Implemented funnelling architecture

refactor/main.py

@@ -4,6 +4,7 @@ from view_generators import *
 from data.dataset_builder import MultilingualDataset
 from util.common import MultilingualIndex
 from util.evaluation import evaluate
+from util.results_csv import CSVlog
 from time import time
 
 
@@ -49,13 +50,34 @@ def main(args):
     print('\n[Testing Generalized Funnelling]')
     time_te = time()
     ly_ = gfun.predict(lXte)
-
     l_eval = evaluate(ly_true=ly, ly_pred=ly_)
-    print(l_eval)
-
     time_te = round(time() - time_te, 3)
     print(f'Testing completed in {time_te} seconds!')
 
+    # Logging ---------------------------------------
+    print('\n[Results]')
+    results = CSVlog('test_log.csv')
+    metrics = []
+    for lang in lXte.keys():
+        macrof1, microf1, macrok, microk = l_eval[lang]
+        metrics.append([macrof1, microf1, macrok, microk])
+        print(f'Lang {lang}: macro-F1 = {macrof1:.3f} micro-F1 = {microf1:.3f}')
+        results.add_row(method='gfun',
+                        setting='TODO',
+                        sif='TODO',
+                        zscore='TRUE',
+                        l2='TRUE',
+                        dataset='TODO',
+                        time_tr=time_tr,
+                        time_te=time_te,
+                        lang=lang,
+                        macrof1=macrof1,
+                        microf1=microf1,
+                        macrok=macrok,
+                        microk=microk,
+                        notes='')
+    print('Averages: MF1, mF1, MK, mK', np.round(np.mean(np.array(metrics), axis=0), 3))
+
     overall_time = round(time() - time_init, 3)
     exit(f'\nExecuted in: {overall_time } seconds!')
 

refactor/util/results_csv.py

@@ -0,0 +1,51 @@
+import os
+import pandas as pd
+import numpy as np
+
+
+class CSVlog:
+    def __init__(self, file, autoflush=True, verbose=False):
+        self.file = file
+        self.columns = ['method',
+                        'setting',
+                        'sif',
+                        'zscore',
+                        'l2',
+                        'dataset',
+                        'time_tr',
+                        'time_te',
+                        'lang',
+                        'macrof1',
+                        'microf1',
+                        'macrok',
+                        'microk',
+                        'notes']
+        self.autoflush = autoflush
+        self.verbose = verbose
+        if os.path.exists(file):
+            self.tell('Loading existing file from {}'.format(file))
+            self.df = pd.read_csv(file, sep='\t')
+        else:
+            self.tell('File {} does not exist. Creating new frame.'.format(file))
+            dir = os.path.dirname(self.file)
+            if dir and not os.path.exists(dir): os.makedirs(dir)
+            self.df = pd.DataFrame(columns=self.columns)
+
+    def already_calculated(self, id):
+        return (self.df['id'] == id).any()
+
+    def add_row(self, method, setting, sif, zscore, l2, dataset, time_tr, time_te, lang,
+                macrof1, microf1, macrok=np.nan, microk=np.nan, notes=''):
+        s = pd.Series([method, setting,sif, zscore, l2, dataset, time_tr, time_te, lang,
+                       macrof1, microf1, macrok, microk, notes],
+                      index=self.columns)
+        self.df = self.df.append(s, ignore_index=True)
+        if self.autoflush: self.flush()
+        self.tell(s.to_string())
+
+    def flush(self):
+        self.df.to_csv(self.file, index=False, sep='\t')
+
+    def tell(self, msg):
+        if self.verbose:
+            print(msg)