if np.isnan(pitches[i]): ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

这个错误发生的原因是pitches[i]这个值是一个数组，而不是一个标量。因此，如果要判断pitches[i]是否为NaN，需要使用np.isnan(pitches[i][0])而不是np.isnan(pitches[i])。这里的[0]是因为pitches[i]这个数组只有一个元素，我们只需要判断这个元素是否为NaN即可。以下是修改后的代码：

x_esti = np.array([0, 0]).reshape(2, 1)
P = 1.0 * np.eye(2)
y_filt4 = np.zeros_like(y)
for i in range(len(y)):
    if np.isnan(pitches[i][0]):
        pitch = pitch
    else:
        pitch = librosa.hz_to_midi(pitches[i][0]) - 69
    z_meas = np.array([pitch, 0]).reshape(2, 1)
    x_esti, P = kalman_filter(z_meas, x_esti, P)
    y_filt4[i] = y[i] - x_esti[0]

这样修改后，就可以正常运行了。

相关问题

np.nonzero(~np.isnan(datMat[:, i].A))什么意思

这段代码使用了NumPy库中的函数nonzero()和isnan()。假设datMat是一个NumPy数组，[:, i]表示选取该数组中的第i列。那么代码np.isnan(datMat[:, i].A)将返回一个布尔值数组，其中每个元素都表示datMat[:, i]对应位置的值是否为NaN。~运算符表示对该数组中的每个元素进行逻辑非操作，即取反。

因此，~np.isnan(datMat[:, i].A)返回一个布尔值数组，其中每个元素都表示datMat[:, i]对应位置的值是否不是NaN。

最后，np.nonzero()函数返回一个元组，其中第一个元素是所有非零元素（即True）的行索引，第二个元素是所有非零元素的列索引。在这里，np.nonzero(~np.isnan(datMat[:, i].A))返回的是所有不是NaN的元素的行索引。

if not np.isnan(ls).all(): m = np.append(ma, ls) ma = m else: x = np.append(xc, i) xc = x

# As an AI language model, I cannot determine the context and purpose of the code. However, I can explain what this code block does.

This code block contains an if-else statement. It checks if all the values in the numpy array 'ls' are NaN (Not a Number). If they are not all NaN, it appends the values of 'ls' to another numpy array 'ma'. If all the values in 'ls' are NaN, it appends a variable 'i' to another numpy array 'xc'.

Here's a breakdown of the code:

if not np.isnan(ls).all():

This line checks if all the values in the numpy array 'ls' are NaN. The 'np.isnan' function returns a boolean array of the same shape as 'ls' with True for NaN values and False for non-NaN values. The 'all' function returns True if all the values in the boolean array are True, which means all the values in 'ls' are NaN. The 'not' keyword negates this result, so if any value in 'ls' is not NaN, the condition is True.

m = np.append(ma, ls)
ma = m

If the condition is True, this block of code appends the values of 'ls' to the numpy array 'ma' using the 'np.append' function. The result is stored in a new numpy array 'm', which is then assigned to 'ma'.

else:

If the condition is False, this block of code is executed.

x = np.append(xc, i)
xc = x

This block of code appends a variable 'i' to the numpy array 'xc' using the 'np.append' function. The result is stored in a new numpy array 'x', which is then assigned to 'xc'.