gini-remove-outliers.py

def get_brasileirao_no_outliers(df):
    """Generate a DF removing the champion and the worst team of the championship

    Parameters
    ----------
    df : Pandas Dataframe
      Dataframe with Brasileirão data
    Returns
    -------
    df_concat : Pandas Dataframe
     Returns a Pandas Dataframe without the outliers

    """    
    
    df_concat = pd.DataFrame()

    for year in df['year'].unique():
        pos_min = df[df['year'] == year]['position'].min()
        pos_max = df[df['year'] == year]['position'].max()

        df_filtered = df[(df['year'] == year) \
                         & (~df['position'].isin([pos_min, pos_max]))]

        df_concat = df_concat.append(df_filtered)
    
    return df_concat
        
def get_gini(df):   
    """Generate a DF with the year and the following Gini Index calculated

    Parameters
    ----------
    df : Pandas Dataframe
      Dataframe with Brasileirão data
    Returns
    -------
    gini_df : Pandas Dataframe
     Returns a Pandas Dataframe with the year, and gini index    

    """  
    gini_per_year = []
    for year in df['year'].unique():
        championship_index = gini(np.array(df[df['year'] == year]['points']))
        gini_per_year.append((year, round(championship_index, 4)))
        
    gini_df = pd.DataFrame(gini_per_year)
    gini_df.columns = ['year', 'gini']
    
    # Indexing the date field for graph it smoothly
    gini_df.set_index('year', inplace=True)
        
    return gini_df
   
   
# Outlier removal
df_brasileirao_no_outliers = get_brasileirao_no_outliers(df_brasileirao)

df_brasileirao_no_outliers_gini = get_gini(df_brasileirao_no_outliers)
df_brasileirao_no_outliers_gini.sort_values(by=['gini'], ascending=True)