熊猫和scikit学习：ValueError：输入包含NaN，无穷大或对于dtype（'float64'）而言太大的值

Question

我正在尝试将Knearest Neigbors模型适合我的数据。但是，我收到此错误：

log.Println(reflect.Indirect(newitem))
log.Println(newitem.Elem())

这是我的Knearest Neigbhors算法的代码：

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

以及数据框的前五行：

def knn_train_test_new(training_col, target_col, df):
    np.random.seed(1)
    df = df.loc[np.random.permutation(len(df))]
#    shuffled_index = np.random.permutation(df.index)
#   df = df.reindex(shuffled_index)

    train_df = df.iloc[0:150] #training set has 75% of the data
    test_df = df.iloc[150:] #test set has 25% of the data  
    k = [5]

    rmse = {}

    for k_val in k:

        model = KNeighborsRegressor(n_neighbors = k_val)
        model.fit(train_df[training_col], train_df[target_col])

        predictions = model.predict(test_df[training_col])

        mse = mean_squared_error(test_df[target_col], predictions)

        rmse[k_val] = (mse ** 0.5)

    return rmse

two_features = ["width", "wheel-base"]
rmse_val = knn_train_test(two_features, 'price', numeric_cars)

当我使用shuffled_index（我已经评论过）而不是np.random.permutation时，我没有收到此错误。我不清楚两者之间的区别。

完整的错误跟踪：

numeric_cars.head()