Merge pull request #60 from JetBrains-Research/dev

Patch 1.0.1

Author: vadyushkins

cfpq_data/__init__.py

@@ -7,7 +7,7 @@
 experimental analysis of context-free path querying algorithms
 """
 
-__version__ = "1.0.0"
+__version__ = "1.0.1"
 
 import cfpq_data.config
 from cfpq_data.config import *

cfpq_data/grammars/readwrite/rsm.py

@@ -52,7 +52,7 @@ def rsm_from_text(source: str, start_symbol: Variable = Variable("S")) -> RSM:
     boxes = list()
 
     for production in source.splitlines():
-        if not production:
+        if " -> " not in production:
             continue
 
         head, body = production.split(" -> ")

cfpq_data/grammars/rsm.py

@@ -71,7 +71,7 @@ def to_text(self) -> str:
         productions = [f"{box[0]} -> {box[1].to_regex()}" for box in self.boxes]
         return "\n".join(productions)
 
-    def to_cfg(self):
+    def to_cfg(self) -> CFG:
         """Create a context-free grammar [1]_
         from Recursive State Machine [2]_.
 

cfpq_data/graphs/generators/fast_labeled_binomial_graph.py

@@ -8,6 +8,7 @@
 import numpy as np
 from networkx import MultiDiGraph, fast_gnp_random_graph
 from numpy.random import RandomState
+from tqdm import tqdm
 
 __all__ = ["fast_labeled_binomial_graph"]
 
@@ -17,6 +18,7 @@ def fast_labeled_binomial_graph(
     edge_probability: float,
     seed: Union[int, RandomState, None] = None,
     edge_labels: Iterable[str] = "a",
+    verbose: bool = True,
 ) -> MultiDiGraph:
     """Returns a $G_{n,p}$ random graph,
     also known as an Erdős-Rényi graph or
@@ -38,12 +40,17 @@ def fast_labeled_binomial_graph(
     edge_labels: Iterable[str]
         Labels that will be used to mark the edges of the graph.
 
+    verbose : bool
+        If true, a progress bar will be displayed.
+
     Examples
     --------
     >>> import cfpq_data
-    >>> g = cfpq_data.fast_labeled_binomial_graph(42, 0.42, seed=42)
-    >>> g.number_of_nodes(), g.number_of_edges()
-    (42, 722)
+    >>> g = cfpq_data.fast_labeled_binomial_graph(42, 0.42, seed=42, verbose=False)
+    >>> g.number_of_nodes()
+    42
+    >>> g.number_of_edges()
+    722
 
     Returns
     -------
@@ -78,7 +85,7 @@ def fast_labeled_binomial_graph(
     random.seed(seed)
     np.random.seed(seed)
 
-    for edge in g.edges:
+    for edge in tqdm(g.edges, disable=not verbose, desc="Generation..."):
         g.edges[edge]["label"] = np.random.choice(list(edge_labels))
 
     return g

cfpq_data/graphs/generators/labeled_barabasi_albert_graph.py

@@ -11,6 +11,7 @@
 import numpy as np
 from networkx import MultiDiGraph, barabasi_albert_graph
 from numpy.random import RandomState
+from tqdm import tqdm
 
 __all__ = ["labeled_barabasi_albert_graph"]
 
@@ -20,6 +21,7 @@ def labeled_barabasi_albert_graph(
     number_of_edges: int,
     seed: Union[int, RandomState, None] = None,
     edge_labels: Iterable[str] = "abcd",
+    verbose: bool = True,
 ) -> MultiDiGraph:
     """Returns a random graph according
     to the Barabási–Albert preferential attachment model
@@ -42,12 +44,17 @@ def labeled_barabasi_albert_graph(
     edge_labels: Iterable[str]
         Labels that will be used to mark the edges of the graph.
 
+    verbose : bool
+        If true, a progress bar will be displayed.
+
     Examples
     --------
     >>> import cfpq_data
-    >>> g = cfpq_data.labeled_barabasi_albert_graph(42, 29, 42)
-    >>> g.number_of_nodes(), g.number_of_edges()
-    (42, 754)
+    >>> g = cfpq_data.labeled_barabasi_albert_graph(42, 29, 42, verbose=False)
+    >>> g.number_of_nodes()
+    42
+    >>> g.number_of_edges()
+    754
 
     Returns
     -------
@@ -73,7 +80,7 @@ def labeled_barabasi_albert_graph(
     random.seed(seed)
     np.random.seed(seed)
 
-    for edge in g.edges:
+    for edge in tqdm(g.edges, disable=not verbose, desc="Generation..."):
         label = np.random.choice(list(edge_labels))
         g.edges[edge]["label"] = label
 

cfpq_data/graphs/generators/labeled_binomial_graph.py

@@ -8,6 +8,7 @@
 import numpy as np
 from networkx import MultiDiGraph, gnp_random_graph
 from numpy.random import RandomState
+from tqdm import tqdm
 
 __all__ = ["labeled_binomial_graph"]
 
@@ -17,6 +18,7 @@ def labeled_binomial_graph(
     edge_probability: float,
     seed: Union[int, RandomState, None] = None,
     edge_labels: Iterable[str] = "a",
+    verbose: bool = True,
 ) -> MultiDiGraph:
     """Returns a $G_{n,p}$ random graph,
     also known as an Erdős-Rényi graph or
@@ -38,12 +40,17 @@ def labeled_binomial_graph(
     edge_labels: Iterable[str]
         Labels that will be used to mark the edges of the graph.
 
+    verbose : bool
+        If true, a progress bar will be displayed.
+
     Examples
     --------
     >>> import cfpq_data
-    >>> g = cfpq_data.labeled_binomial_graph(42, 0.84, seed=42)
-    >>> g.number_of_nodes(), g.number_of_edges()
-    (42, 1453)
+    >>> g = cfpq_data.labeled_binomial_graph(42, 0.84, seed=42, verbose=False)
+    >>> g.number_of_nodes()
+    42
+    >>> g.number_of_edges()
+    1453
 
     Returns
     -------
@@ -70,7 +77,7 @@ def labeled_binomial_graph(
     random.seed(seed)
     np.random.seed(seed)
 
-    for edge in g.edges:
+    for edge in tqdm(g.edges, disable=not verbose, desc="Generation..."):
         g.edges[edge]["label"] = np.random.choice(list(edge_labels))
 
     return g

cfpq_data/graphs/generators/labeled_cycle_graph.py

@@ -7,12 +7,15 @@
 from typing import Union, Iterable, Any
 
 from networkx import MultiDiGraph, cycle_graph
+from tqdm import tqdm
 
 __all__ = ["labeled_cycle_graph"]
 
 
 def labeled_cycle_graph(
-    number_of_nodes: Union[int, Iterable[Any]], edge_label: str = "a"
+    number_of_nodes: Union[int, Iterable[Any]],
+    edge_label: str = "a",
+    verbose: bool = True,
 ) -> MultiDiGraph:
     """Returns a cycle graph $C_n$
     of cyclically connected nodes.
@@ -29,12 +32,17 @@ def labeled_cycle_graph(
     edge_label: str
         Label that will be used to mark the edges of the graph.
 
+    verbose : bool
+        If true, a progress bar will be displayed.
+
     Examples
     --------
     >>> import cfpq_data
-    >>> g = cfpq_data.labeled_cycle_graph(42)
-    >>> g.number_of_nodes(), g.number_of_edges()
-    (42, 42)
+    >>> g = cfpq_data.labeled_cycle_graph(42, verbose=False)
+    >>> g.number_of_nodes()
+    42
+    >>> g.number_of_edges()
+    42
 
     Returns
     -------
@@ -43,7 +51,7 @@ def labeled_cycle_graph(
     """
     g = cycle_graph(n=number_of_nodes, create_using=MultiDiGraph)
 
-    for edge in g.edges:
+    for edge in tqdm(g.edges, disable=not verbose, desc="Generation..."):
         g.edges[edge]["label"] = edge_label
 
     return g

cfpq_data/graphs/generators/labeled_scale_free_graph.py

@@ -7,6 +7,7 @@
 import numpy as np
 from networkx import MultiDiGraph, scale_free_graph
 from numpy.random import RandomState
+from tqdm import tqdm
 
 __all__ = ["labeled_scale_free_graph"]
 
@@ -20,6 +21,7 @@ def labeled_scale_free_graph(
     delta_out: float = 0,
     seed: Union[int, RandomState, None] = None,
     edge_labels: Iterable[str] = "abcd",
+    verbose: bool = True,
 ) -> MultiDiGraph:
     """Returns a scale-free directed graph.
     With labeled edges.
@@ -55,12 +57,17 @@ def labeled_scale_free_graph(
     edge_labels: Iterable[str]
         Labels that will be used to mark the edges of the graph.
 
+    verbose : bool
+        If true, a progress bar will be displayed.
+
     Examples
     --------
     >>> import cfpq_data
-    >>> g = cfpq_data.labeled_scale_free_graph(42, seed=42)
-    >>> g.number_of_nodes(), g.number_of_edges()
-    (42, 88)
+    >>> g = cfpq_data.labeled_scale_free_graph(42, seed=42, verbose=False)
+    >>> g.number_of_nodes()
+    42
+    >>> g.number_of_edges()
+    88
 
     Returns
     -------
@@ -93,7 +100,7 @@ def labeled_scale_free_graph(
     random.seed(seed)
     np.random.seed(seed)
 
-    for edge in g.edges:
+    for edge in tqdm(g.edges, disable=not verbose, desc="Generation..."):
         label = np.random.choice(list(edge_labels))
         g.edges[edge]["label"] = label
 

cfpq_data/graphs/generators/labeled_two_cycles_graph.py

@@ -4,6 +4,7 @@
 from typing import Union, Iterable, Any, Tuple
 
 from networkx import MultiDiGraph, compose, path_graph
+from tqdm import tqdm
 
 __all__ = ["labeled_two_cycles_graph"]
 
@@ -13,6 +14,7 @@ def labeled_two_cycles_graph(
     m: Union[int, Iterable[Any]],
     common: Union[int, Any] = 0,
     edge_labels: Tuple[str, str] = ("a", "b"),
+    verbose: bool = True,
 ) -> MultiDiGraph:
     """Returns a graph with two cycles connected by one node.
     With labeled edges.
@@ -35,12 +37,17 @@ def labeled_two_cycles_graph(
     edge_labels: Tuple[str, str]
         Labels that will be used to mark the edges of the graph.
 
+    verbose : bool
+        If true, a progress bar will be displayed.
+
     Examples
     --------
     >>> import cfpq_data
-    >>> g = cfpq_data.labeled_two_cycles_graph(42, 29)
-    >>> g.number_of_nodes(), g.number_of_edges()
-    (72, 73)
+    >>> g = cfpq_data.labeled_two_cycles_graph(42, 29, verbose=False)
+    >>> g.number_of_nodes()
+    72
+    >>> g.number_of_edges()
+    73
 
     Returns
     -------
@@ -67,10 +74,14 @@ def labeled_two_cycles_graph(
         tmp.add_edge(common, first_node)
         tmp.add_edge(last_node, common)
 
-    for edge in g1.edges:
+    for edge in tqdm(
+        g1.edges, disable=not verbose, desc="Generation of the first cycle..."
+    ):
         g1.edges[edge]["label"] = edge_labels[0]
 
-    for edge in g2.edges:
+    for edge in tqdm(
+        g2.edges, disable=not verbose, desc="Generation of the second cycle..."
+    ):
         g2.edges[edge]["label"] = edge_labels[1]
 
     g = MultiDiGraph(compose(g1, g2))