nicer plots

plot_freq_distrib.py

@@ -6,7 +6,7 @@ import os, mir_eval
 from metadata import species
 np.seterr(divide = 'ignore')
 
-fig, ax = plt.subplots(ncols=3, sharey=True, figsize=(10, 4.8))
+fig, ax = plt.subplots(ncols=3, sharey=True, figsize=(10, 3.5))
 ax[0].set_title('Frequency (Hz)')
 ax[1].set_title('# Voiced time bins')
 ax[2].set_title('Modulation rate (Hz/sec)')

plot_scores.py → plot_scores_bars.py

 import matplotlib.pyplot as plt
 import pandas as pd, numpy as np
 from metadata import species
+import argparse
 
 algos = ['praat', 'tcrepe_ftsp', 'tcrepe_ftoth', 'basic', 'pesto', 'pesto_ft']
-metrics = ['Recall', 'False alarm', 'Pitch acc', 'Chroma acc']
+metrics = ['Pitch acc', 'Chroma acc', 'Recall', 'Specificity']
 
-drop_noisy_bins = False
-drop_noisy_vocs = False
+parser = argparse.ArgumentParser()
+parser.add_argument('--drop_noisy_bins', type=bool, help="drop noisy vocalisations", default=False)
+parser.add_argument('--drop_noisy_vocs', type=bool, help="drop noisy STFT bins", default=False)
+args = parser.parse_args()
+drop_noisy_vocs, drop_noisy_bins = args.drop_noisy_vocs, args.drop_noisy_bins
 
-fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(10, 10), sharex=True, sharey=True)
+fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(10, 5), sharex=True, sharey=True)
 ax[0,0].set_ylim(0, 1)
 
 for i, metric in enumerate(metrics):
     ok = pd.DataFrame()
     for specie in species:
         df = pd.read_csv(f'scores/{specie}_scores{"_minusvocs" if drop_noisy_vocs else ""}{"_minusbins" if drop_noisy_bins else ""}.csv', index_col=0)
-        df['False alarm'] = 1 - df['False alarm']
+        df['Specificity'] = 1 - df['False alarm']
         ok.loc[specie, df.index] = df[metric]
     ok = ok[algos]
     # bar plot
     m_ax = ax[int(i//2), i%2]
-    ok.plot.barh(ax=m_ax, legend=None)
+    ok.plot.bar(ax=m_ax, legend=None, rot=45, width=.6)
     m_ax.grid()
     m_ax.set_title(metric)
     if i%2==1:
         m_ax.legend(bbox_to_anchor=(1,1))
+
 plt.tight_layout()
 plt.savefig(f'scores{"_minusvocs" if drop_noisy_vocs else ""}{"_minusbins" if drop_noisy_bins else ""}.pdf')

plot_scores_scatter.py

+import matplotlib.pyplot as plt
+import pandas as pd, numpy as np
+from metadata import species
+import argparse
+
+algos = ['praat', 'tcrepe', 'tcrepe_ftsp', 'tcrepe_ftoth', 'basic', 'pesto', 'pesto_ft']
+metrics = ['Pitch acc', 'Chroma acc', 'Recall', 'False alarm']
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--drop_noisy_bins', type=bool, help="drop noisy vocalisations", default=False)
+parser.add_argument('--drop_noisy_vocs', type=bool, help="drop noisy STFT bins", default=False)
+args = parser.parse_args()
+drop_noisy_vocs, drop_noisy_bins = args.drop_noisy_vocs, args.drop_noisy_bins
+
+fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(10, 5), sharex=True, sharey=True)
+ax[0,0].set_ylim(0, 1)
+
+for specie in species:
+    df = pd.read_csv(f'scores/{specie}_scores{"_minusvocs" if drop_noisy_vocs else ""}{"_minusbins" if drop_noisy_bins else ""}.csv', index_col=0)
+    df['False alarm'] = 1 - df['False alarm']
+    for algo in algos:
+        if not algo in df.index:
+            df.loc[algo, metrics] = [None]*len(metrics)
+    for i, metric in enumerate(metrics):
+        ax[int(i//2), i%2].scatter(np.arange(len(algos)), df.loc[algos, metric], label=specie)
+
+
+for i, metric in enumerate(metrics):
+    m_ax = ax[int(i//2), i%2]
+    m_ax.grid()
+    m_ax.set_title(metric)
+plt.xticks(np.arange(len(algos)), algos, rotation=22)
+ax[1,0].set_xticklabels(algos, rotation=22)
+plt.tight_layout(rect=(0, 0, .87, 1))
+ax[0, 1].legend(bbox_to_anchor=(1,1))
+
+plt.savefig(f'scatter_scores{"_minusvocs" if drop_noisy_vocs else ""}{"_minusbins" if drop_noisy_bins else ""}.pdf')

plot_snr_distrib.py

@@ -7,13 +7,10 @@ import mir_eval, librosa
 from metadata import species
 np.seterr(divide = 'ignore')
 
-fig, ax = plt.subplots(ncols=2, sharex=True, figsize=(10, 4.8))
+fig, ax = plt.subplots(ncols=2, sharey=True, figsize=(10, 3.5))
 
 SNRs, SHRs = [], []
 for i, specie in enumerate(species):
-    wavpath, FS, nfft, downsample = species[specie].values()
-    dt = nfft / 8 / FS
-    fns = pd.Series(glob(wavpath))
 
     def fun(fn):
         df = pd.read_csv(f'{fn[:-4]}_preds.csv')
@@ -22,20 +19,16 @@ for i, specie in enumerate(species):
             return 0, 0
         return df.salience.quantile(.25), df.SHR.quantile(.25)
     
-    ret = p_umap(fun, glob(wavpath), desc=specie, num_cpus=40)
-    SNRs.append(list(zip(*ret))[0])
-    SHRs.append(list(zip(*ret))[1])
+    ret = p_umap(fun, glob(species[specie]['wavpath']), desc=specie, num_cpus=40)
+    ax[0].violinplot(list(zip(*ret))[0], positions=[i], vert=False)
+    ax[1].violinplot(list(zip(*ret))[1], positions=[i], vert=False)
 
+ax[0].set_title('f0 saliency')
+ax[1].set_title('SHR (dB)')
+plt.yticks(np.arange(len(species)), [s.replace('_',' ') for s in species])
 
-ax[0].violinplot(SNRs, positions=np.arange(len(species)))
-ax[0].set_ylabel('f0 saliency')
-ax[1].violinplot(SHRs, positions=np.arange(len(species)))
-ax[1].set_ylabel('SHR (dB)')
-ax[0].set_xticks(np.arange(len(species)))
-ax[0].set_xticklabels(species.keys(), rotation=45)
-ax[1].set_xticklabels(species.keys(),rotation=45)
-ax[0].hlines(.2, .5, len(species)-.5, linestyle='dashed', colors='k')
-ax[1].hlines(10*np.log10(0.2), -.5, len(species)-.5, linestyle='dashed', colors='k')
+ax[0].vlines(.2, .5, len(species)-.5, linestyle='dashed', colors='k')
+ax[1].vlines(10*np.log10(0.2), -.5, len(species)-.5, linestyle='dashed', colors='k')
 
 plt.tight_layout()
 plt.savefig('SNR_distrib.pdf')