dating_algo_new_man.py

def matchMan(men_df, women_df, ratings, new_man_answers, num_sim=10):
    """
    This function will return the most likely compatible women based on a few given
    dataframes for a new male user.  Will use the top N similar users' compatibility 
    ratings to find the potentially most compatible women.
    """
    
    # First need to replace the DF answers with their numerical values
    men_df = men_df.apply(lambda x: x.cat.codes)

    women_df = women_df.apply(lambda x: x.cat.codes)
    
    # Dataframe of new user
    new_man = pd.DataFrame(
        [new_man_answers],
        columns=men_df.columns,
        index=['m'+str(int(men_df.index[-1][1:])+1)] # Getting the new man's id 
    )
    
    # Categorical answers to the profile questions
    ans = ['A', 'B', 'C', 'D', 'E']
    
    # Categorizing the answers
    new_man = new_man.apply(
        lambda x: pd.Categorical(x, categories=ans)
    ).apply(
        lambda x: x.cat.codes, axis=1
    )
        
    # Getting the top N similar users
    sim_men = men_df.corrwith(
        new_man.iloc[0], 
        axis=1
    ).sort_values(ascending=False)[:num_sim].index
    
    # Getting the similar users' ratings
    sim_rate = ratings.T[sim_men]
    
    # Filling in unseen values with nan for calculation purposes
    sim_rate.replace("unseen", np.nan, inplace=True)
    
    # The potentially most compatible women for the new man
    most_comp = sim_rate.mean(axis=1).sort_values(ascending=False)
    
    return most_comp