masster 0.5.23__tar.gz → 0.5.25__tar.gz

{masster-0.5.23 → masster-0.5.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.23
+Version: 0.5.25
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster
@@ -684,7 +684,6 @@ Requires-Dist: alpharaw>=0.4.8
 Requires-Dist: bokeh>=3.7.3
 Requires-Dist: cmap>=0.6.2
 Requires-Dist: datashader>=0.18.1
-Requires-Dist: get-gecko-driver>=1.4
 Requires-Dist: h5py>=3.14.0
 Requires-Dist: hdbscan>=0.8.40
 Requires-Dist: holoviews>=1.21.0

{masster-0.5.23 → masster-0.5.25}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.23"
+version = "0.5.25"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }
@@ -47,7 +47,6 @@ dependencies = [
     "scikit-learn>=1.7.1",
     "umap-learn>=0.5.9.post2",
     "hdbscan>=0.8.40",
-    "get-gecko-driver>=1.4",
     "webdriver-manager>=4.0.2",
 ]
 

{masster-0.5.23 → masster-0.5.25}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.23"
+__version__ = "0.5.25"
 
 
 def get_version():

{masster-0.5.23 → masster-0.5.25}/src/masster/study/export.py

@@ -1305,10 +1305,34 @@ def export_parquet(self, filename: str | None = None) -> None:
     if self.consensus_df is not None and not self.consensus_df.is_empty():
         consensus_file = f"{filename}_consensus.parquet"
         try:
-            self.consensus_df.write_parquet(consensus_file)
+            # Create a copy of consensus_df for parquet export
+            consensus_export_df = self.consensus_df.clone()
+            
+            # Handle Object dtype columns that can't be serialized to parquet
+            for col in consensus_export_df.columns:
+                if consensus_export_df[col].dtype == pl.Object:
+                    if col == "iso":
+                        # Convert numpy arrays to string representation for parquet compatibility
+                        # This preserves the data while making it parquet-serializable
+                        consensus_export_df = consensus_export_df.with_columns([
+                            pl.col("iso").map_elements(
+                                lambda x: str(x.tolist()) if x is not None else None,
+                                return_dtype=pl.String
+                            ).alias("iso")
+                        ])
+                    else:
+                        # For other Object columns, convert to string representation
+                        consensus_export_df = consensus_export_df.with_columns([
+                            pl.col(col).map_elements(
+                                lambda x: str(x) if x is not None else None,
+                                return_dtype=pl.String
+                            ).alias(col)
+                        ])
+            
+            consensus_export_df.write_parquet(consensus_file)
             exported_files.append(consensus_file)
             self.logger.debug(
-                f"Exported consensus to {consensus_file} ({self.consensus_df.height} rows)",
+                f"Exported consensus to {consensus_file} ({consensus_export_df.height} rows)",
             )
         except Exception as e:
             self.logger.error(f"Error writing consensus parquet file: {e}")

{masster-0.5.23 → masster-0.5.25}/src/masster/study/h5.py

@@ -717,11 +717,33 @@ def _reconstruct_object_column(data_col, col_name: str):
                 # Handle isotope patterns (numpy arrays with [mz, intensity] data)
                 try:
                     import numpy as np
-
-                    iso_data = json.loads(item)
-                    # Convert back to numpy array
-                    reconstructed_data.append(np.array(iso_data) if iso_data else None)
-                except (json.JSONDecodeError, ValueError, ImportError):
+                    
+                    # Try JSON parsing first (new format)
+                    try:
+                        iso_data = json.loads(item)
+                        # Convert back to numpy array
+                        reconstructed_data.append(np.array(iso_data) if iso_data else None)
+                    except json.JSONDecodeError:
+                        # Handle numpy array string representation (old format)
+                        # This handles strings like "[[   875.7865 447675.    ]\n [   876.7902 168819.    ]]"
+                        try:
+                            # Use numpy's string representation parser
+                            iso_array = np.fromstring(item.replace('[', '').replace(']', '').replace('\n', ' '), sep=' ')
+                            # Reshape to 2D array (pairs of mz, intensity)
+                            if len(iso_array) % 2 == 0:
+                                iso_array = iso_array.reshape(-1, 2)
+                                reconstructed_data.append(iso_array)
+                            else:
+                                reconstructed_data.append(None)
+                        except (ValueError, AttributeError):
+                            # If all else fails, try to evaluate the string as a literal
+                            try:
+                                import ast
+                                iso_data = ast.literal_eval(item)
+                                reconstructed_data.append(np.array(iso_data) if iso_data else None)
+                            except (ValueError, SyntaxError):
+                                reconstructed_data.append(None)
+                except (ValueError, ImportError):
                     reconstructed_data.append(None)
             elif col_name == "ms1_spec":
                 # Handle MS1 spectra patterns (numpy arrays with [mz, intensity] data)
@@ -1952,10 +1974,15 @@ def _load_study5(self, filename=None):
                 f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus",
             )
             if "consensus" in f and len(f["consensus"].keys()) > 0:
-                # Only include adducts in object_columns if it actually exists in the file
+                # Only include object columns if they actually exist in the file
                 object_columns = []
-                if "adducts" in f["consensus"]:
-                    object_columns.append("adducts")
+                try:
+                    if "adducts" in f["consensus"]:
+                        object_columns.append("adducts")
+                    if "iso" in f["consensus"]:
+                        object_columns.append("iso")
+                except (KeyError, TypeError):
+                    pass
 
                 self.consensus_df = _load_dataframe_from_group(
                     f["consensus"],

{masster-0.5.23 → masster-0.5.25}/src/masster/wizard/wizard.py

@@ -526,7 +526,7 @@ class Wizard:
             "    # === Processing Parameters ===",
             f'    "adducts": {self.params.adducts!r},  # Adduct specifications for feature detection and annotation',
             f'    "noise": {noise},  # Noise threshold for feature detection',
-            f'    "chrom_fwhm": {self.params.chrom_fwhm},  # Chromatographic peak full width at half maximum (seconds)',
+            f'    "chrom_fwhm": {chrom_fwhm},  # Chromatographic peak full width at half maximum (seconds)',
             f'    "chrom_peak_snr": {self.params.chrom_peak_snr},  # Minimum signal-to-noise ratio for chromatographic peaks',
             "",
             "    # === Alignment & Merging ===",
@@ -1267,7 +1267,7 @@ class Wizard:
             "        )",
             "        sample.find_adducts(adducts=PARAMS['adducts'])",
             "        sample.find_ms2()",
-            "        # sample.find_iso()",
+            "        sample.find_iso()",
             "        # sample.export_mgf()",
             "        # sample.export_mztab()",
             '        # sample.plot_2d(filename="{sample_name}.html")',

{masster-0.5.23 → masster-0.5.25}/uv.lock

@@ -147,18 +147,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/48/ca/ba5f909b40ea12ec542d5d7bdd13ee31c4d65f3beed20211ef81c18fa1f3/bandit-1.8.6-py3-none-any.whl", hash = "sha256:3348e934d736fcdb68b6aa4030487097e23a501adf3e7827b63658df464dddd0", size = 133808, upload-time = "2025-07-06T03:10:49.134Z" },
 ]
 
-[[package]]
-name = "beautifulsoup4"
-version = "4.12.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "soupsieve" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/b3/ca/824b1195773ce6166d388573fc106ce56d4a805bd7427b624e063596ec58/beautifulsoup4-4.12.3.tar.gz", hash = "sha256:74e3d1928edc070d21748185c46e3fb33490f22f52a3addee9aee0f4f7781051", size = 581181, upload-time = "2024-01-17T16:53:17.902Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/b1/fe/e8c672695b37eecc5cbf43e1d0638d88d66ba3a44c4d321c796f4e59167f/beautifulsoup4-4.12.3-py3-none-any.whl", hash = "sha256:b80878c9f40111313e55da8ba20bdba06d8fa3969fc68304167741bbf9e082ed", size = 147925, upload-time = "2024-01-17T16:53:12.779Z" },
-]
-
 [[package]]
 name = "biopython"
 version = "1.85"
@@ -848,21 +836,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/93/0dd45cd283c32dea1545151d8c3637b4b8c53cdb3a625aeb2885b184d74d/fonttools-4.60.1-py3-none-any.whl", hash = "sha256:906306ac7afe2156fcf0042173d6ebbb05416af70f6b370967b47f8f00103bbb", size = 1143175, upload-time = "2025-09-29T21:13:24.134Z" },
 ]
 
-[[package]]
-name = "get-gecko-driver"
-version = "1.4"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "beautifulsoup4" },
-    { name = "requests" },
-    { name = "typer" },
-    { name = "urllib3" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/94/81/79dc8fce839822b53852ef543c529e170593fc42874162dfe2cd9bfb83a9/get_gecko_driver-1.4.tar.gz", hash = "sha256:0a023816dacb363200ae7546e7f75104cae5f22d7f2946cff600b13395c2c5aa", size = 10000, upload-time = "2025-01-24T02:23:28.734Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/5e/f8/2ffa13fd3c26feeec4caa44829e0ea585b95d5111f03d4523e71b15596bc/get_gecko_driver-1.4-py3-none-any.whl", hash = "sha256:67ee0528e85c842ca92b9a2052a39a8940d4196b82ec4b407dbed2a424674e76", size = 11151, upload-time = "2025-01-24T02:23:27.185Z" },
-]
-
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -1473,14 +1446,13 @@ wheels = [
 
 [[package]]
 name = "masster"
-version = "0.5.23"
+version = "0.5.25"
 source = { editable = "." }
 dependencies = [
     { name = "alpharaw" },
     { name = "bokeh" },
     { name = "cmap" },
     { name = "datashader" },
-    { name = "get-gecko-driver" },
     { name = "h5py" },
     { name = "hdbscan" },
     { name = "holoviews" },
@@ -1538,7 +1510,6 @@ requires-dist = [
     { name = "coverage", marker = "extra == 'test'", specifier = ">=7.0.0" },
     { name = "datashader", specifier = ">=0.18.1" },
     { name = "flake8", marker = "extra == 'dev'", specifier = ">=5.0.0" },
-    { name = "get-gecko-driver", specifier = ">=1.4" },
     { name = "h5py", specifier = ">=3.14.0" },
     { name = "hdbscan", specifier = ">=0.8.40" },
     { name = "holoviews", specifier = ">=1.21.0" },
@@ -3149,15 +3120,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c8/78/3565d011c61f5a43488987ee32b6f3f656e7f107ac2782dd57bdd7d91d9a/snowballstemmer-3.0.1-py3-none-any.whl", hash = "sha256:6cd7b3897da8d6c9ffb968a6781fa6532dce9c3618a4b127d920dab764a19064", size = 103274, upload-time = "2025-05-09T16:34:50.371Z" },
 ]
 
-[[package]]
-name = "soupsieve"
-version = "2.8"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/6d/e6/21ccce3262dd4889aa3332e5a119a3491a95e8f60939870a3a035aabac0d/soupsieve-2.8.tar.gz", hash = "sha256:e2dd4a40a628cb5f28f6d4b0db8800b8f581b65bb380b97de22ba5ca8d72572f", size = 103472, upload-time = "2025-08-27T15:39:51.78Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/14/a0/bb38d3b76b8cae341dad93a2dd83ab7462e6dbcdd84d43f54ee60a8dc167/soupsieve-2.8-py3-none-any.whl", hash = "sha256:0cc76456a30e20f5d7f2e14a98a4ae2ee4e5abdc7c5ea0aafe795f344bc7984c", size = 36679, upload-time = "2025-08-27T15:39:50.179Z" },
-]
-
 [[package]]
 name = "sphinx"
 version = "8.2.3"