import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from sklearn.metrics.pairwise import cosine_similarity
import re

class SimilarityRecommender():

    def __init__(self, file):
        data = pd.read_excel(file, index_col=0)
        columns_brands = [re.sub(r'[^a-zA-Z ]', '', brand.upper()) for brand in list(data.index)]
        ex = pd.DataFrame(cosine_similarity(data), index=columns_brands,
                          columns=columns_brands)
        for brand in ex.index:
            ex.loc[brand, brand] = np.nan
        self.similarity_matrix = ex.assign(best_similarity=ex.idxmax())['best_similarity']

    def make_recommendation(self, item):
        key = re.sub(r'[^a-zA-Z ]', '', item.upper())
        key = key.replace('ADIDAS', 'ADIDAS SB')
        if key not in self.similarity_matrix.index:
            print(self.similarity_matrix.index)
            raise ValueError(f'{key} not in matrix')
        return self.similarity_matrix[key]


if __name__ == '__main__':
    rec = SimilarityRecommender("./TopBrands.xlsx")
    print(rec.make_recommendation("louis vuitton-1"))
    print(rec.similarity_matrix)
    print(rec.make_recommendation("Lacoste"))