openms-insight 0.1.1__py3-none-any.whl → 0.1.2__py3-none-any.whl

openms_insight/preprocessing/filtering.py

@@ -8,6 +8,88 @@ import polars as pl
 import streamlit as st
 
 
+def optimize_for_transfer(df: pl.DataFrame) -> pl.DataFrame:
+    """
+    Optimize DataFrame types for efficient Arrow transfer to frontend.
+
+    This function downcasts numeric types to reduce Arrow payload size and
+    avoid BigInt overhead in JavaScript:
+    - Int64 → Int32 (if values fit): Avoids BigInt conversion in JS
+    - Float64 → Float32: Sufficient precision for visualization
+
+    Args:
+        df: Polars DataFrame to optimize
+
+    Returns:
+        DataFrame with optimized types
+    """
+    if len(df) == 0:
+        return df
+
+    casts = []
+
+    for col in df.columns:
+        dtype = df[col].dtype
+
+        # Downcast Int64 to Int32 to avoid BigInt in JavaScript
+        # JS safe integer is 2^53, but Int32 range is simpler and sufficient for most data
+        if dtype == pl.Int64:
+            # Get min/max in a single pass
+            stats = df.select([
+                pl.col(col).min().alias('min'),
+                pl.col(col).max().alias('max'),
+            ]).row(0)
+            col_min, col_max = stats
+
+            if col_min is not None and col_max is not None:
+                # Int32 range: -2,147,483,648 to 2,147,483,647
+                if col_min >= -2147483648 and col_max <= 2147483647:
+                    casts.append(pl.col(col).cast(pl.Int32))
+
+        # Downcast Float64 to Float32 (sufficient for display)
+        # Float32 has ~7 significant digits - enough for visualization
+        elif dtype == pl.Float64:
+            casts.append(pl.col(col).cast(pl.Float32))
+
+    if casts:
+        df = df.with_columns(casts)
+
+    return df
+
+
+def optimize_for_transfer_lazy(lf: pl.LazyFrame) -> pl.LazyFrame:
+    """
+    Optimize LazyFrame types for efficient Arrow transfer (streaming-safe).
+
+    Unlike optimize_for_transfer(), this only applies optimizations that don't
+    require knowing the data values, preserving the ability to stream via sink_parquet().
+
+    Currently applies:
+    - Float64 → Float32: Always safe, no bounds check needed
+
+    Int64 → Int32 is NOT applied here because it requires bounds checking.
+    Use optimize_for_transfer() on collected DataFrames for full optimization.
+
+    Args:
+        lf: Polars LazyFrame to optimize
+
+    Returns:
+        LazyFrame with Float64 columns cast to Float32
+    """
+    schema = lf.collect_schema()
+    casts = []
+
+    for col, dtype in zip(schema.names(), schema.dtypes()):
+        # Only Float64 → Float32 is safe without bounds checking
+        if dtype == pl.Float64:
+            casts.append(pl.col(col).cast(pl.Float32))
+
+    if casts:
+        lf = lf.with_columns(casts)
+
+    return lf
+
+
 def _make_cache_key(
     filters: Dict[str, str],
     state: Dict[str, Any],
@@ -133,6 +215,8 @@ def _filter_and_collect(
         data = data.filter(pl.col(column) == selected_value)
 
     # Collect to Polars DataFrame
+    # Note: Type optimization (Int64→Int32, Float64→Float32) is applied at cache
+    # creation time in base.py._save_to_cache(), so data is already optimized
     df_polars = data.collect()
 
     # Compute hash efficiently (no pickle)

{openms_insight-0.1.1.dist-info → openms_insight-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openms-insight
-Version: 0.1.1
+Version: 0.1.2
 Summary: Interactive visualization components for mass spectrometry data in Streamlit
 Project-URL: Homepage, https://github.com/t0mdavid-m/OpenMS-Insight
 Project-URL: Documentation, https://github.com/t0mdavid-m/OpenMS-Insight#readme

{openms_insight-0.1.1.dist-info → openms_insight-0.1.2.dist-info}/RECORD

@@ -1,28 +1,28 @@
 openms_insight/__init__.py,sha256=-QMPUfCk1DwwlQKW6NFSZodRz-r82R4rJPOiWDf_mwA,830
 openms_insight/components/__init__.py,sha256=aNy1E8ttqQiiA5Ka9sviRy17gQT8lfc_EHsl1v1o-UQ,177
-openms_insight/components/heatmap.py,sha256=7nkNqdogEj6vnm90FeiTOyDtcy_vlb-HydcgZjmwSd4,34612
+openms_insight/components/heatmap.py,sha256=VNlc3wgrzkujj0jmX4RN93yKhPPOvGXdo4YoyQ_elJs,36223
 openms_insight/components/lineplot.py,sha256=fcul7W2RZlTQBse6pDbTAS14_HE14gLDdsUZ-YLjgAQ,19948
 openms_insight/components/sequenceview.py,sha256=IPLyUiXTLYwdZ79B3pZDH1intUsjBIknTSLUQ2ftdD4,14359
 openms_insight/components/table.py,sha256=P2VIGcPf2iuVJ07rl1el_kTjUKBjlJ_PQeFQAO9sgbw,15361
 openms_insight/core/__init__.py,sha256=yKRgLfRm1CQm6ZGqQiyDwblzw2Qh3jw57U-ZSd63PYk,338
-openms_insight/core/base.py,sha256=IUtnLnoLz6yFRsyGrYaCRzmoh6Eq6dRdnpGj2owxnd4,15754
+openms_insight/core/base.py,sha256=fkxAM9KVvzD6T8Guk3AeFWkNK4jeDgM3MbYPbmma8mw,16364
 openms_insight/core/cache.py,sha256=3fnPDWjuWUnxazK2XflcUIeRZZPQ3N45kAKYu-xGBKw,1197
 openms_insight/core/registry.py,sha256=iBb9xWvgOisxjVX74wtCvqWO20eBW5xH-XcNcVuW-Dg,2107
 openms_insight/core/state.py,sha256=VhY_3Yg-zbx9VsdqHElsNyD2UbJj6ApE4TRcUywDrjQ,6871
 openms_insight/core/subprocess_preprocess.py,sha256=E08qEyVinwRM_PXq0bZk-lHJcYeDHmdr3ok4yTRC63I,3155
 openms_insight/preprocessing/__init__.py,sha256=XFnxlvG-VRMrFbreGmFSIDqfYhev8WPUyZluadMmCgY,462
 openms_insight/preprocessing/compression.py,sha256=8oe-vqeSX-Xf1okPX0C0km2DRnl6Iz53Y1UgsLdMUPI,10499
-openms_insight/preprocessing/filtering.py,sha256=DuVdi7tofZyWbGqdRXJy8G1OYptmf1zxnPgsSoYU_zw,10423
+openms_insight/preprocessing/filtering.py,sha256=ZG8P1RLzwJVGdhElXD6UOny0GFz-aNr0LesSKZPVJTA,13191
 openms_insight/rendering/__init__.py,sha256=i9MRFrAEAX5kjbOnMjw2woP_6mEaI6HcxtbrNwUxNaM,198
 openms_insight/rendering/bridge.py,sha256=cPZWMz07jKOcWkkL7FdCY8w1lNk8bME_1xuulCO3VgY,13146
 openms_insight/js-component/dist/index.html,sha256=LSJ3B_YmGUrCCdZ1UaZO2p6Wqsih6nTH62Z_0uZxpD8,430
 openms_insight/js-component/dist/assets/index.css,sha256=ACP0LGYUGQusvfDX9igw5DfoQr60P4IFgSqWhACY46A,884228
-openms_insight/js-component/dist/assets/index.js,sha256=DEqCo6eSi4pFuTafgsFg6imO1xe1g-Vx1KQsEAir3t4,6061023
+openms_insight/js-component/dist/assets/index.js,sha256=9fkS8XuO6U_3-qnGhjpeiLnkacKZ9eDUGTbWyNgHwTc,6061688
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.eot,sha256=CxgxBNL8XyYZbnc8d72vLgVQn9QlnS0V7O3Kebh-hPk,1307880
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.ttf,sha256=YeirpaTpgf4iz3yOi82-oAR251xiw38Bv37jM2HWhCg,1307660
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.woff,sha256=pZKKDVwvYk5G-Y2bFcL2AEU3f3xZTdeKF1kTLqO0Y-s,587984
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.woff2,sha256=Zi_vqPL4qVwYWI0hd0eJwQfGTnccvmWmmvRikcQxGvw,403216
-openms_insight-0.1.1.dist-info/METADATA,sha256=_PtgWhRmLvKT0VsXjT9b8vQ7ZkSomdHGeD4sDmaUq_s,7385
-openms_insight-0.1.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-openms_insight-0.1.1.dist-info/licenses/LICENSE,sha256=INFF4rOMmpah7Oi14hLqu7NTOsx56KRRNChAAUcfh2E,1823
-openms_insight-0.1.1.dist-info/RECORD,,
+openms_insight-0.1.2.dist-info/METADATA,sha256=PZwmhlJVjzVeI23Ow3axp28YYg_84VxxsH9FrkFuRmg,7385
+openms_insight-0.1.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+openms_insight-0.1.2.dist-info/licenses/LICENSE,sha256=INFF4rOMmpah7Oi14hLqu7NTOsx56KRRNChAAUcfh2E,1823
+openms_insight-0.1.2.dist-info/RECORD,,