在 Keras 中显示 'y' 的预测值和相应的实际 'x' 值

Question

I am attempting to write a neural network that uses 100 data points evenly spaced along ay = sin(x) graph, between 0 and (5/2)pi. So the x values go from 0 to 7.854, and the corresponding y values oscillate between 1 and -1.

I have split the data into training and validation points, and it seems to have trained properly, however when I try to print the 'test' data, it is 100% correct, no matter how many neurons, epochs that I use. I think it is simply displaying the actual values, no predictions.

I think that I must have done something wrong in the final predictions part of the code, but I am not sure how to display the predicted values of y by the network for corresponding x values. Any help would be greatly appreciated!

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation
import pandas as pd
import io
import os
import requests
import numpy as np
from sklearn import metrics
from sklearn.model_selection import train_test_split
from tensorflow.keras.callbacks import EarlyStopping

df = pd.read_csv("C:\\Users\\Dan\\Desktop\\UNI\\PROJECT\\y_sinx_values.csv")

x = df['x'].values 
y = df['y'].values

# Split into training and validation sets
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=42)

model = Sequential()
model.add(Dense(100, input_shape = (1,), activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer = 'adam')

monitor = EarlyStopping(monitor='val_loss', min_delta=1e-3, patience=1, verbose=1, mode='auto', restore_best_weights=True)
model.fit(x_train,y_train,validation_data=(x_test,y_test),callbacks=[monitor],verbose=2, epochs=2)

pred = model.predict(x_test)
score = np.sqrt(metrics.mean_squared_error(pred,y_test))
print(f"Final score (RMSE): {score}")

# Sample predictions
for i in range(25):
    print(f"{i+1}. x: {x_test[i]}, y: {y_test[i]}")

Answer 1

# Sample predictions
for i in range(25):
    print(f"{i+1}. x: {x_test[i]}, y: {y_test[i]}")

Yes, you are printing your input test data. You most likely want something like:

# Sample predictions
for i in range(25):
    print(f"{i+1}. x: {x_test[i]}, y: {pred[i]}")

Note the y_test[i] has been changed to pred[i] .