Merge pull request #20 from uwescience/model_versioning

adding model benchmarking workflow

Author: valentina-s

.github/workflows/create_website_benchmarks.yml

@@ -0,0 +1,68 @@
+name: Create Benchmark Website  
+
+on:
+  # Runs on pushes targeting the default branch
+  push:
+    branches: ["main", "model_versioning"]
+  pull_request:
+    types: ["opened", "reopened", "synchronize", "edited"]
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  pages: write
+  id-token: write
+
+jobs:
+  # Build Website
+  build:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+
+
+      - name: Install Python dependencies
+        run: |
+          pip install "dask[dataframe]"
+          pip install ipykernel
+          pip install nbconvert
+
+      - name: Build Website
+        shell: bash -el {0}
+        run: |
+          cd ambient_sound_analysis
+          jupyter nbconvert display_benchmarks.ipynb --execute --to html --output-dir=_build/html --no-input
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: ambient_sound_analysis/_build/html
+
+
+  # Publish Website to GitHub Pages if built successfully
+  deploy:
+    needs: build
+    # if: github.ref == 'refs/heads/model_versioning'
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    steps:
+      - name: Setup Pages
+        uses: actions/configure-pages@v5
+
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.github/workflows/model_benchmarking.yml

@@ -0,0 +1,70 @@
+name: Model Benchmarking
+on:
+  pull_request:
+    types: [opened, synchronize, edited, reopened]
+
+env:
+  pr_username: github.event.pull_request.user.login
+  
+  # schedule:
+  #  - cron: '9 * * * *'
+    
+jobs:
+  process:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - uses: actions/setup-python@v5
+      with:
+        python-version: '3.9.18'
+        cache: 'pip'
+        cache-dependency-path: ambient_sound_analysis/requirements_noise.txt
+
+    - name: Install Python dependencies
+      run: |
+        pip install -r ambient_sound_analysis/requirements_noise.txt
+
+ 
+    # - name: Install ffmpeg
+    #  run: |
+    #   sudo apt-get update
+    #   sudo apt-get install ffmpeg
+    
+    - uses: awalsh128/cache-apt-pkgs-action@latest
+      with:
+        packages: ffmpeg
+
+    - name: Create plots
+      if: steps.cache.outputs.cache-hit != 'true'
+      run: |
+        python ambient_sound_analysis/model_benchmarking.py
+
+
+
+    - name: Append username
+      run: |
+        # sed 's/$/ test trigger/' 'ambient_sound_analysis/csv/2024-06-01 17:00:00.csv' > 'ambient_sound_analysis/csv/2024-06-01 17:00:00_new.csv'
+        
+        export output_file="score_${{ github.event.pull_request.head.sha }}.csv"
+        sed 's/$/,  ${{ github.event.pull_request.user.login }}, ${{ github.event.pull_request.head.sha }}, ${{github.event.pull_request.title}}/' 'ambient_sound_analysis/csv/test.csv' > "ambient_sound_analysis/csv/$output_file"
+
+    - name: Upload to GitHub repo
+      uses: stefanzweifel/git-auto-commit-action@v5
+      with:
+        commit_message: Commit to Github
+        file_pattern: 'ambient_sound_analysis/csv/score*.csv'
+
+    #- name: Upload as artifact
+    #  uses: actions/upload-artifact@v4
+    # with:
+    #     name: ambient_sound_plots
+    #     path: ambient_sound_analysis/img/*.png
+
+    #- name: Upload to Google Drive
+    #  uses: AnimMouse/setup-rclone@v1
+    #  with:
+    #    rclone_config: ${{secrets.RCLONE_CONFIG}}
+      
+    # - run: |
+    #    rclone copy ambient_sound_analysis/img/broadband.png mydrive:rclone_uploads/

ambient_sound_analysis/csv/score_1f3ac5bc8b3a4914606ceebcbd910a5aac64e50e.csv

@@ -0,0 +1 @@
+17,  valentina-s, 1f3ac5bc8b3a4914606ceebcbd910a5aac64e50e, adding model benchmarking workflow

ambient_sound_analysis/csv/score_28401087ddea6a1ac2829d708423b362b8d3840f.csv

@@ -0,0 +1 @@
+17,  valentina-s, 28401087ddea6a1ac2829d708423b362b8d3840f, adding model benchmarking workflow

ambient_sound_analysis/csv/score_42aa52eddaf7494cf272de17396907146982e1fd.csv

@@ -0,0 +1 @@
+17,  valentina-s, 42aa52eddaf7494cf272de17396907146982e1fd, adding model benchmarking workflow

ambient_sound_analysis/csv/score_66b46ac47aa1c2bcbda573e147f3a16eeed61dcd.csv

@@ -0,0 +1 @@
+17,  valentina-s, 66b46ac47aa1c2bcbda573e147f3a16eeed61dcd, adding model benchmarking workflow

ambient_sound_analysis/csv/score_71236d3146ee8b3354b3d8fea71d69028b83126b.csv

@@ -0,0 +1 @@
+17,  valentina-s, 71236d3146ee8b3354b3d8fea71d69028b83126b, adding model benchmarking workflow

ambient_sound_analysis/csv/score_72b13caee35f09369b3d3c6b082e71bac68316c0.csv

@@ -0,0 +1 @@
+1,  valentina-s, 72b13caee35f09369b3d3c6b082e71bac68316c0, adding model benchmarking workflow

ambient_sound_analysis/csv/score_a3d0ab1feae8b9b91c923229c4cf3d5b06e05f98.csv

@@ -0,0 +1 @@
+17,  valentina-s, a3d0ab1feae8b9b91c923229c4cf3d5b06e05f98, adding model benchmarking workflow

ambient_sound_analysis/csv/score_cd12ce8cad03004c315e2c175fd61b3ebecdc3be.csv

@@ -0,0 +1 @@
+17,  valentina-s, cd12ce8cad03004c315e2c175fd61b3ebecdc3be, adding model benchmarking workflow

ambient_sound_analysis/csv/score_f38875f0d0e246c9035abb2f76602e1a89479171.csv

@@ -0,0 +1 @@
+17,  valentina-s, f38875f0d0e246c9035abb2f76602e1a89479171, adding model benchmarking workflow

ambient_sound_analysis/csv/score_fc9e91bb543073453639b8989614702fdeaaa1e4.csv

@@ -0,0 +1 @@
+17,  valentina-s, fc9e91bb543073453639b8989614702fdeaaa1e4, adding model benchmarking workflow

ambient_sound_analysis/display_benchmarks.ipynb

@@ -0,0 +1,144 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "13bdddf3-f048-4bb2-801d-6a8473fa7d9d",
+   "metadata": {},
+   "source": [
+    "# Latest Benchmarks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "9b8f9eff-5009-4d4e-9e17-a9f14960c073",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import dask.dataframe as ddf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "dad42a94-20aa-4976-8ab3-558dc11c67c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = ddf.read_csv(\"csv/*.csv\", header=None, index_col=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "ae56d8d7-aea5-4a09-971d-a05afcfad2ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.compute().reset_index(drop=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "f4354a33-83ca-4878-bb15-2ea116f32996",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.columns = [\"# Ships\", \"username\", \"SHA\", \"title\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "a22b796f-9a02-4d3c-a3b4-335270e0e347",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th># Ships</th>\n",
+       "      <th>username</th>\n",
+       "      <th>SHA</th>\n",
+       "      <th>title</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>valentina-s</td>\n",
+       "      <td>1dbb9106cd9ff69b73a7171f938285650a97d0bb</td>\n",
+       "      <td>$ {{github.event.pull_request.title}}</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>valentina-s</td>\n",
+       "      <td>72b13caee35f09369b3d3c6b082e71bac68316c0</td>\n",
+       "      <td>adding model benchmarking workflow</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   # Ships       username                                        SHA  \\\n",
+       "0        1    valentina-s   1dbb9106cd9ff69b73a7171f938285650a97d0bb   \n",
+       "1        1    valentina-s   72b13caee35f09369b3d3c6b082e71bac68316c0   \n",
+       "\n",
+       "                                    title  \n",
+       "0   $ {{github.event.pull_request.title}}  \n",
+       "1      adding model benchmarking workflow  "
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

ambient_sound_analysis/model_benchmarking.py

@@ -0,0 +1,66 @@
+# importing general Python libraries
+import pandas as pd
+import datetime as dt
+import os
+import matplotlib.pyplot as plt
+import pytz
+import plotly.graph_objects as go
+import numpy as np
+
+# importing orcasound_noise libraries
+from orcasound_noise.pipeline.pipeline import NoiseAnalysisPipeline
+from orcasound_noise.utils import Hydrophone
+from orcasound_noise.pipeline.acoustic_util import plot_spec, plot_bb
+
+
+# Set Location and Resolution
+# Port Townsend, 1 Hz Frequency, 60-second samples
+if __name__ == '__main__':
+    pipeline = NoiseAnalysisPipeline(Hydrophone.ORCASOUND_LAB,
+                                     delta_f=10, bands=None,
+                                     delta_t=60, mode='safe')
+
+
+
+
+# Generate parquet dataframes with noise levels for a time period
+
+# now = dt.datetime.now(pytz.timezone('US/Pacific'))
+# fix time
+now = dt.datetime(2024, 6, 1, 17, 0, 0)
+psd_path, broadband_path = pipeline.generate_parquet_file(now - dt.timedelta(hours = 13), 
+                                                          now - dt.timedelta(hours = 8), 
+                                                          upload_to_s3=False)
+
+# Read the parquet files
+# psd_df = pd.read_parquet(psd_path)
+bb_df = pd.read_parquet(broadband_path)
+
+# set threshold
+threshold = 5
+
+import numpy as np
+nof_ships = (np.diff((bb_df['0']>threshold).astype('uint8'))==1).sum()
+
+
+# Create a new directory if it does not exist
+if not os.path.exists('ambient_sound_analysis/csv'):
+   os.makedirs('ambient_sound_analysis/csv')
+
+# pd.DataFrame([nof_ships]).to_csv('ambient_sound_analysis/csv/'+str(now)+'.csv', header=False, index=False)
+
+print("Nof Ships: "+str(nof_ships))
+pd.DataFrame([nof_ships]).to_csv('ambient_sound_analysis/csv/test.csv', header=False, index=False)
+
+
+
+
+
+
+# Create and save psd plot 
+# fig = plot_spec(psd_df)
+# fig.write_image('ambient_sound_analysis/img/psd.png')
+
+# Create and save bb plot
+# fig = plot_bb(bb_df)
+# fig.savefig('ambient_sound_analysis/img/broadband.png')