updates to formatting, new bench results

Author: pranav-walimbe

README.md

@@ -137,7 +137,7 @@ Run on a single `m7i.2xlarge` (8 vCPU, 32 GB), the same hardware used by [Apache
 </p>
 <p align="center"><sub>Apache SpatialBench SF1 · lower is better · linear axis, bars past the cap truncated with their value · TIMEOUT / ERROR annotated</sub></p>
 
-**SF10** (~60M trips). PyCanopy wins 5/12 testcases.
+**SF10** (~60M trips). PyCanopy wins 3/12 testcases.
 
 <p align="center">
   <img src="assets/spatialbench_sf10_auto.png" alt="PyCanopy vs SedonaDB, DuckDB, and GeoPandas on Apache SpatialBench SF10" width="100%"/>
@@ -154,18 +154,18 @@ All times in seconds. **Bold** = fastest on that query. SedonaDB, DuckDB, and Ge
 
 <table>
 <tr><th>Query</th><th>PyCanopy</th><th>SedonaDB</th><th>DuckDB</th><th>GeoPandas</th></tr>
-<tr><td>q1</td><td>1.41</td><td><b>0.66</b></td><td>0.96</td><td>12.78</td></tr>
-<tr><td>q2</td><td><b>3.94</b></td><td>8.07</td><td>9.95</td><td>20.74</td></tr>
-<tr><td>q3</td><td>1.22</td><td><b>0.80</b></td><td>1.17</td><td>13.59</td></tr>
-<tr><td>q4</td><td>10.88</td><td><b>8.41</b></td><td>9.83</td><td>25.24</td></tr>
-<tr><td>q5</td><td><b>1.77</b></td><td>5.10</td><td>1.80</td><td>47.08</td></tr>
-<tr><td>q6</td><td><b>5.57</b></td><td>8.59</td><td>9.36</td><td>24.43</td></tr>
-<tr><td>q7</td><td>2.22</td><td><b>1.66</b></td><td>1.82</td><td>137.00</td></tr>
-<tr><td>q8</td><td><b>1.06</b></td><td>1.10</td><td>1.08</td><td>16.08</td></tr>
+<tr><td>q1</td><td>1.39</td><td><b>0.66</b></td><td>0.96</td><td>12.78</td></tr>
+<tr><td>q2</td><td><b>3.74</b></td><td>8.07</td><td>9.95</td><td>20.74</td></tr>
+<tr><td>q3</td><td>1.23</td><td><b>0.80</b></td><td>1.17</td><td>13.59</td></tr>
+<tr><td>q4</td><td><b>7.44</b></td><td>8.41</td><td>9.83</td><td>25.24</td></tr>
+<tr><td>q5</td><td><b>1.71</b></td><td>5.10</td><td>1.80</td><td>47.08</td></tr>
+<tr><td>q6</td><td><b>5.51</b></td><td>8.59</td><td>9.36</td><td>24.43</td></tr>
+<tr><td>q7</td><td>2.15</td><td><b>1.66</b></td><td>1.82</td><td>137.00</td></tr>
+<tr><td>q8</td><td><b>1.04</b></td><td>1.10</td><td>1.08</td><td>16.08</td></tr>
 <tr><td>q9</td><td><b>0.23</b></td><td>0.23</td><td>50.15</td><td>0.28</td></tr>
-<tr><td>q10</td><td><b>11.62</b></td><td>18.79</td><td>207.84</td><td>46.13</td></tr>
-<tr><td>q11</td><td><b>12.43</b></td><td>32.98</td><td>TIMEOUT</td><td>51.01</td></tr>
-<tr><td>q12</td><td><b>14.00</b></td><td>14.55</td><td>ERROR</td><td>TIMEOUT</td></tr>
+<tr><td>q10</td><td><b>8.65</b></td><td>18.79</td><td>207.84</td><td>46.13</td></tr>
+<tr><td>q11</td><td><b>9.90</b></td><td>32.98</td><td>TIMEOUT</td><td>51.01</td></tr>
+<tr><td>q12</td><td>14.86</td><td><b>14.55</b></td><td>ERROR</td><td>TIMEOUT</td></tr>
 </table>
 
 </td>
@@ -175,18 +175,18 @@ All times in seconds. **Bold** = fastest on that query. SedonaDB, DuckDB, and Ge
 
 <table>
 <tr><th>Query</th><th>PyCanopy</th><th>SedonaDB</th><th>DuckDB</th><th>GeoPandas</th></tr>
-<tr><td>q1</td><td>8.59</td><td><b>3.04</b></td><td>4.58</td><td>ERROR</td></tr>
-<tr><td>q2</td><td>8.95</td><td>8.89</td><td><b>8.26</b></td><td>ERROR</td></tr>
-<tr><td>q3</td><td>7.12</td><td><b>4.09</b></td><td>5.17</td><td>TIMEOUT</td></tr>
-<tr><td>q4</td><td>21.34</td><td><b>7.52</b></td><td>8.51</td><td>ERROR</td></tr>
-<tr><td>q5</td><td>15.22</td><td>50.81</td><td><b>14.40</b></td><td>ERROR</td></tr>
-<tr><td>q6</td><td>11.19</td><td><b>9.11</b></td><td>10.67</td><td>ERROR</td></tr>
+<tr><td>q1</td><td>8.52</td><td><b>3.04</b></td><td>4.58</td><td>ERROR</td></tr>
+<tr><td>q2</td><td>9.39</td><td>8.89</td><td><b>8.26</b></td><td>ERROR</td></tr>
+<tr><td>q3</td><td>6.88</td><td><b>4.09</b></td><td>5.17</td><td>TIMEOUT</td></tr>
+<tr><td>q4</td><td>17.34</td><td><b>7.52</b></td><td>8.51</td><td>ERROR</td></tr>
+<tr><td>q5</td><td>14.60</td><td>50.81</td><td><b>14.40</b></td><td>ERROR</td></tr>
+<tr><td>q6</td><td>11.07</td><td><b>9.11</b></td><td>10.67</td><td>ERROR</td></tr>
 <tr><td>q7</td><td>22.73</td><td>14.44</td><td><b>14.03</b></td><td>ERROR</td></tr>
-<tr><td>q8</td><td><b>7.03</b></td><td>7.24</td><td>7.57</td><td>TIMEOUT</td></tr>
+<tr><td>q8</td><td>7.30</td><td><b>7.24</b></td><td>7.57</td><td>TIMEOUT</td></tr>
 <tr><td>q9</td><td><b>0.34</b></td><td>0.38</td><td>942.98</td><td>0.49</td></tr>
-<tr><td>q10</td><td><b>28.41</b></td><td>42.02</td><td>ERROR</td><td>ERROR</td></tr>
-<tr><td>q11</td><td><b>37.30</b></td><td>97.52</td><td>ERROR</td><td>ERROR</td></tr>
-<tr><td>q12</td><td>147.67</td><td><b>145.66</b></td><td>ERROR</td><td>TIMEOUT</td></tr>
+<tr><td>q10</td><td><b>27.26</b></td><td>42.02</td><td>ERROR</td><td>ERROR</td></tr>
+<tr><td>q11</td><td><b>37.21</b></td><td>97.52</td><td>ERROR</td><td>ERROR</td></tr>
+<tr><td>q12</td><td>175.31</td><td><b>145.66</b></td><td>ERROR</td><td>TIMEOUT</td></tr>
 </table>
 
 </td>

assets/spatial-bench-sf10_auto-results.txt

@@ -2,15 +2,15 @@ SpatialBench SF10  index mode: auto
 
 query        avg (s)  runs (s)
 ------------------------------
-q1              9.39  (10.86, 8.69, 8.61)
-q2              9.27  (10.14, 8.82, 8.84)
-q3              6.91  (7.03, 6.83, 6.86)
-q4             22.12  (21.81, 21.03, 23.53)
-q5             15.03  (15.65, 14.79, 14.64)
-q6             10.77  (11.04, 10.62, 10.65)
-q7             22.92  (22.65, 23.35, 22.75)
-q8              7.34  (7.37, 7.27, 7.38)
-q9              0.32  (0.32, 0.32, 0.32)
-q10            29.32  (29.42, 29.11, 29.44)
-q11            38.92  (38.65, 38.80, 39.30)
-q12           165.57  (133.56, 222.61, 140.55)
+q1              8.52  (9.61, 7.90, 8.05)
+q2              9.39  (9.89, 8.92, 9.34)
+q3              6.88  (6.96, 6.84, 6.84)
+q4             17.34  (17.43, 17.60, 16.98)
+q5             14.60  (14.83, 14.28, 14.69)
+q6             11.07  (11.28, 10.58, 11.35)
+q7             22.73  (22.90, 22.46, 22.82)
+q8              7.30  (7.26, 7.38, 7.27)
+q9              0.34  (0.34, 0.34, 0.36)
+q10            27.26  (26.50, 26.41, 28.88)
+q11            37.21  (37.26, 37.39, 36.99)
+q12           175.31  (125.98, 159.81, 240.13)

assets/spatial-bench-sf1_auto-results.txt

@@ -2,15 +2,15 @@ SpatialBench SF1  index mode: auto
 
 query        avg (s)  runs (s)
 ------------------------------
-q1              1.45  (1.86, 1.25, 1.24)
-q2              3.67  (3.86, 3.46, 3.69)
-q3              1.25  (1.25, 1.25, 1.24)
-q4             11.06  (11.33, 10.82, 11.03)
-q5              1.77  (1.79, 1.75, 1.76)
-q6              5.88  (5.80, 5.81, 6.03)
-q7              2.19  (2.18, 2.21, 2.19)
-q8              1.07  (1.07, 1.07, 1.07)
-q9              0.25  (0.23, 0.25, 0.26)
-q10            11.86  (11.76, 11.99, 11.82)
-q11            12.95  (12.68, 12.96, 13.22)
-q12            12.19  (14.45, 11.16, 10.94)
+q1              1.39  (1.84, 1.16, 1.16)
+q2              3.74  (3.78, 3.60, 3.82)
+q3              1.23  (1.29, 1.21, 1.20)
+q4              7.44  (7.59, 7.54, 7.20)
+q5              1.71  (1.75, 1.67, 1.73)
+q6              5.51  (5.68, 5.59, 5.27)
+q7              2.15  (2.15, 2.11, 2.19)
+q8              1.04  (1.05, 1.03, 1.04)
+q9              0.23  (0.23, 0.23, 0.22)
+q10             8.65  (8.59, 8.60, 8.77)
+q11             9.90  (9.75, 10.35, 9.61)
+q12            14.86  (13.87, 16.43, 14.28)

assets/spatialbench_sf10_auto.png

@@ -33,11 +33,8 @@
 _RUNS = 3
 _BOX_SIDE = 0.1
 
-# Floor for measured constants
-_MIN_NS = 0.1
-
-# Default destination for the written report
-_OUTPUT_PATH = Path(__file__).resolve().parents[2] / "assets" / "ops.txt"
+_MIN_NS = 0.1  # floor for measured constants
+_OUTPUT_PATH = Path(__file__).resolve().parents[2] / "assets" / "ops.txt"  # written report
 
 _SCAN_FIELDS = ["knn_scan_ns_per_item", "bbox_scan_ns_per_item"]
 _POINT_FIELDS = [

assets/spatialbench_sf1_auto.png

@@ -1,6 +1,5 @@
-"""Launch an ephemeral EC2 box that runs SpatialBench, then fetch the comparison chart.
-
-Reads config.yaml, launches an m7i.2xlarge, measures PyCanopy against published baselines, and downloads the result PNG.
+"""
+Launch an ephemeral EC2 box that runs SpatialBench, then fetch the comparison chart.
 """
 
 from __future__ import annotations

bench/ops/__main__.py

@@ -1,6 +1,5 @@
-"""On-box entry point: measure PyCanopy on SpatialBench and render the chart.
-
-Called by bootstrap.sh after building PyCanopy on the EC2 box.
+"""
+On-box entry point: measure PyCanopy on SpatialBench and render the chart.
 """
 
 from __future__ import annotations

bench/spatial_bench/__main__.py

@@ -1,7 +1,6 @@
-"""Profile path for SpatialBench: per-stage time + sampled memory plus oracle verification.
-
-ProfilingTables wraps only fetch / build so query modules stay unchanged. It is entered
-only by `_runner --profile` and run_profile_suite."""
+"""
+Profile path for SpatialBench: per-stage time + sampled memory plus oracle verification.
+"""
 
 from __future__ import annotations
 
@@ -20,10 +19,8 @@
     spawn_query,
 )
 
-# Coarse stages the harness can attribute without touching query or Rust code
-_STAGES = ("fetch", "build", "query", "collect")
-# How often the background thread samples resident memory, in seconds
-_SAMPLE_INTERVAL = 0.02
+_STAGES = ("fetch", "build", "query", "collect")  # coarse stages the harness can attribute
+_SAMPLE_INTERVAL = 0.02  # how often the background thread samples resident memory, in seconds
 _PAGE_SIZE = os.sysconf("SC_PAGE_SIZE") if hasattr(os, "sysconf") else 4096
 _MIB = 1024 * 1024
 _SEP = "=" * 64

bench/spatial_bench/_onbox.py

@@ -1,4 +1,6 @@
-"""Subprocess entry point: runs one SpatialBench query in an isolated interpreter."""
+"""
+Subprocess entry point: runs one SpatialBench query in an isolated interpreter.
+"""
 
 from __future__ import annotations