visualise_ground_truth_file.py now also shows species abundance

tools/visualise_ground_truth_file.py

@@ -6,21 +6,49 @@ import numpy as np
 
 
 def main():
+    id_to_species = {
+        'NZ_CP053098': 'acinetobacter baumannii',
+        'NZ_DS264586': 'actinomyces odontolyticus',
+        # 'NZ_DS26458': 'schaalia odontolytica',
+        'AE017194': 'bacillus cereus',
+        'CP000139': 'bacteroides vulgatus',
+        'CP000721': 'clostridium beijerinckii',
+        'AE000513': 'deinococcus radiodurans',
+        'CP025020': 'enterococcus faecalis',
+        'U00096': 'escherichia coli',
+        'AE000511': 'helicobacter pylori',
+        'CP000413': 'lactobacillus gasseri',
+        'AL591824': 'listeria monocytogenes',
+        'AE002098': 'neisseria meningitides',
+        'AP009380': 'porphyromonas gingivalis',
+        'AE017283': 'propionibacterium acnes',
+        'AE004091': 'pseudomonas aeruginosa',
+        'CP000144': 'rhodobacter sphaeroides',
+        'CP000730': 'staphylococcus aureus',
+        'AE015929': 'staphylococcus epidermidis',
+        'AE009948': 'streptococcus agalactiae',
+        'AE014133': 'streptococcus mutans',
+        'AE005672': 'streptococcus pneumoniae',
+    }
     ground_truth_csv = Path('/home/noord087/lustre_link/HoiCarlos/'
                             '16Sreads_mockcommunity/ground_truth_with_'
                             'read_id_and_perc_id.csv')
     df = pd.read_csv(ground_truth_csv)
-    fig, axs = plt.subplots(1, 3, figsize=(15, 5), sharey=True)
-    df['query length'].plot.hist(title='Query length', ax=axs[0],
+    fig, axs = plt.subplots(2, 2, figsize=(10, 10))
+    df['query length'].plot.hist(title='Query length', ax=axs[0, 0],
                                  bins=np.linspace(0, 3000, 50))
 
     percent_in_alignment = df['alignment length'] / df['query length']
     percent_in_alignment.plot.hist(title='Relative length of alignment relative to query',
-                                   ax=axs[1], bins=np.linspace(0.5, 1, 20))
+                                   ax=axs[0, 1], bins=np.linspace(0.5, 1, 20))
 
     df['percent identity'].plot.hist(title='Percent identity (based on alignment length)',
-                                     ax=axs[2], bins=np.linspace(0.8, 1, 20))
+                                     ax=axs[1, 0], bins=np.linspace(0.8, 1, 20))
 
+    species_abundance = df['species id'].value_counts()
+    species_abundance.index = [id_to_species[id[:-2]] for id in species_abundance.index]
+    species_abundance.plot.bar(title='Species abundance in ground truth',
+                               ax=axs[1, 1])
     plt.tight_layout()
     plt.show()