risk-network 0.0.7b12__py3-none-any.whl → 0.0.8b1__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: RISK Infers Spatial Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.7-beta.12"
+__version__ = "0.0.8-beta.1"

risk/network/io.py

@@ -153,8 +153,10 @@ class NetworkIO:
         params.log_network(filetype=filetype)
         self._log_loading(filetype)
 
+        # Important: Make a copy of the network to avoid modifying the original
+        network_copy = network.copy()
         # Initialize the graph
-        return self._initialize_graph(network)
+        return self._initialize_graph(network_copy)
 
     @staticmethod
     def load_cytoscape_network(
@@ -475,16 +477,50 @@ class NetworkIO:
             logger.debug(f"Total edges missing weights: {missing_weights}")
 
     def _validate_nodes(self, G: nx.Graph) -> None:
-        """Validate the graph structure and attributes.
+        """Validate the graph structure and attributes with attribute fallback for positions and labels.
 
         Args:
             G (nx.Graph): A NetworkX graph object.
         """
+        # Keep track of nodes missing labels
+        nodes_with_missing_labels = []
+
         for node, attrs in G.nodes(data=True):
-            assert (
-                "x" in attrs and "y" in attrs
-            ), f"Node {node} is missing 'x' or 'y' position attributes."
-            assert "label" in attrs, f"Node {node} is missing a 'label' attribute."
+            # Attribute fallback for 'x' and 'y' attributes
+            if "x" not in attrs or "y" not in attrs:
+                if (
+                    "pos" in attrs
+                    and isinstance(attrs["pos"], (tuple, list))
+                    and len(attrs["pos"]) >= 2
+                ):
+                    attrs["x"], attrs["y"] = attrs["pos"][
+                        :2
+                    ]  # Use only x and y, ignoring z if present
+                else:
+                    raise ValueError(
+                        f"Node {node} is missing 'x', 'y', and a valid 'pos' attribute."
+                    )
+
+            # Attribute fallback for 'label' attribute
+            if "label" not in attrs:
+                # Try alternative attribute names for label
+                if "name" in attrs:
+                    attrs["label"] = attrs["name"]
+                elif "id" in attrs:
+                    attrs["label"] = attrs["id"]
+                else:
+                    # Collect nodes with missing labels
+                    nodes_with_missing_labels.append(node)
+                    attrs["label"] = str(node)  # Use node ID as the label
+
+        # Issue a single warning if any labels were missing
+        if nodes_with_missing_labels:
+            total_nodes = len(G.nodes)
+            fraction_missing_labels = len(nodes_with_missing_labels) / total_nodes
+            logger.warning(
+                f"{len(nodes_with_missing_labels)} out of {total_nodes} nodes "
+                f"({fraction_missing_labels:.2%}) were missing 'label' attributes and were assigned node IDs."
+            )
 
     def _assign_edge_lengths(self, G: nx.Graph) -> None:
         """Prepare the network by adjusting surface depth and calculating edge lengths.

risk/stats/permutation/permutation.py

@@ -133,6 +133,7 @@ def _run_permutation_test(
                     observed_neighborhood_scores,
                     neighborhood_score_func,
                     subset_size + (1 if i < remainder else 0),
+                    num_permutations,
                     progress_counter,
                     max_workers,
                     rng,  # Pass the random number generator to each worker
@@ -144,11 +145,9 @@ def _run_permutation_test(
             results = pool.starmap_async(_permutation_process_subset, params_list, chunksize=1)
 
             # Update progress bar based on progress_counter
-            # NOTE: Waiting for results to be ready while updating progress bar gives a big improvement
-            # in performance, especially for large number of permutations and workers
             while not results.ready():
                 progress.update(progress_counter.value - progress.n)
-                results.wait(0.05)  # Wait for 50ms
+                results.wait(0.1)  # Wait for 100ms
             # Ensure progress bar reaches 100%
             progress.update(total_progress - progress.n)
 
@@ -167,6 +166,7 @@ def _permutation_process_subset(
     observed_neighborhood_scores: np.ndarray,
     neighborhood_score_func: Callable,
     subset_size: int,
+    num_permutations: int,
     progress_counter: ValueProxy,
     max_workers: int,
     rng: np.random.Generator,
@@ -180,6 +180,7 @@ def _permutation_process_subset(
         observed_neighborhood_scores (np.ndarray): Observed neighborhood scores.
         neighborhood_score_func (Callable): Function to calculate neighborhood scores.
         subset_size (int): Number of permutations to run in this subset.
+        num_permutations (int): Number of total permutations across all subsets.
         progress_counter (multiprocessing.managers.ValueProxy): Shared counter for tracking progress.
         max_workers (int): Number of workers for multiprocessing.
         rng (np.random.Generator): Random number generator object.
@@ -190,11 +191,15 @@ def _permutation_process_subset(
     # Initialize local count matrices for this worker
     local_counts_depletion = np.zeros(observed_neighborhood_scores.shape)
     local_counts_enrichment = np.zeros(observed_neighborhood_scores.shape)
+
     # NOTE: Limit the number of threads used by NumPy's BLAS implementation to 1 when more than one worker is used.
-    # This can help prevent oversubscription of CPU resources during multiprocessing, ensuring that each process
-    # doesn't use more than one CPU core.
     limits = None if max_workers == 1 else 1
     with threadpool_limits(limits=limits, user_api="blas"):
+        # Initialize a local counter for batched progress updates
+        local_progress = 0
+        # Calculate the modulo value based on total permutations for 1/100th frequency updates
+        modulo_value = max(1, num_permutations // 100)
+
         for _ in range(subset_size):
             # Permute the annotation matrix using the RNG
             annotation_matrix_permut = annotation_matrix[rng.permutation(idxs)]
@@ -212,7 +217,15 @@ def _permutation_process_subset(
                 local_counts_enrichment,
                 permuted_neighborhood_scores >= observed_neighborhood_scores,
             )
-            # Update the shared progress counter
-            progress_counter.value += 1
+
+            # Update local progress counter
+            local_progress += 1
+            # Update shared progress counter every 1/100th of total permutations
+            if local_progress % modulo_value == 0:
+                progress_counter.value += modulo_value
+
+        # Final progress update for any remaining iterations
+        if local_progress % modulo_value != 0:
+            progress_counter.value += modulo_value
 
     return local_counts_depletion, local_counts_enrichment

{risk_network-0.0.7b12.dist-info → risk_network-0.0.8b1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.7b12
+Version: 0.0.8b1
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>

{risk_network-0.0.7b12.dist-info → risk_network-0.0.8b1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-risk/__init__.py,sha256=b9WNiI1lQZaEaH5NHdgQdLB2MS9EUzlVycFh2JpNEJs,113
+risk/__init__.py,sha256=UNSdF3ch5eG5kY1NsOrjzDZOS-HRak9ASoBVXBkvCAM,112
 risk/constants.py,sha256=XInRaH78Slnw_sWgAsBFbUHkyA0h0jL0DKGuQNbOvjM,550
 risk/risk.py,sha256=FaQhDCBZxZSAXJsScH0rSbjjCTNZA5vgf9rJj1GHW44,20924
 risk/annotations/__init__.py,sha256=vUpVvMRE5if01Ic8QY6M2Ae3EFGJHdugEe9PdEkAW4Y,138
@@ -14,17 +14,17 @@ risk/neighborhoods/neighborhoods.py,sha256=M-wL4xB_BUTlSZg90swygO5NdrZ6hFUFqs6js
 risk/network/__init__.py,sha256=iEPeJdZfqp0toxtbElryB8jbz9_t_k4QQ3iDvKE8C_0,126
 risk/network/geometry.py,sha256=H1yGVVqgbfpzBzJwEheDLfvGLSA284jGQQTn612L4Vc,6759
 risk/network/graph.py,sha256=_LEoom4EEowGALuJKSXcev9RAAHu2FqIeq3u7mkifW0,16479
-risk/network/io.py,sha256=ASoKG4vkCC_aHwxlF4502W_SyaaCrRnHsTmRwL00spI,21266
+risk/network/io.py,sha256=kY7HqmL3wa1NnqHu61_G8IpT21qpBijpAZ4ixmsseJA,22911
 risk/network/plot.py,sha256=9GcLKkH3CMEtraYnfdLXNJCi04rBQCjw4T6Q8k5yNOI,67091
 risk/stats/__init__.py,sha256=WcgoETQ-hS0LQqKRsAMIPtP15xZ-4eul6VUBuUx4Wzc,220
 risk/stats/hypergeom.py,sha256=o6Qnj31gCAKxr2uQirXrbv7XvdDJGEq69MFW-ubx_hA,2272
 risk/stats/poisson.py,sha256=8x9hB4DCukq4gNIlIKO-c_jYG1-BTwTX53oLauFyfj8,1793
 risk/stats/stats.py,sha256=kvShov-94W6ffgDUTb522vB9hDJQSyTsYif_UIaFfSM,7059
 risk/stats/permutation/__init__.py,sha256=neJp7FENC-zg_CGOXqv-iIvz1r5XUKI9Ruxhmq7kDOI,105
-risk/stats/permutation/permutation.py,sha256=kmSZ7bQ-AD0TFiQDgIwfxTeqHa4pjp7fIcOzAqyhUNY,9714
+risk/stats/permutation/permutation.py,sha256=D84Rcpt6iTQniK0PfQGcw9bLcHbMt9p-ARcurUnIXZQ,10095
 risk/stats/permutation/test_functions.py,sha256=lftOude6hee0pyR80HlBD32522JkDoN5hrKQ9VEbuoY,2345
-risk_network-0.0.7b12.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.7b12.dist-info/METADATA,sha256=BHkHe5vNDc1pLERmMqrAQhO0I-DAeQbF8g44BRd1k1I,43143
-risk_network-0.0.7b12.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-risk_network-0.0.7b12.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.7b12.dist-info/RECORD,,
+risk_network-0.0.8b1.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.8b1.dist-info/METADATA,sha256=E0T1xFQXaQfe3oH0ZW7fAukDoB3QbvzswcLc0oczpqA,43142
+risk_network-0.0.8b1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+risk_network-0.0.8b1.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.8b1.dist-info/RECORD,,