src/cocktails/utilities/other_scrubbing_utilities.py

import numpy as np
import pickle
from src.cocktails.utilities.cocktail_utilities import get_profile, profile_keys
from src.cocktails.utilities.ingredients_utilities import extract_ingredients, ingredient_list, ingredient_profiles
from src.cocktails.utilities.glass_and_volume_utilities import glass_volume, volume_ranges

one_dash = 1
one_splash = 6
one_tablespoon = 15
one_barspoon = 5
fill_rate = 0.8
quantity_factors ={'ml':1,
                   'cl':10,
                   'splash':one_splash,
                   'splashes':one_splash,
                   'dash':one_dash,
                   'dashes':one_dash,
                   'spoon':one_barspoon,
                   'spoons':one_barspoon,
                   'tablespoon':one_tablespoon,
                   'barspoons':one_barspoon,
                   'barspoon':one_barspoon,
                   'bar spoons': one_barspoon,
                   'bar spoon': one_barspoon,
                   'tablespoons':one_tablespoon,
                   'teaspoon':5,
                   'teaspoons':5,
                   'drop':0.05,
                   'drops':0.05}
quantitiy_keys = sorted(quantity_factors.keys())
indexes_keys = np.flip(np.argsort([len(k) for k in quantitiy_keys]))
quantity_factors_keys = list(np.array(quantitiy_keys)[indexes_keys])

keys_to_track = ['names', 'urls', 'glass', 'garnish', 'recipe', 'how_to', 'review', 'taste_rep', 'valid']
keys_to_add = ['category', 'subcategory', 'ingredients_str', 'ingredients', 'quantities', 'to_keep']
keys_to_update = ['glass']
keys_for_csv = ['names', 'category', 'subcategory', 'ingredients_str', 'urls', 'glass', 'garnish', 'how_to', 'review', 'taste_rep'] + profile_keys

to_replace_q = {' fresh': ''}
to_replace_ing = {'maple syrup': 'honey syrup',
                  'agave syrup': 'honey syrup',
                  'basil': 'mint'}

def print_recipe(unit='mL', ingredient_str=None, ingredients=None, quantities=None, name='', cat='', to_print=True):
    str_out = ''
    if ingredient_str is None:
        assert len(ingredients) == len(quantities), 'provide either ingredient_str, or list ingredients and quantities'
    else:
        assert ingredients is None and quantities is None, 'provide either ingredient_str, or list ingredients and quantities'
        ingredients, quantities = extract_ingredients(ingredient_str)

    str_out += f'\nRecipe:'
    if name != '' and name is not None: str_out += f' {name}'
    if cat != '': str_out += f' ({cat})'
    str_out += '\n'
    for i in range(len(ingredients)):
        # get quantifier
        if ingredients[i] == 'egg':
            quantities[i] = 1
            ingredients[i] = 'egg white'
            if unit == 'mL':
                quantifier = ' (30 mL)'
            elif unit == 'oz':
                quantifier = ' (1 fl oz)'
            else:
                raise ValueError
        elif ingredients[i] in ['angostura', 'orange bitters']:
            quantities[i] = max(1, int(quantities[i] / 0.6))
            quantifier = ' dash'
            if quantities[i] > 1: quantifier += 'es'
        elif ingredients[i] == 'mint':
            if quantities[i] > 1: quantifier = ' leaves'
            else: quantifier = ' leaf'
        else:
            if unit == "oz":
                quantities[i] = float(f"{quantities[i] * 0.033814:.3f}")  # convert to fl oz
                quantifier = ' fl oz'
            else:
                quantifier = ' mL'
        str_out += f'   {quantities[i]}{quantifier} - {ingredients[i]}\n'

    if to_print:
        print(str_out)
    return str_out


def test_datapoint(datapoint, category, ingredients, quantities):
    # run checks
    ingredient_indexes = [ingredient_list.index(ing) for ing in ingredients]
    profile = get_profile(category, ingredients, quantities)
    volume = profile['end volume']
    alcohol = profile['end alcohol']
    acid = profile['end acid']
    sugar = profile['end sugar']
    # check volume
    if datapoint['glass'] != None:
        if volume > glass_volume[datapoint['glass']] * fill_rate:
            # recompute quantities for it to match
            ratio = fill_rate *  glass_volume[datapoint['glass']] / volume
            for i_q in range(len(quantities)):
                quantities[i_q] = float(f'{quantities[i_q] * ratio:.2f}')
    # check alcohol
    assert alcohol < 30, 'too boozy'
    assert alcohol < 5, 'not boozy enough'
    assert acid < 2, 'too much acid'
    assert sugar < 20, 'too much sugar'
    assert len(ingredients) > 1, 'only one ingredient'
    if len(set(ingredients)) != len(ingredients):
        i_doubles = []
        s_ing = set()
        for i, ing in enumerate(ingredients):
            if ing in s_ing:
                i_doubles.append(i)
            else:
                s_ing.add(ing)
        ingredient_double_ok = ['mint', 'cointreau', 'lemon juice', 'cuban rum', 'double syrup']
        if len(i_doubles) == 1 and ingredients[i_doubles[0]] in ingredient_double_ok:
            ing_double = ingredients[i_doubles[0]]
            double_q = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] == ing_double])
            ingredients.pop(i_doubles[0])
            quantities.pop(i_doubles[0])
            quantities[ingredients.index(ing_double)] = double_q
        else:
            assert False, f'double ingredient, not {ingredient_double_ok}'
    lemon_lime_q = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] in ['lime juice', 'lemon juice']])
    assert lemon_lime_q <= 45, 'too much lemon and lime'
    salt_q = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] == 'salt'])
    assert salt_q <= 8, 'too much salt'
    bitter_q = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] in ['angostura', 'orange bitters']])
    assert bitter_q <= 5 * one_dash, 'too much bitter'
    absinthe_q = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] == 'absinthe'])
    if absinthe_q > 4 * one_dash:
        mix_volume = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] != 'mint'])
        assert absinthe_q < 0.5 * mix_volume, 'filter absinthe glasses'
    if any([w in datapoint['how_to'] or any([w in ing.lower() for ing in datapoint['recipe'][1]]) for w in ['warm', 'boil', 'hot']]) and 'shot' not in datapoint['how_to']:
        assert False
    water_q = np.sum([quantities[i] for i in range(len(ingredients)) if ingredients[i] == 'water'])
    assert water_q < 40
    # n_liqueur = np.sum([ingredient_profiles['type'][i].lower() == 'liqueur' for i in ingredient_indexes])
    # assert n_liqueur <= 2
    n_liqueur_and_vermouth = np.sum([ingredient_profiles['type'][i].lower() in ['liqueur', 'vermouth'] for i in ingredient_indexes])
    assert n_liqueur_and_vermouth <= 3
    return ingredients, quantities

def run_battery_checks_difford(datapoint, category, ingredients, quantities):
    flag = False
    try:
        ingredients, quantities = test_datapoint(datapoint, category, ingredients, quantities)
    except:
        flag = True
        print(datapoint["names"])
        print(datapoint["urls"])
        ingredients, quantities = None, None

    return flag, ingredients, quantities

def tambouille(q, ingredients_scrubbed, quantities_scrubbed, cat):
    # ugly
    ing_scrubbed = ingredients_scrubbed[len(quantities_scrubbed)]
    if q == '4 cube' and ing_scrubbed == 'pineapple juice':
        q = '20 ml'
    elif 'top up with' in q:
        volume_so_far = np.sum([quantities_scrubbed[i] for i in range(len(quantities_scrubbed)) if ingredients_scrubbed[i] != 'mint'])
        volume_mix = np.sum(volume_ranges[cat]) / 2
        if (volume_mix - volume_so_far) < 15:
            q = '15 ml'#
        else:
            q = str(int(volume_mix - volume_so_far)) + ' ml'
    elif q == '1 pinch' and ing_scrubbed == 'salt':
        q = '2 drops'
    elif 'cube' in q and ing_scrubbed == 'double syrup':
        q = f'{float(q.split(" ")[0]) * 2 * 1.7:.2f} ml'  #2g per cube, 1.7 is ratio solid / syrup
    elif 'wedge' in q:
        if ing_scrubbed == 'orange juice':
            vol = 70
        elif ing_scrubbed == 'lime juice':
            vol = 30
        elif ing_scrubbed == 'lemon juice':
            vol = 45
        elif ing_scrubbed == 'pineapple juice':
            vol = 140
        factor = float(q.split(' ')[0]) * 0.15 # consider a wedge to be 0.15*the fruit.
        q = f'{factor * vol:.2f} ml'
    elif 'slice' in q:
        if ing_scrubbed == 'orange juice':
            vol = 70
        elif ing_scrubbed == 'lime juice':
            vol = 30
        elif ing_scrubbed == 'lemon juice':
            vol = 45
        elif ing_scrubbed == 'pineapple juice':
            vol = 140
        f = q.split(' ')[0]
        if len(f.split('⁄')) > 1:
            frac = f.split('⁄')
            factor = float(frac[0]) / float(frac[1])
        else:
            factor = float(f)
        factor *= 0.1 # consider a slice to be 0.1*the fruit.
        q = f'{factor * vol:.2f} ml'
    elif q == '1 whole' and ing_scrubbed == 'luxardo maraschino':
        q = '10 ml'
    elif ing_scrubbed == 'egg' and 'ml' not in q:
        q = f'{float(q) * 30:.2f} ml'  # 30 ml per egg
    return q


def compute_eucl_dist(a, b):
    return np.sqrt(np.sum((a - b)**2))

def evaluate_with_quadruplets(representations, strategy='all'):
    with open(QUADRUPLETS_PATH, 'rb') as f:
        data = pickle.load(f)
    data = list(data.values())
    quadruplets = []
    if strategy != 'all':
        for d in data:
            if d[0] == strategy:
                quadruplets.append(d[1:])
    elif strategy == 'all':
        for d in data:
            quadruplets.append(d[1:])
    else:
        raise ValueError

    scores = []
    for q in quadruplets:
        close = q[0]
        if len(close) == 2:
            far = q[1]
            distance_close = compute_eucl_dist(representations[close[0]], representations[close[1]])
            distances_far = [compute_eucl_dist(representations[far[i][0]], representations[far[i][1]]) for i in range(len(far))]
            scores.append(distance_close < np.min(distances_far))
    if len(scores) == 0:
        score = np.nan
    else:
        score = np.mean(scores)
    return score