masster 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (54) hide show
  1. masster/__init__.py +8 -8
  2. masster/_version.py +1 -1
  3. masster/chromatogram.py +3 -9
  4. masster/data/libs/README.md +1 -1
  5. masster/data/libs/ccm.csv +120 -120
  6. masster/data/libs/ccm.py +116 -62
  7. masster/data/libs/central_carbon_README.md +1 -1
  8. masster/data/libs/urine.py +161 -65
  9. masster/data/libs/urine_metabolites.csv +4693 -4693
  10. masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.mzML +2 -2
  11. masster/logger.py +43 -78
  12. masster/sample/__init__.py +1 -1
  13. masster/sample/adducts.py +264 -338
  14. masster/sample/defaults/find_adducts_def.py +8 -21
  15. masster/sample/defaults/find_features_def.py +1 -6
  16. masster/sample/defaults/get_spectrum_def.py +1 -5
  17. masster/sample/defaults/sample_def.py +1 -5
  18. masster/sample/h5.py +282 -561
  19. masster/sample/helpers.py +75 -131
  20. masster/sample/lib.py +17 -42
  21. masster/sample/load.py +17 -31
  22. masster/sample/parameters.py +2 -6
  23. masster/sample/plot.py +27 -88
  24. masster/sample/processing.py +87 -117
  25. masster/sample/quant.py +51 -57
  26. masster/sample/sample.py +90 -103
  27. masster/sample/sample5_schema.json +44 -44
  28. masster/sample/save.py +12 -35
  29. masster/sample/sciex.py +19 -66
  30. masster/spectrum.py +20 -58
  31. masster/study/__init__.py +1 -1
  32. masster/study/defaults/align_def.py +1 -5
  33. masster/study/defaults/fill_chrom_def.py +1 -5
  34. masster/study/defaults/fill_def.py +1 -5
  35. masster/study/defaults/integrate_chrom_def.py +1 -5
  36. masster/study/defaults/integrate_def.py +1 -5
  37. masster/study/defaults/study_def.py +25 -58
  38. masster/study/export.py +207 -233
  39. masster/study/h5.py +136 -470
  40. masster/study/helpers.py +202 -495
  41. masster/study/helpers_optimized.py +13 -40
  42. masster/study/id.py +110 -213
  43. masster/study/load.py +143 -230
  44. masster/study/plot.py +257 -518
  45. masster/study/processing.py +257 -469
  46. masster/study/save.py +5 -15
  47. masster/study/study.py +276 -379
  48. masster/study/study5_schema.json +96 -96
  49. {masster-0.4.0.dist-info → masster-0.4.1.dist-info}/METADATA +1 -1
  50. masster-0.4.1.dist-info/RECORD +67 -0
  51. masster-0.4.0.dist-info/RECORD +0 -67
  52. {masster-0.4.0.dist-info → masster-0.4.1.dist-info}/WHEEL +0 -0
  53. {masster-0.4.0.dist-info → masster-0.4.1.dist-info}/entry_points.txt +0 -0
  54. {masster-0.4.0.dist-info → masster-0.4.1.dist-info}/licenses/LICENSE +0 -0
masster/study/helpers_optimized.py CHANGED
@@ -92,9 +92,7 @@ def features_select_optimized(
92
92
  if mz is not None:
93
93
  if isinstance(mz, tuple) and len(mz) == 2:
94
94
  min_mz, max_mz = mz
95
- filter_conditions.append(
96
- (pl.col("mz") >= min_mz) & (pl.col("mz") <= max_mz),
97
- )
95
+ filter_conditions.append((pl.col("mz") >= min_mz) & (pl.col("mz") <= max_mz))
98
96
  else:
99
97
  filter_conditions.append(pl.col("mz") >= mz)
100
98
 
@@ -102,9 +100,7 @@ def features_select_optimized(
102
100
  if rt is not None:
103
101
  if isinstance(rt, tuple) and len(rt) == 2:
104
102
  min_rt, max_rt = rt
105
- filter_conditions.append(
106
- (pl.col("rt") >= min_rt) & (pl.col("rt") <= max_rt),
107
- )
103
+ filter_conditions.append((pl.col("rt") >= min_rt) & (pl.col("rt") <= max_rt))
108
104
  else:
109
105
  filter_conditions.append(pl.col("rt") >= rt)
110
106
 
@@ -112,9 +108,7 @@ def features_select_optimized(
112
108
  if inty is not None:
113
109
  if isinstance(inty, tuple) and len(inty) == 2:
114
110
  min_inty, max_inty = inty
115
- filter_conditions.append(
116
- (pl.col("inty") >= min_inty) & (pl.col("inty") <= max_inty),
117
- )
111
+ filter_conditions.append((pl.col("inty") >= min_inty) & (pl.col("inty") <= max_inty))
118
112
  else:
119
113
  filter_conditions.append(pl.col("inty") >= inty)
120
114
 
@@ -124,10 +118,7 @@ def features_select_optimized(
124
118
  if len(sample_uid) == 2 and not isinstance(sample_uid, list):
125
119
  # Treat as range
126
120
  min_uid, max_uid = sample_uid
127
- filter_conditions.append(
128
- (pl.col("sample_uid") >= min_uid)
129
- & (pl.col("sample_uid") <= max_uid),
130
- )
121
+ filter_conditions.append((pl.col("sample_uid") >= min_uid) & (pl.col("sample_uid") <= max_uid))
131
122
  else:
132
123
  # Treat as list
133
124
  filter_conditions.append(pl.col("sample_uid").is_in(sample_uid))
@@ -157,10 +148,7 @@ def features_select_optimized(
157
148
  if len(consensus_uid) == 2 and not isinstance(consensus_uid, list):
158
149
  # Treat as range
159
150
  min_uid, max_uid = consensus_uid
160
- filter_conditions.append(
161
- (pl.col("consensus_uid") >= min_uid)
162
- & (pl.col("consensus_uid") <= max_uid),
163
- )
151
+ filter_conditions.append((pl.col("consensus_uid") >= min_uid) & (pl.col("consensus_uid") <= max_uid))
164
152
  else:
165
153
  # Treat as list
166
154
  filter_conditions.append(pl.col("consensus_uid").is_in(consensus_uid))
@@ -173,10 +161,7 @@ def features_select_optimized(
173
161
  if len(feature_uid) == 2 and not isinstance(feature_uid, list):
174
162
  # Treat as range
175
163
  min_uid, max_uid = feature_uid
176
- filter_conditions.append(
177
- (pl.col("feature_uid") >= min_uid)
178
- & (pl.col("feature_uid") <= max_uid),
179
- )
164
+ filter_conditions.append((pl.col("feature_uid") >= min_uid) & (pl.col("feature_uid") <= max_uid))
180
165
  else:
181
166
  # Treat as list
182
167
  filter_conditions.append(pl.col("feature_uid").is_in(feature_uid))
@@ -198,10 +183,7 @@ def features_select_optimized(
198
183
  if "quality" in available_columns:
199
184
  if isinstance(quality, tuple) and len(quality) == 2:
200
185
  min_quality, max_quality = quality
201
- filter_conditions.append(
202
- (pl.col("quality") >= min_quality)
203
- & (pl.col("quality") <= max_quality),
204
- )
186
+ filter_conditions.append((pl.col("quality") >= min_quality) & (pl.col("quality") <= max_quality))
205
187
  else:
206
188
  filter_conditions.append(pl.col("quality") >= quality)
207
189
  else:
@@ -213,8 +195,7 @@ def features_select_optimized(
213
195
  if isinstance(chrom_coherence, tuple) and len(chrom_coherence) == 2:
214
196
  min_coherence, max_coherence = chrom_coherence
215
197
  filter_conditions.append(
216
- (pl.col("chrom_coherence") >= min_coherence)
217
- & (pl.col("chrom_coherence") <= max_coherence),
198
+ (pl.col("chrom_coherence") >= min_coherence) & (pl.col("chrom_coherence") <= max_coherence),
218
199
  )
219
200
  else:
220
201
  filter_conditions.append(pl.col("chrom_coherence") >= chrom_coherence)
@@ -227,8 +208,7 @@ def features_select_optimized(
227
208
  if isinstance(chrom_prominence, tuple) and len(chrom_prominence) == 2:
228
209
  min_prominence, max_prominence = chrom_prominence
229
210
  filter_conditions.append(
230
- (pl.col("chrom_prominence") >= min_prominence)
231
- & (pl.col("chrom_prominence") <= max_prominence),
211
+ (pl.col("chrom_prominence") >= min_prominence) & (pl.col("chrom_prominence") <= max_prominence),
232
212
  )
233
213
  else:
234
214
  filter_conditions.append(pl.col("chrom_prominence") >= chrom_prominence)
@@ -238,19 +218,14 @@ def features_select_optimized(
238
218
  # Filter by scaled chromatogram prominence
239
219
  if chrom_prominence_scaled is not None:
240
220
  if "chrom_prominence_scaled" in available_columns:
241
- if (
242
- isinstance(chrom_prominence_scaled, tuple)
243
- and len(chrom_prominence_scaled) == 2
244
- ):
221
+ if isinstance(chrom_prominence_scaled, tuple) and len(chrom_prominence_scaled) == 2:
245
222
  min_prominence_scaled, max_prominence_scaled = chrom_prominence_scaled
246
223
  filter_conditions.append(
247
224
  (pl.col("chrom_prominence_scaled") >= min_prominence_scaled)
248
225
  & (pl.col("chrom_prominence_scaled") <= max_prominence_scaled),
249
226
  )
250
227
  else:
251
- filter_conditions.append(
252
- pl.col("chrom_prominence_scaled") >= chrom_prominence_scaled,
253
- )
228
+ filter_conditions.append(pl.col("chrom_prominence_scaled") >= chrom_prominence_scaled)
254
229
  else:
255
230
  warnings.append("'chrom_prominence_scaled' column not found in features_df")
256
231
 
@@ -264,9 +239,7 @@ def features_select_optimized(
264
239
  & (pl.col("chrom_height_scaled") <= max_height_scaled),
265
240
  )
266
241
  else:
267
- filter_conditions.append(
268
- pl.col("chrom_height_scaled") >= chrom_height_scaled,
269
- )
242
+ filter_conditions.append(pl.col("chrom_height_scaled") >= chrom_height_scaled)
270
243
  else:
271
244
  warnings.append("'chrom_height_scaled' column not found in features_df")
272
245
 
@@ -372,7 +345,7 @@ def monkey_patch_study():
372
345
 
373
346
  Call this function to replace the original features_select with the optimized version.
374
347
  """
375
- from master.study.study import Study
348
+ from masster.study.study import Study
376
349
 
377
350
  # Store original method for benchmarking
378
351
  Study.features_select_original = Study.features_select