Merge branch 'master' into graph_for_paper

Author: clegaspi

propnet/core/tests/test_fitting.py

@@ -36,7 +36,7 @@ def test_get_sse(self):
         self.assertAlmostEqual(err, test_val)
         # Big dataset
         err = get_sse(self.evaluated, self.benchmarks)
-        self.assertAlmostEqual(err, 173.5710251)
+        self.assertAlmostEqual(err, 190.002519386222)
 
     def test_get_weight(self):
         q1 = QuantityFactory.create_quantity("band_gap", 3.2)

propnet/dbtools/correlation.py

@@ -293,9 +293,9 @@ def _make_data_combinations(self, prop_x, prop_y, data):
             prop_combos = ((prop_x, prop_y), (prop_y, prop_x))
         for x, y in prop_combos:
             for name, func in self._funcs.items():
-                data_dict = {'x_data': data[x],
+                data_dict = {'x_data': data.get(x, []),
                              'x_name': x,
-                             'y_data': data[y],
+                             'y_data': data.get(y, []),
                              'y_name': y,
                              'func': (name, func)}
                 yield data_dict

propnet/dbtools/mp_builder.py

@@ -28,7 +28,8 @@ class PropnetBuilder(MapBuilder):
     """
 
     def __init__(self, materials, propstore, materials_symbol_map=None,
-                 criteria=None, source_name="", graph_parallel=False,
+                 criteria=None, source_name="", include_deprecated=False,
+                 graph_parallel=False,
                  max_graph_workers=None, graph_timeout=None,
                  allow_child_process=False, **kwargs):
         """
@@ -40,6 +41,11 @@ def __init__(self, materials, propstore, materials_symbol_map=None,
             criteria (dict): criteria for Mongodb find() query specifying
                 criteria for records to process
             source_name (str): identifier for record source
+            include_deprecated (bool): True processes materials marked as
+                deprecated via the "deprecated" field. False skips those materials.
+                If an entry does not have the "deprecated" field, it will be processed.
+                Note that False will create a logical "and" with any criteria specified
+                in "criteria". Default: False
             graph_parallel (bool): True runs the graph algorithm in parallel with
                 the number of workers specified by max_workers. Default: False (serial)
                 Note: there will be no substantial speed-up from using a parallel
@@ -64,6 +70,17 @@ def __init__(self, materials, propstore, materials_symbol_map=None,
         self.materials = materials
         self.propstore = propstore
         self.criteria = criteria
+        self.include_deprecated = include_deprecated
+        if not include_deprecated:
+            deprecated_filter = {
+                "$or": [{"deprecated": {"$exists": False}},
+                        {"deprecated": False}]
+            }
+            if criteria:
+                self.criteria = {'$and': [criteria, deprecated_filter]}
+            else:
+                self.criteria = deprecated_filter
+
         self.materials_symbol_map = materials_symbol_map \
                                     or MPRester.mapping
         if source_name == "":
@@ -84,11 +101,12 @@ def __init__(self, materials, propstore, materials_symbol_map=None,
         props = list(self.materials_symbol_map.keys())
         props += ["task_id", "pretty_formula", "run_type", "is_hubbard",
                   "pseudo_potential", "hubbards", "potcar_symbols", "oxide_type",
-                  "final_energy", "unit_cell_formula", "created_at"]
+                  "final_energy", "unit_cell_formula", "created_at", "deprecated"]
         props = list(set(props))
 
         super(PropnetBuilder, self).__init__(source=materials,
                                              target=propstore,
+                                             query=self.criteria,
                                              ufn=self.process,
                                              projection=props,
                                              **kwargs)
@@ -180,6 +198,9 @@ def process(self, item):
         aggregated_quantities = new_material.get_aggregated_quantities()
 
         for symbol, quantity in aggregated_quantities.items():
+            if symbol.name not in doc:
+                # No new quantities were derived
+                continue
             # Store mean and std dev for aggregated quantities
             sub_doc = {"mean": unumpy.nominal_values(quantity.value).tolist(),
                        "std_dev": unumpy.std_devs(quantity.value).tolist(),
@@ -189,7 +210,8 @@ def process(self, item):
             doc[symbol.name].update(sub_doc)
 
         doc.update({"task_id": item["task_id"],
-                    "pretty_formula": item.get("pretty_formula")})
+                    "pretty_formula": item.get("pretty_formula"),
+                    "deprecated": item.get("deprecated", False)})
         return jsanitize(doc, strict=True)
 
 

propnet/web/layouts_interactive.py

@@ -217,10 +217,23 @@ def clear_data(n_clicks):
     )
     def evaluate(input_rows, data, aggregate):
 
-        quantities = [QuantityFactory.create_quantity(symbol_type=ROW_IDX_TO_SYMBOL_NAME[idx],
-                                                      value=ureg.parse_expression(row['Editable Value']),
-                                                      units=Registry("units").get(ROW_IDX_TO_SYMBOL_NAME[idx]))
-                      for idx, row in enumerate(input_rows) if row['Editable Value']]
+        quantities = []
+
+        for idx, row in enumerate(input_rows):
+            if row['Editable Value']:
+                try:
+                    value = ureg.parse_expression(row['Editable Value'])
+                    units = Registry("units").get(ROW_IDX_TO_SYMBOL_NAME[idx])
+                    value.ito(units)
+                except Exception:
+                    # Someone put an invalid value in the table
+                    # TODO: Make error known to the user
+                    raise PreventUpdate
+                q = QuantityFactory.create_quantity(
+                    symbol_type=ROW_IDX_TO_SYMBOL_NAME[idx],
+                    value=value
+                )
+                quantities.append(q)
 
         if data and len(data) > 0:
             quantities += json.loads(data, cls=MontyDecoder).values()

propnet/web/layouts_plot.py

@@ -24,6 +24,10 @@
 
 from pymongo.errors import ServerSelectionTimeoutError
 
+import logging
+
+logger = logging.getLogger(__name__)
+
 mpr = MPRester()
 
 try:
@@ -213,9 +217,14 @@ def update_info_box(clickData, x_prop, y_prop, z_prop, color_prop):
         mpid = point['text']
         x = point['x']
         y = point['y']
-        print(point)
-
-        s = mpr.get_structure_by_material_id(mpid)
+        logger.debug(f"User clicked: {point}")
+
+        try:
+            s = mpr.get_structure_by_material_id(mpid)
+        except IndexError:
+            logger.error(f"{mpid} cannot be found on MP. Database refresh needed?")
+            return f"{mpid} cannot be found on Materials Project. " \
+                f"It may have been deprecated. This error has been logged."
         formula = unicodeify(s.composition.reduced_formula)
 
         info = f"""
@@ -333,26 +342,27 @@ def get_graph_data(x_prop, y_prop, z_prop, color_prop):
     props_to_get = [prop for prop in (x_prop, y_prop, z_prop, color_prop)
                     if prop is not None]
 
-    data = CorrelationBuilder.get_data_from_quantity_db(store, *props_to_get,
-                                                        include_id=True)
+    query_data = CorrelationBuilder.get_data_from_quantity_db(store, *props_to_get,
+                                                              include_id=True)
 
-    if len(data[x_prop]) == 0:
+    if any(prop not in query_data for prop in props_to_get) or \
+            any(len(query_data[prop]) == 0 for prop in props_to_get):
         return {'query_success': False}
 
     data = {
         'query_success': True,
-        'x': data[x_prop],
+        'x': query_data[x_prop],
         'x_name': x_prop,
-        'y': data[y_prop],
+        'y': query_data[y_prop],
         'y_name': y_prop,
-        'mpids': data['_id'],
+        'mpids': query_data['_id'],
         'zoom': None,
         'color_range': None
     }
     if z_prop:
-        data.update({'z': data[z_prop], 'z_name': z_prop, 'z_enabled': True})
+        data.update({'z': query_data[z_prop], 'z_name': z_prop, 'z_enabled': True})
     if color_prop:
-        data.update({'color': data[color_prop], 'color_name': color_prop, 'color_enabled': True})
+        data.update({'color': query_data[color_prop], 'color_name': color_prop, 'color_enabled': True})
 
     return data