@TOC

一、导包

import pathlib

import matplotlib.pyplot as plt

import pandas as pd

import seaborn as sns

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras import layers

import numpy as np

二、加载数据

# 100个用户，300个物品

data = pd.DataFrame(np.random.randint(5, size=(100, 300)))

三、构建模型

def build_model():

   model = keras.Sequential([

       layers.Dense(100, activation = 'relu', input_shape=[100]),

       layers.Dense(100, activation = 'relu'),

   ])

   

   optimizer = tf.keras.optimizers.RMSprop(0.001)

   

   model.compile(loss = 'mse',

                optimizer = optimizer,

                metrics = ['mae', 'mse'])

   

   return model

model = build_model()

model.summary()

四、训练数据

train_data = data.T

EPOCHS = 500

model.fit(train_data,

          train_data,

          epochs = EPOCHS,

          validation_split = 0.1,

          verbose = 0)

五、预测结果

pd.DataFrame(model.predict(train_data).T)