Upload FeatureExtraction.py

FeatureExtraction.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+import librosa
+import librosa.display
+import numpy as np
+import pandas as pd
+import scipy
+from scipy.stats import skew
+
+import matplotlib.pyplot as plt
+
+SAMPLE_RATE = 44100
+def get_mfcc(name, path):
+    data, _ = librosa.core.load(path + name, sr = SAMPLE_RATE)
+    assert _ == SAMPLE_RATE
+    try:
+        ft1 = librosa.feature.mfcc(data, sr = SAMPLE_RATE, n_mfcc=30)
+        ft2 = librosa.feature.zero_crossing_rate(data)[0]
+        ft3 = librosa.feature.spectral_rolloff(data)[0]
+        ft4 = librosa.feature.spectral_centroid(data)[0]
+        ft5 = librosa.feature.spectral_contrast(data)[0]
+        ft6 = librosa.feature.spectral_bandwidth(data)[0]
+        ft1_trunc = np.hstack((np.mean(ft1, axis=1), np.std(ft1, axis=1), skew(ft1, axis = 1), np.max(ft1, axis = 1), 
+                               np.median(ft1, axis = 1), np.min(ft1, axis = 1)))
+        ft2_trunc = np.hstack((np.mean(ft2), np.std(ft2), skew(ft2), np.max(ft2), np.median(ft2), np.min(ft2)))
+        ft3_trunc = np.hstack((np.mean(ft3), np.std(ft3), skew(ft3), np.max(ft3), np.median(ft3), np.min(ft3)))
+        ft4_trunc = np.hstack((np.mean(ft4), np.std(ft4), skew(ft4), np.max(ft4), np.median(ft4), np.min(ft4)))
+        ft5_trunc = np.hstack((np.mean(ft5), np.std(ft5), skew(ft5), np.max(ft5), np.median(ft5), np.min(ft5)))
+        ft6_trunc = np.hstack((np.mean(ft6), np.std(ft6), skew(ft6), np.max(ft6), np.median(ft6), np.max(ft6)))
+        return pd.Series(np.hstack((ft1_trunc, ft2_trunc, ft3_trunc, ft4_trunc, ft5_trunc, ft6_trunc)))
+    except:
+        print('bad file')
+        return pd.Series([0]*210)
+
+def MFCC_spectrogram(y, sr):
+    # 提取頻域音頻資料 MFCC spectrogram feature  
+    melspec = librosa.feature.melspectrogram(y, sr, n_fft=1024, hop_length=512, n_mels=128)  
+    # 轉成 log scale 已呈現頻譜資料  
+    logmelspec = librosa.power_to_db(melspec)  
+    # 繪圖  
+    plt.figure()  
+    librosa.display.specshow(logmelspec, sr=sr, x_axis='time', y_axis='mel')  
+    plt.title('Features of unknow frog by MFCC (Mel Frquency Cepstral Coefficients)')  
+    plt.show()
+
+
+
+def FeatureExtraction(fname):
+    # 創建文件檔
+    test= pd.DataFrame({'fname':[fname]})
+    # 特徵提取
+    test_data = test['fname'].progress_apply(get_mfcc, path='')
+    test_data = test_data.values
+    return test_data
+