Merge pull request #28 from jsingh811/test-versions

test-versions

Author: jsingh811

README.md

@@ -3,7 +3,7 @@
 ![pyaudioprocessing](https://user-images.githubusercontent.com/16875926/63388515-8e66fe00-c35d-11e9-98f5-a7ad0478a353.png)
 
 A Python based library for processing audio data into features and building Machine Learning models.  
-This was written using `Python 3.7.6`, and should work with python 3.6+.  
+This was written using `Python 3.7.6`, and has been tested to work with Python >= 3.6, <4.  
 
 
 ## Getting Started  
@@ -24,12 +24,17 @@ git clone git@github.com:jsingh811/pyAudioProcessing.git
 cd pyAudioProcessing
 pip install -e .
 ```
-and get the requirements by running
+You can also get the requirements by running
 
 ```
 pip install -r requirements/requirements.txt
 ```  
 
+If you are on Python 3.9 and experience any issues with the code samples regarding numpy, please run  
+```
+pip install -U numpy
+```
+
 ## Choices  
 
 ### Feature options  

pyAudioProcessing/extract_features.py

@@ -71,7 +71,7 @@ def get_features(folder_path, feature_names):
 
 if __name__ == "__main__":
     ARGS = PARSER.parse_args()
-    # dict with stucture
+    # dict with structure
     # {
     #    <folder name inside ARGS.folder>: {
     #       <file name> :{

pyAudioProcessing/features/audioFeatureExtraction.py

@@ -252,7 +252,7 @@ def dirsWavFeatureExtraction(dirNames, mt_win, mt_step, st_win, st_step, feats,
                                        'audioData/classSegmentsRec/brush-teeth','audioData/classSegmentsRec/shower'], 1, 1, 0.02, 0.02);
 
     It can be used during the training process of a classification model ,
-    in order to get feature matrices from various audio classes (each stored in a seperate path)
+    in order to get feature matrices from various audio classes (each stored in a separate path)
     '''
 
     # feature extraction for each class:

pyAudioProcessing/trainer/audioTrainTest.py

@@ -46,7 +46,7 @@ def trainLogisticRegression(features, Cparam):
     Train a multi-class probabilitistic Logistic Regression classifier.
     Note:     This function is simply a wrapper to the sklearn functionality for logistic regression training
     ARGUMENTS:
-        - features:         a list ([numOfClasses x 1]) whose elements containt numpy matrices of features
+        - features:         a list ([numOfClasses x 1]) whose elements contain numpy matrices of features
                             each matrix features[i] of class i is [n_samples x numOfDimensions]
         - Cparam:           Logistic Regression parameter C (Inverse of regularization strength)
     RETURNS:
@@ -65,7 +65,7 @@ def trainLogisticRegression(features, Cparam):
 def evaluateclassifier(features, class_names, n_exp, classifier_name, Params, parameterMode, perTrain=0.90):
     '''
     ARGUMENTS:
-        features:     a list ([numOfClasses x 1]) whose elements containt numpy matrices of features.
+        features:     a list ([numOfClasses x 1]) whose elements contain numpy matrices of features.
                 each matrix features[i] of class i is [n_samples x numOfDimensions]
         class_names:    list of class names (strings)
         n_exp:        number of cross-validation experiments
@@ -239,7 +239,7 @@ def featureAndTrain(list_of_dirs, mt_win, mt_step, st_win, st_step,
     '''
     This function is used as a wrapper to segment-based audio feature extraction and classifier training.
     ARGUMENTS:
-        list_of_dirs:        list of paths of directories. Each directory contains a signle audio class whose samples are stored in seperate WAV files.
+        list_of_dirs:        list of paths of directories. Each directory contains a signle audio class whose samples are stored in separate WAV files.
         mt_win, mt_step:        mid-term window length and step
         st_win, st_step:        short-term window and step
         classifier_type:        "svm" or "knn" or "randomforest" or "gradientboosting" or "extratrees"

requirements/requirements.txt

@@ -7,15 +7,4 @@ eyed3==0.9.5
 pydub==0.23.1
 pyAudioAnalysis==0.2.5
 pytest==6.2.3
-rsa==4.7
-bleach==3.3.0
-docutils==0.17.1
-Pygments==2.8.1
-jmespath==0.9.5
-urllib3==1.26.4
-colorama==0.4.3
-PyYAML==5.4.1
-requests==2.25.1
-tqdm==4.60.0
-pkginfo==1.7.0
-keyring==23.0.1
+ffmpeg==1.4

tests/__init__.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Apr 30 17:37:32 2021
+
+@author: jsingh
+"""
+import os
+import pytest
+from pathlib import Path
+from pyAudioProcessing.extract_features import get_features
+
+def test_get_features():
+    """
+    Test get_features function
+    """
+    test_root = str(Path(__file__).parent)
+    data_dir = os.path.join(test_root, "test_data")
+    features = get_features(data_dir, ["gfcc", "mfcc"])
+    assert "speech" in features
+    assert len([i for i in features["speech"].keys() if "sleep.wav" in i]) > 0
+    key = list(features["speech"].keys())[0]
+    assert "features" in features["speech"][key]
+    assert "feature_names" in features["speech"][key]
+    assert  "mfcc_1_mean" in features["speech"][key]["feature_names"]
+    assert  "gfcc_1_mean" in features["speech"][key]["feature_names"]