我正在根据爵士，古典，西方，流行等类型对音频文件中的音乐进行分类。为此，我正在训练机器学习模型，我正在使用音频文件进行测试。我写了一个效果很好的脚本。我写了一个脚本来创建数据集，在这段代码中我收到了一个错误。
错误：
Traceback (most recent call last): File "CreateDataset.py", line 124, in <module> main() File "CreateDataset.py", line 38, in main dataset_numpy = scaler.fit_transform(dataset_numpy) File "/root/twitter/lib/python3.5/site-packages/sklearn/base.py", line 517, in fit_transform return self.fit(X, **fit_params).transform(X) File "/root/twitter/lib/python3.5/site-packages/sklearn/preprocessing/data.py", line 308, in fit return self.partial_fit(X, y) File "/root/twitter/lib/python3.5/site-packages/sklearn/preprocessing/data.py", line 334, in partial_fit estimator=self, dtype=FLOAT_DTYPES) File "/root/twitter/lib/python3.5/site-packages/sklearn/utils/validation.py", line 441, in check_array "if it contains a single sample.".format(array)) ValueError: Expected 2D array, got 1D array instead: array=[]. Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.
代码如下：
import librosa
import numpy
import pandas
import os
import sklearn
import config
def main():
samp_rate = config.CreateDataset.SAMPLING_RATE
frame_size = config.CreateDataset.FRAME_SIZE
hop_size = config.CreateDataset.HOP_SIZE
dataset_dir = config.CreateDataset.DATASET_DIRECTORY
sub_folders = get_subdirectories(dataset_dir)
labels = []
is_created = False
print("Extracting features from audios...")
# global dataset_numpy
dataset_numpy = []
for sub_folder in sub_folders:
print(".....Working in folder:", sub_folder)
sample_arrays = get_sample_arrays(dataset_dir, sub_folder, samp_rate)
for sample_array in sample_arrays:
row = extract_features(sample_array, samp_rate, frame_size, hop_size)
if not is_created:
dataset_numpy = numpy.array(row)
is_created = True
elif is_created:
dataset_numpy = numpy.vstack((dataset_numpy, row))
labels.append(sub_folder)
print("Normalizing the data...")
scaler = sklearn.preprocessing.MinMaxScaler(feature_range=(-1, 1))
dataset_numpy = scaler.fit_transform(dataset_numpy)
Feature_Names = ['meanZCR', 'stdZCR', 'meanSpecCentroid', 'stdSpecCentroid', 'meanSpecContrast', 'stdSpecContrast',
'meanSpecBandwidth', 'stdSpecBandwidth', 'meanSpecRollof', 'stdSpecRollof',
'meanMFCC_1', 'stdMFCC_1', 'meanMFCC_2', 'stdMFCC_2', 'meanMFCC_3', 'stdMFCC_3',
'meanMFCC_4', 'stdMFCC_4', 'meanMFCC_5', 'stdMFCC_5', 'meanMFCC_6', 'stdMFCC_6',
'meanMFCC_7', 'stdMFCC_7', 'meanMFCC_8', 'stdMFCC_8', 'meanMFCC_9', 'stdMFCC_9',
'meanMFCC_10', 'stdMFCC_10', 'meanMFCC_11', 'stdMFCC_11', 'meanMFCC_12', 'stdMFCC_12',
'meanMFCC_13', 'stdMFCC_13'
]
dataset_pandas = pandas.DataFrame(dataset_numpy, columns=Feature_Names)
dataset_pandas["genre"] = labels
dataset_pandas.to_csv("data_set.csv", index=False)
print("Data set has been created and sent to the project folder!")
def get_subdirectories(a_dir):
return [name for name in os.listdir(a_dir)
if os.path.isdir(os.path.join(a_dir, name))]
def get_sample_arrays(dataset_dir, folder_name, samp_rate):
path_of_audios = librosa.util.find_files(dataset_dir + "/" + folder_name)
audios = []
for audio in path_of_audios:
x, sr = librosa.load(audio, sr=samp_rate, duration=5.0)
audios.append(x)
audios_numpy = numpy.array(audios)
return audios_numpy
def extract_features(signal, sample_rate, frame_size, hop_size):
zero_crossing_rate = librosa.feature.zero_crossing_rate(y=signal, frame_length=frame_size, hop_length=hop_size)
spectral_centroid = librosa.feature.spectral_centroid(y=signal, sr=sample_rate, n_fft=frame_size,
hop_length=hop_size)
spectral_contrast = librosa.feature.spectral_contrast(y=signal, sr=sample_rate, n_fft=frame_size,
hop_length=hop_size)
spectral_bandwidth = librosa.feature.spectral_bandwidth(y=signal, sr=sample_rate, n_fft=frame_size,
hop_length=hop_size)
spectral_rolloff = librosa.feature.spectral_rolloff(y=signal, sr=sample_rate, n_fft=frame_size, hop_length=hop_size)
mfccs = librosa.feature.mfcc(y=signal, sr=sample_rate, n_fft=frame_size, hop_length=hop_size)
return [
numpy.mean(zero_crossing_rate),
numpy.std(zero_crossing_rate),
numpy.mean(spectral_centroid),
numpy.std(spectral_centroid),
numpy.mean(spectral_contrast),
numpy.std(spectral_contrast),
numpy.mean(spectral_bandwidth),
numpy.std(spectral_bandwidth),
numpy.mean(spectral_rolloff),
numpy.std(spectral_rolloff),
numpy.mean(mfccs[1, :]),
numpy.std(mfccs[1, :]),
numpy.mean(mfccs[2, :]),
numpy.std(mfccs[2, :]),
numpy.mean(mfccs[3, :]),
numpy.std(mfccs[3, :]),
numpy.mean(mfccs[4, :]),
numpy.std(mfccs[4, :]),
numpy.mean(mfccs[5, :]),
numpy.std(mfccs[5, :]),
numpy.mean(mfccs[6, :]),
numpy.std(mfccs[6, :]),
numpy.mean(mfccs[7, :]),
numpy.std(mfccs[7, :]),
numpy.mean(mfccs[8, :]),
numpy.std(mfccs[8, :]),
numpy.mean(mfccs[9, :]),
numpy.std(mfccs[9, :]),
numpy.mean(mfccs[10, :]),
numpy.std(mfccs[10, :]),
numpy.mean(mfccs[11, :]),
numpy.std(mfccs[11, :]),
numpy.mean(mfccs[12, :]),
numpy.std(mfccs[12, :]),
numpy.mean(mfccs[13, :]),
numpy.std(mfccs[13, :]),
]
if __name__ == '__main__':
main()
如何解决错误？
我的config.py文件如下所示：
# --- CONFIGURATIONS FOR Convert_to_wav --- #
class ConvertWav:
# Path of the song folder which will be used for wav converting
CONVERT_DIRECTORY = "./TestFiles"
# File extension in song folder
FILE_TYPE = "au"
# --- CONFIGURATIONS FOR Create_Dataset_as_csv --- #
class CreateDataset:
# Path of GTZAN dataset
DATASET_DIRECTORY = "./TrainFiles/"
# Sampling rate (Hz)
SAMPLING_RATE = 22050
# Frame size (Samples)
FRAME_SIZE = 2048
# Hop Size (Samples)
HOP_SIZE = 512
class Test:
# Path for test data
TEST_DATA_PATH = "./TestFiles/"