graphs-ssimon 0.0.1__tar.gz

graphs_ssimon-0.0.1/PKG-INFO

@@ -0,0 +1,210 @@
+Metadata-Version: 2.5
+Name: graphs_ssimon
+Version: 0.0.1
+Summary: Graph algorithms, including Dijkstra's shortest path
+Project-URL: Homepage, https://github.com/ryokojr/hw5ssimon
+Author-email: Samuel Simon <ssimon7@msudenver.edu>
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# graphs_ssimon
+
+Had AI teach me for the bonus point section and ideas for what to add to readme.
+
+A small Python library of graph algorithms, written for CS 3250 at MSU Denver.
+
+A graph here is a dictionary of dictionaries. `graph[u][v] = w` means you can travel from
+vertex `u` to vertex `v` at a cost of `w`:
+
+```python
+graph = {0: {1: 4, 7: 8},
+         1: {0: 4, 2: 8}}
+```
+
+The `data` folder has example graphs stored as plain text, one edge per line, written as
+`source destination weight`.
+
+## Install
+
+```
+pip install git+https://github.com/ryokojr/hw5ssimon.git
+```
+
+## What's in it
+
+**`sp.dijkstra(graph, source)`** — Dijkstra's shortest path algorithm. Finds the cheapest
+route from `source` to every vertex it can reach, adding up the edge weights along the way.
+It returns two dictionaries: the total cost to reach each vertex, and the list of vertices
+you pass through to get there.
+
+```python
+from graphs_ssimon import sp
+
+dist, path = sp.dijkstra(graph, 0)
+print(dist[8])   # 14  -- cheapest total cost from vertex 0 to vertex 8
+print(path[8])   # [0, 1, 2]  -- the vertices visited on the way
+```
+
+**`bfs.bfs(graph, source)`** — breadth-first search. Finds the route with the *fewest edges*
+instead of the cheapest one, so the weights are ignored. Useful when every step costs the
+same, like counting how many connections away something is.
+
+```python
+from graphs_ssimon import bfs
+
+hops, path = bfs.bfs(graph, 0)
+print(hops[8])   # 2  -- vertex 8 is two edges from vertex 0
+print(path[8])   # [0, 7]
+```
+
+The two can disagree, and that's the point: reaching vertex 8 takes 2 edges but costs 15,
+while the cheapest route costs 14 and takes 3 edges.
+
+## Running the example
+
+```
+python test.py data/example1.txt
+```
+
+---
+
+# Overview 
+
+The goal of this assignment is to assess your understanding of how to package a software library, as discussed in class.
+
+More specifically, you are asked to package a Python library that implements Dijkstra's shortest path algorithm, along with other graph-related algorithms.
+
+# Instructions
+
+The name of your package must follow the format: **graphs_unique_id**, where "unique_id" should be replaced with a unique id. For example, I would name my package **graphs_tmota**. 
+
+The implementation of Dijkstra's algorithm has been provided, as the primary goal of this assignment is to give you practice in packaging code into a standardized format.
+
+You should create a public GitHub repository for your project to allow others to contribute in the future. The repository must include:
+
+1. A well-written README file.
+2. A protected main branch.
+3. A separate dev branch for development work.
+
+To receive credit for this assignment, update the README file and add the URL of your public GitHub repository below.
+
+```
+URL for your GitHub repository: https://github.com/ryokojr/hw5ssimon
+```
+
+The expected structure for the GitHub repository is the following: 
+
+```
+src
+|__graphs_<unique_id>
+   |__ __init__.py
+   |__ heapq.py
+   |__ sp.py
+|__test.py
+|__README.md
+|__pyproject.toml
+```
+
+Additionally, I should be able to install your Python package using pip and run the following code—replacing **unique_id** with your own unique id:
+
+```
+from graphs_tmota import sp
+import sys
+
+if __name__ == '__main__':
+    
+    if len(sys.argv) != 2:
+        print(f'Use: {sys.argv[0]} graph_file')
+        sys.exit(1)
+
+    graph = {}
+    with open(sys.argv[1], 'rt') as f:
+        for line in f:
+            line = line.strip()
+            s, d, w = line.split()
+            s = int(s)
+            d = int(d)
+            w = int(w)
+            if s not in graph:
+                graph[s] = {}
+            graph[s][d] = w
+    
+    s = 0
+    dist, path = sp.dijkstra(graph, s)
+    print(f'Shortest distances from {s}:')
+    print(dist)
+    for d in path: 
+        print(f'spf to {d}: {path[d]}')
+```
+
+# Rubric
+
+```
++1 GitHub repository has main and dev branches, with the main branch protected
++1 the GitHub repository has a README file that explains what is this library about 
++3 the library can be installed using pip and it is usable 
++1 (bonus) other graph-related algorithm is added to the library
+```
+
+# The Shortest Path Problem
+
+A graph is a data structure that connects nodes identified by labels. In a graph, a node is normally called **vertex** and the connections between two vertices is called **edge**. The cost to travel through an edge is its **weight**. Below is an example of a weighted graph with 9 vertices. 
+
+![pic1.png](pics/pic1.png)
+
+The **shortest path problem** is about finding the shortest paths from a given source vertex to all vertices. For example, the shortest path to reach vertex "1" from source vertex "0" is shown below, and it has a cost of 4. 
+
+![pic2.png](pics/pic2.png)
+
+The shortest path to reach vertex "8" from source vertex "0" is shown below, and it has a cost of 14. 
+
+![pic3.png](pics/pic3.png)
+
+# Dijkstra's Shortest Path Algorithm
+
+Edsger W. Dijkstra was a Dutch computer scientist that made many contributions to the field, including a solution to the shortest path problem in a graph. The solution discussed here uses a min-heap to store the shortest known distances from the source. Let's look at a step-by-step execution of the algorithm for the example above. 
+
+The algorithm begins by adding the cost to reach the source vertex, which is (of course) 0. We will use the notation (source, weight) to represent that. In the solution for the shortest path problem, the heap uses the weight of an edge to sort the values. A distance list is created to record the cost to reach each of the destinations from source. The distance list is initialized with the maximum possible value for the weight, represented as ∞, except to reach the source, which should be set to zero. 
+
+The distances are initialized as: [0, ∞, ∞, ∞, ∞, ∞, ∞, ∞, ∞]
+
+Hint: to represent ∞ in your code use **sys.maxsize**. 
+
+Next, the algorithm will run a loop until the heap becomes empty. At each iteration of that loop, the following steps are taken: 
+
+* the top of the heap (i.e., its smaller element) is removed; 
+* refer to that edge as (u, w), where w represents the best (known) cost to reach node u from source; 
+* next, the algorithm evaluates if the cost to reach each of u's neighbors is better than what is known so far; 
+* for example, if v is one of u's neighbor, then the algorithm checks if the cost to reach node u plus the weight from u to v is smaller than what is recorded in the distance array; 
+* if that is the case, the distance array is updated; 
+* also, if the cost is updated, the algorithm needs to update that cost if edge v is found in the heap. 
+
+For the example, (u, w) = (0, 0) in the first iteration. Nodes 1 and 7 can be reached from u=0 with costs 4 and 8, respectively. Therefore, the distances are updated to [0, 4, ∞, ∞, ∞, ∞, ∞, 8, ∞]. Also, (1, 4) and (7, 8) are added to the heap, which should now look like: 
+
+```
+    (1, 4)
+(7, 8)
+```
+
+On the second iteration, (u, w) = (1, 4).  Nodes 0, 2 and 7 can be reached from u=1 with costs 4, 8 and 11, respectively. The distance to node 2 is updated (with a cost of 4+8=12) and the pair (2, 12) is added to the heap. The distance to node 0 does not get updated because travelling to node 0 through node 1 didn't improve the cost: 4 vs. 0. Also, the distance to node 7 does not get updated because travelling to node 7 through node 1 didn't improve the cost: 15 vs. 8. The heap should now look like: 
+
+```
+    (7, 8)
+(2, 12)    
+```
+
+The distances are now: [0, 4, 12, ∞, ∞, ∞, ∞, 8, -]
+
+On the third iteration, (u, w) = (7, 8).  Nodes 0, 1, 6, and 8 can be reached from u=7 with costs 8, 11, 1 and 7, respectively. The distance to node 6 is updated (with a cost of 8+1=9) and the pair (6, 9) is added to the heap. The distance to node 8 is also updated (with a cost of 8+7=15) and the pair (8, 15) is added to the heap. The heap should now look like: 
+
+```
+    (6, 9)
+(2, 12) (8, 15)  
+```
+
+The distances are now: [0, 4, 12, ∞, ∞, ∞, 9, 8, 15]
+
+The algorithm repeats until the heap becomes empty. At the end of the loop the array of distances should have the lowest costs to reach each of the destinations from the source. 

graphs_ssimon-0.0.1/README.md

@@ -0,0 +1,198 @@
+# graphs_ssimon
+
+Had AI teach me for the bonus point section and ideas for what to add to readme.
+
+A small Python library of graph algorithms, written for CS 3250 at MSU Denver.
+
+A graph here is a dictionary of dictionaries. `graph[u][v] = w` means you can travel from
+vertex `u` to vertex `v` at a cost of `w`:
+
+```python
+graph = {0: {1: 4, 7: 8},
+         1: {0: 4, 2: 8}}
+```
+
+The `data` folder has example graphs stored as plain text, one edge per line, written as
+`source destination weight`.
+
+## Install
+
+```
+pip install git+https://github.com/ryokojr/hw5ssimon.git
+```
+
+## What's in it
+
+**`sp.dijkstra(graph, source)`** — Dijkstra's shortest path algorithm. Finds the cheapest
+route from `source` to every vertex it can reach, adding up the edge weights along the way.
+It returns two dictionaries: the total cost to reach each vertex, and the list of vertices
+you pass through to get there.
+
+```python
+from graphs_ssimon import sp
+
+dist, path = sp.dijkstra(graph, 0)
+print(dist[8])   # 14  -- cheapest total cost from vertex 0 to vertex 8
+print(path[8])   # [0, 1, 2]  -- the vertices visited on the way
+```
+
+**`bfs.bfs(graph, source)`** — breadth-first search. Finds the route with the *fewest edges*
+instead of the cheapest one, so the weights are ignored. Useful when every step costs the
+same, like counting how many connections away something is.
+
+```python
+from graphs_ssimon import bfs
+
+hops, path = bfs.bfs(graph, 0)
+print(hops[8])   # 2  -- vertex 8 is two edges from vertex 0
+print(path[8])   # [0, 7]
+```
+
+The two can disagree, and that's the point: reaching vertex 8 takes 2 edges but costs 15,
+while the cheapest route costs 14 and takes 3 edges.
+
+## Running the example
+
+```
+python test.py data/example1.txt
+```
+
+---
+
+# Overview 
+
+The goal of this assignment is to assess your understanding of how to package a software library, as discussed in class.
+
+More specifically, you are asked to package a Python library that implements Dijkstra's shortest path algorithm, along with other graph-related algorithms.
+
+# Instructions
+
+The name of your package must follow the format: **graphs_unique_id**, where "unique_id" should be replaced with a unique id. For example, I would name my package **graphs_tmota**. 
+
+The implementation of Dijkstra's algorithm has been provided, as the primary goal of this assignment is to give you practice in packaging code into a standardized format.
+
+You should create a public GitHub repository for your project to allow others to contribute in the future. The repository must include:
+
+1. A well-written README file.
+2. A protected main branch.
+3. A separate dev branch for development work.
+
+To receive credit for this assignment, update the README file and add the URL of your public GitHub repository below.
+
+```
+URL for your GitHub repository: https://github.com/ryokojr/hw5ssimon
+```
+
+The expected structure for the GitHub repository is the following: 
+
+```
+src
+|__graphs_<unique_id>
+   |__ __init__.py
+   |__ heapq.py
+   |__ sp.py
+|__test.py
+|__README.md
+|__pyproject.toml
+```
+
+Additionally, I should be able to install your Python package using pip and run the following code—replacing **unique_id** with your own unique id:
+
+```
+from graphs_tmota import sp
+import sys
+
+if __name__ == '__main__':
+    
+    if len(sys.argv) != 2:
+        print(f'Use: {sys.argv[0]} graph_file')
+        sys.exit(1)
+
+    graph = {}
+    with open(sys.argv[1], 'rt') as f:
+        for line in f:
+            line = line.strip()
+            s, d, w = line.split()
+            s = int(s)
+            d = int(d)
+            w = int(w)
+            if s not in graph:
+                graph[s] = {}
+            graph[s][d] = w
+    
+    s = 0
+    dist, path = sp.dijkstra(graph, s)
+    print(f'Shortest distances from {s}:')
+    print(dist)
+    for d in path: 
+        print(f'spf to {d}: {path[d]}')
+```
+
+# Rubric
+
+```
++1 GitHub repository has main and dev branches, with the main branch protected
++1 the GitHub repository has a README file that explains what is this library about 
++3 the library can be installed using pip and it is usable 
++1 (bonus) other graph-related algorithm is added to the library
+```
+
+# The Shortest Path Problem
+
+A graph is a data structure that connects nodes identified by labels. In a graph, a node is normally called **vertex** and the connections between two vertices is called **edge**. The cost to travel through an edge is its **weight**. Below is an example of a weighted graph with 9 vertices. 
+
+![pic1.png](pics/pic1.png)
+
+The **shortest path problem** is about finding the shortest paths from a given source vertex to all vertices. For example, the shortest path to reach vertex "1" from source vertex "0" is shown below, and it has a cost of 4. 
+
+![pic2.png](pics/pic2.png)
+
+The shortest path to reach vertex "8" from source vertex "0" is shown below, and it has a cost of 14. 
+
+![pic3.png](pics/pic3.png)
+
+# Dijkstra's Shortest Path Algorithm
+
+Edsger W. Dijkstra was a Dutch computer scientist that made many contributions to the field, including a solution to the shortest path problem in a graph. The solution discussed here uses a min-heap to store the shortest known distances from the source. Let's look at a step-by-step execution of the algorithm for the example above. 
+
+The algorithm begins by adding the cost to reach the source vertex, which is (of course) 0. We will use the notation (source, weight) to represent that. In the solution for the shortest path problem, the heap uses the weight of an edge to sort the values. A distance list is created to record the cost to reach each of the destinations from source. The distance list is initialized with the maximum possible value for the weight, represented as ∞, except to reach the source, which should be set to zero. 
+
+The distances are initialized as: [0, ∞, ∞, ∞, ∞, ∞, ∞, ∞, ∞]
+
+Hint: to represent ∞ in your code use **sys.maxsize**. 
+
+Next, the algorithm will run a loop until the heap becomes empty. At each iteration of that loop, the following steps are taken: 
+
+* the top of the heap (i.e., its smaller element) is removed; 
+* refer to that edge as (u, w), where w represents the best (known) cost to reach node u from source; 
+* next, the algorithm evaluates if the cost to reach each of u's neighbors is better than what is known so far; 
+* for example, if v is one of u's neighbor, then the algorithm checks if the cost to reach node u plus the weight from u to v is smaller than what is recorded in the distance array; 
+* if that is the case, the distance array is updated; 
+* also, if the cost is updated, the algorithm needs to update that cost if edge v is found in the heap. 
+
+For the example, (u, w) = (0, 0) in the first iteration. Nodes 1 and 7 can be reached from u=0 with costs 4 and 8, respectively. Therefore, the distances are updated to [0, 4, ∞, ∞, ∞, ∞, ∞, 8, ∞]. Also, (1, 4) and (7, 8) are added to the heap, which should now look like: 
+
+```
+    (1, 4)
+(7, 8)
+```
+
+On the second iteration, (u, w) = (1, 4).  Nodes 0, 2 and 7 can be reached from u=1 with costs 4, 8 and 11, respectively. The distance to node 2 is updated (with a cost of 4+8=12) and the pair (2, 12) is added to the heap. The distance to node 0 does not get updated because travelling to node 0 through node 1 didn't improve the cost: 4 vs. 0. Also, the distance to node 7 does not get updated because travelling to node 7 through node 1 didn't improve the cost: 15 vs. 8. The heap should now look like: 
+
+```
+    (7, 8)
+(2, 12)    
+```
+
+The distances are now: [0, 4, 12, ∞, ∞, ∞, ∞, 8, -]
+
+On the third iteration, (u, w) = (7, 8).  Nodes 0, 1, 6, and 8 can be reached from u=7 with costs 8, 11, 1 and 7, respectively. The distance to node 6 is updated (with a cost of 8+1=9) and the pair (6, 9) is added to the heap. The distance to node 8 is also updated (with a cost of 8+7=15) and the pair (8, 15) is added to the heap. The heap should now look like: 
+
+```
+    (6, 9)
+(2, 12) (8, 15)  
+```
+
+The distances are now: [0, 4, 12, ∞, ∞, ∞, 9, 8, 15]
+
+The algorithm repeats until the heap becomes empty. At the end of the loop the array of distances should have the lowest costs to reach each of the destinations from the source. 

graphs_ssimon-0.0.1/data/example1.txt

@@ -0,0 +1,28 @@
+0 1 4
+0 7 8
+1 0 4
+1 2 8
+1 7 11
+2 1 8
+2 3 7
+2 8 2
+2 5 4
+3 2 7
+3 4 9
+3 5 14
+4 3 9
+4 5 10
+5 2 4
+5 3 14
+5 4 10
+5 6 2
+6 5 2
+6 8 6
+6 7 1
+7 0 8
+7 1 11
+7 6 1
+7 8 7
+8 2 2
+8 6 6
+8 7 7

graphs_ssimon-0.0.1/data/example2.txt

@@ -0,0 +1,15 @@
+4 5 35
+5 4 35
+4 7 37
+5 7 28
+7 5 28
+5 1 32
+0 4 38
+0 2 26
+7 3 39
+1 3 29
+2 7 34
+6 2 40
+3 6 52
+6 0 58
+6 4 93

graphs_ssimon-0.0.1/data/example3.txt

@@ -0,0 +1,22 @@
+0 1 5
+0 2 2
+1 0 5
+1 2 3
+1 6 4
+2 0 2
+2 1 3
+2 3 4
+2 4 8
+3 2 4
+3 4 5
+3 5 2
+4 2 8
+4 3 5
+4 5 1
+4 6 3
+5 3 2
+5 4 1
+5 6 9
+6 1 4
+6 4 3
+6 5 9

graphs_ssimon-0.0.1/data/example4.txt

@@ -0,0 +1,5 @@
+101 202 10
+101 303 5
+202 303 3
+202 404 2
+303 202 3

graphs_ssimon-0.0.1/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "graphs_ssimon"
+version = "0.0.1"
+authors = [
+  { name="Samuel Simon", email="ssimon7@msudenver.edu" },
+]
+description = "Graph algorithms, including Dijkstra's shortest path"
+readme = "README.md"
+requires-python = ">=3.10"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+[project.urls]
+"Homepage" = "https://github.com/ryokojr/hw5ssimon"

graphs_ssimon-0.0.1/src/graphs_ssimon/bfs.py

@@ -0,0 +1,26 @@
+from collections import deque
+
+def bfs(graph, source):
+    """Find the path with the fewest edges from source to every vertex it can reach.
+
+    Dijkstra's algorithm answers "cheapest route" using the edge weights. This one
+    answers "fewest stops" instead, so the weights are ignored. The two disagree
+    whenever a longer chain of cheap edges beats one expensive edge.
+
+    Returns (hops, path), the same shape sp.dijkstra returns: hops[v] is the number
+    of edges to reach v, and path[v] is the list of vertices visited before v.
+    """
+    hops = {source: 0}
+    path = {source: []}
+    queue = deque([source])
+
+    while queue:
+        u = queue.popleft()
+        # graph.get(u, {}) because a vertex with no outgoing edges has no key
+        for v in graph.get(u, {}):
+            if v not in hops:
+                hops[v] = hops[u] + 1
+                path[v] = path[u] + [u]
+                queue.append(v)
+
+    return hops, path

graphs_ssimon-0.0.1/src/graphs_ssimon/heapq.py

@@ -0,0 +1,603 @@
+"""Heap queue algorithm (a.k.a. priority queue).
+
+Heaps are arrays for which a[k] <= a[2*k+1] and a[k] <= a[2*k+2] for
+all k, counting elements from 0.  For the sake of comparison,
+non-existing elements are considered to be infinite.  The interesting
+property of a heap is that a[0] is always its smallest element.
+
+Usage:
+
+heap = []            # creates an empty heap
+heappush(heap, item) # pushes a new item on the heap
+item = heappop(heap) # pops the smallest item from the heap
+item = heap[0]       # smallest item on the heap without popping it
+heapify(x)           # transforms list into a heap, in-place, in linear time
+item = heappushpop(heap, item) # pushes a new item and then returns
+                               # the smallest item; the heap size is unchanged
+item = heapreplace(heap, item) # pops and returns smallest item, and adds
+                               # new item; the heap size is unchanged
+
+Our API differs from textbook heap algorithms as follows:
+
+- We use 0-based indexing.  This makes the relationship between the
+  index for a node and the indexes for its children slightly less
+  obvious, but is more suitable since Python uses 0-based indexing.
+
+- Our heappop() method returns the smallest item, not the largest.
+
+These two make it possible to view the heap as a regular Python list
+without surprises: heap[0] is the smallest item, and heap.sort()
+maintains the heap invariant!
+"""
+
+# Original code by Kevin O'Connor, augmented by Tim Peters and Raymond Hettinger
+
+__about__ = """Heap queues
+
+[explanation by François Pinard]
+
+Heaps are arrays for which a[k] <= a[2*k+1] and a[k] <= a[2*k+2] for
+all k, counting elements from 0.  For the sake of comparison,
+non-existing elements are considered to be infinite.  The interesting
+property of a heap is that a[0] is always its smallest element.
+
+The strange invariant above is meant to be an efficient memory
+representation for a tournament.  The numbers below are `k', not a[k]:
+
+                                   0
+
+                  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
+
+
+In the tree above, each cell `k' is topping `2*k+1' and `2*k+2'.  In
+a usual binary tournament we see in sports, each cell is the winner
+over the two cells it tops, and we can trace the winner down the tree
+to see all opponents s/he had.  However, in many computer applications
+of such tournaments, we do not need to trace the history of a winner.
+To be more memory efficient, when a winner is promoted, we try to
+replace it by something else at a lower level, and the rule becomes
+that a cell and the two cells it tops contain three different items,
+but the top cell "wins" over the two topped cells.
+
+If this heap invariant is protected at all time, index 0 is clearly
+the overall winner.  The simplest algorithmic way to remove it and
+find the "next" winner is to move some loser (let's say cell 30 in the
+diagram above) into the 0 position, and then percolate this new 0 down
+the tree, exchanging values, until the invariant is re-established.
+This is clearly logarithmic on the total number of items in the tree.
+By iterating over all items, you get an O(n ln n) sort.
+
+A nice feature of this sort is that you can efficiently insert new
+items while the sort is going on, provided that the inserted items are
+not "better" than the last 0'th element you extracted.  This is
+especially useful in simulation contexts, where the tree holds all
+incoming events, and the "win" condition means the smallest scheduled
+time.  When an event schedule other events for execution, they are
+scheduled into the future, so they can easily go into the heap.  So, a
+heap is a good structure for implementing schedulers (this is what I
+used for my MIDI sequencer :-).
+
+Various structures for implementing schedulers have been extensively
+studied, and heaps are good for this, as they are reasonably speedy,
+the speed is almost constant, and the worst case is not much different
+than the average case.  However, there are other representations which
+are more efficient overall, yet the worst cases might be terrible.
+
+Heaps are also very useful in big disk sorts.  You most probably all
+know that a big sort implies producing "runs" (which are pre-sorted
+sequences, which size is usually related to the amount of CPU memory),
+followed by a merging passes for these runs, which merging is often
+very cleverly organised[1].  It is very important that the initial
+sort produces the longest runs possible.  Tournaments are a good way
+to that.  If, using all the memory available to hold a tournament, you
+replace and percolate items that happen to fit the current run, you'll
+produce runs which are twice the size of the memory for random input,
+and much better for input fuzzily ordered.
+
+Moreover, if you output the 0'th item on disk and get an input which
+may not fit in the current tournament (because the value "wins" over
+the last output value), it cannot fit in the heap, so the size of the
+heap decreases.  The freed memory could be cleverly reused immediately
+for progressively building a second heap, which grows at exactly the
+same rate the first heap is melting.  When the first heap completely
+vanishes, you switch heaps and start a new run.  Clever and quite
+effective!
+
+In a word, heaps are useful memory structures to know.  I use them in
+a few applications, and I think it is good to keep a `heap' module
+around. :-)
+
+--------------------
+[1] The disk balancing algorithms which are current, nowadays, are
+more annoying than clever, and this is a consequence of the seeking
+capabilities of the disks.  On devices which cannot seek, like big
+tape drives, the story was quite different, and one had to be very
+clever to ensure (far in advance) that each tape movement will be the
+most effective possible (that is, will best participate at
+"progressing" the merge).  Some tapes were even able to read
+backwards, and this was also used to avoid the rewinding time.
+Believe me, real good tape sorts were quite spectacular to watch!
+From all times, sorting has always been a Great Art! :-)
+"""
+
+__all__ = ['heappush', 'heappop', 'heapify', 'heapreplace', 'merge',
+           'nlargest', 'nsmallest', 'heappushpop']
+
+def heappush(heap, item):
+    """Push item onto heap, maintaining the heap invariant."""
+    heap.append(item)
+    _siftdown(heap, 0, len(heap)-1)
+
+def heappop(heap):
+    """Pop the smallest item off the heap, maintaining the heap invariant."""
+    lastelt = heap.pop()    # raises appropriate IndexError if heap is empty
+    if heap:
+        returnitem = heap[0]
+        heap[0] = lastelt
+        _siftup(heap, 0)
+        return returnitem
+    return lastelt
+
+def heapreplace(heap, item):
+    """Pop and return the current smallest value, and add the new item.
+
+    This is more efficient than heappop() followed by heappush(), and can be
+    more appropriate when using a fixed-size heap.  Note that the value
+    returned may be larger than item!  That constrains reasonable uses of
+    this routine unless written as part of a conditional replacement:
+
+        if item > heap[0]:
+            item = heapreplace(heap, item)
+    """
+    returnitem = heap[0]    # raises appropriate IndexError if heap is empty
+    heap[0] = item
+    _siftup(heap, 0)
+    return returnitem
+
+def heappushpop(heap, item):
+    """Fast version of a heappush followed by a heappop."""
+    if heap and heap[0] < item:
+        item, heap[0] = heap[0], item
+        _siftup(heap, 0)
+    return item
+
+def heapify(x):
+    """Transform list into a heap, in-place, in O(len(x)) time."""
+    n = len(x)
+    # Transform bottom-up.  The largest index there's any point to looking at
+    # is the largest with a child index in-range, so must have 2*i + 1 < n,
+    # or i < (n-1)/2.  If n is even = 2*j, this is (2*j-1)/2 = j-1/2 so
+    # j-1 is the largest, which is n//2 - 1.  If n is odd = 2*j+1, this is
+    # (2*j+1-1)/2 = j so j-1 is the largest, and that's again n//2-1.
+    for i in reversed(range(n//2)):
+        _siftup(x, i)
+
+def _heappop_max(heap):
+    """Maxheap version of a heappop."""
+    lastelt = heap.pop()    # raises appropriate IndexError if heap is empty
+    if heap:
+        returnitem = heap[0]
+        heap[0] = lastelt
+        _siftup_max(heap, 0)
+        return returnitem
+    return lastelt
+
+def _heapreplace_max(heap, item):
+    """Maxheap version of a heappop followed by a heappush."""
+    returnitem = heap[0]    # raises appropriate IndexError if heap is empty
+    heap[0] = item
+    _siftup_max(heap, 0)
+    return returnitem
+
+def _heapify_max(x):
+    """Transform list into a maxheap, in-place, in O(len(x)) time."""
+    n = len(x)
+    for i in reversed(range(n//2)):
+        _siftup_max(x, i)
+
+# 'heap' is a heap at all indices >= startpos, except possibly for pos.  pos
+# is the index of a leaf with a possibly out-of-order value.  Restore the
+# heap invariant.
+def _siftdown(heap, startpos, pos):
+    newitem = heap[pos]
+    # Follow the path to the root, moving parents down until finding a place
+    # newitem fits.
+    while pos > startpos:
+        parentpos = (pos - 1) >> 1
+        parent = heap[parentpos]
+        if newitem < parent:
+            heap[pos] = parent
+            pos = parentpos
+            continue
+        break
+    heap[pos] = newitem
+
+# The child indices of heap index pos are already heaps, and we want to make
+# a heap at index pos too.  We do this by bubbling the smaller child of
+# pos up (and so on with that child's children, etc) until hitting a leaf,
+# then using _siftdown to move the oddball originally at index pos into place.
+#
+# We *could* break out of the loop as soon as we find a pos where newitem <=
+# both its children, but turns out that's not a good idea, and despite that
+# many books write the algorithm that way.  During a heap pop, the last array
+# element is sifted in, and that tends to be large, so that comparing it
+# against values starting from the root usually doesn't pay (= usually doesn't
+# get us out of the loop early).  See Knuth, Volume 3, where this is
+# explained and quantified in an exercise.
+#
+# Cutting the # of comparisons is important, since these routines have no
+# way to extract "the priority" from an array element, so that intelligence
+# is likely to be hiding in custom comparison methods, or in array elements
+# storing (priority, record) tuples.  Comparisons are thus potentially
+# expensive.
+#
+# On random arrays of length 1000, making this change cut the number of
+# comparisons made by heapify() a little, and those made by exhaustive
+# heappop() a lot, in accord with theory.  Here are typical results from 3
+# runs (3 just to demonstrate how small the variance is):
+#
+# Compares needed by heapify     Compares needed by 1000 heappops
+# --------------------------     --------------------------------
+# 1837 cut to 1663               14996 cut to 8680
+# 1855 cut to 1659               14966 cut to 8678
+# 1847 cut to 1660               15024 cut to 8703
+#
+# Building the heap by using heappush() 1000 times instead required
+# 2198, 2148, and 2219 compares:  heapify() is more efficient, when
+# you can use it.
+#
+# The total compares needed by list.sort() on the same lists were 8627,
+# 8627, and 8632 (this should be compared to the sum of heapify() and
+# heappop() compares):  list.sort() is (unsurprisingly!) more efficient
+# for sorting.
+
+def _siftup(heap, pos):
+    endpos = len(heap)
+    startpos = pos
+    newitem = heap[pos]
+    # Bubble up the smaller child until hitting a leaf.
+    childpos = 2*pos + 1    # leftmost child position
+    while childpos < endpos:
+        # Set childpos to index of smaller child.
+        rightpos = childpos + 1
+        if rightpos < endpos and not heap[childpos] < heap[rightpos]:
+            childpos = rightpos
+        # Move the smaller child up.
+        heap[pos] = heap[childpos]
+        pos = childpos
+        childpos = 2*pos + 1
+    # The leaf at pos is empty now.  Put newitem there, and bubble it up
+    # to its final resting place (by sifting its parents down).
+    heap[pos] = newitem
+    _siftdown(heap, startpos, pos)
+
+def _siftdown_max(heap, startpos, pos):
+    'Maxheap variant of _siftdown'
+    newitem = heap[pos]
+    # Follow the path to the root, moving parents down until finding a place
+    # newitem fits.
+    while pos > startpos:
+        parentpos = (pos - 1) >> 1
+        parent = heap[parentpos]
+        if parent < newitem:
+            heap[pos] = parent
+            pos = parentpos
+            continue
+        break
+    heap[pos] = newitem
+
+def _siftup_max(heap, pos):
+    'Maxheap variant of _siftup'
+    endpos = len(heap)
+    startpos = pos
+    newitem = heap[pos]
+    # Bubble up the larger child until hitting a leaf.
+    childpos = 2*pos + 1    # leftmost child position
+    while childpos < endpos:
+        # Set childpos to index of larger child.
+        rightpos = childpos + 1
+        if rightpos < endpos and not heap[rightpos] < heap[childpos]:
+            childpos = rightpos
+        # Move the larger child up.
+        heap[pos] = heap[childpos]
+        pos = childpos
+        childpos = 2*pos + 1
+    # The leaf at pos is empty now.  Put newitem there, and bubble it up
+    # to its final resting place (by sifting its parents down).
+    heap[pos] = newitem
+    _siftdown_max(heap, startpos, pos)
+
+def merge(*iterables, key=None, reverse=False):
+    '''Merge multiple sorted inputs into a single sorted output.
+
+    Similar to sorted(itertools.chain(*iterables)) but returns a generator,
+    does not pull the data into memory all at once, and assumes that each of
+    the input streams is already sorted (smallest to largest).
+
+    >>> list(merge([1,3,5,7], [0,2,4,8], [5,10,15,20], [], [25]))
+    [0, 1, 2, 3, 4, 5, 5, 7, 8, 10, 15, 20, 25]
+
+    If *key* is not None, applies a key function to each element to determine
+    its sort order.
+
+    >>> list(merge(['dog', 'horse'], ['cat', 'fish', 'kangaroo'], key=len))
+    ['dog', 'cat', 'fish', 'horse', 'kangaroo']
+
+    '''
+
+    h = []
+    h_append = h.append
+
+    if reverse:
+        _heapify = _heapify_max
+        _heappop = _heappop_max
+        _heapreplace = _heapreplace_max
+        direction = -1
+    else:
+        _heapify = heapify
+        _heappop = heappop
+        _heapreplace = heapreplace
+        direction = 1
+
+    if key is None:
+        for order, it in enumerate(map(iter, iterables)):
+            try:
+                next = it.__next__
+                h_append([next(), order * direction, next])
+            except StopIteration:
+                pass
+        _heapify(h)
+        while len(h) > 1:
+            try:
+                while True:
+                    value, order, next = s = h[0]
+                    yield value
+                    s[0] = next()           # raises StopIteration when exhausted
+                    _heapreplace(h, s)      # restore heap condition
+            except StopIteration:
+                _heappop(h)                 # remove empty iterator
+        if h:
+            # fast case when only a single iterator remains
+            value, order, next = h[0]
+            yield value
+            yield from next.__self__
+        return
+
+    for order, it in enumerate(map(iter, iterables)):
+        try:
+            next = it.__next__
+            value = next()
+            h_append([key(value), order * direction, value, next])
+        except StopIteration:
+            pass
+    _heapify(h)
+    while len(h) > 1:
+        try:
+            while True:
+                key_value, order, value, next = s = h[0]
+                yield value
+                value = next()
+                s[0] = key(value)
+                s[2] = value
+                _heapreplace(h, s)
+        except StopIteration:
+            _heappop(h)
+    if h:
+        key_value, order, value, next = h[0]
+        yield value
+        yield from next.__self__
+
+
+# Algorithm notes for nlargest() and nsmallest()
+# ==============================================
+#
+# Make a single pass over the data while keeping the k most extreme values
+# in a heap.  Memory consumption is limited to keeping k values in a list.
+#
+# Measured performance for random inputs:
+#
+#                                   number of comparisons
+#    n inputs     k-extreme values  (average of 5 trials)   % more than min()
+# -------------   ----------------  ---------------------   -----------------
+#      1,000           100                  3,317               231.7%
+#     10,000           100                 14,046                40.5%
+#    100,000           100                105,749                 5.7%
+#  1,000,000           100              1,007,751                 0.8%
+# 10,000,000           100             10,009,401                 0.1%
+#
+# Theoretical number of comparisons for k smallest of n random inputs:
+#
+# Step   Comparisons                  Action
+# ----   --------------------------   ---------------------------
+#  1     1.66 * k                     heapify the first k-inputs
+#  2     n - k                        compare remaining elements to top of heap
+#  3     k * (1 + lg2(k)) * ln(n/k)   replace the topmost value on the heap
+#  4     k * lg2(k) - (k/2)           final sort of the k most extreme values
+#
+# Combining and simplifying for a rough estimate gives:
+#
+#        comparisons = n + k * (log(k, 2) * log(n/k) + log(k, 2) + log(n/k))
+#
+# Computing the number of comparisons for step 3:
+# -----------------------------------------------
+# * For the i-th new value from the iterable, the probability of being in the
+#   k most extreme values is k/i.  For example, the probability of the 101st
+#   value seen being in the 100 most extreme values is 100/101.
+# * If the value is a new extreme value, the cost of inserting it into the
+#   heap is 1 + log(k, 2).
+# * The probability times the cost gives:
+#            (k/i) * (1 + log(k, 2))
+# * Summing across the remaining n-k elements gives:
+#            sum((k/i) * (1 + log(k, 2)) for i in range(k+1, n+1))
+# * This reduces to:
+#            (H(n) - H(k)) * k * (1 + log(k, 2))
+# * Where H(n) is the n-th harmonic number estimated by:
+#            gamma = 0.5772156649
+#            H(n) = log(n, e) + gamma + 1 / (2 * n)
+#   http://en.wikipedia.org/wiki/Harmonic_series_(mathematics)#Rate_of_divergence
+# * Substituting the H(n) formula:
+#            comparisons = k * (1 + log(k, 2)) * (log(n/k, e) + (1/n - 1/k) / 2)
+#
+# Worst-case for step 3:
+# ----------------------
+# In the worst case, the input data is reversed sorted so that every new element
+# must be inserted in the heap:
+#
+#             comparisons = 1.66 * k + log(k, 2) * (n - k)
+#
+# Alternative Algorithms
+# ----------------------
+# Other algorithms were not used because they:
+# 1) Took much more auxiliary memory,
+# 2) Made multiple passes over the data.
+# 3) Made more comparisons in common cases (small k, large n, semi-random input).
+# See the more detailed comparison of approach at:
+# http://code.activestate.com/recipes/577573-compare-algorithms-for-heapqsmallest
+
+def nsmallest(n, iterable, key=None):
+    """Find the n smallest elements in a dataset.
+
+    Equivalent to:  sorted(iterable, key=key)[:n]
+    """
+
+    # Short-cut for n==1 is to use min()
+    if n == 1:
+        it = iter(iterable)
+        sentinel = object()
+        result = min(it, default=sentinel, key=key)
+        return [] if result is sentinel else [result]
+
+    # When n>=size, it's faster to use sorted()
+    try:
+        size = len(iterable)
+    except (TypeError, AttributeError):
+        pass
+    else:
+        if n >= size:
+            return sorted(iterable, key=key)[:n]
+
+    # When key is none, use simpler decoration
+    if key is None:
+        it = iter(iterable)
+        # put the range(n) first so that zip() doesn't
+        # consume one too many elements from the iterator
+        result = [(elem, i) for i, elem in zip(range(n), it)]
+        if not result:
+            return result
+        _heapify_max(result)
+        top = result[0][0]
+        order = n
+        _heapreplace = _heapreplace_max
+        for elem in it:
+            if elem < top:
+                _heapreplace(result, (elem, order))
+                top, _order = result[0]
+                order += 1
+        result.sort()
+        return [elem for (elem, order) in result]
+
+    # General case, slowest method
+    it = iter(iterable)
+    result = [(key(elem), i, elem) for i, elem in zip(range(n), it)]
+    if not result:
+        return result
+    _heapify_max(result)
+    top = result[0][0]
+    order = n
+    _heapreplace = _heapreplace_max
+    for elem in it:
+        k = key(elem)
+        if k < top:
+            _heapreplace(result, (k, order, elem))
+            top, _order, _elem = result[0]
+            order += 1
+    result.sort()
+    return [elem for (k, order, elem) in result]
+
+def nlargest(n, iterable, key=None):
+    """Find the n largest elements in a dataset.
+
+    Equivalent to:  sorted(iterable, key=key, reverse=True)[:n]
+    """
+
+    # Short-cut for n==1 is to use max()
+    if n == 1:
+        it = iter(iterable)
+        sentinel = object()
+        result = max(it, default=sentinel, key=key)
+        return [] if result is sentinel else [result]
+
+    # When n>=size, it's faster to use sorted()
+    try:
+        size = len(iterable)
+    except (TypeError, AttributeError):
+        pass
+    else:
+        if n >= size:
+            return sorted(iterable, key=key, reverse=True)[:n]
+
+    # When key is none, use simpler decoration
+    if key is None:
+        it = iter(iterable)
+        result = [(elem, i) for i, elem in zip(range(0, -n, -1), it)]
+        if not result:
+            return result
+        heapify(result)
+        top = result[0][0]
+        order = -n
+        _heapreplace = heapreplace
+        for elem in it:
+            if top < elem:
+                _heapreplace(result, (elem, order))
+                top, _order = result[0]
+                order -= 1
+        result.sort(reverse=True)
+        return [elem for (elem, order) in result]
+
+    # General case, slowest method
+    it = iter(iterable)
+    result = [(key(elem), i, elem) for i, elem in zip(range(0, -n, -1), it)]
+    if not result:
+        return result
+    heapify(result)
+    top = result[0][0]
+    order = -n
+    _heapreplace = heapreplace
+    for elem in it:
+        k = key(elem)
+        if top < k:
+            _heapreplace(result, (k, order, elem))
+            top, _order, _elem = result[0]
+            order -= 1
+    result.sort(reverse=True)
+    return [elem for (k, order, elem) in result]
+
+# If available, use C implementation
+try:
+    from _heapq import *
+except ImportError:
+    pass
+try:
+    from _heapq import _heapreplace_max
+except ImportError:
+    pass
+try:
+    from _heapq import _heapify_max
+except ImportError:
+    pass
+try:
+    from _heapq import _heappop_max
+except ImportError:
+    pass
+
+
+if __name__ == "__main__":
+
+    import doctest # pragma: no cover
+    print(doctest.testmod()) # pragma: no cover

graphs_ssimon-0.0.1/src/graphs_ssimon/sp.py

@@ -0,0 +1,19 @@
+import sys
+from heapq import heappush, heappop
+
+def dijkstra(graph, source):
+    dist = {node: sys.maxsize for node in graph}
+    dist[source] = 0
+    heap = []
+    heappush(heap, (0, source))
+    path = {source: []}
+
+    while heap:
+        w, u = heappop(heap)
+        for v in graph[u]:
+            if w + graph[u][v] < dist[v]:
+                dist[v] = w + graph[u][v]
+                heappush(heap, (dist[v], v))
+                path[v] = path[u] + [u]
+
+    return dist, path

graphs_ssimon-0.0.1/test.py

@@ -0,0 +1,29 @@
+import sys
+# replace the following line with:
+# from graph_user_id import sp
+from graphs_ssimon import sp
+
+if __name__ == '__main__':
+    
+    if len(sys.argv) != 2:
+        print(f'Use: {sys.argv[0]} graph_file')
+        sys.exit(1)
+
+    graph = {}
+    with open(sys.argv[1], 'rt') as f:
+        for line in f:
+            line = line.strip()
+            s, d, w = line.split()
+            s = int(s)
+            d = int(d)
+            w = int(w)
+            if s not in graph:
+                graph[s] = {}
+            graph[s][d] = w
+    
+    s = 0
+    dist, path = sp.dijkstra(graph, s)
+    print(f'Shortest distances from {s}:')
+    print(dist)
+    for d in path: 
+        print(f'spf to {d}: {path[d]}')