Simplify benchmark analysis

Makefile

 SHELL = /bin/bash
-PROJECT = cython+
+PROJECT = kdtree
 
 VENV_PATH=`conda info --base`/envs/${PROJECT}
 PIP_EXECUTABLE=${VENV_PATH}/bin/pip

benchmarks/benchmark.py

@@ -35,7 +35,7 @@ def benchmark(config, results_folder, bench_name):
     one_GiB = 1e9
     benchmarks = pd.DataFrame()
 
-    n_threads = _openmp_effective_n_threads()
+    n_threads = int(_openmp_effective_n_threads())
 
     env_specs_file = f"{results_folder}/{bench_name}.json"
 
@@ -112,21 +112,21 @@ def benchmark(config, results_folder, bench_name):
 
                 benchmarks = benchmarks.append(row, ignore_index=True)
                 pprint(row)
-                print("---")                
+                print("---")
 
                 benchmarks.to_csv(
                     f"{results_folder}/{bench_name}.csv",
                     mode="w+",
                     index=False,
                 )
-                
+
                 for k in n_neighbors:
-                    
+
                     t0_ = time.perf_counter()
                     sk_tree.query(X_test, k=k, return_distance=False)
                     t1_ = time.perf_counter()
                     time_elapsed = round(t1_ - t0_, 5)
-                    
+
                     row = dict(
                         trial=trial,
                         func="query",
@@ -143,8 +143,8 @@ def benchmark(config, results_folder, bench_name):
                     benchmarks = benchmarks.append(row, ignore_index=True)
                     pprint(row)
                     print("---")
-                        
-                    closests = np.zeros((ns_test, k), dtype=np.int32) 
+
+                    closests = np.zeros((ns_test, k), dtype=np.int32)
                     t0_ = time.perf_counter()
                     tree.query(X_test, closests)
                     t1_ = time.perf_counter()
@@ -165,7 +165,7 @@ def benchmark(config, results_folder, bench_name):
 
                     benchmarks = benchmarks.append(row, ignore_index=True)
                     pprint(row)
-                    print("---")                
+                    print("---")
 
                     benchmarks.to_csv(
                         f"{results_folder}/{bench_name}.csv",
@@ -173,7 +173,7 @@ def benchmark(config, results_folder, bench_name):
                         index=False,
                     )
 
-                
+
 
     # Overriding again now that all the dyn. lib. have been loaded
     env_specs["threadpool_info"] = threadpoolctl.threadpool_info()
@@ -198,4 +198,4 @@ if __name__ == "__main__":
 
     print(f"Benchmarking {bench_name}")
     benchmark(config, results_folder, bench_name)
-    print(f"Benchmark results wrote in {results_folder}")
\ No newline at end of file
+    print(f"Benchmark results wrote in {results_folder}")

benchmarks/report.py

@@ -77,4 +77,6 @@ if __name__ == "__main__":
         % vals
         )
         _ = fig.suptitle(title, fontsize=16)
-        plt.savefig(f"{commit_result_folder}/{i}.pdf", bbox_inches="tight")
+        fig_file = f"{commit_result_folder}/{i}.pdf"
+        plt.savefig(fig_file, bbox_inches="tight")
+        print(f"{fig_file} written.")

environment.yml

-name: cython+
+name: kdtree
 channels:
   - conda-forge
 dependencies:
@@ -15,6 +15,7 @@ dependencies:
   - pytest
   - scikit-learn
   - memory_profiler
+  - pip
   - pip:
       # Install cython+ from upstream directly
     - -e git+https://lab.nexedi.com/nexedi/cython.git@b30eafec6a7b174afdc4f023b45b21f85104e2fe#egg=Cython