90bdd4f60932859db1f665"},"cell_type":"markdown","source":"## Dateset - Game Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"8c819883293f4cf540aca3ff284a318d60eef336"},"cell_type":"code","source":"Game_Data_Set = Game_Data_Set.rename({\n    'GameKey' : 'Game_Key',\n    'HomeTeamCode' : 'Home_Team_Code',\n    'VisitTeamCode' : 'Visit_Team_Code',\n    'StadiumType' : 'Stadium_Type',\n    'GameWeather' : 'Game_Weather',\n    'OutdoorWeather' : 'Outdoor_Weather'\n    }, axis='columns')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"dda611e7068928f142f185affa3d63954c7886bb"},"cell_type":"markdown","source":"## Dataset - Play Information Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"aeaf5ba92042e5de848c4f5c00cda6100d4ec282"},"cell_type":"code","source":"Play_Information_Data_Set = Play_Information_Data_Set.rename({\n    'GameKey' : 'Game_Key',\n    'PlayID' : 'Play_ID',\n    'YardLine' : 'Yard_Line',\n    'PlayDescription' : 'Play_Description',\n    }, axis='columns')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"819ef4ee44944c309561a9d726374495a680340e"},"cell_type":"markdown","source":"## Dataset - Play Player Role Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"2b61bdf49e352b465f943bdc96deda85f6ab6b6e"},"cell_type":"code","source":"Play_Player_Role_Data_Set = Play_Player_Role_Data_Set.rename({\n    'GameKey' : 'Game_Key',\n    'PlayID' : 'Play_ID'\n    }, axis='columns')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"818ecacadedf2d692c2655d2c403c10be9e9234c"},"cell_type":"markdown","source":"## Dataset - Video Review Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"a672ce3f2f589f674642d4418f7ae68f323f8cee"},"cell_type":"code","source":"Video_Review_Data_Set = Video_Review_Data_Set.rename({\n    'GameKey' : 'Game_Key',\n    'PlayID' : 'Play_ID'\n    }, axis='columns')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1fec3a8d84bc6393159a89de513fc1f06cd27cdb"},"cell_type":"markdown","source":"# 4) Update missing values for all Datasets"},{"metadata":{"_uuid":"dae3e242609e4c554bfc802e06130486610770bc"},"cell_type":"markdown","source":"## Dateset - Game Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"410389a7665507bb42234eda3f560aab329f4e26"},"cell_type":"code","source":"Game_Data_Set['Stadium_Type'].fillna(\"Missing Stadium Type\", inplace=True)\nGame_Data_Set['Turf'].fillna(\"Missing Turf\", inplace=True)\nGame_Data_Set['Game_Weather'].fillna(\"Missing Weather\", inplace=True)\nGame_Data_Set['Temperature'].fillna(\"0.00\", inplace=True)\nGame_Data_Set['Outdoor_Weather'].fillna(\"Missing Outdoor Weather\", inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"2e5812e063fcfbafd4092246606ca56a3f69b6ca"},"cell_type":"markdown","source":"## Dataset - Video Review Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"a524b473ab56a7a32f47fc09030362dabe60c0e6"},"cell_type":"code","source":"Video_Review_Data_Set['Primary_Partner_GSISID'].fillna(\"0.00\", inplace=True)\nVideo_Review_Data_Set['Primary_Partner_Activity_Derived'].fillna(\"Missing Primary Partner Activity\", inplace=True)\nVideo_Review_Data_Set['Friendly_Fire'].fillna(\"Missing Friendly Fire\", inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"813606fbffe310654cf96c39e663ca6d5afa30b5"},"cell_type":"markdown","source":"# 5) Change data type for Video review Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"a5301fa4c0d18914f5f1e10dbb600b9caac34b19"},"cell_type":"code","source":"Video_Review_Data_Set.Season_Year = Video_Review_Data_Set.Season_Year.astype('int64')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"159686a7c59af8377572f3ac739a811b660c0cbf"},"cell_type":"markdown","source":"# 6) Date Types for all Datasets"},{"metadata":{"_uuid":"4acccbdff2d929464135d0d58cf9850a70b1e88d"},"cell_type":"markdown","source":"## Dataset - Game Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"7a3db7ff6a653fb2b653c3e2438671341da8fd48"},"cell_type":"code","source":"Game_Data_Set.info()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"215f30849009292c553e47d8fdb9ddcb1e0240c4"},"cell_type":"markdown","source":"## Dataset - Play Information Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"33d1c3bb9929d270ef121d6c29afdbca5258a88b"},"cell_type":"code","source":"Play_Information_Data_Set.info()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"33dec437b3a6b9af5f8ad17b831c9abda72989eb"},"cell_type":"markdown","source":"## Dataset - Player Punt Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"814a11de6e258c52851b858ea43897c0f0b3f6d9"},"cell_type":"code","source":"Player_Punt_Data_Set.info()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d7493e9474e1deb47950e48e28721863e9bec447"},"cell_type":"markdown","source":"## Dataset - Play Player Role Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"7f9db7b98c7ed77699736ce24301438069ff8215"},"cell_type":"code","source":"Play_Player_Role_Data_Set.info()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"207f6e1bb1f9fe805e7c479358742d25a58b0b2b"},"cell_type":"markdown","source":"## Dataset - Video Review Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"b9d30e797b4ef76b6c7732578b5e59de15dccbd9"},"cell_type":"code","source":"Video_Review_Data_Set.info()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0818d0ec05c001a680ea75d0e33c900e6906bc4b"},"cell_type":"markdown","source":"# 7) Rename field values with proper text"},{"metadata":{"_uuid":"2d58a4abdd33b282e4fd8993edb71443f531df58"},"cell_type":"markdown","source":"## Dataset - Game Data Dataset - Field Name - Stadium"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"4abb311c71ba6431c57d626c7dc79ef7138150ae"},"cell_type":"code","source":"Game_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"AT&T\", \"Stadium\"] = 'AT&T Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Bank of America\", \"Stadium\"] = 'Bank of America Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"CenturyLink\", \"Stadium\"] = 'CenturyLink Field'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"FirstEnergy\", \"Stadium\"] = 'First Energy Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"FirstEnergy Stadium\", \"Stadium\"] = 'First Energy Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"First Energy Stadium\", \"Stadium\"] = 'First Energy Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Los  Angeles Memorial Coliseum\", \"Stadium\"] = 'Los Angeles Memorial Coliseum'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Lucas Oil\", \"Stadium\"] = 'Lucas Oil Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"M & T Bank Stadium\", \"Stadium\"] = 'M&T Bank Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"M&T Stadium\", \"Stadium\"] = 'M&T Bank Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"MetLife\", \"Stadium\"] = 'MetLife Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Mercedes Benz-Superdome\", \"Stadium\"] = 'Mercedes-Benz Superdome'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"NRG Stadiium\", \"Stadium\"] = 'NRG Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Oakland Alameda-County Coliseum\", \"Stadium\"] = 'Oakland Alameda County Coliseum'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Oakland-Alameda County Coliseum\", \"Stadium\"] = 'Oakland Alameda County Coliseum'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Raymon James Stadium\", \"Stadium\"] = 'Raymond James Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Solidier Field\", \"Stadium\"] = 'Solider Field'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"Twickenham\", \"Stadium\"] = 'Twickenham Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"University of Phoenix\", \"Stadium\"] = 'University of Phoenix Stadium'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium\"] == \"US Bank Stadium\", \"Stadium\"] = 'U.S. Bank Stadium'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"9e404639a217bfd359480d9f808d16410b443a9a"},"cell_type":"markdown","source":"## Dataset - Game Data Dataset - Field Name - Stadium Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"5736f57a96e9c796841bc66954efcdd04815a14b"},"cell_type":"code","source":"Game_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Outdoors\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"outdoor\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Outdoors\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Outdor\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Outddors\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Oudoor\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Ourdoor\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Outdoors \", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Outside\", \"Stadium_Type\"] = 'Outdoor'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Indoor\", \"Stadium_Type\"] = 'Indoors'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Indoor, fixed roof\", \"Stadium_Type\"] = 'Indoor, Fixed Roof'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Dome, closed\", \"Stadium_Type\"] = 'Closed Dome'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Domed, Closed\", \"Stadium_Type\"] = 'Closed Dome'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Retr. Roof-Closed\", \"Stadium_Type\"] = 'Retr. Roof - Closed'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Retr. roof - closed\", \"Stadium_Type\"] = 'Retr. Roof - Closed'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Retr. Roof Closed\", \"Stadium_Type\"] = 'Retr. Roof - Closed'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Indoor, non-retractable roof\", \"Stadium_Type\"] = 'Indoor, Non-Retractable Roof'\nGame_Data_Set.loc[Game_Data_Set[\"Stadium_Type\"] == \"Retr. Roof-Open\", \"Stadium_Type\"] = 'Retr. Roof - Open'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1201a1b40a9386f65bd026739be04ef678f48206"},"cell_type":"markdown","source":"## Dataset - Game Data Dataset - Field Name - Turf"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"a674ad7b98dd442c4b23b143723e3f09f9e025a5"},"cell_type":"code","source":"Game_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"FieldTurf\", \"Turf\"] = 'Field Turf'\nGame_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"FieldTurf360\", \"Turf\"] = 'Field Turf 360'\nGame_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"FieldTurf 360\", \"Turf\"] = 'Field Turf 360'\nGame_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"grass\", \"Turf\"] = 'Grass'\nGame_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"Natrual Grass\", \"Turf\"] = 'Natural Grass'\nGame_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"Natural grass\", \"Turf\"] = 'Natural Grass'\nGame_Data_Set.loc[Game_Data_Set[\"Turf\"] == \"Naturall Grass\", \"Turf\"] = 'Natural Grass'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"cb29333b0344aa78347191916243480ee342e034"},"cell_type":"markdown","source":"## Dataset - Game Data Dataset - Field Name - Game Weather"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"1b38cd66fb847cacc3b948461efa1774dce75910"},"cell_type":"code","source":"Game_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Mostly cloudy\", \"Game_Weather\"] = 'Mostly Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Mostly Coudy\", \"Game_Weather\"] = 'Mostly Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Mostly CLoudy\", \"Game_Weather\"] = 'Mostly Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Partly sunny\", \"Game_Weather\"] = 'Partly Sunny'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"cloudy\", \"Game_Weather\"] = 'Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Party Cloudy\", \"Game_Weather\"] = 'Partly Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Partly CLoudy\", \"Game_Weather\"] = 'Partly Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Partly cloudy\", \"Game_Weather\"] = 'Partly Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Suny\", \"Game_Weather\"] = 'Sunny'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Sunny intervals\", \"Game_Weather\"] = 'Sunny Intervals'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Snow showers\", \"Game_Weather\"] = 'Snow Showers'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Indoor\", \"Game_Weather\"] = 'Indoors'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Coudy\", \"Game_Weather\"] = 'Cloudy'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"CLEAR\", \"Game_Weather\"] = 'Clear'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Cloudy and cold\", \"Game_Weather\"] = 'Cloudy and Cold'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Controlled\", \"Game_Weather\"] = 'Controlled Climate'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Sunny and cool\", \"Game_Weather\"] = 'Sunny and Cool'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Sunny and warm\", \"Game_Weather\"] = 'Sunny and Warm'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Sunny intervals\", \"Game_Weather\"] = 'Sunny Intervals'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Clear and warm\", \"Game_Weather\"] = 'Clear and Warm'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Clear skies\", \"Game_Weather\"] = 'Clear Skies'\nGame_Data_Set.loc[Game_Data_Set[\"Game_Weather\"] == \"Mostly Clear. Gusting ot 14.\", \"Game_Weather\"] = 'Mostly Clear'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"4fe5ba440220d8208efe40bfa4498f69b10943a9"},"cell_type":"markdown","source":"## Dataset - Game Data Dataset - Field Name - Season Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"27b28eab90da23e95e8e801d38b612b9be32964c"},"cell_type":"code","source":"Game_Data_Set.loc[Game_Data_Set[\"Season_Type\"] == \"Reg\", \"Season_Type\"] = 'Regular Season'\nGame_Data_Set.loc[Game_Data_Set[\"Season_Type\"] == \"Pre\", \"Season_Type\"] = 'Pre Season'\nGame_Data_Set.loc[Game_Data_Set[\"Season_Type\"] == \"Post\", \"Season_Type\"] = 'Post Season'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"65778592e1996b6abe1d487a24610e6e68be67e5"},"cell_type":"markdown","source":"## Dataset - Play Information - Field Name - Season Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"86f5f598f4a6a50729ff3401723fba4ca7097550"},"cell_type":"code","source":"Play_Information_Data_Set.loc[Play_Information_Data_Set[\"Season_Type\"] == \"Reg\", \"Season_Type\"] = 'Regular Season'\nPlay_Information_Data_Set.loc[Play_Information_Data_Set[\"Season_Type\"] == \"Pre\", \"Season_Type\"] = 'Pre Season'\nPlay_Information_Data_Set.loc[Play_Information_Data_Set[\"Season_Type\"] == \"Post\", \"Season_Type\"] = 'Post Season'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d9b1dfc47f1c1a1040afba1cd221e2d3928c70bb"},"cell_type":"markdown","source":"## Dataset - Video Review - Field Name - Primary Impact Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"499e833563cd669d296d739f78eac97f82eaf6c2"},"cell_type":"code","source":"Video_Review_Data_Set.loc[Video_Review_Data_Set[\"Primary_Impact_Type\"] == \"Helmet-to-body\", \"Primary_Impact_Type\"] = 'Helmet-to-Body'\nVideo_Review_Data_Set.loc[Video_Review_Data_Set[\"Primary_Impact_Type\"] == \"Helmet-to-ground\", \"Primary_Impact_Type\"] = 'Helmet-to-Ground'\nVideo_Review_Data_Set.loc[Video_Review_Data_Set[\"Primary_Impact_Type\"] == \"Helmet-to-helmet\", \"Primary_Impact_Type\"] = 'Helmet-to-Helmet'","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"30a19290bf818b2b2119aaeb480088f7757a3568"},"cell_type":"markdown","source":"# 8) Basic graphs for few Datasets"},{"metadata":{"_uuid":"be596db86d0307b8edb147a615d43bb5d0c085ee"},"cell_type":"markdown","source":"## Dataset - Game Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"270fddf17d79cb20272f19bf51f7f9d59cd98819"},"cell_type":"code","source":"f, axarr = plt.subplots(2, 2, figsize=(20, 10))\n\nf.subplots_adjust(hspace=0.5)\n\nsns.countplot(Game_Data_Set['Season_Year'], ax=axarr[0][0], color='#EC7063', order = Game_Data_Set['Season_Year'].value_counts().index)\naxarr[0][0].set_title(\"Season Year\", fontsize=14)\n\nsns.countplot(Game_Data_Set['Season_Type'], ax=axarr[0][1], color='#9B59B6',order = Game_Data_Set['Season_Type'].value_counts().index)\naxarr[0][1].set_title(\"Season Type\", fontsize=14)\n\nsns.countplot(Game_Data_Set['Week'], ax=axarr[1][0], color='#45B39D',order = Game_Data_Set['Week'].value_counts().index)\naxarr[1][0].set_title(\"Week\", fontsize=14)\n\nsns.countplot(Game_Data_Set['Game_Day'], ax=axarr[1][1], color='#F39C12',order = Game_Data_Set['Game_Day'].value_counts().index)\naxarr[1][1].set_title(\"Game Day\", fontsize=14)\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"4d7c121aacfd6a109ff7ed49141eceacc9fbc025"},"cell_type":"markdown","source":"## Dataset - Play Information Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"101a4f8252077046a6e7396fd7d3e52c5682c420"},"cell_type":"code","source":"f, axarr = plt.subplots(2, 2, figsize=(20, 10))\n\nf.subplots_adjust(hspace=0.5)\n\nsns.countplot(Play_Information_Data_Set['Season_Year'], ax=axarr[0][0], color='#EC7063', order = Play_Information_Data_Set['Season_Year'].value_counts().index)\naxarr[0][0].set_title(\"Season Year\", fontsize=14)\n\nsns.countplot(Play_Information_Data_Set['Season_Type'], ax=axarr[0][1], color='#45B39D',order = Play_Information_Data_Set['Season_Type'].value_counts().index)\naxarr[0][1].set_title(\"Season Type\", fontsize=14)\n\nsns.countplot(Play_Information_Data_Set['Week'], ax=axarr[1][0], color='#9B59B6',order = Play_Information_Data_Set['Week'].value_counts().index)\naxarr[1][0].set_title(\"Week\", fontsize=14)\n\nsns.countplot(Play_Information_Data_Set['Quarter'], ax=axarr[1][1], color='#F39C12',order = Play_Information_Data_Set['Quarter'].value_counts().index)\naxarr[1][1].set_title(\"Quarter\", fontsize=14)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d769e294364e526aefe0b15fe80065442d9b1e61"},"cell_type":"markdown","source":"## Dataset - Video Peview Dataset"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"a73150b8f90ee13549e40e147e880e05fe06a3a8"},"cell_type":"code","source":"f, axarr = plt.subplots(2, 2, figsize=(20, 10))\n\nf.subplots_adjust(hspace=0.5)\n\nsns.countplot(Video_Review_Data_Set['Season_Year'], ax=axarr[0][0], color='#EC7063', order = Video_Review_Data_Set['Season_Year'].value_counts().index)\naxarr[0][0].set_title(\"Season Year\", fontsize=14)\n\nsns.countplot(Video_Review_Data_Set['Player_Activity_Derived'], ax=axarr[0][1], color='#45B39D',order = Video_Review_Data_Set['Player_Activity_Derived'].value_counts().index)\naxarr[0][1].set_title(\"Player Activity Derived\", fontsize=14)\n\nsns.countplot(Video_Review_Data_Set['Primary_Impact_Type'], ax=axarr[1][0], color='#9B59B6',order = Video_Review_Data_Set['Primary_Impact_Type'].value_counts().index)\naxarr[1][0].set_title(\"Primary Impact Type\", fontsize=14)\n\nsns.countplot(Video_Review_Data_Set['Primary_Partner_Activity_Derived'], ax=axarr[1][1], color='#F39C12',order = Video_Review_Data_Set['Primary_Partner_Activity_Derived'].value_counts().index)\naxarr[1][1].set_title(\"Primary Partner Activity Derived\", fontsize=14)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0ea1ac5c5534ac239aaa621840ec0d052c5a89ab"},"cell_type":"markdown","source":"# 9) Data Analysis for all Datasets"},{"metadata":{"_uuid":"42dc500c3ba47e1016eb99f736a375b81a15df2e"},"cell_type":"markdown","source":"## Dataset - Game Dataset"},{"metadata":{"_uuid":"ff8463308c3529ffa92be0cf9880b5f66859f4a0"},"cell_type":"markdown","source":"### Field Name - Season Year"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"856734f554f945c1e630ecff2ac41860c1afefbf"},"cell_type":"code","source":"TotalGame2017 = Game_Data_Set[Game_Data_Set['Season_Year']==2017]['Season_Year'].value_counts()\nTotalGame2017Percentage = round(TotalGame2017 / len(Game_Data_Set.Season_Year) * 100,2)\n\nTotalGame2016 = Game_Data_Set[Game_Data_Set['Season_Year']==2016]['Season_Year'].value_counts()\nTotalGame2016Percentage = round(TotalGame2016 / len(Game_Data_Set.Season_Year) * 100,2)\n\nTotalPercentage = round(len(Game_Data_Set.Season_Year) / len(Game_Data_Set.Season_Year) * 100,2)\n\nField_1 = pd.Series({'Description': 'Year 2017',\n                        'Total Records': int(TotalGame2017.values),\n                         'Percentage' : float(TotalGame2017Percentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Year 2016',\n                        'Total Records': int(TotalGame2016.values),\n                         'Percentage' : float(TotalGame2016Percentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Total',\n                        'Total Records': Game_Data_Set['Season_Year'].count(),\n                         'Percentage' : TotalPercentage})\nYearSummary = pd.DataFrame([Field_1,Field_2,Field_3], index=['1','2','3'])\nYearSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"d9c7d5c5d8a09dc2b420c54fededada997fdf459"},"cell_type":"code","source":"labels = (np.array(Game_Data_Set[\"Season_Year\"].unique()))\nvalues = Game_Data_Set[\"Season_Year\"].value_counts()\ncolors = ['#F15854 ', '#60BD68  ']\n\ntrace = go.Pie(labels=labels, values=values,\n               hoverinfo='percent+label', textinfo='value', \n               textfont=dict(size=20),\n               marker=dict(colors=colors, \n                           line=dict(color='#FFFFFF', width=2)))\npy.offline.iplot([trace], filename='styled_pie_chart')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c0df84ea9a86a060a04ff85eefed472f92fec197"},"cell_type":"markdown","source":"### Field Name - Game Day"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"487b226550f13f757c76a4156ca669c9b8817cc6"},"cell_type":"code","source":"TotalSunday = Game_Data_Set[Game_Data_Set['Game_Day']=='Sunday']['Game_Day'].value_counts()\nTotalSundayPercentage = round(TotalSunday / len(Game_Data_Set.Game_Day) * 100,2)\n\nTotalThursday = Game_Data_Set[Game_Data_Set['Game_Day']=='Thursday']['Game_Day'].value_counts()\nTotalThursdayPercentage = round(TotalThursday / len(Game_Data_Set.Game_Day) * 100,2)\n\nTotalSaturday = Game_Data_Set[Game_Data_Set['Game_Day']=='Saturday']['Game_Day'].value_counts()\nTotalSaturdayPercentage = round(TotalSaturday / len(Game_Data_Set.Game_Day) * 100,2)\n\nTotalMonday = Game_Data_Set[Game_Data_Set['Game_Day']=='Monday']['Game_Day'].value_counts()\nTotalMondayPercentage = round(TotalMonday / len(Game_Data_Set.Game_Day) * 100,2)\n\nTotalFriday = Game_Data_Set[Game_Data_Set['Game_Day']=='Friday']['Game_Day'].value_counts()\nTotalFridayPercentage = round(TotalFriday / len(Game_Data_Set.Game_Day) * 100,2)\n\nTotalWednesday = Game_Data_Set[Game_Data_Set['Game_Day']=='Wednesday']['Game_Day'].value_counts()\nTotalWednesdayPercentage = round(TotalWednesday / len(Game_Data_Set.Game_Day) * 100,2)\n\nTotalPercentage = round(len(Game_Data_Set.Game_Day) / len(Game_Data_Set.Game_Day) * 100,2)\n\nField_1 = pd.Series({'Description': 'Sunday',\n                        'Total Records': int(TotalSunday.values),\n                         'Percentage' : float(TotalSundayPercentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Thursday',\n                        'Total Records': int(TotalThursday.values),\n                         'Percentage' : float(TotalThursdayPercentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Saturday',\n                        'Total Records': int(TotalSaturday.values),\n                         'Percentage' : float(TotalSaturdayPercentage.values),                     \n                    })\nField_4 = pd.Series({'Description': 'Monday',\n                        'Total Records': int(TotalMonday.values),\n                         'Percentage' : float(TotalMondayPercentage.values),                     \n                    })\nField_5 = pd.Series({'Description': 'Friday',\n                        'Total Records': int(TotalFriday.values),\n                         'Percentage' : float(TotalFridayPercentage.values),                     \n                    })\nField_6 = pd.Series({'Description': 'Wednesday',\n                        'Total Records': int(TotalWednesday.values),\n                         'Percentage' : float(TotalWednesdayPercentage.values),                     \n                    })\nField_7 = pd.Series({'Description': 'Total',\n                        'Total Records': Game_Data_Set['Game_Day'].count(),\n                         'Percentage' : TotalPercentage})\nGameDaySummary = pd.DataFrame([Field_1,Field_2,Field_3,Field_4,Field_5,Field_6,Field_7], index=['1','2','3','4','5','6','7'])\nGameDaySummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"2b0d799ac09aa687add3fb442d14da8f99a19f08"},"cell_type":"code","source":"GraphData=Game_Data_Set.groupby('Game_Day').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Total Records', title='Game Day')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1bba51424c0121ff01e08c9a1514e0c514ce21e4"},"cell_type":"markdown","source":"### Field Name - Season Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"8f23a12322651373b8055fd44a2840ec70c42aa1"},"cell_type":"code","source":"TotalReg = Game_Data_Set[Game_Data_Set['Season_Type']=='Regular Season']['Season_Type'].value_counts()\nTotalRegPercentage = round(TotalReg / len(Game_Data_Set.Season_Type) * 100,2)\n\nTotalPre = Game_Data_Set[Game_Data_Set['Season_Type']=='Pre Season']['Season_Type'].value_counts()\nTotalPrePercentage = round(TotalPre / len(Game_Data_Set.Season_Type) * 100,2)\n\nTotalPost = Game_Data_Set[Game_Data_Set['Season_Type']=='Post Season']['Season_Type'].value_counts()\nTotalPostPercentage = round(TotalPost / len(Game_Data_Set.Season_Type) * 100,2)\n\nTotalPercentage = round(len(Game_Data_Set.Season_Type) / len(Game_Data_Set.Season_Type) * 100,2)\n\nField_1 = pd.Series({'Description': 'Regular Season',\n                        'Total Records': int(TotalReg.values),\n                         'Percentage' : float(TotalRegPercentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Pre Season',\n                        'Total Records': int(TotalPre.values),\n                         'Percentage' : float(TotalPrePercentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Post Season',\n                        'Total Records': int(TotalPost.values),\n                         'Percentage' : float(TotalPostPercentage.values),                     \n                    })\nField_4 = pd.Series({'Description': 'Total',\n                        'Total Records': Game_Data_Set['Season_Type'].count(),\n                         'Percentage' : TotalPercentage})\nSeasonTypeSummary = pd.DataFrame([Field_1,Field_2,Field_3,Field_4], index=['1','2','3','4'])\nSeasonTypeSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"d74dfce153ccca441961c32819b0fb47313d8684"},"cell_type":"code","source":"GraphData=Game_Data_Set.groupby('Season_Type').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Total Records', title='Season Type')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ab4163ab43db2a2ee4f1db64de207a67542a2521"},"cell_type":"markdown","source":"## Dataset - Play Information Dataset"},{"metadata":{"_uuid":"6bce61fdd310bb5a086f061eb17abfcb32c3c3ec"},"cell_type":"markdown","source":"### Field Name - Season Year"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"9a70b2ed16979be3973aabbd498fe6e2de4c8fbd"},"cell_type":"code","source":"TotalGame2017 = Play_Information_Data_Set[Play_Information_Data_Set['Season_Year']==2017]['Season_Year'].value_counts()\nTotalGame2017Percentage = round(TotalGame2017 / len(Play_Information_Data_Set.Season_Year) * 100,2)\n\nTotalGame2016 = Play_Information_Data_Set[Play_Information_Data_Set['Season_Year']==2016]['Season_Year'].value_counts()\nTotalGame2016Percentage = round(TotalGame2016 / len(Play_Information_Data_Set.Season_Year) * 100,2)\n\nTotalPercentage = round(len(Play_Information_Data_Set.Season_Year) / len(Play_Information_Data_Set.Season_Year) * 100,2)\n\nField_1 = pd.Series({'Description': 'Year 2017',\n                        'Total Records': int(TotalGame2017.values),\n                         'Percentage' : float(TotalGame2017Percentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Year 2016',\n                        'Total Records': int(TotalGame2016.values),\n                         'Percentage' : float(TotalGame2016Percentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Total',\n                        'Total Records': Play_Information_Data_Set['Season_Year'].count(),\n                         'Percentage' : TotalPercentage})\nYearSummary = pd.DataFrame([Field_1,Field_2,Field_3], index=['1','2','3'])\nYearSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"3e0523f429bea17e75b2d346006b8d00919a2abc"},"cell_type":"code","source":"labels = (np.array(Play_Information_Data_Set[\"Season_Year\"].unique()))\nvalues = Play_Information_Data_Set[\"Season_Year\"].value_counts()\ncolors = ['#F15854', '#60BD68']\n\ntrace = go.Pie(labels=labels, values=values,\n               hoverinfo='percent+label', textinfo='value', \n               textfont=dict(size=20),\n               marker=dict(colors=colors, \n                           line=dict(color='#FFFFFF', width=2)))\npy.offline.iplot([trace], filename='styled_pie_chart')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"4164d532e296a2a0cd28add7d05987427e027837"},"cell_type":"markdown","source":"### Field Name - Season Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"784df50bef751ee4560839e707baec6a086d3a9e"},"cell_type":"code","source":"TotalReg = Play_Information_Data_Set[Play_Information_Data_Set['Season_Type']=='Regular Season']['Season_Type'].value_counts()\nTotalRegPercentage = round(TotalReg / len(Play_Information_Data_Set.Season_Type) * 100,2)\n\nTotalPre = Play_Information_Data_Set[Play_Information_Data_Set['Season_Type']=='Pre Season']['Season_Type'].value_counts()\nTotalPrePercentage = round(TotalPre / len(Play_Information_Data_Set.Season_Type) * 100,2)\n\nTotalPost = Play_Information_Data_Set[Play_Information_Data_Set['Season_Type']=='Post Season']['Season_Type'].value_counts()\nTotalPostPercentage = round(TotalPost / len(Play_Information_Data_Set.Season_Type) * 100,2)\n\nTotalPercentage = round(len(Play_Information_Data_Set.Season_Type) / len(Play_Information_Data_Set.Season_Type) * 100,2)\n\nField_1 = pd.Series({'Description': 'Regular Season',\n                        'Total Records': int(TotalReg.values),\n                         'Percentage' : float(TotalRegPercentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Pre Season',\n                        'Total Records': int(TotalPre.values),\n                         'Percentage' : float(TotalPrePercentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Post Season',\n                        'Total Records': int(TotalPost.values),\n                         'Percentage' : float(TotalPostPercentage.values),                     \n                    })\nField_4 = pd.Series({'Description': 'Total',\n                        'Total Records': Play_Information_Data_Set['Season_Type'].count(),\n                         'Percentage' : TotalPercentage})\nSeasonTypeSummary = pd.DataFrame([Field_1,Field_2,Field_3,Field_4], index=['1','2','3','4'])\nSeasonTypeSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"d00f2eb1c8f61f35b43b7cc458c806c2ae78d6da"},"cell_type":"code","source":"GraphData=Play_Information_Data_Set.groupby('Season_Type').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Total Records', title='Season Type')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"03d62b56013337544613caf62d10fe4e1d2ad3dc"},"cell_type":"markdown","source":"### Field Name - Quarter"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"67fc6e7d0fba19f43b73c189331cdb4449538d1d"},"cell_type":"code","source":"TotalSecond = Play_Information_Data_Set[Play_Information_Data_Set['Quarter']==2]['Quarter'].value_counts()\nTotalSecondPercentage = round(TotalSecond / len(Play_Information_Data_Set.Quarter) * 100,2)\n\nTotalFirst = Play_Information_Data_Set[Play_Information_Data_Set['Quarter']==1]['Quarter'].value_counts()\nTotalFirstPercentage = round(TotalFirst / len(Play_Information_Data_Set.Quarter) * 100,2)\n\nTotalFourth = Play_Information_Data_Set[Play_Information_Data_Set['Quarter']==4]['Quarter'].value_counts()\nTotalFourthPercentage = round(TotalFourth / len(Play_Information_Data_Set.Quarter) * 100,2)\n\nTotalThird = Play_Information_Data_Set[Play_Information_Data_Set['Quarter']==3]['Quarter'].value_counts()\nTotalThirdPercentage = round(TotalThird / len(Play_Information_Data_Set.Quarter) * 100,2)\n\nTotalOverTime = Play_Information_Data_Set[Play_Information_Data_Set['Quarter']==5]['Quarter'].value_counts()\nTotalOverTimePercentage = round(TotalOverTime / len(Play_Information_Data_Set.Quarter) * 100,2)\n\nTotalPercentage = round(len(Play_Information_Data_Set.Quarter) / len(Play_Information_Data_Set.Quarter) * 100,2)\n\nField_1 = pd.Series({'Description': 'Second Quarter',\n                        'Total Records': int(TotalSecond.values),\n                         'Percentage' : float(TotalSecondPercentage.values),\n                    })\nField_2 = pd.Series({'Description': 'First Quarter',\n                        'Total Records': int(TotalFirst.values),\n                         'Percentage' : float(TotalFirstPercentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Fourth Quarter',\n                        'Total Records': int(TotalFourth.values),\n                         'Percentage' : float(TotalFourthPercentage.values),                     \n                    })\nField_4 = pd.Series({'Description': 'Third Quarter',\n                        'Total Records': int(TotalThird.values),\n                         'Percentage' : float(TotalThirdPercentage.values),                     \n                    })\n\nField_5 = pd.Series({'Description': 'Overtime',\n                        'Total Records': int(TotalOverTime.values),\n                         'Percentage' : float(TotalOverTimePercentage.values),                     \n                    })\n\nField_6 = pd.Series({'Description': 'Total',\n                        'Total Records': Play_Information_Data_Set['Quarter'].count(),\n                         'Percentage' : TotalPercentage})\nQuarterSummary = pd.DataFrame([Field_1,Field_2,Field_3,Field_4,Field_5,Field_6], index=['1','2','3','4','5','6'])\nQuarterSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"943037dbaf084f610a813ac0feea369336221dcd"},"cell_type":"code","source":"GraphData=Play_Information_Data_Set.groupby('Quarter').size().nlargest(6)\nGraphData.iplot(kind='bar',yTitle='Total Records', title='Quarter')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"860d4257932fda9b23118f0b0dd01690de393fc9"},"cell_type":"markdown","source":"## Dataset - Video Review Dataset"},{"metadata":{"_uuid":"b7906e84b46d926e2a695fa69c46841576d29821"},"cell_type":"markdown","source":"### Field Name - Season Year"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"0484f26374d5174e6b8b8efc0453d987c5d06bd3"},"cell_type":"code","source":"TotalGame2017 = Video_Review_Data_Set[Video_Review_Data_Set['Season_Year']==2017]['Season_Year'].value_counts()\nTotalGame2017Percentage = round(TotalGame2017 / len(Video_Review_Data_Set.Season_Year) * 100,2)\n\nTotalGame2016 = Video_Review_Data_Set[Video_Review_Data_Set['Season_Year']==2016]['Season_Year'].value_counts()\nTotalGame2016Percentage = round(TotalGame2016 / len(Video_Review_Data_Set.Season_Year) * 100,2)\n\nTotalPercentage = round(len(Video_Review_Data_Set.Season_Year) / len(Video_Review_Data_Set.Season_Year) * 100,2)\n\nField_1 = pd.Series({'Description': 'Year 2017',\n                        'Total Records': int(TotalGame2017.values),\n                         'Percentage' : float(TotalGame2017Percentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Year 2016',\n                        'Total Records': int(TotalGame2016.values),\n                         'Percentage' : float(TotalGame2016Percentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Total',\n                        'Total Records': Video_Review_Data_Set['Season_Year'].count(),\n                         'Percentage' : TotalPercentage})\nYearSummary = pd.DataFrame([Field_1,Field_2,Field_3], index=['1','2','3'])\nYearSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"87a5fad7f592c6a533e5798027e8967ed9b0ecab"},"cell_type":"code","source":"labels = (np.array(Video_Review_Data_Set[\"Season_Year\"].unique()))\nvalues = Video_Review_Data_Set[\"Season_Year\"].value_counts()\ncolors = ['#F15854', '#60BD68']\n\ntrace = go.Pie(labels=labels, values=values,\n               hoverinfo='percent+label', textinfo='value', \n               textfont=dict(size=20),\n               marker=dict(colors=colors, \n                           line=dict(color='#FFFFFF', width=2)))\npy.offline.iplot([trace], filename='styled_pie_chart')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d94ce74f1f34e72514c66699a6cf73c1b51306bd"},"cell_type":"markdown","source":"### Field Name - Player Activity Derived"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"d80d0fe070a650654ae4a57c7855d40fccf59507"},"cell_type":"code","source":"TotalTackling = Video_Review_Data_Set[Video_Review_Data_Set['Player_Activity_Derived']=='Tackling']['Player_Activity_Derived'].value_counts()\nTotalTacklingPercentage = round(TotalTackling / len(Video_Review_Data_Set.Season_Year) * 100,2)\n\nTotalBlocked = Video_Review_Data_Set[Video_Review_Data_Set['Player_Activity_Derived']=='Blocked']['Player_Activity_Derived'].value_counts()\nTotalBlockedPercentage = round(TotalBlocked / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nTotalBlocking = Video_Review_Data_Set[Video_Review_Data_Set['Player_Activity_Derived']=='Blocking']['Player_Activity_Derived'].value_counts()\nTotalBlockingPercentage = round(TotalBlocking / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nTotalTackled = Video_Review_Data_Set[Video_Review_Data_Set['Player_Activity_Derived']=='Tackled']['Player_Activity_Derived'].value_counts()\nTotalTackledPercentage = round(TotalTackled / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nTotalActivity = round(len(Video_Review_Data_Set.Player_Activity_Derived) / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nField_1 = pd.Series({'Description': 'Tackling',\n                        'Total Records': int(TotalTackling.values),\n                         'Percentage' : float(TotalTacklingPercentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Blocked',\n                        'Total Records': int(TotalBlocked.values),\n                         'Percentage' : float(TotalBlockedPercentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Blocking',\n                        'Total Records': int(TotalBlocking.values),\n                         'Percentage' : float(TotalBlockingPercentage.values),                     \n                    })\nField_4 = pd.Series({'Description': 'Tackled',\n                        'Total Records': int(TotalTackled.values),\n                         'Percentage' : float(TotalTackledPercentage.values),                     \n                    })\nField_5 = pd.Series({'Description': 'Total',\n                        'Total Records': Video_Review_Data_Set['Player_Activity_Derived'].count(),\n                         'Percentage' : TotalActivity})\nActivitySummary = pd.DataFrame([Field_1,Field_2,Field_3,Field_4,Field_5], index=['1','2','3','4','5'])\nActivitySummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"61317c4bc74c04b75ba454f02271cd84515a8d45"},"cell_type":"code","source":"GraphData=Video_Review_Data_Set.groupby('Player_Activity_Derived').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Number of Injuries', title='Player Activity Derived')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"57b02624b5b11df9200cf622bb88ccecf849aa78"},"cell_type":"markdown","source":"### Field Name - Primary Impact Type"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"e40593cd3064cce9066b8b0bbbbf067a043b6142"},"cell_type":"code","source":"TotalHTB = Video_Review_Data_Set[Video_Review_Data_Set['Primary_Impact_Type']=='Helmet-to-Body']['Primary_Impact_Type'].value_counts()\nTotalHTBPercentage = round(TotalHTB / len(Video_Review_Data_Set.Season_Year) * 100,2)\n\nTotalHTH = Video_Review_Data_Set[Video_Review_Data_Set['Primary_Impact_Type']=='Helmet-to-Helmet']['Primary_Impact_Type'].value_counts()\nTotalHTHPercentage = round(TotalHTH / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nTotalHTG = Video_Review_Data_Set[Video_Review_Data_Set['Primary_Impact_Type']=='Helmet-to-Ground']['Primary_Impact_Type'].value_counts()\nTotalHTGPercentage = round(TotalHTG / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nTotalUnclear = Video_Review_Data_Set[Video_Review_Data_Set['Primary_Impact_Type']=='Unclear']['Primary_Impact_Type'].value_counts()\nTotalUnclearPercentage = round(TotalUnclear / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nTotalActivity = round(len(Video_Review_Data_Set.Player_Activity_Derived) / len(Video_Review_Data_Set.Player_Activity_Derived) * 100,2)\n\nField_1 = pd.Series({'Description': 'Helmet-to-Body',\n                        'Total Records': int(TotalHTB.values),\n                         'Percentage' : float(TotalHTBPercentage.values),\n                    })\nField_2 = pd.Series({'Description': 'Helmet-to-Helmet',\n                        'Total Records': int(TotalHTH.values),\n                         'Percentage' : float(TotalHTHPercentage.values),                     \n                    })\nField_3 = pd.Series({'Description': 'Helmet-to-Ground',\n                        'Total Records': int(TotalHTG.values),\n                         'Percentage' : float(TotalHTGPercentage.values),                     \n                    })\nField_4 = pd.Series({'Description': 'Unclear',\n                        'Total Records': int(TotalUnclear.values),\n                         'Percentage' : float(TotalUnclearPercentage.values),                     \n                    })\nField_5 = pd.Series({'Description': 'Total',\n                        'Total Records': Video_Review_Data_Set['Primary_Impact_Type'].count(),\n                         'Percentage' : TotalActivity})\nImpactSummary = pd.DataFrame([Field_1,Field_2,Field_3,Field_4,Field_5], index=['1','2','3','4','5'])\nImpactSummary","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"cba06489807e262270a8d719c96e2a485c6cba90"},"cell_type":"code","source":"GraphData=Video_Review_Data_Set.groupby('Primary_Impact_Type').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Number of Injuries', title='Primary Impact Type')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b4544ff3f0aa262c20b6ed0f953fcf9fbab8ea50"},"cell_type":"markdown","source":"# 10) Summary of Game Start Time"},{"metadata":{"_uuid":"12f3d403e1b11242a54abca43022662bb0f65bc8"},"cell_type":"markdown","source":"## Total Game Start Time"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"6670156b8fbe9e76426dc798b489f2cf17cf23d6"},"cell_type":"code","source":"Game_Data_Set.Start_Time.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"6b9f980f7d9893a74356c6b4cc7d51402e3ddaf3"},"cell_type":"code","source":"GraphData=Game_Data_Set.groupby('Start_Time').size().nlargest(666)\nGraphData.iplot(kind='bar',yTitle='Number of Match', title='Game Start Time')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8e30172e0765b9ef22000b4f74077590530cf00b"},"cell_type":"markdown","source":"## Total Game Injuries Start Time"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"d2a810fc95511ba3fd3ea55f41e3522a42890273"},"cell_type":"code","source":"Game_Video_Data_Set = pd.merge(Game_Data_Set, Video_Review_Data_Set,\n                          how='inner',\n                          on=['Game_Key'])\nGraphData=Game_Video_Data_Set.groupby('Start_Time').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Number of Injuires', title='Game Injuries Start Time')","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"96ca6fb67d377ce8c49d51cb275a8ea564f3e39a"},"cell_type":"code","source":"plt.figure(figsize = (18,5))\nsns.swarmplot(x= Video_Review_Data_Set[\"Primary_Impact_Type\"], y = Video_Review_Data_Set[\"Game_Key\"])\nplt.title(\"Total Primary Impact Type\")\nplt.xlabel(\"Primary Impact Type\")\nplt.ylabel(\"Total\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"077644d301a309c4cb92346fd062a6922f62d2e1"},"cell_type":"markdown","source":"## 11) Summary of the Stadium"},{"metadata":{"_uuid":"5294ada0f723d6449beb7a5edb1b92dc49d8feb6"},"cell_type":"markdown","source":"## No. of Game played in the Stadium"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"ad437bfb943df7e8d448364aaedfdc0b5aa7512a"},"cell_type":"code","source":"Game_Data_Set.Stadium.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"15aebb715287caf32ce60b712fccc97489944aae"},"cell_type":"code","source":"GraphData=Game_Data_Set.groupby('Stadium').size().nlargest(666)\nGraphData.iplot(kind='bar',yTitle='Number of Match', title='Stadium Name')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"4c15001a48f96d5f8c45a737b887ae074b189420"},"cell_type":"markdown","source":"## List of the Stadium that incurred injuries"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"6b8e69f3484c28b01c168634fba2a3302f02bf0a"},"cell_type":"code","source":"Game_Video_Stadium_Data_Set = pd.merge(Game_Data_Set,Video_Review_Data_Set,\n                          how='inner',\n                          on=['Game_Key'])","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"6ed8222ffedf9963a9230b27fc4a31116c8291e0"},"cell_type":"code","source":"Game_Video_Stadium_Data_Set.Stadium.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"4b0de79957ff6ce54cf677d318be6c18d7f80c7b"},"cell_type":"code","source":"GraphData=Game_Video_Stadium_Data_Set.groupby('Stadium').size().nlargest(10)\nGraphData.iplot(kind='bar',yTitle='Number of Match Injuries', title='Stadium Name')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c3399d45d47b67b8599585f47a12f7c199d9b6be"},"cell_type":"markdown","source":"# 12) Summary of Punt Player Position"},{"metadata":{"_uuid":"29e1a26e0e8642a2ddc45f2650d583ce3bbe1128"},"cell_type":"markdown","source":"## Comparison of Helmet-to-Helmet and Helmet-to-Body"},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"2209c2a3a8914605352da1e64855b3e72637833e"},"cell_type":"code","source":"Game_Video_Data_Set = pd.merge(Video_Review_Data_Set,Play_Player_Role_Data_Set,\n                          how='inner',\n                          on=['Play_ID','Game_Key','GSISID'])","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"a3c17e71341d040eaedfbed6c4583af9b351514b"},"cell_type":"code","source":"HTH = Game_Video_Data_Set[(Game_Video_Data_Set.Primary_Impact_Type == 'Helmet-to-Helmet')]\nHTH.Role.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"41f5f1eb27f6f1627c60a2b9795899a6927341b0"},"cell_type":"code","source":"GraphData=HTH.groupby('Role').size().nlargest(11)\nGraphData.iplot(kind='bar',yTitle='Number of Injuires', title='Helmet-to-Helmet')","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"1e89906513397542f035b9837190b4a113be8094"},"cell_type":"code","source":"HTB = Game_Video_Data_Set[(Game_Video_Data_Set.Primary_Impact_Type == 'Helmet-to-Body')]\nHTB.Role.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":false,"_uuid":"691e653a05290ce7edaae8fa98f2221a53585692"},"cell_type":"code","source":"GraphData=HTB.groupby('Role').size().nlargest(11)\nGraphData.iplot(kind='bar',yTitle='Number of Injuires', title='Helmet-to-Body')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"4ee0cfff7b326fcbd5457ed7867d8abab85bbe3d"},"cell_type":"markdown","source":"### I would like to Thank You for spending time to review my Kernel I hope that this might help you to reduce punt player injuires."}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}