MRG: update pyo3_branchwater to 0.7.0

benchmarking.snakefile

@@ -5,11 +5,16 @@ rule all:
     input:
         expand("benchmarks/{x}_vs_{y}.txt", x=['a'],
                y=['a', 'b', 'c', 'd', 'e']),
+        expand("outputs/output_{x}_vs_{y}.csv", x=['a'],
+               y=['a', 'b', 'c', 'd', 'e']),
+
+rule big:
+    input:
+        expand("benchmarks/a_vs_a_1000_t{t}.txt", t=[4,8,16]),
         "outputs/output_a_vs_largest_10k.csv",
+        expand("benchmarks/a_vs_catalog.txt"),
         expand("benchmarks/a_{n}_vs_a.txt", n=range(100, 1000, 100)),
         expand("benchmarks/a_vs_a_{n}.txt", n=range(1000, 10000, 1000)),
-        expand("benchmarks/a_vs_a_1000_t{t}.txt", t=[4,8,16]),
-        expand("benchmarks/a_vs_catalog.txt"),
 
 rule threads:
     input:

benchmarks/a_vs_a.txt

@@ -1,2 +1,2 @@
 s	h:m:s	max_rss	max_vms	max_uss	max_pss	io_in	io_out	mean_load	cpu_time
-875.6504	0:14:35	18036.04	24671.35	17774.06	17778.36	0.00	82.84	2567.74	22488.25
+919.6511	0:15:19	17597.27	24031.18	17298.20	17302.42	0.00	102.35	2633.43	24221.92

benchmarks/a_vs_b.txt

@@ -1,2 +1,2 @@
 s	h:m:s	max_rss	max_vms	max_uss	max_pss	io_in	io_out	mean_load	cpu_time
-827.8913	0:13:47	16330.66	22992.92	16727.98	16732.33	0.01	79.96	2671.40	22116.21
+933.1807	0:15:33	17187.03	24217.97	16875.07	16879.28	0.00	0.00	2548.04	23730.38

benchmarks/a_vs_c.txt

@@ -1,2 +1,2 @@
 s	h:m:s	max_rss	max_vms	max_uss	max_pss	io_in	io_out	mean_load	cpu_time
-759.2550	0:12:39	17084.92	22578.64	16849.08	16853.45	0.01	82.22	2845.20	21602.36
+847.8818	0:14:07	15040.67	21140.09	14697.48	14701.73	0.00	102.20	2710.66	22987.35

benchmarks/a_vs_d.txt

@@ -1,2 +1,2 @@
 s	h:m:s	max_rss	max_vms	max_uss	max_pss	io_in	io_out	mean_load	cpu_time
-807.2910	0:13:27	15190.04	20914.19	15028.30	15032.68	0.00	82.21	2735.69	22088.67
+841.7877	0:14:01	18019.69	24126.99	17811.66	17815.86	0.00	101.58	2829.97	23825.85

benchmarks/a_vs_e.txt

@@ -1,2 +1,2 @@
 s	h:m:s	max_rss	max_vms	max_uss	max_pss	io_in	io_out	mean_load	cpu_time
-743.7042	0:12:23	17108.77	22594.65	17374.48	17378.82	0.00	84.39	2892.58	21516.02
+992.2560	0:16:32	13746.12	19312.14	14108.83	14113.00	0.00	104.90	2323.13	23054.95

environment.yml

@@ -10,4 +10,4 @@ dependencies:
     - rust
     - maturin>=1,<2
     - pip:
-      - pyo3_branchwater==0.6.1
+      - pyo3_branchwater==0.7.0

summarize.py

@@ -0,0 +1,20 @@
+import pandas as pd
+
+def load_benchmark_replicate(filename, ident):
+    df = pd.read_csv(filename, sep='\t')
+    df['ident'] = ident
+
+    return df
+
+print("reading from benchmarks/a_vs_{x}.txt...")
+replicates_df = [ load_benchmark_replicate(f"benchmarks/a_vs_{x}.txt", x) for x in ('a','b','c','d','e')]
+#query_line.append(load_benchmark_and_annotate('benchmarks/a_vs_a.txt', 1000, 10000))
+replicates_df = pd.concat(replicates_df)
+replicates_df
+
+replicates_df['m'] = replicates_df['s'] / 60.0
+print(f"mean time (minutes) {replicates_df.m.mean():.1f} +/- {replicates_df.m.std():.1f}")
+
+print(f"mean RSS (GB) {replicates_df.max_rss.mean()/1000:.1f} +/- {replicates_df.max_rss.std()/1000:.1f}")
+
+print(f"mean I/O (kb) {replicates_df.io_in.mean():.1f} +/- {replicates_df.io_in.std():.1f}")