我正在尝试用Python编写一个程序，使用机器学习来预测数字的平方根。我列出了我在程序中所做的一切：
- 创建了一个包含数字及其平方的CSV文件
- 从CSV文件中提取数据到合适的变量中（X存储平方，y存储数字）
- 使用sklearn的StandardScaler对数据进行缩放
- 构建了具有两个隐藏层的神经网络，每层有6个单元（无激活函数）
- 使用SGD作为优化器，均方误差作为损失函数编译神经网络
- 训练模型。损失大约为0.063
- 尝试预测，但结果与预期不符。
我的实际代码：
import numpy as npimport tensorflow as tfimport pandas as pddf = pd.read_csv('CSV/SQUARE-ROOT.csv')X = df.iloc[:, 1].valuesX = X.reshape(-1, 1)y = df.iloc[:, 0].valuesy = y.reshape(-1, 1)from sklearn.model_selection import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0, test_size=0.2)from sklearn.preprocessing import StandardScalersc = StandardScaler()X_test_sc = sc.fit_transform(X_test)X_train_sc = sc.fit_transform(X_train)sc1 = StandardScaler()y_test_sc1 = sc1.fit_transform(y_test)y_train_sc1 = sc1.fit_transform(y_train)ann = tf.keras.models.Sequential()ann.add(tf.keras.layers.Dense(units=6))ann.add(tf.keras.layers.Dense(units=6))ann.add(tf.keras.layers.Dense(units=1))ann.compile(optimizer='SGD', loss=tf.keras.losses.MeanSquaredError())ann.fit(x = X_train_sc, y = y_train_sc1, batch_size=5, epochs = 100)print(sc.inverse_transform(ann.predict(sc.fit_transform([[144]]))))输出： array([[143.99747]], dtype=float32)
输出不应该是12吗？为什么给我的结果是错误的？
我还附上了用于训练模型的CSV文件： SQUARE-ROOT.csv
回答：
你的代码不工作的原因是你对测试集应用了fit_transform，这是错误的。你可以通过将fit_transform(test)替换为transform(test)来修复它。虽然我认为StandardScaler不是必须的，请尝试以下代码：
import numpy as npimport tensorflow as tfimport pandas as pdfrom sklearn.preprocessing import StandardScalerfrom sklearn.model_selection import train_test_splitN = 10000X = np.arange(1, N).reshape(-1, 1)y = np.sqrt(X)X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0, test_size=0.2)sc = StandardScaler()X_train_sc = sc.fit_transform(X_train) #X_test_sc = sc.fit_transform(X_test) # wrong!!!X_test_sc = sc.transform(X_test)sc1 = StandardScaler() y_train_sc1 = sc1.fit_transform(y_train) #y_test_sc1 = sc1.fit_transform(y_test) # wrong!!!y_test_sc1 = sc1.transform(y_test)ann = tf.keras.models.Sequential()ann.add(tf.keras.layers.Dense(units=32, activation='relu')) # 你有10000个数据，可能需要一个稍微深一些的网络ann.add(tf.keras.layers.Dense(units=32, activation='relu'))ann.add(tf.keras.layers.Dense(units=32, activation='relu'))ann.add(tf.keras.layers.Dense(units=1))ann.compile(optimizer='SGD', loss='MSE')ann.fit(x=X_train_sc, y=y_train_sc1, batch_size=32, epochs=100, validation_data=(X_test_sc, y_test_sc1))#print(sc.inverse_transform(ann.predict(sc.fit_transform([[144]])))) # wrong!!!print(sc1.inverse_transform(ann.predict(sc.transform([[144]]))))