diskmelts 2.1.1__tar.gz → 2.2.0__tar.gz

{diskmelts-2.1.1/src/diskmelts.egg-info → diskmelts-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diskmelts
-Version: 2.1.1
+Version: 2.2.0
 Summary: Machine-learning Enabled Line fitting Tool for Spectra of protoplanetary disks
 Author: Chengyan Xie, Dingshan Deng
 License-Expression: MIT
@@ -49,7 +49,9 @@ density (`logN`), and emitting area scaling (`A`) from observed spectra.
 
 ## Installation
 
-DiskMELTS 2.1.1 is available on [PyPI](https://pypi.org/project/diskmelts/).
+DiskMELTS is available on [PyPI](https://pypi.org/project/diskmelts/).
+Version 2.2.0 bundles 44 production checkpoints, including sigma=2 models for
+18 species and CH3 in both sigma versions.
 With Python 3.9 or newer, install it from any directory. These commands use
 `python` in an activated environment; the
 [installation guide](https://diskmelts.readthedocs.io/en/latest/installation.html)
@@ -73,6 +75,18 @@ downloads; pass their local path as `grid_root`.
 Example notebooks and spectra can be downloaded from the repository when
 needed; they are not installed by pip.
 
+To install from a checkout with Conda or Mamba, run:
+
+```bash
+git clone https://github.com/wddlx/DiskMELTS.git
+cd DiskMELTS
+conda env create -f environment.yaml
+conda activate diskmelts
+```
+
+Use `environment-notebooks.yaml` or `environment-dev.yaml` for the corresponding
+notebook or contributor dependencies.
+
 ## Runtime dependencies
 
 | Package | Purpose |
@@ -177,8 +191,17 @@ python examples/dev_v2_realobs.py
 The v2 fitting API is `load_fitting_models`, `fit_stage`, `fit_observation`, and
 `plot_saved_observation`. The production checkpoints are packaged under
 `src/diskmelts/models/` and included in the wheel. Model fitting requires no
-`Model_grids/` or `Pretrain_grid/` directory. The model metadata, including
-PCA counts and network layers, are in `diskmelts.MODEL_SPECS` and checked when
+`Model_grids/` or `Pretrain_grid/` directory. `diskmelts.MODEL_SPECS` records
+PCA counts, network layers, and `grid_sigma=0` for the original checkpoints.
+In version 2.2.0, sigma=2 checkpoints are available for H2O,
+C2H2, HCN, CO2, 13C12CH2, 13CO2, C4H2, HC3N, C2H6, C2H4, CH4,
+C2HD, CO17O, CO18O, C3H4, CH3, C6H6, and OH. Select them with
+`load_fitting_models(['H2O', 'C2H2'], sigma=2)` or
+`fit_observation(..., sigma=2)`. The C2H2 bank covers 6–9 and 11.5–17 µm;
+choose fit windows within those bands. OH covers 15–26 µm. Both C6H6
+checkpoints cover 13–17 µm and 100–675 K; the sigma=2 checkpoint is selected
+with `load_fitting_models('C6H6', sigma=2)`.
+The checkpoint settings are checked when
 loading. The checkpoint flux convention is 1 au² at 140 pc; `distance_pc`
 sets the source distance and makes the returned emitting area physical.
 The [fitting notebook](https://github.com/wddlx/DiskMELTS/blob/main/notebooks/Example_Fitting.ipynb) requires 13C12CH2 to
@@ -189,27 +212,29 @@ joint stage to choose those constraints. See the
 [fitting guide](https://diskmelts.readthedocs.io/en/latest/quickstart.html) for examples.
 
 For an optional fit directly from slab grids, use `fit_grid_stage` or
-`fit_observation_grids` and supply `grid_root='Model_grids'` explicitly. This
+`fit_observation_grids` and supply `grid_root='Model_grids/sigma0'` explicitly. This
 separate method does require the full local grids. See the
 [quick start](https://diskmelts.readthedocs.io/en/latest/quickstart.html) for both workflows and saved-result
 plotting.
+For complete sigma=2 grids, pass `grid_root='Model_grids/sigma2'`.
 
 ## Training and validation data
 
-`Model_grids/` and `Pretrain_grid/` are intentionally ignored by Git because
-they contain the full local training data. The generated checkpoint directories
-under the top-level `Trained_model/` are also optional; the package bundles
+Generated data under `Model_grids/` and `Pretrain_grid/` are intentionally
+ignored by Git because they contain the full local training data. Generated
+checkpoint directories under the top-level `Trained_model/` are also optional; the package bundles
 only the production checkpoints needed for v2 fitting. To run
 `examples/dev_v2_pt_validation.py` or
 `notebooks/Example_Training_Validation.ipynb`, place the complete model grids
-under `Model_grids/<molecule>/`. The workflows create or reuse the corresponding
+under `Model_grids/sigma0/<molecule>/`. The workflows create or reuse the corresponding
 pretraining CSV under `Pretrain_grid/`.
 
 The maintained v2 workflow uses a hybrid design after restricting the expanded
 IRIS grids to the intended physical domain. H2O uses five overlapping
 wavelength checkpoints covering 4.9–25.0 µm, all sharing `T=100–1400 K` and
 `logN=13–19`. Primary carbon-bearing and rarer molecules use one checkpoint
-each, the same temperature range, and `logN=13–19.5`.
+each and `logN=13–19.5`; C6H6 is limited to `T=100–675 K`, while the others
+use `T=100–1400 K`.
 The new C2HD checkpoint spans 11.5–20.5 µm to include its 19 µm band;
 CO17O and CO18O span 13–18 µm. The updated 13C12CH2 checkpoint keeps
 11.5–17 µm. To retrain these four grids, run:
@@ -218,6 +243,18 @@ CO17O and CO18O span 13–18 µm. The updated 13C12CH2 checkpoint keeps
 DISKMELTS_MOLECULES=13C12CH2,C2HD,CO17O,CO18O python examples/dev_v2_pt_validation.py
 ```
 
+C6H6 and C3H4 also have bundled fitting checkpoints. The C6H6 checkpoint
+covers 13–17 µm and 100–675 K; C3H4 covers 15–18 µm and 100–1400 K. Load
+either by name with `load_fitting_models`. Direct grid fitting
+uses the same names with local `Model_grids/sigma0/C6H6/` and `Model_grids/sigma0/C3H4/`
+files. See the [training guide](https://diskmelts.readthedocs.io/en/latest/training.html)
+for peak audits and retraining commands.
+
+Version 2.2.0 also includes a CH3 checkpoint for 15–18 µm,
+`T=100–1400 K`, and `logN=13–19.5`. Its strongest grid feature in this window
+is near 16.4–16.6 µm. Use `load_fitting_models('CH3')` after installing this
+package; direct-grid fitting uses local `Model_grids/sigma0/CH3/` files.
+
 Five to ten percent of complete `(T, logN)` grid spectra are excluded before
 PCA or neural-network training. They are used to select the PCA dimension and
 to validate spectral reconstruction and full parameter fitting. The

{diskmelts-2.1.1 → diskmelts-2.2.0}/README.md

@@ -10,7 +10,9 @@ density (`logN`), and emitting area scaling (`A`) from observed spectra.
 
 ## Installation
 
-DiskMELTS 2.1.1 is available on [PyPI](https://pypi.org/project/diskmelts/).
+DiskMELTS is available on [PyPI](https://pypi.org/project/diskmelts/).
+Version 2.2.0 bundles 44 production checkpoints, including sigma=2 models for
+18 species and CH3 in both sigma versions.
 With Python 3.9 or newer, install it from any directory. These commands use
 `python` in an activated environment; the
 [installation guide](https://diskmelts.readthedocs.io/en/latest/installation.html)
@@ -34,6 +36,18 @@ downloads; pass their local path as `grid_root`.
 Example notebooks and spectra can be downloaded from the repository when
 needed; they are not installed by pip.
 
+To install from a checkout with Conda or Mamba, run:
+
+```bash
+git clone https://github.com/wddlx/DiskMELTS.git
+cd DiskMELTS
+conda env create -f environment.yaml
+conda activate diskmelts
+```
+
+Use `environment-notebooks.yaml` or `environment-dev.yaml` for the corresponding
+notebook or contributor dependencies.
+
 ## Runtime dependencies
 
 | Package | Purpose |
@@ -138,8 +152,17 @@ python examples/dev_v2_realobs.py
 The v2 fitting API is `load_fitting_models`, `fit_stage`, `fit_observation`, and
 `plot_saved_observation`. The production checkpoints are packaged under
 `src/diskmelts/models/` and included in the wheel. Model fitting requires no
-`Model_grids/` or `Pretrain_grid/` directory. The model metadata, including
-PCA counts and network layers, are in `diskmelts.MODEL_SPECS` and checked when
+`Model_grids/` or `Pretrain_grid/` directory. `diskmelts.MODEL_SPECS` records
+PCA counts, network layers, and `grid_sigma=0` for the original checkpoints.
+In version 2.2.0, sigma=2 checkpoints are available for H2O,
+C2H2, HCN, CO2, 13C12CH2, 13CO2, C4H2, HC3N, C2H6, C2H4, CH4,
+C2HD, CO17O, CO18O, C3H4, CH3, C6H6, and OH. Select them with
+`load_fitting_models(['H2O', 'C2H2'], sigma=2)` or
+`fit_observation(..., sigma=2)`. The C2H2 bank covers 6–9 and 11.5–17 µm;
+choose fit windows within those bands. OH covers 15–26 µm. Both C6H6
+checkpoints cover 13–17 µm and 100–675 K; the sigma=2 checkpoint is selected
+with `load_fitting_models('C6H6', sigma=2)`.
+The checkpoint settings are checked when
 loading. The checkpoint flux convention is 1 au² at 140 pc; `distance_pc`
 sets the source distance and makes the returned emitting area physical.
 The [fitting notebook](https://github.com/wddlx/DiskMELTS/blob/main/notebooks/Example_Fitting.ipynb) requires 13C12CH2 to
@@ -150,27 +173,29 @@ joint stage to choose those constraints. See the
 [fitting guide](https://diskmelts.readthedocs.io/en/latest/quickstart.html) for examples.
 
 For an optional fit directly from slab grids, use `fit_grid_stage` or
-`fit_observation_grids` and supply `grid_root='Model_grids'` explicitly. This
+`fit_observation_grids` and supply `grid_root='Model_grids/sigma0'` explicitly. This
 separate method does require the full local grids. See the
 [quick start](https://diskmelts.readthedocs.io/en/latest/quickstart.html) for both workflows and saved-result
 plotting.
+For complete sigma=2 grids, pass `grid_root='Model_grids/sigma2'`.
 
 ## Training and validation data
 
-`Model_grids/` and `Pretrain_grid/` are intentionally ignored by Git because
-they contain the full local training data. The generated checkpoint directories
-under the top-level `Trained_model/` are also optional; the package bundles
+Generated data under `Model_grids/` and `Pretrain_grid/` are intentionally
+ignored by Git because they contain the full local training data. Generated
+checkpoint directories under the top-level `Trained_model/` are also optional; the package bundles
 only the production checkpoints needed for v2 fitting. To run
 `examples/dev_v2_pt_validation.py` or
 `notebooks/Example_Training_Validation.ipynb`, place the complete model grids
-under `Model_grids/<molecule>/`. The workflows create or reuse the corresponding
+under `Model_grids/sigma0/<molecule>/`. The workflows create or reuse the corresponding
 pretraining CSV under `Pretrain_grid/`.
 
 The maintained v2 workflow uses a hybrid design after restricting the expanded
 IRIS grids to the intended physical domain. H2O uses five overlapping
 wavelength checkpoints covering 4.9–25.0 µm, all sharing `T=100–1400 K` and
 `logN=13–19`. Primary carbon-bearing and rarer molecules use one checkpoint
-each, the same temperature range, and `logN=13–19.5`.
+each and `logN=13–19.5`; C6H6 is limited to `T=100–675 K`, while the others
+use `T=100–1400 K`.
 The new C2HD checkpoint spans 11.5–20.5 µm to include its 19 µm band;
 CO17O and CO18O span 13–18 µm. The updated 13C12CH2 checkpoint keeps
 11.5–17 µm. To retrain these four grids, run:
@@ -179,6 +204,18 @@ CO17O and CO18O span 13–18 µm. The updated 13C12CH2 checkpoint keeps
 DISKMELTS_MOLECULES=13C12CH2,C2HD,CO17O,CO18O python examples/dev_v2_pt_validation.py
 ```
 
+C6H6 and C3H4 also have bundled fitting checkpoints. The C6H6 checkpoint
+covers 13–17 µm and 100–675 K; C3H4 covers 15–18 µm and 100–1400 K. Load
+either by name with `load_fitting_models`. Direct grid fitting
+uses the same names with local `Model_grids/sigma0/C6H6/` and `Model_grids/sigma0/C3H4/`
+files. See the [training guide](https://diskmelts.readthedocs.io/en/latest/training.html)
+for peak audits and retraining commands.
+
+Version 2.2.0 also includes a CH3 checkpoint for 15–18 µm,
+`T=100–1400 K`, and `logN=13–19.5`. Its strongest grid feature in this window
+is near 16.4–16.6 µm. Use `load_fitting_models('CH3')` after installing this
+package; direct-grid fitting uses local `Model_grids/sigma0/CH3/` files.
+
 Five to ten percent of complete `(T, logN)` grid spectra are excluded before
 PCA or neural-network training. They are used to select the PCA dimension and
 to validate spectral reconstruction and full parameter fitting. The

{diskmelts-2.1.1 → diskmelts-2.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "diskmelts"
-version = "2.1.1"
+version = "2.2.0"
 description = "Machine-learning Enabled Line fitting Tool for Spectra of protoplanetary disks"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -47,7 +47,7 @@ notebooks = ["jupyterlab", "ipykernel"]
 where = ["src"]
 
 [tool.setuptools.package-data]
-diskmelts = ["models/Trained_model/*/*.pt", "models/Trained_model/*/*.json",
+diskmelts = ["models/Trained_model/sigma*/*/*.pt", "models/Trained_model/sigma*/*/*.json",
             "consub/*.csv", "consub/regions/*.csv", "consub/regions/*.json"]
 
 [tool.pytest.ini_options]

{diskmelts-2.1.1 → diskmelts-2.2.0}/src/diskmelts/__init__.py

@@ -39,6 +39,7 @@ from diskmelts.plotting import (
 )
 from diskmelts.v2_fitting import (
     MODEL_SPECS,
+    SIGMA2_MODEL_SPECS,
     load_fitting_models,
     fit_stage,
     fit_observation,
@@ -58,6 +59,7 @@ from diskmelts import consub
 __all__ = [
     "consub",
     "MODEL_SPECS",
+    "SIGMA2_MODEL_SPECS",
     "load_fitting_models",
     "fit_stage",
     "fit_observation",

{diskmelts-2.1.1 → diskmelts-2.2.0}/src/diskmelts/fitting.py

@@ -226,6 +226,7 @@ def load_model_bank(
     return {
         'is_model_bank': True,
         'mol': manifest['mol'],
+        'grid_sigma': manifest.get('grid_sigma'),
         'manifest_path': manifest_path,
         'tiles': loaded_tiles,
         'wav_ranges': sorted(set(tile['wav_range'] for tile in loaded_tiles)),
@@ -1347,14 +1348,14 @@ def save_fitted_comparison(csv_path, source_name, all_fits):
 
     def _v(comp, key):
         if comp not in all_params:
-            return ''
+            return np.nan
         return round(all_params[comp][key], 4)
 
     def _e(comp, key, which):
         if comp not in all_unc:
-            return ''
+            return np.nan
         v = all_unc[comp].get(key, {}).get(which, float('nan'))
-        return round(v, 4) if np.isfinite(v) else ''
+        return round(v, 4) if np.isfinite(v) else np.nan
 
     row = {
         'Source':               source_name,

{diskmelts-2.1.1/src/diskmelts/models/Trained_model → diskmelts-2.2.0/src/diskmelts/models/Trained_model/sigma0}/H2O_wavelength_bank_v2_fixed/H2O_model_bank.json

@@ -1,5 +1,6 @@
 {
   "schema_version": 1,
+  "grid_sigma": 0,
   "mol": "H2O",
   "n_pca": 30,
   "hidden": [

diskmelts-2.2.0/src/diskmelts/models/Trained_model/sigma2/C2H2_wavelength_bank_v2/C2H2_model_bank.json

@@ -0,0 +1,26 @@
+{
+  "schema_version": 1,
+  "mol": "C2H2",
+  "grid_sigma": 2,
+  "n_pca": 30,
+  "hidden": [64, 128, 64],
+  "wavelength_ranges": [[6.0, 9.0], [11.5, 17.0]],
+  "T_ranges": [[100.0, 1400.0]],
+  "logN_ranges": [[13.0, 19.5]],
+  "tiles": [
+    {
+      "path": "net_C2H2_w6to9.pt",
+      "wav_range": [6.0, 9.0],
+      "T_range": [100.0, 1400.0],
+      "logN_range": [13.0, 19.5],
+      "n_pca": 30
+    },
+    {
+      "path": "net_C2H2_w11p5to17.pt",
+      "wav_range": [11.5, 17.0],
+      "T_range": [100.0, 1400.0],
+      "logN_range": [13.0, 19.5],
+      "n_pca": 30
+    }
+  ]
+}

diskmelts-2.2.0/src/diskmelts/models/Trained_model/sigma2/H2O_wavelength_bank_v2_fixed/H2O_model_bank.json

@@ -0,0 +1,132 @@
+{
+  "schema_version": 1,
+  "mol": "H2O",
+  "pretrain_csv": "/Users/chengyanxie/Documents/Github_myself/DiskMELTS/Pretrain_grid/sigma2/pretrain_H2O_wavelength_bank_T100to1400_N13to19.csv",
+  "n_pca": 30,
+  "hidden": [
+    64,
+    128,
+    64
+  ],
+  "peak_normalization": "window",
+  "shape_loss": "spectral",
+  "shape_edge_weight": 10.0,
+  "temperature_transform": "log10",
+  "wavelength_ranges": [
+    [
+      4.9,
+      7.4
+    ],
+    [
+      7.2,
+      11.2
+    ],
+    [
+      9.9,
+      15.1
+    ],
+    [
+      13.5,
+      19.2
+    ],
+    [
+      19.0,
+      25.0
+    ]
+  ],
+  "logN_ranges": [
+    [
+      13.0,
+      19.0
+    ]
+  ],
+  "T_ranges": [
+    [
+      100.0,
+      1400.0
+    ]
+  ],
+  "tiles": [
+    {
+      "path": "net_H2O_w4p9to7p4_n13to19_t100to1400.pt",
+      "wav_range": [
+        4.9,
+        7.4
+      ],
+      "logN_range": [
+        13.0,
+        19.0
+      ],
+      "T_range": [
+        100.0,
+        1400.0
+      ],
+      "n_pca": 30
+    },
+    {
+      "path": "net_H2O_w7p2to11p2_n13to19_t100to1400.pt",
+      "wav_range": [
+        7.2,
+        11.2
+      ],
+      "logN_range": [
+        13.0,
+        19.0
+      ],
+      "T_range": [
+        100.0,
+        1400.0
+      ],
+      "n_pca": 30
+    },
+    {
+      "path": "net_H2O_w9p9to15p1_n13to19_t100to1400.pt",
+      "wav_range": [
+        9.9,
+        15.1
+      ],
+      "logN_range": [
+        13.0,
+        19.0
+      ],
+      "T_range": [
+        100.0,
+        1400.0
+      ],
+      "n_pca": 30
+    },
+    {
+      "path": "net_H2O_w13p5to19p2_n13to19_t100to1400.pt",
+      "wav_range": [
+        13.5,
+        19.2
+      ],
+      "logN_range": [
+        13.0,
+        19.0
+      ],
+      "T_range": [
+        100.0,
+        1400.0
+      ],
+      "n_pca": 30
+    },
+    {
+      "path": "net_H2O_w19to25_n13to19_t100to1400.pt",
+      "wav_range": [
+        19.0,
+        25.0
+      ],
+      "logN_range": [
+        13.0,
+        19.0
+      ],
+      "T_range": [
+        100.0,
+        1400.0
+      ],
+      "n_pca": 30
+    }
+  ],
+  "grid_sigma": 2
+}

{diskmelts-2.1.1 → diskmelts-2.2.0}/src/diskmelts/plotting.py

@@ -43,6 +43,9 @@ _MOL_LABEL = {
     'C2HD':      r'C$_2$HD',
     'CO17O':     r'C$^{16}$O$^{17}$O',
     'CO18O':     r'C$^{16}$O$^{18}$O',
+    'C6H6':      r'C$_6$H$_6$',
+    'C3H4':      r'C$_3$H$_4$',
+    'CH3':       r'CH$_3$',
 }
 
 _MOL_COLOR = {
@@ -64,6 +67,9 @@ _MOL_COLOR = {
     'C2HD':     'teal',
     'CO17O':    'slateblue',
     'CO18O':    'goldenrod',
+    'C6H6':     'darkorange',
+    'C3H4':     'purple',
+    'CH3':      'crimson',
 }
 
 # ---------------------------------------------------------------------------

{diskmelts-2.1.1 → diskmelts-2.2.0}/src/diskmelts/trainmodel.py

@@ -945,6 +945,7 @@ def train_model_bank(
     scheduler_patience=10,
     min_lr=0.0,
     temperature_transform='linear',
+    grid_sigma=None,
 ):
     """Train a bank of overlapping forward-surrogate tiles for one molecule.
 
@@ -968,6 +969,8 @@ def train_model_bank(
     Returns:
         dict: manifest data plus in-memory ``models`` and ``model_bank``.
     """
+    if grid_sigma is not None and grid_sigma not in (0, 2):
+        raise ValueError('grid_sigma must be 0 or 2')
     wavelength_ranges = [tuple(map(float, item)) for item in wavelength_ranges]
     logN_ranges = [tuple(map(float, item)) for item in logN_ranges]
     T_ranges = [tuple(map(float, item)) for item in T_ranges]
@@ -1087,6 +1090,8 @@ def train_model_bank(
         'T_ranges': [list(item) for item in T_ranges],
         'tiles': tiles,
     }
+    if grid_sigma is not None:
+        manifest['grid_sigma'] = grid_sigma
     os.makedirs(os.path.dirname(manifest_path), exist_ok=True)
     with open(manifest_path, 'w', encoding='utf-8') as stream:
         json.dump(manifest, stream, indent=2)
@@ -1136,7 +1141,7 @@ if __name__ == '__main__':
     # -- Paths ---------------------------------------------------------------
     _here        = os.path.dirname(os.path.abspath(__file__))
     ROOT_DIR     = os.path.join(_here, '..', '..')              # project root
-    GRID_ROOT    = os.path.join(ROOT_DIR, 'Model_grids')
+    GRID_ROOT    = os.path.join(ROOT_DIR, 'Model_grids', 'sigma0')
     DATA_DIR     = os.path.join(ROOT_DIR, 'Pretrain_grid')
     MODEL_DIR    = os.path.join(ROOT_DIR, 'Trained_model')
     FIG_DIR      = os.path.join(ROOT_DIR, 'figures', 'trainmodel')