Develop (#328)

* Fix repo.

* Update databases.md

* Update databases.md

* Update databases.md

* Version update.

* Update utils.py

* Update utils.py

* Update solar.py

* Add model bug fix.

* Lint fix.

* Add Alexandria DB.

* Update databases.md

* Add Alexandria DB.

Author: knc6

docs/databases.md

@@ -2,6 +2,10 @@
 
 ## [FigShare](https://figshare.com/authors/Kamal_Choudhary/4445539) based databases
 
+[![Open in Colab]](https://colab.research.google.com/github/knc6/jarvis-tools-notebooks/blob/master/jarvis-tools-notebooks/Analyzing_data_in_the_JARVIS_DFT_dataset.ipynb)
+[![Open in SLMat]](https://deepmaterials.github.io/slmat/lab?fromURL=https://raw.githubusercontent.com/deepmaterials/slmat/main/content/Database_analysis.ipynb)
+
+
 | Database name     | Number of data-points | Description                                                                                                                           |
 |-------------------|-----------------------|---------------------------------------------------------------------------------------------------------------------------------------|
 | `dft_3d`          | 75993                 | Various 3D materials properties in JARVIS-DFT database computed with OptB88vdW and TBmBJ methods                                      |
@@ -25,8 +29,8 @@
 | `mp_3d_2020`      | 127k                  | CFID descriptors for materials project                                                                                                |
 | `mp_3d`           | 84k                   | CFID descriptors for 84k materials project                                                                                            |
 | `megnet2`         | 133k                  | 133k materials and their formation energy in MP                                                                                       |
-| `m3gnet_mpf`        | 168k                  | 168k structures and their energy, forces and stresses in MP                                                                                       |
-| `m3gnet_mpf_1.5mil`        | 1.5 million                  | 1.5 million structures  and their energy, forces and stresses in MP                                                                                       |
+| `m3gnet_mpf`      | 168k                | 168k structures and their energy, forces and stresses in MP                                                                                       |
+| `m3gnet_mpf_1.5mil` | 1.5 million          | 1.5 million structures  and their energy, forces and stresses in MP                                                                                       |
 | `twod_matpd`      | 6351                  | Formation energy and bandgaps of 2D materials properties in 2DMatPedia database                                                       |
 | `c2db`            | 3514                  | Various properties in C2DB database                                                                                                   |
 | `polymer_genome`  | 1073                  | Electronic bandgap and diecltric constants of crystall ine polymer in polymer genome database                                         |
@@ -36,6 +40,12 @@
 | `oqmd_3d_no_cfid` | 817636                | Formation energies and bandgaps of 3D materials from OQMD database                                                                    |
 | `oqmd_3d`         | 460k                  | CFID descriptors for 460k materials in OQMD                                                                                           |
 | `omdb`            | 12500                 | Bandgaps for organic polymers in OMDB database                                                                                        |
+| `alex_pbe_hull`   | 116k                 | Alexandria DB convex hull stable materials with PBE functional                                                                                    |
+| `alex_pbe_3d_all` | 5 million            | Alexandria DB all 3D materials with PBE                                                                                   |
+| `alex_pbe_2d_all` | 200k                 | Alexandria DB all 2D materials with PBE                                                                                       |
+| `alex_pbe_1d_all` | 100k                 | Alexandria DB all 1D materials with PBE                                                                                       |
+| `alex_scan_3d_all` | 500k                 | Alexandria DB all 3D materials with SCAN                                                                                     |
+| `alex_pbesol_3d_all` | 500k                 | Alexandria DB all 3D materials with PBEsol                                                                                    |
 | `hopv`            | 4855                  | Various properties of molecules in HOPV15 dataset                                                                                     |
 | `pdbbind`         | 11189                 | Bio-molecular complexes database from PDBBind v2015                                                                                   |
 | `pdbbind_core`    | 195                   | Bio-molecular complexes database from PDBBind core                                                                                    |
@@ -88,4 +98,6 @@ df = pd.DataFrame(d)
 print(df)
 ```
 
+[Open in SLMat]: https://img.shields.io/badge/Open-SLMat-blue
 
+[Open in Colab]: https://colab.research.google.com/assets/colab-badge.svg

jarvis/__init__.py

@@ -1,6 +1,6 @@
 """Version number."""
 
-__version__ = "2024.8.30"
+__version__ = "2024.10.10"
 
 import os
 

jarvis/analysis/solarefficiency/solar.py

@@ -4,12 +4,19 @@
 Please find more detailsin:
 https://pubs.acs.org/doi/abs/10.1021/acs.chemmater.9b02166
 """
+
 import numpy as np
 import os
 from scipy.interpolate import interp1d
 from numpy import interp
 import scipy.constants as constants
-from scipy.integrate import simps
+
+try:
+    from scipy.integrate import simps
+except Exception:
+    from scipy.integrate import simpson as simps
+
+    pass
 import matplotlib.pyplot as plt
 
 
@@ -69,7 +76,7 @@ def calculate_SQ(
         # units of W/(m**3), different than solar_spectra_irradiance!!! (This
         # is intentional, it is for convenience)
         blackbody_irradiance = (
-            2.0 * h * c ** 2 / (solar_spectra_wavelength_meters ** 5)
+            2.0 * h * c**2 / (solar_spectra_wavelength_meters**5)
         ) * (
             1.0
             / (
@@ -109,7 +116,7 @@ def calculate_SQ(
         )
 
         bandgap_blackbody = (
-            (2.0 * h * c ** 2 / (bandgap_wavelength ** 5))
+            (2.0 * h * c**2 / (bandgap_wavelength**5))
             * (
                 1.0
                 / (
@@ -273,7 +280,7 @@ def slme(
         # units of W/(m**3), different than solar_spectra_irradiance!!! (This
         # is intentional, it is for convenience)
         blackbody_irradiance = (
-            2.0 * h * c ** 2 / (solar_spectra_wavelength_meters ** 5)
+            2.0 * h * c**2 / (solar_spectra_wavelength_meters**5)
         ) * (
             1.0
             / (
@@ -298,7 +305,7 @@ def slme(
         # units of nm
         material_wavelength_for_absorbance_data = (
             (c * h_e) / (material_energy_for_absorbance_data + 0.00000001)
-        ) * 10 ** 9
+        ) * 10**9
 
         # absorbance interpolation onto each solar spectrum wavelength
 

jarvis/analysis/structure/spacegroup.py

@@ -12,7 +12,7 @@
 
 try:
     import spglib
-except Exception as exp:
+except Exception:
     # print(exp)
     pass
 # from numpy import gcd

jarvis/core/atoms.py

@@ -1438,6 +1438,9 @@ def hook(model, input, output):
 
         from alignn.graphs import Graph
         from alignn.pretrained import get_figshare_model
+        import torch
+
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
         g, lg = Graph.atom_dgl_multigraph(
             self,
@@ -1452,6 +1455,8 @@ def hook(model, input, output):
             model = get_figshare_model(
                 model_name="jv_formation_energy_peratom_alignn"
             )
+        g.to(device)
+        lg.to(device)
         h = get_val(model, g, lg)
         return h
 
@@ -1571,11 +1576,15 @@ def describe(
         cutoff=4,
         take_n_bonds=2,
         include_spg=True,
+        include_mineral_name=False,
     ):
         """Describe for NLP applications."""
         from jarvis.analysis.diffraction.xrd import XRD
 
-        min_name = self.get_minaral_name()
+        if include_mineral_name:
+            min_name = self.get_minaral_name()
+        else:
+            min_name = "na"
         if include_spg:
             from jarvis.analysis.structure.spacegroup import Spacegroup3D
 
@@ -1713,7 +1722,8 @@ def describe(
             + struct_info["wyckoff"]
             + "."
         )
-        if min_name is not None:
+        if min_name != "na":
+            # if min_name is not None:
             line3 = (
                 chem_info["atomic_formula"]
                 + " is "

jarvis/core/utils.py

@@ -2,6 +2,8 @@
 
 from collections import OrderedDict
 from collections import defaultdict
+from scipy import sparse
+from scipy.sparse.linalg import spsolve
 import random
 import numpy as np
 import math
@@ -334,6 +336,52 @@ def cos_formula(a, b, c):
     return np.arccos(res)
 
 
+def baseline_als(y, lam, p, niter=10):
+    """
+    Adaptive Least Squares fitting for baseline correction
+
+    Parameters:
+    y: array_like
+        Input signal
+    lam: float
+        Lambda (smoothness)
+    p: float
+        Asymmetry
+    niter: int, optional
+        Number of iterations
+
+    Returns:
+    array_like
+        The estimated baseline
+    """
+    L = len(y)
+    D = sparse.diags([1, -2, 1], [0, -1, -2], shape=(L, L - 2))
+    w = np.ones(L)
+    for i in range(niter):
+        W = sparse.spdiags(w, 0, L, L)
+        Z = W + lam * D.dot(D.transpose())
+        z = spsolve(Z, w * y)
+        w = p * (y > z) + (1 - p) * (y < z)
+    return z
+
+
+def recast_array(
+    x_original=[], y_original=[], x_new=np.arange(0, 90, 1), tol=0.1
+):
+    x_original = np.array(x_original)
+    # Initialize the new y array with NaNs or a default value
+    y_new = np.full_like(x_new, 0, dtype=np.float64)
+
+    # Fill the corresponding bins
+    for x_val, y_val in zip(x_original, y_original):
+        closest_index = np.abs(
+            x_new - x_val
+        ).argmin()  # Find the closest x_new index
+        y_new[closest_index] = y_val
+    # y_new[y_new<tol]=0
+    return x_new, y_new
+
+
 # def is_xml_valid(xsd="jarvisdft.xsd", xml="JVASP-1002.xml"):
 #   """Check if XML is valid."""
 #   xml_file = etree.parse(xml)

jarvis/db/figshare.py

@@ -457,6 +457,48 @@ def get_db_info():
             "Obtaining CCCBDB dataset 1333...",
             "https://cccbdb.nist.gov/",
         ],
+        # https://doi.org/10.6084/m9.figshare.27174897
+        "alex_pbe_hull": [
+            "https://figshare.com/ndownloader/files/49622718",
+            "alexandria_convex_hull_pbe_2023.12.29_jarvis_tools.json",
+            "Obtaining Alexandria_DB PBE on hull 116k...",
+            "https://alexandria.icams.rub.de/",
+        ],
+        # https://doi.org/10.6084/m9.figshare.27174897
+        "alex_pbe_3d_all": [
+            "https://figshare.com/ndownloader/files/49622946",
+            "alexandria_pbe_3d_2024.10.1_jarvis_tools.json",
+            "Obtaining Alexandria_DB PBE 3D all 5 million, large file...",
+            "https://alexandria.icams.rub.de/",
+        ],
+        # https://doi.org/10.6084/m9.figshare.27174897
+        "alex_pbe_2d_all": [
+            "https://figshare.com/ndownloader/files/49622988",
+            "alexandria_pbe_2d_2024.10.1_jarvis_tools.json",
+            "Obtaining Alexandria_DB PBE 2D all 200k...",
+            "https://alexandria.icams.rub.de/",
+        ],
+        # https://doi.org/10.6084/m9.figshare.27174897
+        "alex_pbe_1d_all": [
+            "https://figshare.com/ndownloader/files/49622991",
+            "alexandria_pbe_1d_2024.10.1_jarvis_tools.json",
+            "Obtaining Alexandria_DB PBE 1D all 100k...",
+            "https://alexandria.icams.rub.de/",
+        ],
+        # https://doi.org/10.6084/m9.figshare.27174897
+        "alex_scan_3d_all": [
+            "https://figshare.com/ndownloader/files/49623090",
+            "alexandria_scan_3d_2024.10.1_jarvis_tools.json",
+            "Obtaining Alexandria_DB SCAN 3D all 500k...",
+            "https://alexandria.icams.rub.de/",
+        ],
+        # https://doi.org/10.6084/m9.figshare.27174897
+        "alex_pbesol_3d_all": [
+            "https://figshare.com/ndownloader/files/49623096",
+            "alexandria_ps_3d_2024.10.1_jarvis_tools.json",
+            "Obtaining Alexandria_DB PBEsol 3D all 500k...",
+            "https://alexandria.icams.rub.de/",
+        ],
         # https://doi.org/10.6084/m9.figshare.13154159
         "raw_files": [
             "https://ndownloader.figshare.com/files/25295732",
@@ -671,6 +713,7 @@ def get_wann_phonon(jid="JVASP-1002", factor=15.633302):
     # Requires phonopy
     from jarvis.io.phonopy.outputs import get_phonon_tb
     from jarvis.io.vasp.outputs import Vasprun
+    from jarvis.io.wannier.outputs import WannierHam
 
     fls = data("raw_files")
 

setup.py

@@ -12,7 +12,7 @@
 
 setup(
     name="jarvis-tools",
-    version="2024.8.30",
+    version="2024.10.10",
     long_description=long_d,
     install_requires=[
         "numpy>=1.20.1",