{"cells":[{"metadata":{},"cell_type":"markdown","source":"# The Two-Team Factor: Gender in March Madness"},{"metadata":{},"cell_type":"markdown","source":"![small_champ_wm.jpg](attachment:small_champ_wm.jpg)","attachments":{"small_champ_wm.jpg":{"image/jpeg":"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"}}},{"metadata":{},"cell_type":"markdown","source":"### The purpose of this notebook is to explore the connection between Men and Women's NCAA Basketball. \n"},{"metadata":{},"cell_type":"markdown","source":"**We want to know whether the success of one program has any effect on the other?**\n\nWe seek to establish a factor based on this connection that can be used to predict the performance of a team in the NCAA Tournament.\nThe factor being examined is whether a college program that has both a men's and women's team participating in the NCAA Tournament in the same season will perform better than a program that only has a single team participating. We will call this the **\"Two-Team Factor.\"**\n\nWe will call programs that have both Men's and Women's teams playing in the tournament Two-Team Programs, and programs that have only a men's or a women's team competing Single Team Programs."},{"metadata":{},"cell_type":"markdown","source":"### Table of Contents\n1. Introduction\n2. Preparations\n    * 2.1 Creating Dataframes\n    * 2.2 Add Tournament Rounds    \n3. Exploration\n    * 3.1 Breakdown of Teams in Each Round\n    * 3.2 Win Percentage per Round\n    * 3.3 By Season   \n    * 3.4 Two-Team Programs vs Single Team Programs    \n4. Other Factors\n    * 4.1 PPG\n    * 4.2 Seed\n    * 4.3 Conference  \n5. Conclusion\n    "},{"metadata":{},"cell_type":"markdown","source":"# 1. Introduction"},{"metadata":{},"cell_type":"markdown","source":"March Madness is a special time of year. Fans are able to root for their favorite teams in a single elimination tournament that crowns the champion of College Basketball. We have two opportunities to watch our favorite teams because both the Men's and Women's NCAA Tournaments happen in March. Some lucky fans even get the opportunity to cheer for both teams at the same time. But this isn't the only reason they are lucky. When a school's men's and women's teams are competing in the tournament, they're actually more likely to win.\n\n**We start with a simple hypothesis:** NCAA Division I Basketball programs that have both a Women and Men's team participating in the NCAA Tournament in the same season, perform better than teams that do not. \n\n**The Goal** is to show that there is evidence in the historical data to suggest this phenomenon exists, and this \"Two-team\" factor can be used in predicting the outcome of future tournament games.\n\n**The Data:** We will be using tournament and regular season data from both the women's and men's data files in this competition."},{"metadata":{},"cell_type":"markdown","source":"In general, we don't consider Men's and Women's games to be related. They do not share a coach, players, or even the same strategies. However, programs that have two teams participating in the tournament appear to be much more competitive than programs that only have one. In tournament play, we see Two-Team Programs win at a much higher rate, and as a result, consistently make it futher in the tournamnet than Single team programs. We think this phenomenon makes sense both empirically and logically . If one team at a school (men or women) becomes dominant it is likely this attracts more fans, increases ticket sales, and eventually impacts other sports programs at the university, creating a kind of loop where if one basketball team is good the other one builds off of this. \n\n"},{"metadata":{},"cell_type":"markdown","source":"# 2. Preparations"},{"metadata":{},"cell_type":"markdown","source":"Loading the libraries and data:"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"# Import libraries\nimport numpy as np\n#import warnings\n#warnings.simplefilter(action='ignore', category=FutureWarning)\nimport pandas as pd \nfrom datetime import date, timedelta\nfrom sklearn import preprocessing\n\n# Vizualizations\n!pip install joypy\nimport joypy\nimport seaborn as sns\n%matplotlib inline\nimport matplotlib.pyplot as plt\nimport plotly.express as px\nfrom scipy import stats\nfrom matplotlib.pyplot import figure\nplt.style.use('seaborn-whitegrid')\nimport warnings\nimport matplotlib.cbook\nwarnings.filterwarnings(\"ignore\")\n\n# This prints out the path (or directory) for each file so I \n#can use that to import it when needed.\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Load data\n# Women Data\nWTeams = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Womens-Data/WDataFiles_Stage1/WTeams.csv')\nWTourney_comp = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Womens-Data/WDataFiles_Stage1/WNCAATourneyCompactResults.csv')\nWreg_season_comp = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Womens-Data/WDataFiles_Stage1/WRegularSeasonCompactResults.csv')\nWConferences = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Womens-Data/WDataFiles_Stage1/WTeamConferences.csv')\nWSeeds = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Womens-Data/WDataFiles_Stage1/WNCAATourneySeeds.csv')\n\n# Men Data\nMTeams = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Mens-Data/MDataFiles_Stage1/MTeams.csv')\nMTourney_comp = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Mens-Data/MDataFiles_Stage1/MNCAATourneyCompactResults.csv')\nMreg_season_comp = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Mens-Data/MDataFiles_Stage1/MRegularSeasonCompactResults.csv')\nMConferences = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Mens-Data/MDataFiles_Stage1/MTeamConferences.csv')\nMSeeds = pd.read_csv('/kaggle/input/march-madness-analytics-2020/2020DataFiles/2020DataFiles/2020-Mens-Data/MDataFiles_Stage1/MNCAATourneySeeds.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 2.1 Creating Dataframes"},{"metadata":{},"cell_type":"markdown","source":"First, we are going to create our own data frame using the data supplied for this competition. The data in this competition consists of regular season and tournament data for Men and Women's teams competing in the NCAA Tournament. We are going to create new datasets for the Women and Men's teams, as we will incorporate both sets of data into our analysis. \n\nThis data frame will show every team that has competed in the tournament from the seasons 1998-2019. We use the same time frame for both men's and women's tournaments. It will include relevant features such as the Seed of the team and their historical points per game (PPG), as well as a feature for our Two-Team Factor. "},{"metadata":{},"cell_type":"markdown","source":"### Women Teams"},{"metadata":{"trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"# Give the teams names\nW_results = WTourney_comp.merge(WTeams, left_on='WTeamID',right_on = 'TeamID',\n                                validate='many_to_one').drop('TeamID',axis=1).rename(columns={'TeamName':'WTeamName'})\\\n                        .merge(WTeams, left_on='LTeamID', right_on = 'TeamID',\n                        validate='many_to_one').drop('TeamID',\n                                                          axis=1).rename(columns={'TeamName':'LTeamName'})\n\n\n# Number of wins in tournament per team\ndef Wppg_wins(season_data):\n    ls = season_data[['Season','WTeamName', 'WScore']].groupby(['Season','WTeamName'])['WScore'].mean()\n    df = pd.DataFrame(ls) #puts data into pandas dataframe\n    df['Num_wins'] = season_data.groupby('Season').WTeamName.value_counts()\n    dff = df.reset_index().rename(columns = {'WTeamName': 'TeamName'}) \n    return dff\n\ndef Wppg_loss(season_data):\n    ls = season_data[['Season','LTeamName', 'LScore']].groupby(['Season','LTeamName'])['LScore'].mean()\n    df = pd.DataFrame(ls)   #puts data into pandas dataframe\n    dff = df.reset_index().rename(columns = {'LTeamName': 'TeamName'}) \n    return dff\n\n\nWom_gw = Wppg_wins(W_results)\nWom_gl = Wppg_loss(W_results)\n\n# merge\nWomens_Tournament = pd.merge(Wom_gl, Wom_gw, on=['Season','TeamName'], how='outer', indicator='FirstRound', sort='Season')\n\n# fill the missing values(NaN) with 0 because those teams have no wins in the tournament\n# drop FirstRound\nWomens_Tournament = Womens_Tournament.drop(['LScore', 'WScore','FirstRound'], axis=1)\nWomens_Tournament['Num_wins'].fillna(0, inplace=True)\n\nWomens_Tournament.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Add a points per game (PPG), Seed, and Conference Column\n\nWe are building a dataframe with common factors associated with tournament performance: Points per Game (PPG), Seed, and Conference"},{"metadata":{"trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"# Get the ppg from regular season\nW_ppg = Wreg_season_comp.merge(WTeams, left_on='WTeamID',right_on = 'TeamID',\n                                validate='many_to_one').drop('TeamID',axis=1).rename(columns={'TeamName':'WTeamName'})\\\n                        .merge(WTeams, left_on='LTeamID', right_on = 'TeamID',\n                        validate='many_to_one').drop('TeamID',\n                                                          axis=1).rename(columns={'TeamName':'LTeamName'})\n\n                                                                             \n\n\n# We make a datafram from the regular season data \ndef Wppg_wins(season_data):\n    #gathers the avg ppg for each team in each season\n    ls = season_data[['Season','WTeamName', 'WScore']].groupby(['Season','WTeamName'])['WScore'].mean().round(3)\n    df = pd.DataFrame(ls) #puts data into pandas dataframe\n    df['Num_wins'] = season_data.groupby('Season').WTeamName.value_counts()\n    dff = df.reset_index().rename(columns = {'WTeamName': 'TeamName'}) \n    return dff\n\ndef Wppg_loss(season_data):\n    #gathers the avg ppg for each team in each season\n    ls = season_data[['Season','LTeamName', 'LScore']].groupby(['Season','LTeamName'])['LScore'].mean().round(3)\n    df = pd.DataFrame(ls)   #puts data into pandas dataframe\n    dff = df.reset_index().rename(columns = {'LTeamName': 'TeamName'}) \n    return dff\n\nWom_ppgw = Wppg_wins(W_ppg)\nWom_ppgl = Wppg_loss(W_ppg)\n\n\n# merge\nWomens_Season = pd.merge(Wom_ppgl, Wom_ppgw, on=['Season','TeamName'], how='outer', indicator='FirstRound', sort='Season')\n# Create PPG column\nWomens_Season['PPG'] = Womens_Season[['LScore', 'WScore']].mean(axis=1)\n# fill Num_wins NaN with 0\nWomens_Season = Womens_Season.drop(['LScore', 'WScore','FirstRound'], axis=1)\nWomens_Season['Num_wins'].fillna(0, inplace=True)\n\n# Now we combine the regular season data with the tournament data\nWomens_ppg = pd.merge(Womens_Tournament, Womens_Season, on=['Season','TeamName'], how='outer', indicator='Tour', sort='Season')\nWomens_Tournament = Womens_ppg.loc[Womens_ppg['Tour'] == \"both\"]\nWomens_Tournament = Womens_Tournament.drop(['Num_wins_y', 'Tour'], axis=1).rename(columns={'Num_wins_x': 'Num_wins'})\n\n# Add seed column by merging datasets\nW_Seeds = WSeeds.merge(WTeams, on= 'TeamID', how='left', validate='many_to_one')\nW_Seeds = W_Seeds.drop('TeamID', axis=1)\n# merge the seed and tournament data\nWomens_Tournament = pd.merge(Womens_Tournament, W_Seeds, on=['Season','TeamName'], how='left' , sort='Season')\n# Make region and seed into separate columns\nWomens_Tournament['Region'] = Womens_Tournament['Seed'].apply(lambda x: x[0][:1])\nWomens_Tournament['Seed'] = Womens_Tournament['Seed'].apply(lambda x: int(x[1:3]))\n\n# Conference\nW_Conference = WConferences.merge(WTeams, on= 'TeamID', how='left', validate='many_to_one')\nW_Conference = W_Conference.drop('TeamID', axis=1)\n\n# add column\nWomens_Tournament= pd.merge(Womens_Tournament, W_Conference, on=['Season','TeamName'], how='left' , sort='Season')\nWomens_Tournament.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Add the Two-Team Factor (or Both Column)**\n\nThis is the column that describes our factor. This columns signifies whether a women's program also has a men's team in the Men's NCAA Tournament in the same year. We use the name Both because this feature tells us whether or not a program has both teams participating. Both will equal **1** if there are two teams and **0** if there is only a Women's Team."},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Add team names and rearange the columns for Men's teams\nMen_Teams = MSeeds.merge(MTeams, left_on='TeamID',right_on = 'TeamID',\n                                validate='many_to_one').drop(['TeamID','FirstD1Season', 'LastD1Season'],axis=1)\nMen_Teams = Men_Teams[['Season', 'TeamName', 'Seed']]\n\n# Cut off at 1998 because thats when the women's data starts\nMen_Teams = Men_Teams.loc[Men_Teams.Season >= 1998]\nMen_Teams = Men_Teams.drop('Seed', axis=1)\n\n\n# Create the Feature\nWom_Tourney = pd.merge(Womens_Tournament, Men_Teams, on=['Season','TeamName'], how='left', indicator='Both')\nWom_Tourney['Both'] = np.where(Wom_Tourney.Both == 'both', 1, 0)\n\nWom_Tourney.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Men Teams"},{"metadata":{"trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"# add team names to the dataset\nM_results = MTourney_comp.merge(MTeams, left_on='WTeamID',right_on = 'TeamID',\n                                validate='many_to_one').drop('TeamID',axis=1).rename(columns={'TeamName':'WTeamName'})\\\n                        .merge(MTeams, left_on='LTeamID', right_on = 'TeamID',\n                              validate='many_to_one').drop('TeamID',\n                                                          axis=1).rename(columns={'TeamName':'LTeamName'})\n\n\n#Must be in year 1998 or later because thats when women's data starts\nM_results = M_results.loc[M_results.Season >= 1998]\n\n# add number of wins and mean score columns\ndef Mppg_wins(season_data):\n    ls = season_data[['Season','WTeamName', 'WScore']].groupby(['Season','WTeamName'])['WScore'].mean()\n    df = pd.DataFrame(ls) #puts data into pandas dataframe\n    df['Num_wins'] = season_data.groupby('Season').WTeamName.value_counts()\n    dff = df.reset_index().rename(columns = {'WTeamName': 'TeamName'}) \n    return dff\n\ndef Mppg_loss(season_data):\n    ls = season_data[['Season','LTeamName', 'LScore']].groupby(['Season','LTeamName'])['LScore'].mean()\n    df = pd.DataFrame(ls)   #puts data into pandas dataframe\n    dff = df.reset_index().rename(columns = {'LTeamName': 'TeamName'}) \n    return dff\n\nMen_gw = Mppg_wins(M_results)\nMen_gl = Mppg_loss(M_results)\n# merge\nMens_Tournament = pd.merge(Men_gw, Men_gl, on=['Season','TeamName'], how='outer', indicator='FirstRound', sort='Season')\n\n# fill Num_wins NaN with 0\n# drop FirstRound\nMens_Tournament = Mens_Tournament.drop(['LScore', 'WScore','FirstRound'], axis=1)\nMens_Tournament['Num_wins'].fillna(0, inplace=True)\n\nMens_Tournament.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":" #### Add PPG, Seed, and Conference Columns"},{"metadata":{"trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"# Take only men's teams after 1998\nMReg_seas_comp = Mreg_season_comp.loc[Mreg_season_comp['Season'] >= 1998]\n# add team names to the dataset\nM_seas_results = MReg_seas_comp.merge(MTeams, left_on='WTeamID',right_on = 'TeamID',\n                                validate='many_to_one').drop('TeamID',axis=1).rename(columns={'TeamName':'WTeamName'})\\\n                        .merge(MTeams, left_on='LTeamID', right_on = 'TeamID',\n                              validate='many_to_one').drop('TeamID',\n                                                          axis=1).rename(columns={'TeamName':'LTeamName'})\n\n                                                                            \n# add number of wins and mean score columns\ndef Mppg_wins(season_data):\n    #gathers the avg ppg for each team in each season\n    ls = season_data[['Season','WTeamName', 'WScore']].groupby(['Season','WTeamName'])['WScore'].mean().round(3)\n    df = pd.DataFrame(ls) #puts data into pandas dataframe\n    df['Num_wins'] = season_data.groupby('Season').WTeamName.value_counts()\n    dff = df.reset_index().rename(columns = {'WTeamName': 'TeamName'}) \n    return dff\n\ndef Mppg_loss(season_data):\n    #gathers the avg ppg for each team in each season\n    ls = season_data[['Season','LTeamName', 'LScore']].groupby(['Season','LTeamName'])['LScore'].mean().round(3)\n    df = pd.DataFrame(ls)   #puts data into pandas dataframe\n    dff = df.reset_index().rename(columns = {'LTeamName': 'TeamName'}) \n    return dff\n\nMen_ppgw = Mppg_wins(M_seas_results)\nMen_ppgl = Mppg_loss(M_seas_results)\n\n\n# merge\nMens_Season = pd.merge(Men_ppgw, Men_ppgl, on=['Season','TeamName'], how='outer', indicator='FirstRound', sort='Season')\n# Create PPG column\nMens_Season['PPG'] = Mens_Season[['LScore', 'WScore']].mean(axis=1)\n# fill Num_wins NaN with 0\nMens_Season = Mens_Season.drop(['LScore', 'WScore','FirstRound'], axis=1)\nMens_Season['Num_wins'].fillna(0, inplace=True)\n\n\n# merge\nMens_ppg = pd.merge(Mens_Tournament, Mens_Season, on=['Season','TeamName'], how='outer', indicator='Tour', sort='Season')\nMens_Tournament = Mens_ppg.loc[Mens_ppg['Tour'] == \"both\"]\nMens_Tournament = Mens_Tournament.drop(['Num_wins_y', 'Tour'], axis=1).rename(columns={'Num_wins_x': 'Num_wins'})\n\n\n# Seed Column\nM_Seeds = MSeeds.merge(MTeams, on= 'TeamID', how='left', validate='many_to_one')\nM_Seeds = M_Seeds.drop('TeamID', axis=1)\n# merge the seed and tournament data\nMens_Tournament = pd.merge(Mens_Tournament, M_Seeds, on=['Season','TeamName'], how='left' , sort='Season')\n# Drop unneeded columns\nMens_Tournament = Mens_Tournament.drop(['FirstD1Season', 'LastD1Season'], axis=1)\n# Make region and seed into separate columns\nMens_Tournament['Region'] = Mens_Tournament['Seed'].apply(lambda x: x[0][:1])\nMens_Tournament['Seed'] = Mens_Tournament['Seed'].apply(lambda x: int(x[1:3]))\n\n\n# Conference\nM_Conference = MConferences.merge(MTeams, on= 'TeamID', how='left', validate='many_to_one')\nM_Conference = M_Conference.drop(['TeamID', 'FirstD1Season', 'LastD1Season'], axis=1)\n# add column\nMens_Tournament= pd.merge(Mens_Tournament, M_Conference, on=['Season','TeamName'], how='left' , sort='Season')\nMens_Tournament.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Add Two-Team Factor (Both Column)**\n"},{"metadata":{},"cell_type":"markdown","source":"The Both feature is our factor. \n\nIt will state whether a program has two both a women's and men's team participating in the tournament in the same season. For programs that do have two teams in the tournament, the Both column will show a value of **1**. For programs that only have one team in the tournament, the Both column will show a value of **0**. "},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Add team names and rearange the columns\nWomen_Teams = WSeeds.merge(WTeams, left_on='TeamID',right_on = 'TeamID',\n                                validate='many_to_one').drop(['TeamID'],axis=1)\n\nWomen_Teams = Women_Teams[['Season', 'TeamName', 'Seed']]\nWomen_Teams = Women_Teams.drop('Seed', axis=1)\n\n# Combining Data\nMen_Tourney = pd.merge(Mens_Tournament, Women_Teams, on=['Season','TeamName'], how='left', indicator='Both')\nMen_Tourney['Both'] = np.where(Men_Tourney.Both == 'both', 1, 0)\n\n# print both men and women's dataframes with labels for each\nMen_Tourney.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"As you can see, our initial dataset shows each team that participated in the tournament and the number of wins they have in the tournament, ranging from 0 (no wins) to 6 (tournament champion). We also include their average points per game (PPG) from the regular season, their seed and region in the tournament, and their conference. The final column labeled **Both** tells us whether the program has both a women and men's team participating in the tournament in the same season (yes=1; no=0). "},{"metadata":{},"cell_type":"markdown","source":"## 2.2 Add Tournament Round Columns"},{"metadata":{},"cell_type":"markdown","source":"We are now going to add a column for each round showing whether the team won, lost, or did not particpiate (NaN) in that round. There will also be another column (Round_Out) stating the round the team lost in (if the team won the tournament, this column will say \"Winner\"). "},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#Women Teams\nWom_Tourney['Gender'] = 'W'\nWom_Tourney['First_Round'] = Wom_Tourney['Num_wins'].map({0: 'Lost',\n                                                      1: 'Won',\n                                                      2: 'Won',\n                                                      3: 'Won', \n                                                      4: 'Won',\n                                                      5: 'Won',\n                                                      6: 'Won'\n                                                     })\n\n# Round of Thirty Two\nWom_Tourney['Thirty_Two'] = Wom_Tourney['Num_wins'].map({1: 'Lost',\n                                            2: 'Won',\n                                            3: 'Won', \n                                            4: 'Won',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Sweet Sixteen\nWom_Tourney['Sweet_Sixteen'] = Wom_Tourney['Num_wins'].map({\n                                            2: 'Lost',\n                                            3: 'Won', \n                                            4: 'Won',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Elite Eight\nWom_Tourney['Elite_Eight'] = Wom_Tourney['Num_wins'].map({\n                                            3: 'Lost', \n                                            4: 'Won',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Final Fourt\nWom_Tourney['Final_Four'] = Wom_Tourney['Num_wins'].map({ \n                                            4: 'Lost',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Championship\nWom_Tourney['Championship'] = Wom_Tourney['Num_wins'].map({\n                                            5: 'Lost',\n                                            6: 'Won'\n                                           })\n\n\n\n###-------------------------------------------------------------------------------------###\n#Men Teams\nMen_Tourney['Gender'] = 'M'\nMen_Tourney['First_Round'] = Men_Tourney['Num_wins'].map({0: 'Lost',\n                                                      1: 'Won',\n                                                      2: 'Won',\n                                                      3: 'Won', \n                                                      4: 'Won',\n                                                      5: 'Won',\n                                                      6: 'Won'\n                                                     })\n\n# Round of Thirty Two\nMen_Tourney['Thirty_Two'] = Men_Tourney['Num_wins'].map({1: 'Lost',\n                                            2: 'Won',\n                                            3: 'Won', \n                                            4: 'Won',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Sweet Sixteen\nMen_Tourney['Sweet_Sixteen'] = Men_Tourney['Num_wins'].map({\n                                            2: 'Lost',\n                                            3: 'Won', \n                                            4: 'Won',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Elite Eight\nMen_Tourney['Elite_Eight'] = Men_Tourney['Num_wins'].map({\n                                            3: 'Lost', \n                                            4: 'Won',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Final Fourt\nMen_Tourney['Final_Four'] = Men_Tourney['Num_wins'].map({ \n                                            4: 'Lost',\n                                            5: 'Won',\n                                            6: 'Won'\n                                           })\n\n# Championship\nMen_Tourney['Championship'] = Men_Tourney['Num_wins'].map({\n                                            5: 'Lost',\n                                            6: 'Won'\n                                           })\n\n##-------------------------------------------------------------------------------------##\n\n# Column for last round team appeared in (or round they lost in, if they lost)\n#Men\nMen_Tourney['Round_Out'] = Men_Tourney['Num_wins'].map({0: 'First Round',\n                                            1: 'Round of 32',\n                                            2: 'Sweet Sixteen',\n                                            3: 'Elite Eight', \n                                            4: 'Final Four',\n                                            5: 'Championship',\n                                            6: 'Winner'\n                                           })\n\n# Women\nWom_Tourney['Round_Out'] = Wom_Tourney['Num_wins'].map({0: 'First Round',\n                                        1: 'Round of 32',\n                                        2: 'Sweet Sixteen',\n                                        3: 'Elite Eight', \n                                        4: 'Final Four',\n                                        5: 'Championship',\n                                        6: 'Winner'\n                                       })\n\nMen_Tourney.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 3. Exploration"},{"metadata":{},"cell_type":"markdown","source":"This section of the notebook will comprise our initial analysis of Two-Team and Single Team program performance in the tournament. We will begin by looking at the number (or percentage) of Two-Team programs in each round. Then we will look at the two types of programs' historical win percentages at each stage of the tournament and how that correlates with the types of programs competing in each round. Finally, we will explore the results of head-to-head matchups between Two-Team programs and Single Team programs. "},{"metadata":{},"cell_type":"markdown","source":"## 3.1 Breakdown of Teams in Each Round"},{"metadata":{},"cell_type":"markdown","source":"The purpose of this section is to first get an idea of the types of teams that make up the tourament. \n\nEach tournament starts with 64 teams, and we want to know what the breakdown is between Two-Team programs and single team programs. We will do an anlysis of the programs involved in both the Men and Women's NCAA Tournament. Our graphs will show what percentage of each round, on average, is made up of \"Two-Team\" programs."},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Creating the Men's dataset\ndef FR_Men(dataset):\n    RTT = dataset.Both.value_counts(normalize=True).round(2)\n    RTR = pd.DataFrame({'Coed Team in Round': RTT})\n    RTR = RTR.reset_index()\n    RTR['Round'] = 'First Round'\n    RTR = RTR.loc[RTR['index']==1]\n    return RTR\n\nMen_perc_teams = FR_Men(Men_Tourney)\n\nw = range(1,7)\nrnd = ['First Round', 'Round of 32', 'Sweet Sixteen', 'Elite Eight', 'Final Four', 'Championship', 'Tournament Champion']\n\nfor n in w:\n    RT = Men_Tourney.loc[Men_Tourney['Num_wins'] >= n]\n    r = RT.Both.value_counts(normalize=True).round(2)\n    df = pd.DataFrame({'Coed Team in Round': r})\n    df = df.reset_index()\n    rt = df.loc[df['index']==1]\n    Men_perc_teams = Men_perc_teams.append(rt)\n    \n# add in rounds\ni=1\nwhile i < 7:\n    Men_perc_teams['Round'].iloc[i] = rnd[i]\n    i += 1\n\n#Men_perc_teams.head(10)\n\n\n# Graph\n# Men Teams\nplt.style.use('seaborn-whitegrid')\nfig = plt.figure(figsize=[11,6])\nax = fig.add_axes([0,0,1,1])\nrounds = Men_perc_teams.Round\nteams = Men_perc_teams['Coed Team in Round']\nax.bar(rounds,teams)\nplt.xlabel('Rounds', fontsize=16)\nplt.ylabel('Perc of Two-Team Programs in Round', fontsize=16)\nplt.title(\"Men's Program w/ Women's Counterpart in NCAA Tournament\", fontsize=22)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Dataset Preparation\n# Creating Women's Dataset\ndef FR_Women(dataset):\n    RTT = dataset.Both.value_counts(normalize=True).round(2)\n    RTR = pd.DataFrame({'Coed Team in Round': RTT})\n    RTR = RTR.reset_index()\n    RTR['Round'] = 'First Round'\n    RTR = RTR.loc[RTR['index']==1]\n    return RTR\n\nWom_perc_teams = FR_Women(Wom_Tourney)\n\n\nw = range(1,7)\nrnd = ['First Round', 'Round of 32', 'Sweet Sixteen', 'Elite Eight', 'Final Four', 'Championship', 'Tournament Champion']\n\n# adding the other rows\nfor n in w:\n    RT = Wom_Tourney.loc[Wom_Tourney['Num_wins'] >= n]\n    r = RT.Both.value_counts(normalize=True).round(2)\n    df = pd.DataFrame({'Coed Team in Round': r})\n    df = df.reset_index()\n    rt = df.loc[df['index']==1]\n    Wom_perc_teams = Wom_perc_teams.append(rt)\n    \n# add in rounds column\ni=1\nwhile i < 7:\n    Wom_perc_teams['Round'].iloc[i] = rnd[i]\n    i += 1\n#Wom_perc_teams.head(10)\n\n\n#Graph\n# Women Teams\nfig = plt.figure(figsize=[11,6])\nax = fig.add_axes([0,0,1,1])\nrounds = Wom_perc_teams.Round\nteams = Wom_perc_teams['Coed Team in Round']\nax.bar(rounds,teams)\nplt.xlabel('Rounds', fontsize=16)\nplt.ylabel('Perc of Two-Team Programs in Round', fontsize=16)\nplt.title(\"Women's Program w/ Men's Counterpart in NCAA Tournament\", fontsize=22)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We can see above that the number of Two-Team programs entering the tournament each year is low; they make up less than 40% of the total teams in both the Men's and Women's tournaments.\n\nHowever, as the tournament progresses, the ratio of Two-Team programs to Single Team programs in the tournament rises. This eventually results in 60% or more of the teams in the final rounds of the tournament being comprised of Two-Team programs. This type of growth in the ratio of Two-Team programs per round would suggest that the programs with two teams are winning at higher rate than single team programs each round.\n\nIn the next section we investigate this relationship by looking at the win percentages of each type of program in every round."},{"metadata":{},"cell_type":"markdown","source":"## 3.3 Winning Percentages"},{"metadata":{},"cell_type":"markdown","source":"Now we are going to review the winning percentage of the two types of programs in each round of the tournament. \n\nFrom our above analysis, we know that the percentage of programs with two teams in the tournament increases as the tournament progresses. The most logical explanation for this is that these programs are winning at a higher rate than programs with only one team particpating in the tournament. Therefore, a larger number of these \"Two-team\" programs are moving on to the next round, until eventually, the majority of the programs remaining in the tournaments are \"Two-team\" programs.  "},{"metadata":{},"cell_type":"markdown","source":"The code below can be viewed to see how I created the new datasets for plotting the win percentages:"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# MEN TEAMS\n# Teams with counterpart\nmen_winperc_both = Men_Tourney.loc[Men_Tourney['Both']==1]\n# Teams without counterpart\nmen_winperc_single = Men_Tourney.loc[Men_Tourney['Both']==0]\n###-------------------------------------------------------###\n# WOMEN TEAMS\n# Teams with counterpart\nwom_winperc_both = Wom_Tourney.loc[Wom_Tourney['Both']==1]\n# Teams without counterpart\nwom_winperc_single = Wom_Tourney.loc[Wom_Tourney['Both']==0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Get the percentage of teams that won that round of the tournament for both = 1 & 0\n\n# First Round\ndef get_perc_FR(dataset):\n    c = dataset.First_Round\n    percent = c.value_counts(normalize=True).round(2)\n    ab = pd.DataFrame({'Prob_win': percent})\n    ab = ab.reset_index()\n    ab['Round'] = 'First_Round'\n    ba = ab.loc[ab['index']=='Won']\n    return ba\n\n# Round of 32\ndef get_perc_TT(dataset):\n    c = dataset.Thirty_Two\n    #percent = c.value_counts(normalize=True).mul(100).round(1).astype(str) + '%'\n    percent = c.value_counts(normalize=True).round(2)\n    ab = pd.DataFrame({'Prob_win': percent})\n    ab = ab.reset_index()\n    ab['Round'] = 'Round of Thirty-Two'\n    ba = ab.loc[ab['index']=='Won']\n    return ba\n\n\n# Sweet Sixteen\ndef get_perc_SS(dataset):\n    c = dataset.Sweet_Sixteen\n    percent = c.value_counts(normalize=True).round(2)\n    ab = pd.DataFrame({'Prob_win': percent})\n    ab = ab.reset_index()\n    ab['Round'] = 'Sweet Sixteen'\n    ba = ab.loc[ab['index']=='Won']\n    return ba\n\n# Elite eight\ndef get_perc_EE(dataset):\n    c = dataset.Elite_Eight\n    percent = c.value_counts(normalize=True).round(2)\n    ab = pd.DataFrame({'Prob_win': percent})\n    ab = ab.reset_index()\n    ab['Round'] = 'Elite Eight'\n    ba = ab.loc[ab['index']=='Won']\n    return ba\n\n# Final Four\ndef get_perc_FF(dataset):\n    c = dataset.Final_Four\n    percent = c.value_counts(normalize=True).round(2)\n    ab = pd.DataFrame({'Prob_win': percent})\n    ab = ab.reset_index()\n    ab['Round'] = 'Final Four'\n    ba = ab.loc[ab['index']=='Won']\n    return ba\n\n# Championship\ndef get_perc_CC(dataset):\n    c = dataset.Championship\n    percent = c.value_counts(normalize=True).round(2)\n    ab = pd.DataFrame({'Prob_win': percent})\n    ab = ab.reset_index()\n    ab['Round'] = 'Championship'\n    ba = ab.loc[ab['index']=='Won']\n    return ba","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Two-Team Programs\n# Men's programs with women's team in tournament; Both=1\nM_FR = get_perc_FR(men_winperc_both)\nM_TT = get_perc_TT(men_winperc_both)\nM_SS = get_perc_SS(men_winperc_both)\nM_EE = get_perc_EE(men_winperc_both)\nM_FF = get_perc_FF(men_winperc_both)\nM_CC = get_perc_CC(men_winperc_both)\n# Concatinate into one dataset\nmba_list = [M_FR,M_TT, M_SS, M_EE, M_FF, M_CC]\nmen_win_perc = pd.concat(mba_list)\nmen_win_perc = men_win_perc.drop('index', axis=1)\n##--------------------------------------------------------------------##\n# Women's programs with men's team in tournament; Both=1\nW_FR = get_perc_FR(wom_winperc_both)\nW_TT = get_perc_TT(wom_winperc_both)\nW_SS = get_perc_SS(wom_winperc_both)\nW_EE = get_perc_EE(wom_winperc_both)\nW_FF = get_perc_FF(wom_winperc_both)\nW_CC = get_perc_CC(wom_winperc_both)\n# Concatinate into one dataset\nwba_list = [W_FR,W_TT, W_SS, W_EE, W_FF, W_CC]\nwom_win_perc = pd.concat(wba_list)\nwom_win_perc = wom_win_perc.drop('index', axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Single Team Programs\n# Men's programs without women's team in tournament: Both=0\nM_FR_wo = get_perc_FR(men_winperc_single)\nM_TT_wo = get_perc_TT(men_winperc_single)\nM_SS_wo = get_perc_SS(men_winperc_single)\nM_EE_wo = get_perc_EE(men_winperc_single)\nM_FF_wo = get_perc_FF(men_winperc_single)\nM_CC_wo = get_perc_CC(men_winperc_single)\n\n# Concatinate into one dataset\nmab_list = [M_FR_wo, M_TT_wo, M_SS_wo, M_EE_wo, M_FF_wo, M_CC_wo]\nmen_win_perc_wo = pd.concat(mab_list)\nmen_win_perc_wo = men_win_perc_wo.drop('index', axis=1)\n##--------------------------------------------------------------------------------------------##\n# Women's programs without men's team in tournament; Both=0\nW_FR_wo = get_perc_FR(wom_winperc_single)\nW_TT_wo = get_perc_TT(wom_winperc_single)\nW_SS_wo = get_perc_SS(wom_winperc_single)\nW_EE_wo = get_perc_EE(wom_winperc_single)\nW_FF_wo = get_perc_FF(wom_winperc_single)\nW_CC_wo = get_perc_CC(wom_winperc_single)\n\n# Concatinate into one dataset\nwab_list = [W_FR_wo, W_TT_wo, W_SS_wo, W_EE_wo, W_FF_wo, W_CC_wo]\nwom_win_perc_wo = pd.concat(wab_list)\nwom_win_perc_wo = wom_win_perc_wo.drop('index', axis=1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The graphs below visualize the win percentages of both Two-Team and Single Team programs in each round of the tournament. The first graph shows the results for the Men's NCAA Tournament and the second graph shows results for the Women's NCAA Tournament."},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Men Teams winning percentage plot\nplt.style.use(\"fivethirtyeight\")\nplt.subplots(figsize=(10,6))\nplt.plot('Round', 'Prob_win', '-ok', data = men_win_perc, \n         label=\"Two-Team Programs\",\n         color = 'blue'\n        )\nplt.xlabel('Round')\nplt.plot('Round', 'Prob_win', '-ok', data = men_win_perc_wo,\n         label=\"Single Team Programs\",\n         color = 'red'\n        )\nplt.ylabel('Win Rate')\nplt.title(\"Men's NCAA Tournament\", fontsize=22)\nplt.legend()\nplt.show;","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women Teams winning percentage plot\nplt.style.use(\"fivethirtyeight\")\nplt.subplots(figsize=(10,6))\nplt.plot('Round', 'Prob_win', '-ok', data = wom_win_perc, \n         label=\"Two-Team Programs\",\n         color = 'blue'\n        )\nplt.xlabel('Round')\nplt.plot('Round', 'Prob_win', '-ok', data = wom_win_perc_wo,\n         label=\"Single Team Programs\",\n         color = 'red'\n        )\nplt.ylabel('Win Rate')\nplt.title(\"Women's NCAA Tournament\", fontsize= 22)\nplt.legend()\nplt.show;","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The first thing we notice is that the two graphs are very similar. The graphs indicate that both men's and women's Two-Team programs:\n* Exhibit high win percentages in early rounds (both over 60% in the First Round)\n* Each show only one round where their historical win percentage is NOT higher than the single team programs'\n* Possess higher average overall win percentages compared to single team programs\n* Significantly outperform in the championship game\n\nThe Single Team programs for both the Men's and Women's tournaments have historical win percentages below 50% for every single round except one. "},{"metadata":{},"cell_type":"markdown","source":"## 3.4 Wins by Season"},{"metadata":{},"cell_type":"markdown","source":"We now know that the Two-Team Programs win more games on average than Single Team Programs. \n\nHowever, we want to dig further to see if this phenomenon holds true year over year, or if the numbers are skewed because of a few outlier seasons where Two-Team programs did exceptionally well. To do this we create a joyplot (or ridgeline plot) showing the distribution of wins in the tournament for both programs in each season. \n\nThe distribution of tournament wins in each season are visualized below:\n\nTwo-Team Programs = Green\n\nSingle Team Programs = Red"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"W1_joy = wom_winperc_both[['Season', 'TeamName', 'Num_wins', 'Seed', 'Both', 'Gender']]\nW0_joy = wom_winperc_single[['Season', 'TeamName', 'Num_wins', 'Seed', 'Both', 'Gender']]\n\nW_joy = pd.concat([W1_joy, W0_joy])\nW_joy['both_wins'] = W_joy['Num_wins'].loc[W_joy['Both']==1]\n\nW_joy['nboth_wins'] = W_joy['Num_wins'].loc[W_joy['Both']==0]\n\n# Women's Joyplot\njoy_labels = ['Two-Team Programs', 'Single Team Programs']\nplt.style.use(\"default\");\nfig = joypy.joyplot(W_joy, column=['both_wins', 'nboth_wins'], by=\"Season\", ylim='own', color=['g', 'r'], \n                           figsize=(14,10), grid=True, overlap=1, legend=True);\n\nplt.title(\"Women's Tournament Wins by Season\", fontsize=22);\nplt.xlabel('Num of Wins in Tournament', fontsize=16);\nplt.ylabel('Season');","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"M1_joy = men_winperc_both[['Season', 'TeamName', 'Num_wins', 'Seed', 'Both', 'Gender']]\nM0_joy = men_winperc_single[['Season', 'TeamName', 'Num_wins', 'Seed', 'Both', 'Gender']]\n\nM_joy = pd.concat([M1_joy, M0_joy])\nM_joy['both_wins'] = M_joy['Num_wins'].loc[M_joy['Both']==1]\n\nM_joy['nboth_wins'] = M_joy['Num_wins'].loc[M_joy['Both']==0]\n#M_joy.head()\n\n# Men's Joyplot\nfig, axes = joypy.joyplot(M_joy, column=['both_wins', 'nboth_wins'], by=\"Season\", ylim='own', color=['g', 'r'], \n                          figsize=(14,10), grid=True, overlap=1, legend=True);\n\nplt.title(\"Men's Tournament Wins by Season\", fontsize=22)\nplt.ylabel('Season');\nplt.xlabel('Num of Wins in Tournament', fontsize=16);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Takeaways:\n* Programs with only one team participating in the tournament have a higher density of teams with 0 or 1 win. This reinforces our earlier conclusion that most of the teams entering the tournament are Single Team programs, many of which lose in the first two rounds.\n* The Two-Team Programs have a flatter curve and more teams in the 3-5 win range, indicating that there are less Two-Team programs competing, but on average they make it futher in the tournament. \n* This holds true for nearly all of the seasons plotted above, and shows that the phenomenon is consistent year over year. "},{"metadata":{},"cell_type":"markdown","source":"## 3.5 Two-Team Programs vs. Single Team Programs"},{"metadata":{},"cell_type":"markdown","source":"The above analysis gets us started, but what we really want to know is **Which type of program will win in a head-to-head game.**\n\nThis section will examine the tournament games where a Two-Team program faces a Single Team program. Based on what we have seen above, we would expect the Two-Team Programs to win a large percentage of these games. \n\nWe will begin by looking at a breakdown of all of these match-ups in our dataset. Then we will examine the result of these matchups in each round of the tournament. "},{"metadata":{},"cell_type":"markdown","source":"To begin, we create a new dataset that has the outcome for each game in the NCAA Tournament for seasons from 1998-2019. "},{"metadata":{},"cell_type":"markdown","source":"#### Men"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# We use the M_results dataframe from earlier\n# Drop columns we don't need\nM_result = M_results.drop(['FirstD1Season_x', 'LastD1Season_x', 'FirstD1Season_y', 'LastD1Season_y'], axis=1)\n# Map Round of game to DayNum\nM_result['Round'] = M_result['DayNum'].map({134: \"Play-in\",\n                                            135: \"Play-in\",\n                                            136: \"First Round\",\n                                            137: \"First Round\", \n                                            138: \"Round of 32\",\n                                            139: \"Round of 32\",  \n                                            143: \"Sweet Sixteen\",\n                                            144: \"Sweet Sixteen\",\n                                            145: \"Elite Eight\",\n                                            146: \"Elite Eight\",\n                                            152: \"Final Four\",\n                                            154: \"Championship\" \n                                           })\n\n\n\n# Add seed column by merging datasets\nM_Seeds = MSeeds.merge(MTeams, on= 'TeamID', how='left', validate='many_to_one')\nM_Seeds = M_Seeds.drop(['TeamID', 'FirstD1Season', 'LastD1Season'], axis=1)\n\n# changing names so we can merge the datasets \nMSeeds_W = M_Seeds.rename(columns={'TeamName': 'WTeamName'})\nMSeeds_L = M_Seeds.rename(columns={'TeamName': 'LTeamName'})\n\n# merge the seed and tournament data\nM_result = pd.merge(M_result, MSeeds_W, on=['Season','WTeamName'], how='left' , sort='Season')\nM_result = pd.merge(M_result, MSeeds_L, on=['Season', 'LTeamName'], how='left', sort='Season')\n\n# Make region and seed into separate columns\nM_result['WRegion'] = M_result['Seed_x'].apply(lambda x: x[0][:1])\nM_result['WSeed'] = M_result['Seed_x'].apply(lambda x: int(x[1:3]))\n\nM_result['LRegion'] = M_result['Seed_y'].apply(lambda x: x[0][:1])\nM_result['LSeed'] = M_result['Seed_y'].apply(lambda x: int(x[1:3]))\n#drop original Seed columns\nM_result = M_result.drop(['Seed_x', 'Seed_y'], axis=1)\n\n\n#ADD CONFERENCE\n# changing names so we can merge the datasets \nM_Conference_W = M_Conference.rename(columns={'TeamName': 'WTeamName'})\nM_Conference_L = M_Conference.rename(columns={'TeamName': 'LTeamName'})\n# add column\nM_result= pd.merge(M_result, M_Conference_W, on=['Season','WTeamName'], how='left' , sort='Season')\nM_result= pd.merge(M_result, M_Conference_L, on=['Season','LTeamName'], how='left' , sort='Season')\nM_result = M_result.rename(columns={'ConfAbbrev_x': 'WConf', 'ConfAbbrev_y': 'LConf'})\n\n\n# ADD BOTH COLUMNS\n# changing names so we can merge the datasets \nWom_Teams_W = Women_Teams.rename(columns={'TeamName': 'WTeamName'})\nWom_Teams_L = Women_Teams.rename(columns={'TeamName': 'LTeamName'})\n#Both column for win and lose team\nMen_Both = pd.merge(M_result, Wom_Teams_W, on=['Season','WTeamName'], how='left', indicator='WBoth')\nMen_Both['WBoth'] = np.where(Men_Both.WBoth == 'both', 1, 0)\nMen_Both = pd.merge(Men_Both, Wom_Teams_L, on=['Season','LTeamName'], how='left', indicator='LBoth')\nMen_Both['LBoth'] = np.where(Men_Both.LBoth == 'both', 1, 0)\n\n# Now we can see which teams have counterparts in each game of the tournament\nMen_Both.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Women"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# We use the W_results dataframe from earlier\n# Need to separate dataset to map DayNum to rounds becasue different time periods have rounds on different days\nW_results_early = W_results.loc[W_results.Season < 2003]\nW_results_mid = W_results[(W_results.Season >= 2003) & (W_results.Season < 2015)]\nW_results_late = W_results[W_results.Season >= 2015]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"# Map Round of game to DayNum\nW_results_early['Round'] = W_results_early['DayNum'].map({137: \"First Round\",\n                                                          138: \"First Round\", \n                                                          139: \"Round of 32\",\n                                                          140: \"Round of 32\",\n                                                          145: \"Sweet Sixteen\",\n                                                          147: \"Elite Eight\",\n                                                          151: \"Final Four\",\n                                                          153: \"Championship\" \n                                                        })\n\nW_results_mid['Round'] = W_results_mid['DayNum'].map({138: \"First Round\",\n                                                      139: \"First Round\", \n                                                      140: \"Round of 32\",\n                                                      141: \"Round of 32\",\n                                                      145: \"Sweet Sixteen\",\n                                                      146: \"Sweet Sixteen\",\n                                                      147: \"Elite Eight\",\n                                                      148: \"Elite Eight\",\n                                                      153: \"Final Four\",\n                                                      155: \"Championship\" \n                                                       })\n\nW_results_late['Round'] = W_results_late['DayNum'].map({137: \"First Round\",\n                                                        138: \"First Round\", \n                                                        139: \"Round of 32\",\n                                                        140: \"Round of 32\",\n                                                        144: \"Sweet Sixteen\",\n                                                        145: \"Sweet Sixteen\",\n                                                        146: \"Elite Eight\",\n                                                        147: \"Elite Eight\",\n                                                        153: \"Final Four\",\n                                                        155: \"Championship\" \n                                                       })\n\n# Concatinate datasets\nW_result_one = pd.concat([W_results_early, W_results_mid], axis=0)\nW_result = pd.concat([W_result_one, W_results_late], axis=0)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":false,"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# add seed for WTeam and LTeam\n# Add seed column by merging datasets\nW_Seeds = WSeeds.merge(WTeams, on= 'TeamID', how='left', validate='many_to_one')\nW_Seeds = W_Seeds.drop('TeamID', axis=1)\n\n# changing names so we can merge the datasets \nWSeeds_W = W_Seeds.rename(columns={'TeamName': 'WTeamName'})\nWSeeds_L = W_Seeds.rename(columns={'TeamName': 'LTeamName'})\n\n# merge the seed and tournament data\nW_result = pd.merge(W_result, WSeeds_W, on=['Season','WTeamName'], how='left' , sort='Season')\nW_result = pd.merge(W_result, WSeeds_L, on=['Season', 'LTeamName'], how='left', sort='Season')\n\n# Make region and seed into separate columns\nW_result['WRegion'] = W_result['Seed_x'].apply(lambda x: x[0][:1])\nW_result['WSeed'] = W_result['Seed_x'].apply(lambda x: int(x[1:3]))\nW_result['LRegion'] = W_result['Seed_y'].apply(lambda x: x[0][:1])\nW_result['LSeed'] = W_result['Seed_y'].apply(lambda x: int(x[1:3]))\n#drop original Seed columns\nW_result = W_result.drop(['Seed_x', 'Seed_y'], axis=1)\n\n\n#ADD CONFERENCE\n# changing names so we can merge the datasets \nW_Conference_W = W_Conference.rename(columns={'TeamName': 'WTeamName'})\nW_Conference_L = W_Conference.rename(columns={'TeamName': 'LTeamName'})\n# add column\nW_result= pd.merge(W_result, W_Conference_W, on=['Season','WTeamName'], how='left' , sort='Season')\nW_result= pd.merge(W_result, W_Conference_L, on=['Season','LTeamName'], how='left' , sort='Season')\nW_result = W_result.rename(columns={'ConfAbbrev_x': 'WConf', 'ConfAbbrev_y': 'LConf'})\n\n\n# ADD BOTH COLUMNS\n# changing names so we can merge the datasets \nMen_Teams_W = Men_Teams.rename(columns={'TeamName': 'WTeamName'})\nMen_Teams_L = Men_Teams.rename(columns={'TeamName': 'LTeamName'})\n#Both column for win and lose team\nWom_Both = pd.merge(W_result, Men_Teams_W, on=['Season','WTeamName'], how='left', indicator='WBoth')\nWom_Both['WBoth'] = np.where(Wom_Both.WBoth == 'both', 1, 0)\nWom_Both = pd.merge(Wom_Both, Men_Teams_L, on=['Season','LTeamName'], how='left', indicator='LBoth')\nWom_Both['LBoth'] = np.where(Wom_Both.LBoth == 'both', 1, 0)\n\n\n# Now we can see which teams have counterparts in each game of the tournament\nWom_Both.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### The Overall Win Percentage for each type of program is presented below."},{"metadata":{},"cell_type":"markdown","source":"Women Win percentage in head-to-head matches"},{"metadata":{"_kg_hide-output":false,"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"# Women\n# Column for WBoth=1 and LBoth=0\nWom_Both['DT_Wins'] = np.where((Wom_Both.WBoth==1) & (Wom_Both.LBoth==0), 1, 0)\n#add column for if winning team Both=0 and losing team Both=1\nWom_Both['DT_Lose'] = np.where((Wom_Both.WBoth==0) & (Wom_Both.LBoth==1), 1, 0)\n\n# I want dataset with just data where DT_Wins=1 and DT_Lose=1\n# This way we can determine what percentage of these games each type of team wins\nWom_Both_DT = Wom_Both.loc[(Wom_Both.DT_Wins==1) | (Wom_Both.DT_Lose==1)]\n\n# Win percentage for Teams w/ counterpart\nWins = Wom_Both_DT.DT_Wins.value_counts(normalize=True).round(3)\nLoses = Wom_Both_DT.DT_Lose.value_counts(normalize=True).round(3)\n\n# Make into DataFrame\nWins = pd.DataFrame(Wins)\nWins['Programs'] = Wins.index.map({1: 'Two-Team Programs', 0: 'Single Team Programs'})\nWins = Wins.reset_index().rename(columns={'DT_Wins': 'Win Percentage'})\nWins.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Men win percentage in head-to-head matches"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#Men\n# Column for WBoth=1 and LBoth=0\nMen_Both['DT_Wins'] = np.where((Men_Both.WBoth==1) & (Men_Both.LBoth==0), 1, 0)\n#add column for if winning team Both=0 and losing team Both=1\nMen_Both['DT_Lose'] = np.where((Men_Both.WBoth==0) & (Men_Both.LBoth==1), 1, 0)\n\n# I want dataset with just data where DT_Wins=1 and DT_Lose=1\n# This way we can determine what percentage of these games each type of team wins\nMen_Both_DT = Men_Both.loc[(Men_Both.DT_Wins==1) | (Men_Both.DT_Lose==1)]\n\n# Win percentage for Teams w/ counterpart\nMWins = Men_Both_DT.DT_Wins.value_counts(normalize=True).round(3)\nMLoses = Men_Both_DT.DT_Lose.value_counts(normalize=True).round(3)\n\n# Make into DataFrame\nMWins = pd.DataFrame(MWins)\nMWins['Programs'] = MWins.index.map({1: 'Two-Team Programs', 0: 'Single Team Programs'})\nMWins = MWins.reset_index().rename(columns={'DT_Wins': 'Win Percentage'})\nMWins.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Visualization of Two-Team vs. Single Team Games:"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"plt.style.use('seaborn-whitegrid')\n\nfig, axs = plt.subplots(1, 2, figsize=(10, 5))\naxs[0].set_title(\"Women's NCAA Tournament\", fontsize=19)\nb1 = sns.barplot(Wins.Programs, Wins[\"Win Percentage\"], ax=axs[0])\naxs[1].set_title(\"Men's NCAA Tournament\", fontsize=19)\nb2 = sns.barplot(MWins.Programs, MWins[\"Win Percentage\"], ax=axs[1])\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"As we can see above, in the games where a program that has both a women's and men's team in the tournament faces a program without two teams in the tournament, the program with both teams in the tournament wins a significantly higher percentage of the games. \n* For the women's tournaments, Two-Team programs win that matchup over 64% of the time. \n* In the men's tournament, Two-Team programs win 63% of the time. "},{"metadata":{},"cell_type":"markdown","source":"Though it seems these Two-Team Programs have an advantage in games, this could just be the result of many early round wins, where highly ranked Two-Teamed programs beat lower ranked Single Team programs. To determine if this phenomenon holds true in games that are harder to predict, we look at the outcome of these matchups in each round."},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women\n# Two-team Programs\nWin_by_Round = Wom_Both_DT[['Round', 'DT_Wins']].groupby('Round')['DT_Wins'].value_counts(normalize=True).round(3).rename(columns = {'DT_Wins': 'Win_perc'})\n\n# make dataframe Two-Team program\nWin_per_Round = pd.DataFrame(Win_by_Round)\nWin_per_Round = Win_per_Round.reset_index()\nWin_per_Round = Win_per_Round.rename(columns={0: 'win_perc'})\nWin_per_Round = Win_per_Round.loc[Win_per_Round.DT_Wins == 1]\nWin_per_Round = Win_per_Round.reindex([6,8,10,3,4,0])\n\n# Single team programs\nLose_by_Round = pd.DataFrame(Win_by_Round)\nLose_by_Round = Lose_by_Round.reset_index()\nLose_by_Round = Lose_by_Round.rename(columns={0: 'win_perc'})\nLose_by_Round = Lose_by_Round.loc[Lose_by_Round.DT_Wins == 0]\nLose_by_Round = Lose_by_Round.reindex([7,9,11,2,5,1])\n\n# Women Graph\nimport plotly.graph_objects as go\nfig = go.Figure()\nfig.add_trace(go.Bar(name='Two-Team Programs', x = Win_per_Round['Round'], y=Win_per_Round['win_perc'], text=Win_per_Round['win_perc']))\nfig.add_trace(go.Bar(name='Single Team Programs', x = Lose_by_Round['Round'], y=Lose_by_Round['win_perc'], marker_color='LightGrey'))\n    \nfig.update_layout(barmode='stack', title={'text':\"Women's NCAA Tournament\",'x':0.5}, yaxis_title='Win Percentage', \n                  uniformtext_minsize=8, uniformtext_mode='hide')\nfig.update_traces(texttemplate='%{text:%.2f}', textposition='outside', marker_line_width=1.5, marker_line_color='DarkSlateGrey')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"For the Women's Tournament, we see higher win percentages for Two-Team programs in matchups against Single Team programs than we did in the overview of the entire tournament. "},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Men\n# Two-team Programs\nWin_in_Round = Men_Both_DT[['Round', 'DT_Wins']].groupby('Round')['DT_Wins'].value_counts(normalize=True).round(3).rename(columns = {'DT_Wins': 'Win_perc'})\n\n# make dataframe\nWin_Round = pd.DataFrame(Win_in_Round)\nWin_Round = Win_Round.reset_index()\nWin_Round = Win_Round.rename(columns={0: 'win_perc'})\nWin_Round = Win_Round.loc[Win_Round.DT_Wins == 1]\nWin_Round = Win_Round.reindex([6,10,12,2,5,0])\n\n# Single team programs\nLose_in_Round = pd.DataFrame(Win_in_Round)\nLose_in_Round = Lose_in_Round.reset_index()\nLose_in_Round = Lose_in_Round.rename(columns={0: 'win_perc'})\nLose_in_Round = Lose_in_Round.loc[Lose_in_Round.DT_Wins == 0]\nLose_in_Round = Lose_in_Round.reindex([7,11,13,3,4,1])\n\n# Men\nimport plotly.graph_objects as go\nfig = go.Figure()\nfig.add_trace(go.Bar(name='Two-Team Programs', x = Win_Round['Round'], y=Win_Round['win_perc'], text=Win_Round['win_perc']))\nfig.add_trace(go.Bar(name='Single Team Programs', x = Lose_in_Round['Round'], y=Lose_in_Round['win_perc'], marker_color='LightGrey'))\n    \nfig.update_layout(barmode='stack', title={'text':\"Men's NCAA Tournament\",'x':0.5}, yaxis_title='Win Percentage', \n                  uniformtext_minsize=8, uniformtext_mode='hide')\nfig.update_traces(texttemplate='%{text:%.2f}', textposition='outside', marker_line_width=1.5, marker_line_color='DarkSlateGrey')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"In the Men's Tournament we also see higher win percentages for matchups against Single Team programs. There are multiple rounds where the Two-Team programs win 60% or more of the matchups against Single Team programs, including the Championship Game. \n\nThe only exception is the final four, where the win percentage of the Two-Team programs dropped. We have attributed this drop to the fact that so few Single-Team programs made it to the final four, and even fewer competed against Two-Team programs. We know from Section 3.1 that in the Men's Tournament the Final Four had the highest number of Two-Team programs competing in that round. "},{"metadata":{},"cell_type":"markdown","source":"**Conclusion:**\n\nWhen adjusting for head-to-head matches against Single Team programs, the Two-Team programs win percentage rises in nearly all rounds. This can give us increased predictability in later round games where many of the teams competing have similar Seeding and historical performance measures like PPG. "},{"metadata":{},"cell_type":"markdown","source":"# 4. Other Factors"},{"metadata":{},"cell_type":"markdown","source":"This section will explore whether the Two-Team factor holds true analyzed together with other factors, or whether it is just a duplicate of traditional factors like points-per-game (PPG) or Seeding. We first explore the effect of PPG on team performance and whether it has a high correlation with the Two-Team Factor. Next, we move on to the Seed in the tournament to determine if the Two-Team factor holds true for different Seeds. Finally, we determine whether the Two-Team factor can be explained simply by the Conference of the team, or whether Two-Team programs outperform regardless of what conference they are in. "},{"metadata":{},"cell_type":"markdown","source":"## 4.1 PPG"},{"metadata":{},"cell_type":"markdown","source":"Points-per-game (PPG) is a common measure of performance by a team. It tells us whether, on avergae, the team scores a high or low number of points in each game. The higher the number of points scored, the higher the chance of winning the game. Our PPG calculations are taken from the average PPG of each team over the course of the season preceeding the tournament. We see below that ppg correlates highly with a team's seeding in the tournemant. The higher your regular season PPG, the higher your seed. "},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"plt.style.use('seaborn')\nsns.boxplot(x=Wom_Tourney['Seed'], y = Wom_Tourney['PPG']);\nplt.title(\"PPG and Seed\");","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"However, our concern is not on predicting the seed of a team, but whether that team will perform well in the tournament. \n\nWe know, from anecdotal evidence of watching games, that higher seeds usually make it further in the tournament. This means there is at least some correlation between high PPG and tournament performance. We observe the relationship between a team's PPG and their performance below:"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"plt.style.use('seaborn-whitegrid')\nfig, axs = plt.subplots(1, 2, figsize=(12, 6))\naxs[0].set_title(\"Women's NCAA Tournament\", fontsize=22)\nsns.boxplot(x=Wom_Tourney['Num_wins'],y=Wom_Tourney['PPG'], ax=axs[0]);\naxs[1].set_title(\"Men's NCAA Tournament\", fontsize=22)\nsns.boxplot(x=Men_Tourney['Num_wins'],y=Men_Tourney['PPG'], ax=axs[1]);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The x-axis is the number a wins a team has in the tournament, so the zero wins means they lost in the first round and six wins means that team won the tournament. \n\nWe see a correlation between PPG and tournament performance, but not as strong as the one we saw with the Seed. Most of the teams in the later rounds have higher PPG, but some of the teams in the lower rounds also have higher PPG. We see a stronger correlation between PPG and wins in the Women's bracket, and a much more subtle correlation in the Men's. "},{"metadata":{},"cell_type":"markdown","source":"#### The real question now becomes: Is the Two-Team Factor independent of PPG?\n\n\nIt is possible this factor is only predictive of higher wins because all of the Two-Team programs have high PPGs anyway, and as a result they are simply beating teams with lower PPGs. "},{"metadata":{},"cell_type":"markdown","source":"We know that in each round, these \"Two-Team\" programs perform better than programs with only one team. So one way to determine if PPG is the cause of this outperformance is to look at the average PPG of Two-Team and Single Team programs for each round. If the \"Two-Team\" factor is just a result of higher PPG, then those Two-Team programs should have a consistently higher PPG in all of the rounds, even the later ones. "},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#Women programs with Men also\nwppg1 = wom_winperc_both[['Num_wins', 'PPG']].groupby('Num_wins')['PPG'].mean()\nwppg_1 = pd.DataFrame(wppg1,  columns=['PPG'])\nwppg_1 = wppg_1.reset_index()\n\n#Women programs only\nwppg2 = wom_winperc_single[['Num_wins', 'PPG']].groupby('Num_wins')['PPG'].mean()\nwppg_2 = pd.DataFrame(wppg2,  columns=['PPG'])\nwppg_2 = wppg_2.reset_index()\n\n# Men\n#Men programs with women also\nmppg1 = men_winperc_both[['Num_wins', 'PPG']].groupby('Num_wins')['PPG'].mean()\nmppg_1 = pd.DataFrame(mppg1,  columns=['PPG'])\nmppg_1 = mppg_1.reset_index()\n\n#Men programs only\nmppg2 = men_winperc_single[['Num_wins', 'PPG']].groupby('Num_wins')['PPG'].mean()\nmppg_2 = pd.DataFrame(mppg2,  columns=['PPG'])\nmppg_2 = mppg_2.reset_index()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women\n# plotly barchart for ppg\nimport plotly.graph_objects as go\n\nfig = go.Figure(data=[\n    go.Bar(name='Two-Team Programs', x = wppg_1['Num_wins'], y=wppg_1['PPG']),\n    go.Bar(name='Single Team Programs', x = wppg_2['Num_wins'], y=wppg_2['PPG'])\n])\n\nfig.update_layout(barmode='group', title={'text':\"Women's NCAA Tournament\",'x':0.5}, yaxis_title='PPG', \n                  uniformtext_minsize=8, uniformtext_mode='hide')\n\nfig.show()\n\n# Men\nfig = go.Figure(data=[\n    go.Bar(name='Men & Women Teams', x = mppg_1['Num_wins'], y=mppg_1['PPG']),\n    go.Bar(name='Only Men Teams', x = mppg_2['Num_wins'], y=mppg_2['PPG'])\n])\nfig.update_layout(barmode='group', title={'text':\"Men's NCAA Tournament\",'x':0.5}, yaxis_title='PPG', \n                  uniformtext_minsize=8, uniformtext_mode='hide')\n\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We conclude from the plots that there is no significant difference in most of the PPGs represented above. In the Women's Tournament, the PPG of Single Team programs was actually higher in later rounds. This means the Two-team programs that won most of the games had a lower PPG on average. In the Men's Tournament, we do see that Two-Team programs have higher PPGs in most rounds above. However, we do not think this is a significant enough difference to explain all of the outperformance by the \"Two-Team\" programs, especially considering the the trend in overall PPG of the teams per round is nearly flat. "},{"metadata":{},"cell_type":"markdown","source":"#### Individual Teams and PPG\n\nSo far we know that PPG has a strong correlation with the ranking of a team in the tournament, and a semi-strong correlation with performance in the tournament. To get a better idea of the effect of PPG and the Two-Team factor on performance in each round we create the graph below: \n\n**Note:** The **RED** dots represent Two-Team programs (Both=1), and the **BLUE** dots represent Single Team programs (Both=0)."},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women\nplt.style.use('fivethirtyeight') \norder = ['Winner', 'Championship','Final Four','Elite Eight','Sweet Sixteen','Round of 32','First Round']\ng = sns.FacetGrid(Wom_Tourney, col = \"Season\", hue =\"Both\", aspect= 1.1, height = 2.1, col_wrap=5, legend_out=True)\ng.map(sns.swarmplot,'PPG', 'Round_Out', order=order)\ng.add_legend(title=\"Program\")\nplt.subplots_adjust(top=0.9)\ng.fig.suptitle(\"Women's NCAA Tournament\", fontsize=26);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We see above that a significant portion of the tournament winners, and even teams participating in the last two rounds, did not have the highest PPG in the tournament.\n\n* Also, in most of the Seasons (obvious exception 2018), the final rounds are made up of mostly \"Two-Team\" programs, with \"Two-Team\" programs winning 73% of the tournaments. Of those wins, nearly 70% of the champions did not have the highest PPG in the tournament, some even had extremely low ppg. \n\n* The overall trend is that the higher the PPG, the more likely a team makes it to later rounds. But in the later rounds, this relationship does not have the same strength. \n\n* The one factor that does, however, show a relationship with late round performance is whether that program has two teams participating in the tournament. If it does, it is more likely to make it to later rounds, and significantly more likely to win the tournament. "},{"metadata":{},"cell_type":"markdown","source":"We see a breakdown in PPG as a predictor of performance in later rounds like the elite eight, final four, and championship. Once this stage of the tournament is reached, most of the teams remaining are the top seeds (1-7), who possess similar PPGs. But we know PPG and seeds do not decide who wins the game in a tournament format. For factors like these, those predictions are elusive.\n\nOne thing we can determine from our analysis is that, in later rounds, the \"Two-Team\" Facotr is not highly correlated to PPG, but is predictive of outcomes. Two-Team programs are much more likely to win the championship than the team with the highest PPG. "},{"metadata":{},"cell_type":"markdown","source":"## 4.2 Seed"},{"metadata":{},"cell_type":"markdown","source":"We know from above that Seeds and PPG are highly correlated, but we still want to determine if the \"Two-Team\" factor is independent of Seeding. \n\nSeeding is very predictive of outcomes. We believe in general that teams with high Seeds usually beat much lower seeded teams, and we do not think the Two-Team factor overcomes this phenomenon. But in games where the two teams have similar Seeds, the predictive value of the higher Seed breaks down. We proposition that the Two-Team factor can be of use in these scenarios.\n\nLet's take a look at the distribution of Seeds for each type of program:"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women\n# density plot for multiple variables\n# x-axis=Seed, y-axis=count of teams, variable is Both\nplt.style.use('seaborn')\nmy_labels = ['Two-Team Programs', 'Single Team Programs']\nfig, axs = plt.subplots(1, 2, figsize=(12, 5.5))\naxs[0].set_title(\"Women's NCAA Tournament\", fontsize=19)\np1=sns.kdeplot(wom_winperc_both['Seed'], shade=True, color=\"r\", legend=True, ax=axs[0])\np1=sns.kdeplot(wom_winperc_single['Seed'], shade=True, color=\"b\", legend=True, ax=axs[0])\naxs[0].legend(labels=my_labels);\naxs[1].set_title(\"Men's NCAA Tournament\", fontsize=19)\np1=sns.kdeplot(men_winperc_both['Seed'], shade=True, color=\"r\", legend=True, ax=axs[1])\np1=sns.kdeplot(men_winperc_single['Seed'], shade=True, color=\"b\", legend=True, ax=axs[1])\naxs[1].legend(labels=my_labels);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\nWe create another visualization to show the actual number of Seeds for each type of program:"},{"metadata":{},"cell_type":"markdown","source":"Women's NCAA Tournament"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Initial distribution plot for men and women\n# barchart for teams with and without (side by side)\n# Women\nplt.style.use('seaborn')\nfig, axs = plt.subplots(1, 2, figsize=(11, 6))\naxs[0].set_title(\"Programs with Women and Men's Teams in Tournament\", fontsize=15)\nsns.countplot(data=wom_winperc_both, x='Seed', ax=axs[0])\naxs[1].set_title(\"Programs with Only Women's Team in Tournament\", fontsize=15)\nsns.countplot(data=wom_winperc_single, x='Seed', ax=axs[1]);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Men's NCAA Tournament"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Men\nplt.style.use('seaborn')\nfig, axs = plt.subplots(1, 2, figsize=(12, 6))\naxs[0].set_title(\"Programs with Men and Women's Teams in Tournament\", fontsize=15)\nsns.countplot(data=men_winperc_both, x='Seed', ax=axs[0])\naxs[1].set_title(\"Programs with Only Men's Team in Tournament\", fontsize=15)\nsns.countplot(data=men_winperc_single, x='Seed', ax=axs[1]);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"A few things to note initially: The graphs on the left hand side are showing ranges from 0-50 teams on the y-axis, and the graphs on the right are showing ranges from 0-100. \n\nAside from the counts, we can clearly see that they have opposite distributions when it comes to Seeds. For both the men and women's tournaments we notice a couple key factors:\n* The single team program group is much larger than the Two-Team program group\n* The single team group has a large distribution of teams in the higher number seeds (10-16)\n* The programs with two teams participating have a large distribution of teams that are seeded high (1-5), and very few teams that have are seeded in the 12-16 range\n* Even though the distributions are very different, both types of programs have a similar number of teams ranked 1-5; they each have around 30 to 60 teams for each Seed "},{"metadata":{},"cell_type":"markdown","source":"Looking at the distribution of rankings, we can take a guess as to why Two-Team programs were so successful in the first round, winning 70% of their games against Single Team programs. This was because many of the lower seeded teams are single team programs and they went  up against highly ranked teams in the first round, at least half of whom were Two-Team programs. "},{"metadata":{},"cell_type":"markdown","source":"**Below, we break down the win percentages of the head-to-head match-ups by Seed:**"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women\n# Win percentage for Two-Team programs per seed in Two-Team v. Single Team games\nSeed_Wins = Wom_Both_DT[['DT_Wins', 'WSeed']].groupby('WSeed')['DT_Wins'].value_counts(normalize=True).round(3)\nSeed_Wins = pd.DataFrame(Seed_Wins).rename(columns={'DT_Wins': 'win_perc'})\nSeed_Wins = Seed_Wins.reset_index()\nSeed_Wins = Seed_Wins.loc[Seed_Wins.DT_Wins == 1]\n\n# Win percentage for single team programs per seed in Two-Team v. Single Team games\nSeed_lose = Wom_Both_DT[['DT_Lose', 'LSeed']].groupby('LSeed')['DT_Lose'].value_counts(normalize=True).round(3)\nSeed_lose = pd.DataFrame(Seed_lose).rename(columns={'DT_Lose': 'win_perc'})\nSeed_lose = Seed_lose.reset_index()\nSeed_lose = Seed_lose.loc[Seed_lose.DT_Lose == 1]\n\n\n#Ploly barchart\n# Women\nimport plotly.graph_objects as go\nfig = go.Figure()\nfig.add_trace(go.Bar(name='Two-Team', x = Seed_Wins['WSeed'], y=Seed_Wins['win_perc'], text=Seed_Wins['win_perc']))\nfig.add_trace(go.Bar(name='Single Team', x = Seed_lose['LSeed'], y=Seed_lose['win_perc'], marker_color='Red'))\n    \nfig.update_layout(barmode='group', title={'text':\"Women's NCAA Tournament\",'x':0.5}, yaxis_title='Win Percentage', \n                  xaxis_title='Seed', uniformtext_minsize=8, uniformtext_mode='hide')\nfig.update_traces(texttemplate='%{text:%.2f}', textposition='outside', marker_line_width=1.5, marker_line_color='DarkSlateGrey')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Women's NCAA Tournament Findings:\n* The lower seeded Two-Team Programs played no games against Single-team programs before they were eliminated (likely in the first round by another Two-Seed Program)\n* The Two-Team Programs have a higher winning percentage (i.e. win more games in the tournament) than the Single team programs.\n* This phenomenon holds constant for every seed in the tournament\n\nThis means in games where a Two-Team progam plays a single team program, the Two-Team program has a higher chance of winning"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"# Men's Tournament\n# Win percentage for Two-Team programs per seed in Two-Team v. Single Team games\nMSeed_Wins = Men_Both_DT[['DT_Wins', 'WSeed']].groupby('WSeed')['DT_Wins'].value_counts(normalize=True).round(3)\nMSeed_Wins = pd.DataFrame(MSeed_Wins).rename(columns={'DT_Wins': 'win_perc'})\nMSeed_Wins = MSeed_Wins.reset_index()\nMSeed_Wins = MSeed_Wins.loc[MSeed_Wins.DT_Wins == 1]\n\n# Win percentage for single team programs per seed in Two-Team v. Single Team games\nMSeed_lose = Men_Both_DT[['DT_Lose', 'LSeed']].groupby('LSeed')['DT_Lose'].value_counts(normalize=True).round(3)\nMSeed_lose = pd.DataFrame(MSeed_lose).rename(columns={'DT_Lose': 'win_perc'})\nMSeed_lose = MSeed_lose.reset_index()\nMSeed_lose = MSeed_lose.loc[MSeed_lose.DT_Lose == 1]\n\n#Ploly barchart\n# Men\nimport plotly.graph_objects as go\nfig = go.Figure()\nfig.add_trace(go.Bar(name='Two-Team', x = MSeed_Wins['WSeed'], y=MSeed_Wins['win_perc'], text=MSeed_Wins['win_perc']))\nfig.add_trace(go.Bar(name='Single Team', x = MSeed_lose['LSeed'], y=MSeed_lose['win_perc'], marker_color='Red'))\n    \nfig.update_layout(barmode='group', title={'text':\"Men's NCAA Tournament\",'x':0.5}, yaxis_title='Win Percentage', \n                  xaxis_title='Seed', uniformtext_minsize=8, uniformtext_mode='hide')\nfig.update_traces(texttemplate='%{text:%.2f}', textposition='outside', marker_line_width=1.5, marker_line_color='DarkSlateGrey')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Men's NCAA Tournament Findings:\n* There are matchups where lower seeded Two-Team programs played Sinlge Team programs\n* Two-Team programs outperform in every Seed except one (Seed # 14)\n* Unlike the Women's Tournament, some of the lower seeds (3,4 and 6) have the highest win percentages"},{"metadata":{},"cell_type":"markdown","source":"For both types of programs the higher seed wins more times than not, but the Two-Team programs significantly outperform. I believe this shows that the high seeded teams for each type of program win most of the time in the early rounds against lower seeds, but when it comes to facing other highly seeded teams in the tournament in later rounds the Two-Team programs defeat the similarly ranked single team programs most of the time. "},{"metadata":{},"cell_type":"markdown","source":"## 4.3 Conference"},{"metadata":{},"cell_type":"markdown","source":"Finally, we come to our last factor comparison, which is with the conference of the team. Normally a few conferences dominate the tournament, filling most of the spots and winning most of the championships. These are, not surprisingly, the conferences with the largest schools. This is an important feature to look at because if there is a huge difference between the conferences the Two-Team programs come from and the conferences the Single team programs come from, this factor could be easily explained by that difference. So, in this section we will explore which conferences each type of program comes from, and whether the Two-Team advantage exists across conferences. "},{"metadata":{},"cell_type":"markdown","source":"Women"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Women\nplt.style.use('seaborn')\nfig, axs = plt.subplots(1, 2, figsize=(12, 6))\naxs[0].set_title(\"Program with Women and Men's Teams in Tournament\", fontsize=15)\nsns.countplot(data=wom_winperc_both, x='ConfAbbrev', ax=axs[0],order=pd.value_counts(wom_winperc_both['ConfAbbrev']).iloc[:10].index)\naxs[1].set_title(\"Program with Only Women's Team in Tournament\", fontsize=15)\nsns.countplot(data=wom_winperc_single, x='ConfAbbrev', ax=axs[1],order=pd.value_counts(wom_winperc_single['ConfAbbrev']).iloc[:10].index);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Men"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# Men\nplt.style.use('seaborn')\nfig, axs = plt.subplots(1, 2, figsize=(12, 6))\naxs[0].set_title(\"Program with Men and Women's Teams in Tournament\", fontsize=15)\nsns.countplot(data=men_winperc_both, x='ConfAbbrev', ax=axs[0], order=pd.value_counts(men_winperc_both['ConfAbbrev']).iloc[:10].index)\naxs[1].set_title(\"Program with Only Men's Team in Tournament\", fontsize=15)\nsns.countplot(data=men_winperc_single, x='ConfAbbrev', ax=axs[1], order=pd.value_counts(men_winperc_single['ConfAbbrev']).iloc[:10].index);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"A few takeaways from the graphs:\n* The same 5 or 6 conferences make up the most of the teams competing for both types of programs\n* Even though it is the same conferences, there is clear differnce in which conferences make up each type of program\n* In the Women's Tournament, the \"Two-team\" programs have the most teams from the Big 12 and ACC. The single team programs get the highest number of their teams from the SEC and Big East. "},{"metadata":{},"cell_type":"markdown","source":"#### Win Percentages per Conference"},{"metadata":{},"cell_type":"markdown","source":"Women"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"# Win percentage for Two-Team programs per seed in Two-Team v. Single Team games\nWConf_Wins = Wom_Both_DT[['DT_Wins', 'WConf']].groupby('WConf')['DT_Wins'].value_counts(normalize=True).round(3)\nWConf_Wins = pd.DataFrame(WConf_Wins).rename(columns={'DT_Wins': 'win_perc'})\nWConf_Wins = WConf_Wins.reset_index()\nWConf_Wins = WConf_Wins.loc[WConf_Wins.DT_Wins == 1]\n\n# Win percentage for single team programs per seed in Two-Team v. Single Team games\nWConf_lose = Wom_Both_DT[['DT_Lose', 'LConf']].groupby('LConf')['DT_Lose'].value_counts(normalize=True).round(3)\nWConf_lose = pd.DataFrame(WConf_lose).rename(columns={'DT_Lose': 'win_perc'})\nWConf_lose = WConf_lose.reset_index()\nWConf_lose = WConf_lose.loc[WConf_lose.DT_Lose == 1]\n\n#Ploly barchart\n# Women\nimport plotly.graph_objects as go\nfig = go.Figure()\nfig.add_trace(go.Bar(name='Two-Team', x = WConf_Wins['WConf'], y=WConf_Wins['win_perc'], text=WConf_Wins['win_perc']))\nfig.add_trace(go.Bar(name='Single Team', x = WConf_lose['LConf'], y=WConf_lose['win_perc'], marker_color='Orange'))\n    \nfig.update_layout(barmode='group', title={'text':\"Women's NCAA Tournament\",'x':0.5}, yaxis_title='Win Percentage', \n                  xaxis_title='Seed', uniformtext_minsize=8, uniformtext_mode='hide')\nfig.update_traces(texttemplate='%{text:%.2f}', textposition='outside', marker_line_width=1.5, marker_line_color='DarkSlateGrey')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"In the Women's NCAA Tournament:\n\nThe outperformance of Two-Team programs holds true in nearly all of the conferences. In a few smaller conferences like Confernce USA (CUSA), the Mountain West (MWC), and the Missouri Valley Conference (MVC) the Single Team programs have higher win percentages, which is likely due to a much smaller sample size. \n\nIn the \"Power Five\" confernces, which are the ACC, Big 10, Big 12, Pac 12, and SEC, the Two-Team Programs all have higher win percentages in the tournament than single team programs. "},{"metadata":{},"cell_type":"markdown","source":"Men"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"# Win percentage for Two-Team programs per seed in Two-Team v. Single Team games\nMConf_Wins = Men_Both_DT[['DT_Wins', 'WConf']].groupby('WConf')['DT_Wins'].value_counts(normalize=True).round(3)\nMConf_Wins = pd.DataFrame(MConf_Wins).rename(columns={'DT_Wins': 'win_perc'})\nMConf_Wins = MConf_Wins.reset_index()\nMConf_Wins = MConf_Wins.loc[MConf_Wins.DT_Wins == 1]\n\n# Win percentage for single team programs per seed in Two-Team v. Single Team games\nMConf_lose = Men_Both_DT[['DT_Lose', 'LConf']].groupby('LConf')['DT_Lose'].value_counts(normalize=True).round(3)\nMConf_lose = pd.DataFrame(MConf_lose).rename(columns={'DT_Lose': 'win_perc'})\nMConf_lose = MConf_lose.reset_index()\nMConf_lose = MConf_lose.loc[MConf_lose.DT_Lose == 1]\n\n#Ploly barchart\n# Men\nimport plotly.graph_objects as go\nfig = go.Figure()\nfig.add_trace(go.Bar(name='Two-Team', x = MConf_Wins['WConf'], y=MConf_Wins['win_perc'], text=MConf_Wins['win_perc']))\nfig.add_trace(go.Bar(name='Single Team', x = MConf_lose['LConf'], y=MConf_lose['win_perc'], marker_color='Orange'))\n    \nfig.update_layout(barmode='group', title={'text':\"Men's NCAA Tournament\",'x':0.5}, yaxis_title='Win Percentage', \n                  xaxis_title='Seed', uniformtext_minsize=8, uniformtext_mode='hide')\nfig.update_traces(texttemplate='%{text:%.2f}', textposition='outside', marker_line_width=1.5, marker_line_color='DarkSlateGrey')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"In the Men's NCAA Tournament:\n\n**The Two-Team programs outperform single team programs in every single conference except the Atlantic Ten Conference (A_ten)**, where the two programs have the same win percentage. Again we see outperformance in all of the \"Power Five\" conferences. In both the Men and Women Tournaments there are multiple smaller conferences which have only had Single Team programs compete in the NCAA Tournament. This makes sense, as larger schools are more likely to have both a Men's and Women's programs that are competitive in the same year. "},{"metadata":{},"cell_type":"markdown","source":"## Conclusion"},{"metadata":{},"cell_type":"markdown","source":"We conclude that Two-Team programs perform better in the NCAA Tournament than Single Team programs. Some observations that make this point include:\n1. Tournament Champions\n    * a. 73% of Women's Tournament Champions are Two-Team Programs\n    * b. 59% of Men's Tournament Champions are Two-Team Programs\n2. Both Men's and Women's Two-Team Programs have an average win rate of over 50%\n3. Two-Team Programs on average make it further in the tournament\n4. In Games where Two-Team programs play Single Team programs:\n    * a. Women's Two-Team programs win 64% of the time\n    * b. Men's Two-Team programs win 63% of the time\n5. The Outperformance by Two-Team Programs persists over nearly every:\n    * a. Round\n    * b. Season\n    * c. Seed\n    * d. Conference\n\n\nAfter pouring over the data, I have concluded that the real beauty of this factor is that it appears to stay strong when other factors fall apart. When two teams that have high PPG or high Seeds face each other, it becomes extremely difficult to predict the outcome, but this factor can make that prediction."},{"metadata":{},"cell_type":"markdown","source":"March Madness is a competitive and grueling environment where anything can happen. This is what makes it so exciting, and also what makes it so difficult to quantify. Thousands of people make their brackets every year trying to call the big games, and very few get them correct. We believe that quantifying performance can be extremely useful, but after a certain point it is nearly a guess. There is value in looking outside of the common statistics, and at something that may not be intuitive. \n\nThe connection between men's and women's team performance may not even make sense at first. Afterall, how could these two be connected? The games are so different. But there is value in a factor even if we cannot fully explain it. This Two-Team Factor is predictive of success in the NCAA Tournament, and if we think about it, it starts to make sense. Schools large enough to have two successful programs attract great players and coaches, and must have a great athletic department. But then we turn to the seemingly unquantifiable: school passion that results from competing in the tournament. These schools have not just one, but two teams competing in the NCAA Tournament. That has to have some effect on the passion and competitiveness of the players, and this may be the way to capture it. "}],"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":4,"nbformat_minor":4}