geometallurgy 0.4.10__py3-none-any.whl → 0.4.12__py3-none-any.whl

elphick/geomet/base.py

@@ -2,6 +2,7 @@ import copy
 import inspect
 import logging
 import re
+import uuid
 from abc import ABC
 from pathlib import Path
 from typing import Optional, Union, Literal, TypeVar, TYPE_CHECKING
@@ -15,7 +16,6 @@ from elphick.geomet.config import read_yaml
 from elphick.geomet.utils.components import get_components, is_compositional
 from elphick.geomet.utils.moisture import solve_mass_moisture
 from elphick.geomet.utils.pandas import mass_to_composition, composition_to_mass, composition_factors
-from elphick.geomet.utils.sampling import random_int
 from elphick.geomet.utils.timer import log_timer
 from .config.config_read import get_column_config
 from .plot import parallel_plot, comparison_plot
@@ -714,8 +714,8 @@ class MassComposition(ABC):
         comp: 'Stream'
 
         # create the relationships
-        ref.nodes = [self.nodes[1], random_int()]
-        comp.nodes = [self.nodes[1], random_int()]
+        ref.nodes = [self.nodes[1], uuid.uuid4()]
+        comp.nodes = [self.nodes[1], uuid.uuid4()]
 
         return ref, comp
 
@@ -747,7 +747,7 @@ class MassComposition(ABC):
 
         # create the relationships
         other.nodes = [other.nodes[0], self.nodes[1]]
-        res.nodes = [self.nodes[1], random_int()]
+        res.nodes = [self.nodes[1], uuid.uuid4()]
 
         return res
 
@@ -780,7 +780,7 @@ class MassComposition(ABC):
 
         # create the relationships
         other.nodes = [self.nodes[1], other.nodes[1]]
-        res.nodes = [self.nodes[1], random_int()]
+        res.nodes = [self.nodes[1], uuid.uuid4()]
 
         return res
 

elphick/geomet/flowsheet/flowsheet.py

@@ -1,6 +1,7 @@
 import copy
 import json
 import logging
+import uuid
 from pathlib import Path
 from typing import Dict, List, Optional, Tuple, Union, TypeVar, TYPE_CHECKING
 import re
@@ -15,6 +16,7 @@ import seaborn as sns
 import yaml
 from matplotlib import pyplot as plt
 from matplotlib.colors import ListedColormap, LinearSegmentedColormap
+from networkx.algorithms.dag import is_directed_acyclic_graph
 from plotly.subplots import make_subplots
 
 from elphick.geomet import Sample
@@ -24,7 +26,6 @@ from elphick.geomet.flowsheet.operation import NodeType, OP, PartitionOperation,
 from elphick.geomet.plot import parallel_plot, comparison_plot
 from elphick.geomet.utils.layout import digraph_linear_layout
 from elphick.geomet.flowsheet.loader import streams_from_dataframe
-from elphick.geomet.utils.sampling import random_int
 
 # if TYPE_CHECKING:
 from elphick.geomet.flowsheet.stream import Stream
@@ -306,6 +307,12 @@ class Flowsheet:
     def solve(self):
         """Solve missing streams"""
 
+        if not is_directed_acyclic_graph(self.graph):
+            self._logger.error("Graph is not a Directed Acyclic Graph (DAG), so cannot be solved.")
+            self._logger.debug(f"Graph nodes: {self.graph.nodes(data=True)}")
+            self._logger.debug(f"Graph edges: {self.graph.edges(data=True)}")
+            raise ValueError("Graph is not a Directed Acyclic Graph (DAG), so cannot be solved.")
+
         # Check the number of missing mc's on edges in the network
         missing_count: int = sum([1 for u, v, d in self.graph.edges(data=True) if d['mc'] is None])
         prev_missing_count = missing_count + 1  # Initialize with a value greater than missing_count
@@ -350,6 +357,12 @@ class Flowsheet:
                         self.set_operation_data(node)
 
             missing_count: int = sum([1 for u, v, d in self.graph.edges(data=True) if d['mc'] is None])
+            self._logger.info(f"Missing count: {missing_count}")
+
+        if missing_count > 0:
+            self._logger.error(f"Failed to solve the flowsheet. Missing count: {missing_count}")
+            raise ValueError(
+                f"Failed to solve the flowsheet. Some streams are still missing. Missing count: {missing_count}")
 
     def query(self, expr: str, stream_name: Optional[str] = None, inplace=False) -> 'Flowsheet':
         """Reduce the Flowsheet Stream records with a query
@@ -424,6 +437,8 @@ class Flowsheet:
         degrees = {n: d for n, d in self.graph.degree()}
 
         res: list[MC] = [d['mc'] for u, v, d in self.graph.edges(data=True) if degrees[u] == 1]
+        if not res:
+            raise ValueError("No input streams found")
         return res
 
     def get_output_streams(self) -> list[MC]:
@@ -437,6 +452,8 @@ class Flowsheet:
         degrees = {n: d for n, d in self.graph.degree()}
 
         res: list[MC] = [d['mc'] for u, v, d in self.graph.edges(data=True) if degrees[v] == 1]
+        if not res:
+            raise ValueError("No output streams found")
         return res
 
     @staticmethod
@@ -1036,6 +1053,7 @@ class Flowsheet:
             if ('mc' in self.graph.nodes[node].keys()) and (node in node_names.keys()):
                 self.graph.nodes[node]['mc'].name = node_names[node]
 
+
     def set_stream_data(self, stream_data: dict[str, Optional[MC]]):
         """Set the data (MassComposition) of network edges (streams) with a Dict"""
         for stream_name, stream_data in stream_data.items():
@@ -1057,6 +1075,7 @@ class Flowsheet:
                     self.graph.nodes[node]['mc'].outputs = [self.graph.get_edge_data(e[0], e[1])['mc'] for e in
                                                             self.graph.out_edges(node)]
 
+
     def set_operation_data(self, node):
         """Set the input and output data for a node.
         Uses the data on the edges (streams) connected to the node to refresh the data and check for node balance.
@@ -1066,6 +1085,7 @@ class Flowsheet:
         node_data.outputs = [self.graph.get_edge_data(e[0], e[1])['mc'] for e in self.graph.out_edges(node)]
         node_data.check_balance()
 
+
     def streams_to_dict(self) -> Dict[str, MC]:
         """Export the Stream objects to a Dict
 
@@ -1079,6 +1099,7 @@ class Flowsheet:
                 streams[data['mc'].name] = data['mc']
         return streams
 
+
     def nodes_to_dict(self) -> Dict[int, OP]:
         """Export the MCNode objects to a Dict
 
@@ -1092,13 +1113,14 @@ class Flowsheet:
                 nodes[node] = self.graph.nodes[node]['mc']
         return nodes
 
+
     def set_nodes(self, stream: str, nodes: Tuple[int, int]):
         mc: MC = self.get_stream_by_name(stream)
         mc._nodes = nodes
         self._update_graph(mc)
 
-    def reset_nodes(self, stream: Optional[str] = None):
 
+    def reset_nodes(self, stream: Optional[str] = None):
         """Reset stream nodes to break relationships
 
         Args:
@@ -1112,13 +1134,14 @@ class Flowsheet:
         if stream is None:
             streams: Dict[str, MC] = self.streams_to_dict()
             for k, v in streams.items():
-                streams[k] = v.set_nodes([random_int(), random_int()])
+                streams[k] = v.set_nodes([uuid.uuid4(), uuid.uuid4()])
             self.graph = Flowsheet(name=self.name).from_objects(objects=list(streams.values())).graph
         else:
             mc: MC = self.get_stream_by_name(stream)
-            mc.set_nodes([random_int(), random_int()])
+            mc.set_nodes([uuid.uuid4(), uuid.uuid4()])
             self._update_graph(mc)
 
+
     def _update_graph(self, mc: MC):
         """Update the graph with an existing stream object
 
@@ -1137,6 +1160,7 @@ class Flowsheet:
                 strms.append(a['mc'])
         self.graph = Flowsheet(name=self.name).from_objects(objects=strms).graph
 
+
     def get_stream_by_name(self, name: str) -> MC:
         """Get the Stream object from the network by its name
 
@@ -1157,18 +1181,20 @@ class Flowsheet:
 
         return res
 
+
     def set_stream_parent(self, stream: str, parent: str):
         mc: MC = self.get_stream_by_name(stream)
         mc.set_parent_node(self.get_stream_by_name(parent))
         self._update_graph(mc)
 
+
     def set_stream_child(self, stream: str, child: str):
         mc: MC = self.get_stream_by_name(stream)
         mc.set_child_node(self.get_stream_by_name(child))
         self._update_graph(mc)
 
-    def reset_stream_nodes(self, stream: Optional[str] = None):
 
+    def reset_stream_nodes(self, stream: Optional[str] = None):
         """Reset stream nodes to break relationships
 
         Args:
@@ -1182,9 +1208,9 @@ class Flowsheet:
         if stream is None:
             streams: Dict[str, MC] = self.streams_to_dict()
             for k, v in streams.items():
-                streams[k] = v.set_nodes([random_int(), random_int()])
+                streams[k] = v.set_nodes([uuid.uuid4(), uuid.uuid4()])
             self.graph = Flowsheet(name=self.name).from_objects(objects=list(streams.values())).graph
         else:
             mc: MC = self.get_stream_by_name(stream)
-            mc.set_nodes([random_int(), random_int()])
+            mc.set_nodes([uuid.uuid4(), uuid.uuid4()])
             self._update_graph(mc)

elphick/geomet/flowsheet/stream.py

@@ -1,10 +1,12 @@
+import uuid
+
 from elphick.geomet.base import MassComposition
 
 
 class Stream(MassComposition):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.nodes = [self.random_int(), self.random_int()]
+        self.nodes = [uuid.uuid4(), uuid.uuid4()]
 
     def set_parent_node(self, parent: 'Stream') -> 'Stream':
         self.nodes = [parent.nodes[1], self.nodes[1]]
@@ -15,14 +17,13 @@ class Stream(MassComposition):
         return self
 
     def set_nodes(self, nodes: list) -> 'Stream':
+        if len(nodes) != 2:
+            raise ValueError('Nodes must be a list of length 2')
+        if nodes[0] == nodes[1]:
+            raise ValueError('Nodes must be different')
         self.nodes = nodes
         return self
 
-    @staticmethod
-    def random_int():
-        import random
-        return random.randint(0, 100)
-
     # @classmethod
     # def from_mass_composition(cls, obj: MassComposition) -> 'Stream':
     #     filtered_kwargs = filter_kwargs(obj, **obj.__dict__)

elphick/geomet/interval_sample.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import functools
+import uuid
 from pathlib import Path
 from typing import Optional, Literal, Callable, Union, Iterable, TYPE_CHECKING
 
@@ -18,7 +19,6 @@ from elphick.geomet.utils.interp import mass_preserving_interp
 from elphick.geomet.utils.interp2 import mass_preserving_interp_2d
 from elphick.geomet.utils.pandas import MeanIntervalIndex, weight_average, calculate_recovery, calculate_partition, \
     cumulate, mass_to_composition
-from elphick.geomet.utils.sampling import random_int
 
 from elphick.geomet.base import MassComposition
 
@@ -146,10 +146,10 @@ class IntervalSample(MassComposition):
 
         sample_1 = self.create_congruent_object(name=name_1).to_stream()
         sample_1.mass_data = self.mass_data.copy().multiply(pn, axis=0)
-        sample_1.set_nodes([self.nodes[1], random_int()])
+        sample_1.set_nodes([self.nodes[1], uuid.uuid4()])
         sample_2 = self.create_congruent_object(name=name_2)
         sample_2.mass_data = self.mass_data.copy().multiply((1 - pn), axis=0)
-        sample_2.set_nodes([self.nodes[1], random_int()])
+        sample_2.set_nodes([self.nodes[1], uuid.uuid4()])
 
         return sample_1, sample_2
 
@@ -585,6 +585,7 @@ class IntervalSample(MassComposition):
         df_upsampled: pd.DataFrame = mass_preserving_interp(self.mass_data,
                                                             interval_edges=interval_edges, precision=precision,
                                                             include_original_edges=include_original_edges,
+                                                            mass_wet=None, mass_dry=self.mass_dry_var,
                                                             interval_data_as_mass=True)
 
         obj: IntervalSample = IntervalSample(df_upsampled, name=self.name, moisture_in_scope=False,

elphick/geomet/utils/interp.py

@@ -9,7 +9,7 @@ from elphick.geomet.utils.pandas import composition_to_mass, mass_to_composition
 
 def mass_preserving_interp(df_intervals: pd.DataFrame, interval_edges: Union[Iterable, int],
                            include_original_edges: bool = True, precision: Optional[int] = None,
-                           mass_wet: str = 'mass_wet', mass_dry: str = 'mass_dry',
+                           mass_wet: Optional[str] = 'mass_wet', mass_dry: str = 'mass_dry',
                            interval_data_as_mass: bool = False) -> pd.DataFrame:
     """Interpolate with zero mass loss using pchip
 
@@ -81,7 +81,7 @@ def mass_preserving_interp(df_intervals: pd.DataFrame, interval_edges: Union[Ite
     # if the new grid extrapolates (on the coarse side), mass will be lost, so we assume that when extrapolating.
     # the mass in the extrapolated fractions is zero.  By inserting these records the spline will conform.
     x_extra = grid_vals[grid_vals > mass_cum.index.max()]
-    if x_extra:
+    if len(x_extra) > 0:
         cum_max: pd.Series = mass_cum.iloc[-1, :]
         mass_cum = mass_cum.reindex(index=mass_cum.index.append(pd.Index(x_extra)))  # reindex to enable insert
         mass_cum.loc[x_extra, :] = cum_max.values
@@ -180,7 +180,8 @@ def mass_preserving_interp_2d(intervals: pd.DataFrame, interval_edges: dict[str,
             # proportion the dim_1 interpolated values by the dim_2 recovery
             new_vals: pd.DataFrame = dim_2_deportment.mul(filtered_intervals_mass.loc[dim_1_interp_interval].values)
             # create a multiindex by combining the dim_1 and dim_2 intervals
-            new_index = pd.MultiIndex.from_arrays([pd.IntervalIndex([dim_1_interp_interval] * len(new_vals)), new_vals.index])
+            new_index = pd.MultiIndex.from_arrays(
+                [pd.IntervalIndex([dim_1_interp_interval] * len(new_vals)), new_vals.index])
             new_vals.index = new_index
             chunks.append(new_vals)
 
@@ -190,4 +191,3 @@ def mass_preserving_interp_2d(intervals: pd.DataFrame, interval_edges: dict[str,
     # convert to composition
     res = mass_to_composition(res, mass_dry=mass_dry)
     return res
-

elphick/geomet/utils/pandas.py

@@ -88,7 +88,7 @@ def composition_to_mass(df: pd.DataFrame,
         df: The pd.DataFrame containing mass.  H2O if provided will be ignored.  All columns other than the
          mass_wet and mass_dry are assumed to be `additive`, that is, dry mass weighting is valid.
          Assumes composition is in %w/w units.
-        mass_wet: The wet mass column, optional. If not provided, it's assumed to be equal to mass_dry.
+        mass_wet: The wet mass column, optional.
         mass_dry: The dry mass column, not optional.  Consider solve_mass_moisture prior to this call if needed.
         moisture_column_name: if mass_wet is provided, the resultant moisture will be returned with this column name.
          If None, and moisture is detected in the input, that column name will be used instead.

elphick/geomet/utils/timer.py

@@ -10,7 +10,7 @@ from typing import Union
 
 class MyLogger:
     def __init__(self):
-        logging.basicConfig(level=logging.INFO,
+        logging.basicConfig(level=logging.DEBUG,
                             format=' %(asctime)s - %(levelname)s - %(message)s')
 
     def get_logger(self, name=None):

{geometallurgy-0.4.10.dist-info → geometallurgy-0.4.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geometallurgy
-Version: 0.4.10
+Version: 0.4.12
 Summary: Tools for the geometallurgist
 Home-page: https://github.com/elphick/geometallurgy
 Author: Greg

{geometallurgy-0.4.10.dist-info → geometallurgy-0.4.12.dist-info}/RECORD

@@ -1,5 +1,5 @@
 elphick/geomet/__init__.py,sha256=gcaArz-agLsm_Tf9KNvmGznw4Jml2QTjj_CxKUC1Ejg,274
-elphick/geomet/base.py,sha256=4e4cJUDUPsVgv6xEyU8ML9xYUkOznCLPidQB3fXcVnM,50644
+elphick/geomet/base.py,sha256=vp0C7DEAAUDGhTdQ8_Hz9WmqZRjNGn7m5CqEGy3L_98,50603
 elphick/geomet/block_model.py,sha256=Q-LEdILajUoteO0834IXeS75k8pcPqSaMrinMcWD8R4,14639
 elphick/geomet/config/__init__.py,sha256=F94hbxN3KzSaljbElIGVhdEwX0FKmHxST4jJ7rNohxY,35
 elphick/geomet/config/config_read.py,sha256=frRwfRwUXpgxwMNCiBVFUw1-yPbBHs3h2KjmzXImvxY,1396
@@ -15,11 +15,11 @@ elphick/geomet/datasets/register.csv,sha256=-N3F6L0097C-I79axINi_ewFAxiqbT_SOSW3
 elphick/geomet/datasets/sample_data.py,sha256=jt5DWxdMmPbZGDuon2s8Q2wlX3cEegB0dSmRKF4pz4I,7684
 elphick/geomet/extras.py,sha256=0yDwbPMylP21EOo27juu4gUiewygSXLSjggYDrPvDcQ,1128
 elphick/geomet/flowsheet/__init__.py,sha256=-lxSLPZNQfiLXKZ2qqS5XbbhrZA2ABi3ppx0LaHnNEI,33
-elphick/geomet/flowsheet/flowsheet.py,sha256=ZSTXcdIo8ERRFsgDU8x1Wdh49mVDi4cIi5AY8hH8Yg8,51105
+elphick/geomet/flowsheet/flowsheet.py,sha256=__kgowBIyWfvXcdPWCFihoEUdOqTj7KszSbKGF1AkBo,52032
 elphick/geomet/flowsheet/loader.py,sha256=8nd9Vqbg1de35iuoc4mdRFxrUsIBZed0ivXIAu80jBk,4756
 elphick/geomet/flowsheet/operation.py,sha256=f8k0-Gr_Uy2SlEp8bwAaG4yeBa3DU0HoPn9wyWhYipE,9720
-elphick/geomet/flowsheet/stream.py,sha256=RL4ZNcSm-u0MwdXp1gWq2q6FTnPs5q4xIOavs9FEDVg,1286
-elphick/geomet/interval_sample.py,sha256=6Cu9hN6Vnl8w3Tuzs7YP7Fv4H7-70vw-tJimJbP96Ng,31258
+elphick/geomet/flowsheet/stream.py,sha256=NOXcYeZLSmOSoSRFc7M36Jc8c1ARgjiCvtRuixYfuqA,1370
+elphick/geomet/interval_sample.py,sha256=fhcWBTA01TqvCBsJv7dzWZHRBpw_4W2Ahawks5SPj28,31320
 elphick/geomet/io.py,sha256=tZsX_getGxL07dPlF3Ozyzvt2tFHE5OdgPM5pc5xL68,15709
 elphick/geomet/plot.py,sha256=e9uz8L3QZ23CW4OYm78NhdZl01i0DxHfC4r1kigz7Ss,5732
 elphick/geomet/profile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -30,20 +30,19 @@ elphick/geomet/utils/block_model_converter.py,sha256=REYbS4cu-8z0IzCpuU9ISlPnAvx
 elphick/geomet/utils/components.py,sha256=oDR8w7aFKRP38u98yfHp-8MtOaG-c0YcGtwNjgrhGWA,3546
 elphick/geomet/utils/data.py,sha256=AnQ3JXEt2M-T5doGljM_fvdX1CvGbMr6wwjxqcw0fjs,1983
 elphick/geomet/utils/estimates.py,sha256=-x6KDQb-04IrxN8yO38Fx93F6_SGG67koagCtYBtW3c,4892
-elphick/geomet/utils/interp.py,sha256=VLzz1ui5j7iyYDKtJeZ8FIdArYEPipuvgW9iAquoBi0,10644
+elphick/geomet/utils/interp.py,sha256=9lb2sEFfAWYzFECybLPD4nF0S85Xo37nNkxU1DG__A4,10679
 elphick/geomet/utils/interp2.py,sha256=ybuQBNTQOdVzmVYOhQDx2LkGKpl8yxgbQPz_hwS8ClQ,6633
 elphick/geomet/utils/layout.py,sha256=-c1EF-G0qGRQbLrrTS-LsbII-lnvw71y97iUBLd02do,2080
 elphick/geomet/utils/moisture.py,sha256=t9WMwADyz-QAMW-cdah1tIlzTDrhooSoKOPdIlVQHvU,2192
-elphick/geomet/utils/pandas.py,sha256=prMAtLlgRJaFICwbZXX7Fn4R_PbzJsVoLWsr7oYEcN8,17452
+elphick/geomet/utils/pandas.py,sha256=6sKl3WUjXLR7qFmqBzuCjnfCoUsLRapwZk2nO5BfzYI,17397
 elphick/geomet/utils/parallel.py,sha256=l38JBTkCmdqKHQkS8njoA-sBN9XQGkhF59XtAhWShgs,842
 elphick/geomet/utils/partition.py,sha256=U0jFpvdvZJVdutfB6RzUzKfO9NWCGtBkeySx-QbP-l4,1534
-elphick/geomet/utils/sampling.py,sha256=qwf1ZUjsg431rpFqto_8WxLwlMCGyC5bWUlPXo-nHIM,61
 elphick/geomet/utils/size.py,sha256=EmV_sv2bOImQN3s7TWCniU_y83HNJEPtZH7fMMkYTcc,2272
-elphick/geomet/utils/timer.py,sha256=J09nGNSkH8jdHzSmY1F3goBmycDacVe0SUMEhj7ATzw,3111
+elphick/geomet/utils/timer.py,sha256=8WNKLFcINRsZ3IsKtOIZ77YbKtqczyOOTEWY9h9Uxxw,3112
 elphick/geomet/utils/viz.py,sha256=M0CnfDXBHtYb8aak1Sfz6XLvRSmkzX3ybIDllEmDR8A,1718
 elphick/geomet/validate.py.hide,sha256=qAWJlgq0jp19UakVV0dEU_AsqV_JctUn1QTHn8cCRw0,6738
-geometallurgy-0.4.10.dist-info/LICENSE,sha256=GrSVdcGtNbGvAYC_tIjLHBrIVPyg-Ksfe7ZGr087yCI,1069
-geometallurgy-0.4.10.dist-info/METADATA,sha256=W0FwaOzfkkhGA55im6RoioV5CkvcnSxQQWKm5pL3fxE,4386
-geometallurgy-0.4.10.dist-info/WHEEL,sha256=WGfLGfLX43Ei_YORXSnT54hxFygu34kMpcQdmgmEwCQ,88
-geometallurgy-0.4.10.dist-info/entry_points.txt,sha256=aQI-8kmaba_c9ZGOFkJgWl0MWBke5BQLNyPSVcbS7EU,58
-geometallurgy-0.4.10.dist-info/RECORD,,
+geometallurgy-0.4.12.dist-info/LICENSE,sha256=GrSVdcGtNbGvAYC_tIjLHBrIVPyg-Ksfe7ZGr087yCI,1069
+geometallurgy-0.4.12.dist-info/METADATA,sha256=iatuwf4Pey2ZHhaEu-p-NJ-tEVCdZAijNXZf91jhgpM,4386
+geometallurgy-0.4.12.dist-info/WHEEL,sha256=WGfLGfLX43Ei_YORXSnT54hxFygu34kMpcQdmgmEwCQ,88
+geometallurgy-0.4.12.dist-info/entry_points.txt,sha256=aQI-8kmaba_c9ZGOFkJgWl0MWBke5BQLNyPSVcbS7EU,58
+geometallurgy-0.4.12.dist-info/RECORD,,

elphick/geomet/utils/sampling.py

@@ -1,5 +0,0 @@
-import uuid
-
-
-def random_int():
-    return int(uuid.uuid4())