core-lens 0.1.dev174__tar.gz → 0.1.dev175__tar.gz

{core_lens-0.1.dev174 → core_lens-0.1.dev175}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: core-lens
-Version: 0.1.dev174
+Version: 0.1.dev175
 Summary: Query, analyse, and visualise CoreStack's microwatershed and Earth science data through a clean, composable Python API.
 Project-URL: Homepage, https://github.com/ApoorvaKashyap/core-lens
 Project-URL: Issues, https://github.com/ApoorvaKashyap/core-lens/issues

{core_lens-0.1.dev174 → core_lens-0.1.dev175}/benchmarks/bench_view.py

@@ -2,7 +2,7 @@
 =======================================================
 Targets:
   - View.where()                attribute filter (Polars semi-join on static file)
-  - View.spatial_filter()       STRtree filter narrowing existing keys
+  - View.spatial_filter()       vectorized centroid test (or STRtree for area)
   - View.between()              time-filter dict construction (no I/O)
   - View.between(season=CURRENT)  current-season resolution
   - View.between(year=tuple)    year-range season filter

{core_lens-0.1.dev174 → core_lens-0.1.dev175}/src/core_lens/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.1.dev174'
-__version_tuple__ = version_tuple = (0, 1, 'dev174')
+__version__ = version = '0.1.dev175'
+__version_tuple__ = version_tuple = (0, 1, 'dev175')
 
 __commit_id__ = commit_id = None

{core_lens-0.1.dev174 → core_lens-0.1.dev175}/src/core_lens/base/namespaces/plot.py

@@ -731,31 +731,45 @@ class PlotNamespace:
             )
 
             entities = df.get_column(key_col).unique().to_list()
-            for i, entity in enumerate(entities):
-                row = df.filter(pl.col(key_col) == entity)
-
-                # Replace None with NaN for numeric columns to prevent Bokeh JS rendering crashes
-                source_data = {}
-                for c in hover_cols:
-                    if c in row.columns:
-                        lst = row.get_column(c).to_list()
-                        if row.schema[c].is_numeric():
-                            lst = [float("nan") if v is None else v for v in lst]
-                        source_data[c] = lst
-
-                source = ColumnDataSource(source_data)  # type: ignore[arg-type]
+
+            if len(entities) > 20:
+                # Fast path: single dataset, single colour, no legend
+                pdf = df.drop_nulls(subset=[x, y_col]).select(hover_cols).to_pandas()
+                source = ColumnDataSource(pdf)
                 fig.scatter(
                     x=x,
                     y=y_col,
                     source=source,
-                    color=_color_for(i),
-                    legend_label=str(entity),
+                    color=_color_for(0),
                     size=8,
                     alpha=0.7,
                 )
-            if fig.legend:
-                fig.legend.click_policy = "hide"
-                fig.add_layout(fig.legend[0], "right")
+            else:
+                for i, entity in enumerate(entities):
+                    row = df.filter(pl.col(key_col) == entity)
+
+                    # Replace None with NaN for numeric columns to prevent Bokeh JS rendering crashes
+                    source_data = {}
+                    for c in hover_cols:
+                        if c in row.columns:
+                            lst = row.get_column(c).to_list()
+                            if row.schema[c].is_numeric():
+                                lst = [float("nan") if v is None else v for v in lst]
+                            source_data[c] = lst
+
+                    source = ColumnDataSource(source_data)  # type: ignore[arg-type]
+                    fig.scatter(
+                        x=x,
+                        y=y_col,
+                        source=source,
+                        color=_color_for(i),
+                        legend_label=str(entity),
+                        size=8,
+                        alpha=0.7,
+                    )
+                if fig.legend:
+                    fig.legend.click_policy = "hide"
+                    fig.add_layout(fig.legend[0], "right")
             _apply_theme(fig, self.result, "Scatter Distribution")
             return fig
 

core_lens-0.1.dev174/parse_scalene.py

@@ -1,50 +0,0 @@
-import json
-import glob
-import os
-
-profiles = glob.glob('/home/akashyap54/workstation/Projects/benchmarks/profiles/*_profile.json')
-
-for profile in profiles:
-    name = os.path.basename(profile).replace('_profile.json', '')
-    try:
-        d = json.load(open(profile))
-    except Exception as e:
-        print(f"Error loading {name}: {e}")
-        continue
-    
-    print(f"\n# {name.upper()}")
-    print("-" * 40)
-    
-    line_stats = []
-    
-    for filename, f_data in d.get('files', {}).items():
-        short_filename = os.path.basename(filename)
-        for line_data in f_data.get('lines', []):
-            cpu_percent = line_data.get('n_cpu_percent_c', 0) + line_data.get('n_cpu_percent_python', 0)
-            malloc_mb = line_data.get('n_malloc_mb', 0)
-            peak_mb = line_data.get('n_peak_mb', 0)
-            line_str = line_data.get('line', '').strip()
-            lineno = line_data.get('lineno', 0)
-            
-            if cpu_percent > 0 or malloc_mb > 0 or peak_mb > 0:
-                line_stats.append({
-                    'file': short_filename,
-                    'lineno': lineno,
-                    'line': line_str[:60] + ('...' if len(line_str) > 60 else ''),
-                    'cpu': cpu_percent,
-                    'malloc_mb': malloc_mb,
-                    'peak_mb': peak_mb
-                })
-    
-    # Top 5 by CPU
-    print(f"Top 5 lines by CPU %:")
-    top_cpu = sorted(line_stats, key=lambda x: x['cpu'], reverse=True)[:5]
-    for x in top_cpu:
-        print(f"  {x['file']}:{x['lineno']} | CPU: {x['cpu']:.1f}% | Line: {x['line']}")
-        
-    # Top 5 by Malloc
-    print(f"\nTop 5 lines by Memory Allocation (MB):")
-    top_mem = sorted(line_stats, key=lambda x: x['malloc_mb'], reverse=True)[:5]
-    for x in top_mem:
-        if x['malloc_mb'] > 0:
-            print(f"  {x['file']}:{x['lineno']} | Malloc: {x['malloc_mb']:.1f} MB | Line: {x['line']}")