add chemfp algorithm

ann_benchmarks/main.py

@@ -214,7 +214,7 @@ def _test(df):
 
         try:
             if args.local:
-                run(definition, args.dataset, args.count, args.runs, args.batch, args.rq, args.radius)
+                run(definition, args.dataset, args.count, args.runs, args.batch, args.rq)
             elif args.docker:
                 run_docker(definition, args.dataset, args.count, args.runs, args.timeout, args.batch, args.rq, args.radius)
             else:# by default run Singularity

ann_benchmarks/runner.py

@@ -34,8 +34,8 @@ def run_individual_query(algoname, algo, X_train, X_test, distance, count, run_c
         n_items_processed = [0]  # a bit dumb but can't be a scalar since of Python's scoping rules
 
         def single_query(v):
-            # special code for the Risc and DivideSkip
-            if "Risc" in algoname or 'DivideSkip' in algoname:
+            # special code for the Risc, DivideSkip, and Chemfp
+            if algoname in ['Risc', 'DivideSkip', 'Chemfp']:
                 algo.pre_query(v, count)
 
             start = time.time()
@@ -45,8 +45,8 @@ def single_query(v):
                 candidates = algo.query(v, count)
             total = (time.time() - start)
 
-            # special code for the Risc and DivideSkip
-            if "Risc" in algoname or 'DivideSkip' in algoname:
+            # special code for the Risc, DivideSkip, and Chemfp
+            if algoname in ['Risc', 'DivideSkip', 'Chemfp']:
                 candidates = algo.post_query()
 
             if issparse(X_train):
@@ -123,12 +123,15 @@ def run(definition, dataset, count, run_count, batch, rq):
     print('got %d queries' % len(X_test))
 
     try:
-        # special code for the Risc and DivideSkip
         print(X_train.shape)
-        if 'Risc' in definition.algorithm or 'DivideSkip' in definition.algorithm:
+        # special code for Risc and DivideSkip
+        if definition.algorithm in ['Risc', 'DivideSkip']:
             X_train = numpy.concatenate((X_train, [numpy.ones(X_train.shape[1], dtype=numpy.bool)]), axis=0)
             print(X_train.shape)
             algo.pre_fit(X_train)
+        # special code for Chemfp
+        if definition.algorithm in 'Chemfp':
+            algo.pre_fit(X_train)
 
         t0 = time.time()
         index_size_before = algo.get_index_size("self")
@@ -298,11 +301,9 @@ def run_singularity(definition, dataset, count, runs, timeout, batch, rq, radius
     strCmd = ' '.join(["'" + k + "'" for k in cmd])
     print('String of command', strCmd)
 
-    subprocess.check_call('singularity exec %s/%s.sif python3 run_algorithm.py %s' %(sif_dir, definition.singularity_tag, strCmd), shell=True)
-    #subprocess.check_call('singularity exec ../../singularity/ann-bench-nmslib3.sif python3 run_algorithm.py %s' %(strCmd), shell=True)
-    #subprocess.check_call('singularity exec ../singularity/ann-bench-pynndescent.sif python3 run_algorithm.py %s' %(strCmd), shell=True)
-    #subprocess.check_call('singularity exec ../singularity/ann-bench-datasketch.sif python3 run_algorithm.py %s' %(strCmd), shell=True)
-    #subprocess.check_call('singularity exec ../singularity/ann-bench-sklearn.sif python3 run_algorithm.py %s' %(strCmd), shell=True)
-    #subprocess.check_call('singularity exec ../singularity/ann-bench-risc.sif python3 run_algorithm.py %s' %(strCmd), shell=True)
-    #subprocess.check_call('singularity exec ../singularity/ann-bench-ngt.sif python3 run_algorithm.py %s' %(strCmd), shell=True)
+    # Chemfp uses Python2 while others use Python3
+    if definition.algorithm in 'Chemfp':
+        subprocess.check_call('singularity exec %s/%s.sif python run_algorithm.py %s' %(sif_dir, definition.singularity_tag, strCmd), shell=True)
+    else:
+        subprocess.check_call('singularity exec %s/%s.sif python3 run_algorithm.py %s' %(sif_dir, definition.singularity_tag, strCmd), shell=True)