recipe_cleanup.py 文件源码

def flavor_profile(df,ingr,comp,ingr_comp):
    sorted_ingredients = df.columns
    underscore_ingredients=[]
    for item in sorted_ingredients:
        underscore_ingredients.append(item.replace(' ','_'))

    print len(underscore_ingredients), len(sorted_ingredients)

    ingr_total = ingr_comp.join(ingr,how='right',on='# ingredient id')
    ingr_total = ingr_total.join(comp,how='right',on='compound id')

    ingr_pivot = pd.crosstab(ingr_total['ingredient name'],ingr_total['compound id'])
    ingr_flavor = ingr_pivot[ingr_pivot.index.isin(underscore_ingredients)]

    df_flavor = df.values.dot(ingr_flavor.values)
    print df.shape, df_flavor.shape

    return df_flavor

#normalize flavor matrix with tfidf method