masster 0.4.11__py3-none-any.whl → 0.4.12__py3-none-any.whl

masster/study/plot.py

@@ -679,19 +679,34 @@ def plot_consensus_2d(
             source=source,
         )
     # add hover tool
+    # Start with base tooltips
+    tooltips = [
+        ("consensus_uid", "@consensus_uid"),
+        ("consensus_id", "@consensus_id"),
+        ("number_samples", "@number_samples"),
+        ("number_ms2", "@number_ms2"),
+        ("rt", "@rt"),
+        ("mz", "@mz"),
+        ("inty_mean", "@inty_mean"),
+        ("iso_mean", "@iso_mean"),
+        ("coherence_mean", "@chrom_coherence_mean"),
+        ("prominence_scaled_mean", "@chrom_prominence_scaled_mean"),
+    ]
+    
+    # Add id_top_* columns if they exist and have non-null values
+    id_top_columns = ["id_top_name", "id_top_class", "id_top_adduct", "id_top_score"]
+    for col in id_top_columns:
+        if col in data.columns:
+            # Check if the column has any non-null values
+            if data.filter(pl.col(col).is_not_null()).height > 0:
+                # Format score column with decimal places, others as strings
+                if col == "id_top_score":
+                    tooltips.append((col.replace("id_top_", "id_"), f"@{col}{{0.0000}}"))
+                else:
+                    tooltips.append((col.replace("id_top_", "id_"), f"@{col}"))
+    
     hover = HoverTool(
-        tooltips=[
-            ("consensus_uid", "@consensus_uid"),
-            ("consensus_id", "@consensus_id"),
-            ("number_samples", "@number_samples"),
-            ("number_ms2", "@number_ms2"),
-            ("rt", "@rt"),
-            ("mz", "@mz"),
-            ("inty_mean", "@inty_mean"),
-            ("iso_mean", "@iso_mean"),
-            ("coherence_mean", "@chrom_coherence_mean"),
-            ("prominence_mean", "@chrom_prominence_mean"),
-        ],
+        tooltips=tooltips,
         renderers=[scatter_renderer],
     )
     p.add_tools(hover)
@@ -1898,7 +1913,7 @@ def plot_pca(
     alpha=0.8,
     markersize=6,
     n_components=2,
-    color_by=None,
+    colorby=None,
     title="PCA of Consensus Matrix",
 ):
     """
@@ -2001,25 +2016,25 @@ def plot_pca(
     color_column = None
     color_mapper = None
 
-    if color_by and color_by in pca_df.columns:
-        color_column = color_by
-        unique_values = pca_df[color_by].unique()
+    if colorby and colorby in pca_df.columns:
+        color_column = colorby
+        unique_values = pca_df[colorby].unique()
 
         # Handle categorical vs numeric coloring
-        if pca_df[color_by].dtype in ["object", "string", "category"]:
+        if pca_df[colorby].dtype in ["object", "string", "category"]:
             # Categorical coloring
             if len(unique_values) <= 20:
                 palette = Category20[min(20, max(3, len(unique_values)))]
             else:
                 palette = viridis(min(256, len(unique_values)))
-            color_mapper = factor_cmap(color_by, palette, unique_values)
+            color_mapper = factor_cmap(colorby, palette, unique_values)
         else:
             # Numeric coloring
             palette = viridis(256)
             color_mapper = LinearColorMapper(
                 palette=palette,
-                low=pca_df[color_by].min(),
-                high=pca_df[color_by].max(),
+                low=pca_df[colorby].min(),
+                high=pca_df[colorby].max(),
             )
 
     # Create Bokeh plot
@@ -2044,7 +2059,7 @@ def plot_pca(
                 "PC2",
                 size=markersize,
                 alpha=alpha,
-                color={"field": color_by, "transform": color_mapper},
+                color={"field": colorby, "transform": color_mapper},
                 source=source,
             )
             # Add colorbar for numeric coloring
@@ -2058,7 +2073,7 @@ def plot_pca(
                 alpha=alpha,
                 color=color_mapper,
                 source=source,
-                legend_field=color_by,
+                legend_field=colorby,
             )
     else:
         # If no color_by provided, use sample_color column from samples_df
@@ -2130,7 +2145,7 @@ def plot_pca(
     p.add_tools(hover)
 
     # Add legend if using categorical coloring
-    if color_mapper and not isinstance(color_mapper, LinearColorMapper) and color_by:
+    if color_mapper and not isinstance(color_mapper, LinearColorMapper) and colorby:
         # Only set legend properties if legends exist (avoid Bokeh warning when none created)
         if getattr(p, "legend", None) and len(p.legend) > 0:
             p.legend.location = "top_left"

masster/study/processing.py

@@ -829,6 +829,11 @@ def merge(self, **kwargs):
                 "adduct_mass_shift_top": round(adduct_mass_shift_top, 6)
                 if adduct_mass_shift_top is not None
                 else None,
+                # New columns for top-scoring identification results
+                "id_top_name": None,
+                "id_top_class": None,
+                "id_top_adduct": None,
+                "id_top_score": None,
             },
         )
 

masster/study/study.py

@@ -338,6 +338,7 @@ class Study:
 
         # Library DataFrame (populated by lib_load)
         self.lib_df = pl.DataFrame()
+
         # Identification results DataFrame (populated by identify)
         self.id_df = pl.DataFrame()
 
@@ -358,53 +359,44 @@ class Study:
         # cache for Sample instances created/loaded by this Study
         self._samples_cache = {}
 
-    # Attach module functions as class methods
+    # ===== ATTACH MODULE FUNCTIONS AS CLASS METHODS =====
+    
+    # === File I/O Operations ===
     load = load
     save = save
     save_consensus = save_consensus
     save_samples = save_samples
+    sanitize = sanitize
+    set_folder = set_folder
+    
+    # === Sample Management ===
+    add = add
+    add_folder = add  # backward compatibility alias
+    add_sample = add_sample
+    
+    # === Core Processing Operations ===
     align = align
-    fill_single = fill_single
-    fill_chrom_single = fill_single  # Backward compatibility alias
     merge = merge
     find_consensus = merge  # Backward compatibility alias
     find_ms2 = find_ms2
     integrate = integrate
     integrate_chrom = integrate  # Backward compatibility alias
-    store_history = store_history
-    get_parameters = get_parameters
-    update_parameters = update_parameters
-    get_parameters_property = get_parameters_property
-    set_parameters_property = set_parameters_property
-    plot_alignment = plot_alignment
-    plot_chrom = plot_chrom
-    plot_consensus_2d = plot_consensus_2d
-    plot_consensus_stats = plot_consensus_stats
-    plot_pca = plot_pca
-    plot_samples_2d = plot_samples_2d
-    plot_bpc = plot_bpc
-    plot_rt_correction = plot_rt_correction
-    plot_tic = plot_tic
-    plot_eic = plot_eic
+    fill = fill
+    fill_chrom = fill  # Backward compatibility alias
+    fill_single = fill_single
+    fill_chrom_single = fill_single  # Backward compatibility alias
+    
+    # === Data Retrieval and Access ===
     get_consensus = get_consensus
     get_chrom = get_chrom
     get_sample = get_sample
     get_consensus_matches = get_consensus_matches
-    compress = compress
-    compress_features = compress_features
-    compress_ms2 = compress_ms2
-    compress_chrom = compress_chrom
-    restore_features = restore_features
-    restore_chrom = restore_chrom
-    restore_ms2 = restore_ms2
-    decompress = decompress
-    fill_reset = fill_reset
-    align_reset = align_reset
-    set_source = set_source
-    sample_color = sample_color
-    sample_color_reset = sample_color_reset
-    name_replace = sample_name_replace
-    name_reset = sample_name_reset
+    get_consensus_matrix = get_consensus_matrix
+    get_gaps_matrix = get_gaps_matrix
+    get_gaps_stats = get_gaps_stats
+    get_orphans = get_orphans
+    
+    # === Data Selection and Filtering ===
     samples_select = samples_select
     samples_delete = samples_delete
     features_select = features_select
@@ -413,16 +405,67 @@ class Study:
     consensus_select = consensus_select
     consensus_filter = consensus_filter
     consensus_delete = consensus_delete
+    # Backward compatibility aliases
     filter_consensus = consensus_filter
     select_consensus = consensus_select
     filter_features = features_filter
     select_features = features_select
     consensus_find = merge
-    filter_features = features_filter
-
-    add_folder = add  # backward compatibility alias
-    add = add
-    add_sample = add_sample
+    
+    # === Sample Metadata and Styling ===
+    set_source = set_source
+    sample_color = sample_color
+    sample_color_reset = sample_color_reset
+    name_replace = sample_name_replace
+    name_reset = sample_name_reset
+    
+    # === Data Compression and Storage ===
+    compress = compress
+    compress_features = compress_features
+    compress_ms2 = compress_ms2
+    compress_chrom = compress_chrom
+    restore_features = restore_features
+    restore_chrom = restore_chrom
+    restore_ms2 = restore_ms2
+    decompress = decompress
+    
+    # === Reset Operations ===
+    fill_reset = fill_reset
+    align_reset = align_reset
+    
+    # === Plotting and Visualization ===
+    plot_alignment = plot_alignment
+    plot_chrom = plot_chrom
+    plot_consensus_2d = plot_consensus_2d
+    plot_consensus_stats = plot_consensus_stats
+    plot_pca = plot_pca
+    plot_samples_2d = plot_samples_2d
+    plot_bpc = plot_bpc
+    plot_rt_correction = plot_rt_correction
+    plot_tic = plot_tic
+    plot_eic = plot_eic
+    
+    # === Export Operations ===
+    export_mgf = export_mgf
+    export_mztab = export_mztab
+    export_xlsx = export_xlsx
+    export_parquet = export_parquet
+    
+    # === Identification and Library Matching ===
+    lib_load = lib_load
+    identify = identify
+    get_id = get_id
+    id_reset = id_reset
+    lib_reset = lib_reset
+    
+    # === Parameter Management ===
+    store_history = store_history
+    get_parameters = get_parameters
+    update_parameters = update_parameters
+    get_parameters_property = get_parameters_property
+    set_parameters_property = set_parameters_property
+    
+    # === Private/Internal Methods ===
     _add_samples_batch = _add_samples_batch
     _add_sample_optimized = _add_sample_optimized
     _add_sample_standard = _add_sample_standard
@@ -434,38 +477,20 @@ class Study:
     _get_feature_uids = _get_feature_uids
     _get_sample_uids = _get_sample_uids
     _ensure_features_df_schema_order = _ensure_features_df_schema_order
-    get_consensus_matrix = get_consensus_matrix
-    get_gaps_matrix = get_gaps_matrix
-    get_gaps_stats = get_gaps_stats
-    get_orphans = get_orphans
-    set_folder = set_folder
-    fill = fill
-    fill_chrom = fill  # Backward compatibility alias
     _process_sample_for_parallel_fill = _process_sample_for_parallel_fill
     _get_missing_consensus_sample_combinations = (
         _get_missing_consensus_sample_combinations
     )
     _load_consensusXML = _load_consensusXML
     load_features = load_features
-    sanitize = sanitize
     _save_consensusXML = _save_consensusXML
-    export_mgf = export_mgf
-    export_mztab = export_mztab
-    export_xlsx = export_xlsx
-    export_parquet = export_parquet
-    _get_mgf_df = _get_mgf_df  # New function for MGF data extraction
-    # Identification helpers
-    lib_load = lib_load
-    identify = identify
-    get_id = get_id
-    id_reset = id_reset
-    lib_reset = lib_reset
+    _get_mgf_df = _get_mgf_df
     _get_adducts = _get_adducts
     _calculate_formula_mass_shift = _calculate_formula_mass_shift
     _format_adduct_name = _format_adduct_name
     _parse_element_counts = _parse_element_counts
-
-    # defaults
+    
+    # === Default Parameters ===
     study_defaults = study_defaults
     align_defaults = align_defaults
     export_mgf_defaults = export_mgf_defaults
@@ -526,7 +551,17 @@ class Study:
             ):
                 sample_modules.append(module_name)
 
-        all_modules_to_reload = core_modules + sample_modules + study_modules
+        # Add lib submodules
+        lib_modules = []
+        lib_module_prefix = f"{base_modname}.lib."
+        for module_name in sys.modules:
+            if (
+                module_name.startswith(lib_module_prefix)
+                and module_name != current_module
+            ):
+                lib_modules.append(module_name)
+
+        all_modules_to_reload = core_modules + sample_modules + study_modules + lib_modules
 
         # Reload all discovered modules
         for full_module_name in all_modules_to_reload:

masster/study/study5_schema.json

@@ -99,6 +99,18 @@
       },
       "adduct_top": {
         "dtype": "pl.Utf8"
+      },
+      "id_top_name": {
+        "dtype": "pl.String"
+      },
+      "id_top_class": {
+        "dtype": "pl.String"
+      },
+      "id_top_adduct": {
+        "dtype": "pl.String"
+      },
+      "id_top_score": {
+        "dtype": "pl.Float64"
       }
     }
   },

{masster-0.4.11.dist-info → masster-0.4.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.4.11
+Version: 0.4.12
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.4.11.dist-info → masster-0.4.12.dist-info}/RECORD

@@ -1,5 +1,5 @@
 masster/__init__.py,sha256=8U4cIteNlYyHDrxWSbB_MsDKCX9tds07SJG8-vh8Oa8,738
-masster/_version.py,sha256=Ra822EfcCSSsug6aojKBn4P__-I2P5hLd9y2DnUcJqg,257
+masster/_version.py,sha256=x0uMqls6EQCEi4k0gtRCy4mKPHH34Z_XjD04eht65oU,257
 masster/chromatogram.py,sha256=iYpdv8C17zVnlWvOFgAn9ns2uFGiF-GgoYf5QVVAbHs,19319
 masster/logger.py,sha256=W50V_uh8RSYwGxDrDFhOuj5jpu2tKJyt_16lMw9kQwA,14755
 masster/spectrum.py,sha256=_upC_g2N9gwTaflXAugs9pSXpKUmzbIehofDordk7WI,47718
@@ -15,7 +15,7 @@ masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecR
 masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.wiff.scan,sha256=ahi1Y3UhAj9Bj4Q2MlbgPekNdkJvMOoMXVOoR6CeIxc,13881220
 masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.wiff2,sha256=TFB0HW4Agkig6yht7FtgjUdbXax8jjKaHpSZSvuU5vs,3252224
 masster/lib/__init__.py,sha256=TcePNx3SYZHz6763TL9Sg4gUNXaRWjlrOtyS6vsu-hg,178
-masster/lib/lib.py,sha256=seAOqzat74iF6YnbNakU3rF5MN5t9WABIpcIPTvU1q8,24987
+masster/lib/lib.py,sha256=mxUYBCBmkSBZB82557smSHCS25BAusuCewvW8zwsLGg,27130
 masster/sample/__init__.py,sha256=HL0m1ept0PMAYUCQtDDnkdOS12IFl6oLAq4TZQz83uY,170
 masster/sample/adducts.py,sha256=jdtkkiMFeObRv3myluUx--IfpRsEq3-hPgkCb2VUxy4,32590
 masster/sample/h5.py,sha256=7NJeErlIHwC2Qh3nchusLZJWjBGue9zExAx08C89qhg,111889
@@ -39,15 +39,15 @@ masster/sample/defaults/sample_def.py,sha256=keoXyMyrm_iLgbYqfIbqCpJ3XHBVlNwCNmb
 masster/study/__init__.py,sha256=Zspv6U8jFqjkHGYdNdDy1rfUnCSolCzUdgSSg98PRgE,166
 masster/study/export.py,sha256=L-YOUGSgVeTprYnrQxaN0qC8MRqUdDQ0D4o2h7HLi2Q,54813
 masster/study/h5.py,sha256=Sbde1cxAAIq0EjNiTxQgJgHHVKFw29q510YBJRa_egw,83691
-masster/study/helpers.py,sha256=TS1x9sMlcUPhEqGcPgDnzd84XqbUkJkf770iAUcI8RQ,160278
-masster/study/id.py,sha256=EOw-2dM8nnx8QcQF1qAFfGqql75JusONuDBjmAuMU2w,44723
+masster/study/helpers.py,sha256=M5_q8O5tuFchKPW04PTuj3X335lDA2VZqcs4D8ZQJEk,158604
+masster/study/id.py,sha256=V2R2L3NtiPvl1STDOonBbYGtHikeN0VGH78ruUNhgNE,55263
 masster/study/load.py,sha256=tK3ueWxrauyveZukyh1YaV8h8fSFDytLnTmrEpFvcwU,70458
 masster/study/parameters.py,sha256=0elaF7YspTsB7qyajWAbRNL2VfKlGz5GJLifmO8IGkk,3276
-masster/study/plot.py,sha256=c_VxZxupGi7UYx2r4b2XR-SWRefLuo8s8zbIoVg0PgE,86876
-masster/study/processing.py,sha256=JlIstxo9mdqudl30yI-Wd-Ru9AfAeiwBPmqaW-dTl54,73867
+masster/study/plot.py,sha256=Wp48DH5x1t8w6R67AMjxLaUIKZpDa82fnUoAgEeNY5E,87564
+masster/study/processing.py,sha256=Mzm0ronIAvI2at9x-4t9X_PYeyYdLRsF9hQYzWeAlcs,74093
 masster/study/save.py,sha256=F_H34zmvxV54Ds64ju90JJLy_F4hg6nRdHhJ9ssWKLA,6704
-masster/study/study.py,sha256=k097_YaYykhtkI6Ykcr5QCcFvo1eBLWXWLKycrid51w,34846
-masster/study/study5_schema.json,sha256=vZIaGfcPJmhy_6pDEweKF7nEYrHwmV4_uxbGLcYfK30,7246
+masster/study/study.py,sha256=ILKZBbLrno0vPbaLLUwhROIyAk0w9l2k9PxSqeTyR3E,35761
+masster/study/study5_schema.json,sha256=c0w24QdHak01m04I1VPu97KvF2468FcaqROhf6pmLk4,7507
 masster/study/defaults/__init__.py,sha256=m3Z5KXGqsTdh7GjYzZoENERt39yRg0ceVRV1DeCt1P0,610
 masster/study/defaults/align_def.py,sha256=hHQbGgsOqMRHHr0Wn8Onr8XeaRz3-fFE0qGE-OMst80,20324
 masster/study/defaults/export_def.py,sha256=eXl3h4aoLX88XkHTpqahLd-QZ2gjUqrmjq8IJULXeWo,1203
@@ -60,8 +60,8 @@ masster/study/defaults/integrate_chrom_def.py,sha256=0MNIWGTjty-Zu-NTQsIweuj3UVq
 masster/study/defaults/integrate_def.py,sha256=Vf4SAzdBfnsSZ3IRaF0qZvWu3gMDPHdgPfMYoPKeWv8,7246
 masster/study/defaults/merge_def.py,sha256=EBsKE3hsAkTEzN9dpdRD5W3_suTKy_WZ_96rwS0uBuE,8572
 masster/study/defaults/study_def.py,sha256=h8dYbi9xv0sesCSQik49Z53IkskMmNtW6ixl7it5pL0,16033
-masster-0.4.11.dist-info/METADATA,sha256=d-0v4eIqBo_LJNbnSN-6FncgNRMX_a1enOjueLtPGTs,44189
-masster-0.4.11.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-masster-0.4.11.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
-masster-0.4.11.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-masster-0.4.11.dist-info/RECORD,,
+masster-0.4.12.dist-info/METADATA,sha256=yUxDZ2otabugBoNIjjFvBF4W8x07alJeeMaM5DZJUdU,44189
+masster-0.4.12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+masster-0.4.12.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
+masster-0.4.12.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+masster-0.4.12.dist-info/RECORD,,