python - Tf.keras.Model类〜自变量性能

我创建了一个可复制的示例，但没有遇到任何问题：

import random
import string

import pandas


def gen_random_word(word_length=30):
    return ''.join((random.choice(string.ascii_letters) for _ in range(word_length)))

# I create a list of 300000 labels (but only 150k distinct labels) of 30 characters
labels = [gen_random_word() for _ in range(150000)]
labels = labels + labels
random.shuffle(labels)

# A dataframe here is useless but I try to get close to your own example
df = pandas.DataFrame(
    {'labels': labels}
)

class A:
    def __init__(self):
        self.direct = {}
        self.inverse = {}
        self.progressive = 0

    def fromDataset(self, column):

        # create direct map
        for label in column:
            # skip if present
            if str(label) in self.direct:
                continue
            # else add to direct
            self.direct[str(label)] = self.progressive
            self.inverse[self.progressive] = str(label)
            self.progressive += 1

class B:
    def __init__(self):
        self.direct = {}
        self.inverse = {}
        self.progressive = 0

    def fromDataset(self, column):
        # reset map
        direct = {}
        inverse = {}

        # progressive
        progressive = 0

        # create direct map
        for label in column:
            # skip if present
            if str(label) in direct:
                continue
            # else add to direct
            direct[str(label)] = progressive
            inverse[progressive] = str(label)
            progressive += 1

        self.direct = direct
        self.inverse = inverse
        self.progressive = progressive

第一次测试：

%%time # remove that if you are not using jupyter and use another timing solution

direct = {}
inverse = {}
# progressive
progressive = 0

# create direct map
for label in df['labels']:
    # skip if present
    if str(label) in direct:
        continue
    # else add to direct
    direct[str(label)] = progressive
    inverse[progressive] = str(label)
    progressive += 1

挂墙时间：267毫秒

第二次测试：

%%time
a = A()
a.fromDataset(df['labels'])

挂墙时间：249毫秒

第三次测试：

%%time
b = B()
b.fromDataset(df['labels'])

挂墙时间：220毫秒

所以...没什么大不了的。