Skip to content

2.2. Cleaning datasets

Jump to bottom
Jim Schwoebel edited this page Aug 10, 2020 · 10 revisions

This part of Allie's skills relates to data cleaning.

Data cleansing is the process of making clean datasets - like removing noise in audio files. It allows for data with a higher signal-to-noise ratio for modeling, increasing robustness of models.

How to use cleaning scripts

To clean an entire folder of a certain file type (e.g. audio files of .WAV format), you can run:

cd /Users/jim/desktop/allie
cd cleaning/audio_cleaning
python3 clean.py /Users/jim/desktop/allie/train_dir/males/
python3 clean.py /Users/jim/desktop/allie/train_dir/females/

Click the .GIF below to follow along this example in a video format:

The code above will featurize all the audio files in the folderpath via the default_cleaner specified in the settings.json file (e.g. 'clean_mono16hz').

Extending to other file types

Note you can extend this to any of the file types. The table below overviews how you could call each as a augmenter. In the code below, you must be in the proper folder (e.g. ./allie/augmentation/audio_augmentations for audio files, ./allie/augmentation/image_augmentation for image files, etc.) for the scripts to work properly.

Data type Supported formats Call to featurizer a folder Current directory must be
audio files .MP3 / .WAV python3 clean.py [folderpath] ./allie/cleaning/audio_cleaning
text files .TXT python3 clean.py [folderpath] ./allie/cleaning/text_cleaning
image files .PNG python3 clean.py [folderpath] ./allie/cleaning/image_cleaning
video files .MP4 python3 clean.py [folderpath] ./allie/cleaning/video_cleaning
csv files .CSV python3 clean.py [folderpath] ./allie/cleaning/csv_cleaning

Implemented

Implemented for all file types

  • delete_duplicates - deletes duplicate files in the directory
  • delete_json - deletes all .JSON files in the directory (this is to clean the featurizations)

Audio

  • clean_getfirst3secs - gets the first 3 seconds of the audio file
  • clean_keyword - keeps only keywords that are spoken based on a transcript (from the default_audio_transcriber)
  • clean_mono16hz - converts all audio to mono 16000 Hz for analysis (helps prepare for many preprocessing techniques)
  • clean_towav - converts all audio files to wav files
  • clean_multispeaker - deletes audio files from a dataset that have been identified as having multiple speakers from a deep learning model
  • clean_normalizevolume - normalizes the volume of all audio files using peak normalization methods from ffmpeg-normalize
  • clean_opus - converts an audio file to .OPUS audio file format then back to wav (a lossy conversion) - narrowing in more on voice signals over noise signals.
  • clean_randomsplice - take a random splice (time specified in the script) from the audio file.
  • clean_removenoise - removes noise from the audio file using SoX program and noise floors.
  • clean_removesilence - removes silence from an audio file using voice activity detectors.
  • clean_rename - renames all the audio files in the current directory with a new UUID
  • clean_utterances - converts all audio files into unique utterances (1 .WAV file --> many .WAV file utterances) for futher analysis.

Text

Image

Video

CSV

  • clean_csv - uses datacleaner, a standard excel sheet cleaning script that imputes missing values and prepares CSV spreadsheets for machine learning

Settings

Allie has multiple default settings for model training to help you start out with the framework. Here are some of the settings that relate to Allie's cleaning API. Settings can be modified in the settings.json file.

setting description default setting all options
clean_data whether or not to clean datasets during the model training process via default cleaning scripts. False True, False
default_audio_cleaners the default cleaning strategies used during audio modeling if clean_data == True ["clean_mono16hz"] ["clean_getfirst3secs", "clean_keyword", "clean_mono16hz", "clean_towav", "clean_multispeaker", "clean_normalizevolume", "clean_opus", "clean_randomsplice", "clean_removenoise", "clean_removesilence", "clean_rename", "clean_utterances"]
default_csv_cleaners the default cleaning strategies used to clean .CSV file types as part of model training if clean_data==True ["clean_csv"] ["clean_csv"]
default_image_cleaners the default cleaning techniques used for image data as a part of model training is clean_data == True ["clean_greyscale"] ["clean_extractfaces", "clean_greyscale", "clean_jpg2png"]
default_text_cleaners the default cleaning techniques used during model training on text data if clean_data == True ["clean_textacy"] ["clean_summary", "clean_textacy"]
default_video_cleaners the default cleaning strategies used for videos if clean_data == True ["clean_alignfaces"] ["clean_alignfaces", "clean_videostabilize"]
Clone this wiki locally