Spaces:
Running
Running
File size: 6,480 Bytes
f121890 e6e9684 f121890 e6e9684 f121890 68c303a 20d40ec e6e9684 20d40ec e6e9684 20d40ec f121890 20d40ec f121890 e6e9684 f121890 e6e9684 f121890 20d40ec e6e9684 20d40ec f121890 e6e9684 f121890 e6e9684 f121890 e6e9684 f121890 e6e9684 20d40ec e6e9684 f121890 20d40ec f121890 20d40ec e6e9684 20d40ec f121890 e6e9684 f121890 e6e9684 3dde8a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 |
import os
import crystal_toolkit.components as ctc
import dash
from crystal_toolkit.settings import SETTINGS
from dash import dcc, html
from dash.dependencies import Input, Output, State
from datasets import load_dataset
from pymatgen.core import Structure
from pymatgen.ext.matproj import MPRester
HF_TOKEN = os.environ.get("HF_TOKEN")
# Load only the train split of the dataset
dataset = load_dataset(
"LeMaterial/leDataset",
token=HF_TOKEN,
split="train",
columns=[
"lattice_vectors",
"species_at_sites",
"cartesian_site_positions",
"energy",
"energy_corrected",
"immutable_id",
"elements",
"functional",
"stress_tensor",
"magnetic_moments",
"forces",
"band_gap_direct",
"band_gap_indirect",
"dos_ef",
"charges",
"functional",
"chemical_formula_reduced",
"chemical_formula_descriptive",
"total_magnetization",
],
)
# Convert the train split to a pandas DataFrame
train_df = dataset.to_pandas()
del dataset
# Initialize the Dash app
app = dash.Dash(__name__, assets_folder=SETTINGS.ASSETS_PATH)
server = app.server # Expose the server for deployment
# Define the app layout
layout = html.Div(
[
dcc.Markdown("## Interactive Crystal Viewer"),
html.Div(
[
html.Div(
[
html.Label("Search by Chemical System (e.g., 'Ac-Cd-Ge')"),
dcc.Input(
id="query-input",
type="text",
value="Ac-Cd-Ge",
placeholder="Ac-Cd-Ge",
style={"width": "100%"},
),
],
style={
"width": "70%",
"display": "inline-block",
"verticalAlign": "top",
},
),
html.Div(
[
html.Button("Search", id="search-button", n_clicks=0),
],
style={
"width": "28%",
"display": "inline-block",
"paddingLeft": "2%",
"verticalAlign": "top",
},
),
],
style={"margin-bottom": "20px"},
),
html.Div(
[
html.Label("Select Material"),
dcc.Dropdown(
id="material-dropdown",
options=[], # Empty options initially
value=None,
),
],
style={"margin-bottom": "20px"},
),
html.Button("Display Material", id="display-button", n_clicks=0),
html.Div(
[
html.Div(
id="structure-container",
style={
"width": "48%",
"display": "inline-block",
"verticalAlign": "top",
},
),
html.Div(
id="properties-container",
style={
"width": "48%",
"display": "inline-block",
"paddingLeft": "4%",
"verticalAlign": "top",
},
),
],
style={"margin-top": "20px"},
),
]
)
# Function to search for materials
def search_materials(query):
element_list = [el.strip() for el in query.split("-")]
isubset = lambda x: set(x).issubset(element_list)
isintersection = lambda x: len(set(x).intersection(element_list)) > 0
entries_df = train_df[
[isintersection(l) and isubset(l) for l in train_df.elements.values.tolist()]
]
options = [
{
"label": f"{res.chemical_formula_reduced} ({res.immutable_id}) Calculated with {res.functional}",
"value": n,
}
for n, res in entries_df.iterrows()
]
del entries_df
return options
# Callback to update the material dropdown based on search
@app.callback(
[Output("material-dropdown", "options"), Output("material-dropdown", "value")],
Input("search-button", "n_clicks"),
State("query-input", "value"),
)
def update_material_dropdown(n_clicks, query):
if n_clicks is None or not query:
return [], None
options = search_materials(query)
if not options:
return [], None
return options, options[0]["value"]
# Callback to display the selected material
@app.callback(
[
Output("structure-container", "children"),
Output("properties-container", "children"),
],
Input("display-button", "n_clicks"),
State("material-dropdown", "value"),
)
def display_material(n_clicks, material_id):
if n_clicks is None or not material_id:
return "", ""
row = train_df.iloc[material_id]
structure = Structure(
[x for y in row["lattice_vectors"] for x in y],
row["species_at_sites"],
row["cartesian_site_positions"],
coords_are_cartesian=True,
)
# Create the StructureMoleculeComponent
structure_component = ctc.StructureMoleculeComponent(structure)
# Extract key properties
properties = {
"Material ID": row.immutable_id,
"Formula": row.chemical_formula_descriptive,
"Energy per atom (eV/atom)": row.energy / len(row.species_at_sites),
"Band Gap (eV)": row.band_gap_direct or row.band_gap_indirect,
"Total Magnetization (μB/f.u.)": row.total_magnetization,
}
# Format properties as an HTML table
properties_html = html.Table(
[
html.Tbody(
[
html.Tr([html.Th(key), html.Td(str(value))])
for key, value in properties.items()
]
)
],
style={
"border": "1px solid black",
"width": "100%",
"borderCollapse": "collapse",
},
)
return structure_component.layout(), properties_html
# Register crystal toolkit with the app
ctc.register_crystal_toolkit(app, layout)
if __name__ == "__main__":
app.run_server(debug=True, port=7860, host="0.0.0.0")
|