kitzeslab · sammlapp · Apr 28, 2023 · Jan 12, 2023 · Jan 18, 2023 · Feb 9, 2023
diff --git a/.github/workflows/poetry.yml b/.github/workflows/poetry.yml
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: [3.8, 3.9]
       # Ensure that all flavours are run to completion even if an other flavor failed
       fail-fast: false
 
@@ -39,7 +39,7 @@ jobs:
     runs-on: macos-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: [3.8, 3.9]
       # Ensure that all flavours are run to completion even if an other flavor failed
       fail-fast: false
     steps:

diff --git a/.gitignore b/.gitignore
@@ -8,3 +8,4 @@ doc/_build/
 *.DS_Store
 docs/tutorials/woodcock_labeled_data
 .vscode
+docs/tutorials/wandb
diff --git a/README.md b/README.md
@@ -12,15 +12,14 @@ OpenSoundscape is currently in active development. If you find a bug, please sub
 
 #### Suggested Citation
 ```
-Lapp, Rhinehart, Freeland-Haynes, Khilnani, Syunkova, and Kitzes, 2022. "OpenSoundscape v0.8.0".
+Lapp, Rhinehart, Freeland-Haynes, Khilnani, Syunkova, and Kitzes, 2023. "OpenSoundscape v0.9.0".
 ```
 
 # Installation
 
-OpenSoundscape can be installed on Windows, Mac, and Linux machines. It has been tested on Python 3.7, 3.8, and 3.9. For Apple Silicon (M1 chip) users, Python 3.9 is recommended and may be required to avoid dependency issues. Python version 3.7.0 causes dependency issues 
-and should be avoided. 
+OpenSoundscape can be installed on Windows, Mac, and Linux machines. It has been tested on Python 3.8, and 3.9. For Apple Silicon (M1 chip) users, Python 3.9 is recommended and may be required to avoid dependency issues.
 
-Most users should install OpenSoundscape via pip: `pip install opensoundscape==0.8.0`. Contributors and advanced users can also use Poetry to install OpenSoundscape.
+Most users should install OpenSoundscape via pip: `pip install opensoundscape==0.9.0`. Contributors and advanced users can also use Poetry to install OpenSoundscape.
 
 For more detailed instructions on how to install OpenSoundscape and use it in Jupyter, see the [documentation](http://opensoundscape.org).
 
@@ -66,7 +65,7 @@ Audio.from_file(path, start_timestamp=start_time,duration=audio_length)
 
 Using a pre-trained CNN to make predictions on long audio files
 ```python
-from opensoundscape.torch.models.cnn import load_model
+from opensoundscape import load_model
 
 #get list of audio files
 files = glob('./dir/*.WAV')
@@ -81,7 +80,7 @@ scores = model.predict(files)
 
 Training a CNN with labeled audio data
 ```python
-from opensoundscape.torch.models.cnn import CNN
+from opensoundscape import CNN
 from sklearn.model_selection import train_test_split
 
 #load a DataFrame of one-hot audio clip labels

diff --git a/docs/api/modules.rst b/docs/api/modules.rst
@@ -1,52 +1,42 @@
-Annotations
-^^^^^^^^^^^
-.. automodule:: opensoundscape.annotations
- :members:
-
-Audio
+ Audio
 ^^^^^
 .. automodule:: opensoundscape.audio
   :members:
 
 
-AudioMoth
-^^^^^^^^^
-.. automodule:: opensoundscape.audiomoth
- :members:
-
-Audio Tools
-^^^^^^^^^^^
- .. automodule:: opensoundscape.audio_tools
-    :members:
-
 Spectrogram
 ^^^^^^^^^^^
 .. automodule:: opensoundscape.spectrogram
  :members:
-
+ 
 CNN
 ^^^
-.. automodule:: opensoundscape.torch.models.cnn
+.. automodule:: opensoundscape.ml.cnn
   :members:
 
-torch.models.utils
-^^^^^^^^^^^^^^^^^^
-.. automodule:: opensoundscape.torch.models.utils
+Annotations
+^^^^^^^^^^^
+.. automodule:: opensoundscape.annotations
+ :members:
+
+ARU
+^^^
+.. automodule:: opensoundscape.aru
+ :members:
+
+Machine Learning utils
+^^^^^^^^^^^^^^^^^^^^^^
+.. automodule:: opensoundscape.ml.utils
   :members:
 
 CNN Architectures
 ^^^^^^^^^^^^^^^^^
-.. automodule:: opensoundscape.torch.architectures.cnn_architectures
-  :members:
-
-torch.architectures.utils
-^^^^^^^^^^^^^^^^^^^^^^^^^
-.. automodule:: opensoundscape.torch.architectures.utils
+.. automodule:: opensoundscape.ml.cnn_architectures
   :members:
 
-WandB (Weights and Biases)
-^^^^^^^^^^^^^^^^^^^^^^^^^^
-.. automodule:: opensoundscape.wandb
+Logging with WandB (Weights and Biases)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+.. automodule:: opensoundscape.logging
   :members:
 
 Data Selection
@@ -56,27 +46,32 @@ Data Selection
 
 Datasets
 ^^^^^^^^
-.. automodule:: opensoundscape.torch.datasets
+.. automodule:: opensoundscape.ml.datasets
   :members:
 
-GradCam
-^^^^^^^
-.. automodule:: opensoundscape.torch.grad_cam
+CAM (Class Activation Maps)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+.. automodule:: opensoundscape.ml.cam
   :members:
 
 Loss
 ^^^^
-.. automodule:: opensoundscape.torch.loss
+.. automodule:: opensoundscape.ml.loss
   :members:
 
 Safe Dataset
 ^^^^^^^^^^^^
-.. automodule:: opensoundscape.torch.safe_dataset
+.. automodule:: opensoundscape.ml.safe_dataset
+  :members:
+
+Sample
+^^^^^^
+.. automodule:: opensoundscape.sample
   :members:
 
 Sampling
 ^^^^^^^^
-.. automodule:: opensoundscape.torch.sampling
+.. automodule:: opensoundscape.ml.sampling
   :members:
 
 Metrics
@@ -129,7 +124,7 @@ Localization
 .. automodule:: opensoundscape.localization
    :members:
 
-helpers
-^^^^^^^
-.. automodule:: opensoundscape.helpers
+utils
+^^^^^
+.. automodule:: opensoundscape.utils
    :members:
diff --git a/docs/conf.py b/docs/conf.py
@@ -26,7 +26,7 @@
 author = "Sam Lapp, Tessa Rhinehart, Louis Freeland-Haynes, Jatin Khilnani, Alexandra Syunkova, Justin Kitzes"
 
 # The full version, including alpha/beta/rc tags
-release = "0.8.0"
+release = "0.9.0"
 
 
 # -- General configuration ---------------------------------------------------
@@ -101,6 +101,7 @@ def setup(app):
     "deprecated",
     "skimage",
     "wandb",
+    "pytorch_grad_cam",
 ]
 
 master_doc = "index"
diff --git a/docs/installation/mac_and_linux.md b/docs/installation/mac_and_linux.md
@@ -1,6 +1,6 @@
 # Mac and Linux
 
-OpenSoundscape can be installed on Mac and Linux machines with Python 3.7, 3.8, or 3.9 using the pip command `pip install opensoundscape==0.8.0`. We recommend installing OpenSoundscape in a virtual environment to prevent dependency conflicts.
+OpenSoundscape can be installed on Mac and Linux machines with Python 3.8, or 3.9 using the pip command `pip install opensoundscape==0.9.0`. We recommend installing OpenSoundscape in a virtual environment to prevent dependency conflicts.
 
 Below are instructions for installation with two package managers:
 * `conda`: Python and package management through Anaconda, a package manager popular among scientific programmers
@@ -13,23 +13,23 @@ Feel free to use another virtual environment manager (e.g. `virtualenvwrapper`)
 * Install Anaconda if you don't already have it.
    * Download the installer [here](https://www.anaconda.com/products/individual), or
    * follow the [installation instructions](https://docs.anaconda.com/anaconda/install/) for your operating system.
-* Create a Python (3.7, 3.8, or 3.9) conda environment for opensoundscape: `conda create --name opensoundscape pip python=3.9`
+* Create a Python (3.8, or 3.9) conda environment for opensoundscape: `conda create --name opensoundscape pip python=3.9`
 * Activate the environment: `conda activate opensoundscape`
-* Install opensoundscape using pip: `pip install opensoundscape==0.8.0`
+* Install opensoundscape using pip: `pip install opensoundscape==0.9.0`
 * Deactivate the environment when you're done using it: `conda deactivate`
 
 ## Installation via `venv`
 
-Download Python 3.7, 3.8, or 3.8 from [this website](https://www.python.org/downloads/).
+Download Python 3.8 or 3.9 from [this website](https://www.python.org/downloads/).
 
 Run the following commands in your bash terminal:
-* Check that you have installed Python 3.7, 3.8, or 3.9.\_: `python3 --version`
+* Check that you have installed Python 3.8 or 3.9.\_: `python3 --version`
 * Change directories to where you wish to store the environment: `cd [path for environments folder]`
     * Tip:  You can use this folder to store virtual environments for other projects as well, so put it somewhere that makes sense for you, e.g. in your home directory.
 * Make a directory for virtual environments and `cd` into it: `mkdir .venv && cd .venv`
 * Create an environment called `opensoundscape` in the directory: `python3 -m venv opensoundscape`
 * Activate/use the environment: `source opensoundscape/bin/activate`
-* Install OpenSoundscape in the environment: `pip install opensoundscape==0.8.0`
+* Install OpenSoundscape in the environment: `pip install opensoundscape==0.9.0`
 * Once you are done with OpenSoundscape, deactivate the environment: `deactivate`
 * To use the environment again, you will have to refer to absolute path of the virtual environments folder. For instance, if I were on a Mac and created `.venv` inside a directory `/Users/MyFiles/Code` I would activate the virtual environment using: `source /Users/MyFiles/Code/.venv/opensoundscape/bin/activate`
 

diff --git a/docs/installation/windows.md b/docs/installation/windows.md
@@ -49,9 +49,9 @@ We recommend installing OpenSoundscape in a package manager. We find that the ea
 You can now manage packages with `conda`.
 
 ## Install OpenSoundscape in virtual environment
-- Create a Python (3.7, 3.8, or 3.9) conda environment for opensoundscape: `conda create --name opensoundscape pip python=3.9`
+- Create a Python (3.8, or 3.9) conda environment for opensoundscape: `conda create --name opensoundscape pip python=3.9`
 - Activate the environment: `conda activate opensoundscape`
-- Install opensoundscape using pip: `pip install opensoundscape==0.8.0`
+- Install opensoundscape using pip: `pip install opensoundscape==0.9.0`
 
 If you see an error that says "No matching distribution found...", your
 best bet is to use these commands to download then install the package:
@@ -64,7 +64,7 @@ pip install .
 
 If you run into this error and you are on a Windows 10 machine:
 ```
-(opensoundscape_environment) username@computername:~$ pip install opensoundscape==0.8.0
+(opensoundscape_environment) username@computername:~$ pip install opensoundscape==0.9.0
 WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPSConnection object at 0x7f7603c5da90>: Failed to establish a new connection: [Errno -2] Name or service not known')': /simple/opensoundscape/
 ```
 You may be able to solve it by going to System Settings, searching for “Proxy Settings,” and beneath “Automatic proxy setup,” turning “Automatically detect settings” OFF. Restart your terminal for changes to take effect. Then activate the environment and install OpenSoundscape using pip.