机器学习————逻辑回归练习（音乐分析）

逻辑回归练习（音乐分析）

问题详情

根据已给的数据预测出测试数据的音乐风格

代码实现

'''
Date:2019-08-04 16:53
User:ChenXi
E-mail:15091630326@163.com
'''
import numpy as np
from sklearn.linear_model import LogisticRegression
from scipy import fft
from scipy.io import wavfile
from tqdm import tqdm


# 准备音乐数据
def create_fit(g, n):
    # zfill返回指定长度的字符串，原字符串右对齐，前面填充0
    rad = './genres/' + g + '/converted/' + g + '.' + str(n).zfill(5) + '.au.wav'
    # sample_rate:采样率
    # 模电(连续的信号)变数电(数字的表达)
    # 采样率越高，如果单位时间采样点越多，信息损失的越少
    # x是音乐文件
    sample_rate, X = wavfile.read(rad)
    fft_features = abs(fft(X)[:1000])

    sad = './genres/' + g + '.' + str(n).zfill(5) + '.fft'
    np.save(sad, fft_features)


if __name__ == '__main__':
    genre_list = ["classical", "blues", "country", "disco"]
    X, Y = [], []
    for g in tqdm(genre_list):
        for n in range(100):

            rad = "./genres/"+g + "." + str(n).zfill(5) + ".fft.npy"
            fft_features = np.load(rad)
            X.append(fft_features)
            Y.append(genre_list.index(g))

    X = np.array(X)
    Y = np.array(Y)
    # test file
    rad_test = "wudizirong" + ".fft.npy"
    fft_features = np.load(rad_test)
    X_test = np.array([fft_features])

    # study
    log_reg = LogisticRegression(multi_class='ovr', solver='sag')
    log_reg.fit(X, Y)
    print(log_reg.score(X, Y))
    print(log_reg.predict(X_test))
    #
    # #处理测试数据
    # rad_test = "./genres/heibao-wudizirong-remix.wav"
    # sample_rate, X_test = wavfile.read(rad_test)
    # fft_features = abs(fft(X_test)[:1000])
    # sad =  'wudizirong' + ".fft"
    # np.save(sad, fft_features)

结果图示