masster 0.5.23__py3-none-any.whl → 0.5.25__py3-none-any.whl

masster/_version.py

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

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/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/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.dist-info → masster-0.5.25.dist-info}/METADATA

@@ -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.dist-info → masster-0.5.25.dist-info}/RECORD

@@ -1,5 +1,5 @@
 masster/__init__.py,sha256=B7zftzdElF2Wb5B7KvkD6TONnMIY-Jxeen3s49dgmzs,1029
-masster/_version.py,sha256=AAUbq19nHieC5cNn0e7AMQbQcm3CFM5qt-dNA9Bc6e0,257
+masster/_version.py,sha256=1ymsIuIjSvggBFAIWxPqWntiqdxjPZEjAmDJy3vRsLE,257
 masster/chromatogram.py,sha256=iYpdv8C17zVnlWvOFgAn9ns2uFGiF-GgoYf5QVVAbHs,19319
 masster/logger.py,sha256=oHEFPH1LzBHbmeP9WFaRZCWyqd14GasJjZMLI8a4O3I,19439
 masster/spectrum.py,sha256=LlmxrI5MFS3aPrGSdqUSKVY0rJnKeBh3Frdh6a4dPvA,49722
@@ -35,8 +35,8 @@ masster/sample/defaults/get_spectrum_def.py,sha256=o62p31PhGd-LiIkTOzKQhwPtnO2At
 masster/sample/defaults/sample_def.py,sha256=MWWeEexGG2Ahbs-id4uq2doIgH-Ja96GioXaSl2CxN8,15449
 masster/study/__init__.py,sha256=55axdFuqRX4aXtJ8ocnhcLB32fNtmmJpCi58moO0r4g,237
 masster/study/analysis.py,sha256=bf2o_ywvwdPz1mZAHPETCPjWbvhoL9eEl1rLaz46Rp4,82032
-masster/study/export.py,sha256=63xP7pPBNsrAKWZP6XnqAyWO4lEfqtqKfO0SafNvzyg,58871
-masster/study/h5.py,sha256=XZDhMNGEt8D5ueyDEFfzhcpSduux8CfWGZK6AcDA5kk,97447
+masster/study/export.py,sha256=oRgM4F4hL3-nBRr_xd4KTin8WoH8QqCJnz3K_S1M14E,60258
+masster/study/h5.py,sha256=gJRWNQxBTyFKD3qRmEbM24YZ-HdyUk-veYgwQbK0eoE,99104
 masster/study/helpers.py,sha256=pRcVvGmm6NX-GEvWfYZXZjGc_C0WyklqSQx1PdpYn2E,189694
 masster/study/id.py,sha256=dTMNdBE7eOQZdFSU0KZwd7vFpqOmNlQnLI0VGW98y8w,89570
 masster/study/importers.py,sha256=iOe9w6uEn39ShosRms8n_zIrsSBczb51CAMoMrxSUw4,13587
@@ -60,9 +60,9 @@ masster/study/defaults/integrate_def.py,sha256=Vf4SAzdBfnsSZ3IRaF0qZvWu3gMDPHdgP
 masster/study/defaults/merge_def.py,sha256=99TJtIk7mSoq8NMJMJ4b-cy7gUUixQN69krxttBnkfA,12899
 masster/study/defaults/study_def.py,sha256=xXOAcb8hez0woWwA1_T3fcokjiLJkq3hwA3OS6elb6I,15965
 masster/wizard/__init__.py,sha256=L9G_datyGSFJjrBVklEVpZVLGXzUhDiWobtiygBH8vQ,669
-masster/wizard/wizard.py,sha256=9lGqslH5OTwktS_nnP-Nymh74kyRlYUpdnhmfhKBXBU,66497
-masster-0.5.23.dist-info/METADATA,sha256=4Ilme9EZdtcP_0UvMKczmzMgbyw-JRT9ACtGy5hcSlw,45970
-masster-0.5.23.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-masster-0.5.23.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
-masster-0.5.23.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-masster-0.5.23.dist-info/RECORD,,
+masster/wizard/wizard.py,sha256=11utDrZSt7R8D16Sl-NbRKHcgzhQEu8gW_q2V02-Qi0,66483
+masster-0.5.25.dist-info/METADATA,sha256=cs-J_TOWWtYmlrTJPL_XVSLg9iyxNYdGd24C1mE4wIo,45933
+masster-0.5.25.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+masster-0.5.25.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
+masster-0.5.25.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+masster-0.5.25.dist-info/RECORD,,