{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Please enter your names\n", "name = \"Fabian Langer, Yannik Bretschneider\"\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Programming Exercise: Minimum Spanning Tree Clustering\n", "Implement the MST clustering below. A basic datastructure is already defined as well as a function for plotting the result. \n" ] }, { "cell_type": "code", "execution_count": 177, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "\n", "# Tell matplotlib to plot inside the Notebook\n", "%matplotlib inline\n", "\n", "class Point:\n", " x = 0\n", " y = 0\n", " cluster = 0\n", " def __init__(self, x = 0, y = 0, c = 0):\n", " self.x = x\n", " self.y = y\n", " self.cluster = c\n", " def distanceTo(self,point):\n", " distance = ((self.x-point.x)**2 + (self.y-point.y)**2)**(0.5)\n", " return distance\n", " \n", " def __repr__(self):\n", " return f\"Point(x={self.x}, y={self.y}, cluster={self.cluster})\"\n", " \n", " def __eq__(self, value):\n", " return self.x == value.x and self.y == value.y and self.cluster == value.cluster\n", "\n", "def plot(points):\n", " x = []\n", " y = []\n", " cl = []\n", " for p in points:\n", " x.append(p.x)\n", " y.append(p.y)\n", " cl.append(p.cluster)\n", "\n", " plt.suptitle('MST Clustering')\n", " # Our colors for plotting the data points\n", " scl = list(set(cl)) # reduce to unique colors by converting to a set\n", " colors = np.random.rand(len(scl))\n", " colormap = []\n", " for icl in cl:\n", " for i in range(0, len(scl)):\n", " if icl == scl[i]:\n", " colormap.append(colors[i])\n", " break\n", " # Plot the data\n", " plt.scatter(x, y, c=colormap, s=40)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Implement the Minimum Spanning Tree Clustering below. You will need some sort of data structure to represent a graph and it nodes. " ] }, { "cell_type": "code", "execution_count": 178, "metadata": { "collapsed": true }, "outputs": [], "source": [ "from random import Random\n", "\n", "\n", "class Tree:\n", "\n", " root: int # index of the root node\n", " edges: list[tuple[int, int]] # list of edges (tuples of indices)\n", " points: list[Point] # list of points\n", " visited: list[bool] # list of visited nodes\n", "\n", " def __init__(self, points: list[Point], root: int | None = None):\n", " self.edges = []\n", " self.points = points\n", " self.visited = [False] * len(points)\n", " if root is None:\n", " print(len(points) - 1)\n", " self.root = Random().randint(0, len(points) - 1)\n", " else:\n", " self.root = root\n", " \n", " def add_edge(self, edge: tuple[int, int]):\n", " assert edge[0] < len(self.points) and edge[1] < len(self.points) and edge[0] >= 0 and edge[1] >= 0\n", " self.edges.append(edge)\n", " \n", " def not_visited(self, index: int) -> bool:\n", " return not self.visited[index]\n", " \n", " def iter_not_visited(self):\n", " for i in range(len(self.visited)):\n", " if self.not_visited(i):\n", " yield i\n", " \n", " def iter_visited(self):\n", " for i in range(len(self.visited)):\n", " if not self.not_visited(i):\n", " yield i\n", " \n", " def find_nearest_unvisited_to(self, index: int) -> tuple[int, float]: # o(n)\n", " nearest = None\n", " min_distance = float(\"inf\")\n", " for p in self.iter_not_visited():\n", " distance = self.points[index].distanceTo(self.points[p])\n", " if distance < min_distance:\n", " nearest = p\n", " min_distance = distance\n", " return nearest, min_distance\n", " \n", " def find_nearest_unvisited(self) -> tuple[int, float]: # o(n^2)\n", " nearest = None\n", " min_distance = float(\"inf\")\n", " for p in self.iter_visited():\n", " n, distance = self.find_nearest_unvisited_to(p)\n", " if distance < min_distance:\n", " nearest = n\n", " min_distance = distance\n", " return nearest, min_distance\n", " \n", " def find_longest_edge(self) -> tuple[int, int]:\n", " longest = None\n", " max_distance = 0\n", " for edge in self.edges:\n", " distance = self.points[edge[0]].distanceTo(self.points[edge[1]])\n", " if distance > max_distance:\n", " longest = edge\n", " max_distance = distance\n", " return longest\n", " \n", " def find_all_connected(self, index: int) -> list[int]:\n", " connected = [index]\n", " connected_len = 1\n", " prev_len = 0\n", " while connected_len != prev_len:\n", " prev_len = connected_len\n", " for edge in self.edges:\n", " if edge[0] in connected and edge[1] not in connected:\n", " connected.append(edge[1])\n", " elif edge[1] in connected and edge[0] not in connected:\n", " connected.append(edge[0])\n", " connected_len = len(connected)\n", " return connected\n", " \n", " \n", "def mst(points: list[Point]) -> Tree:\n", " tree = Tree(points)\n", " tree.visited[tree.root] = True\n", " for i in range(len(points) - 1):\n", " nearest, distance = tree.find_nearest_unvisited()\n", " if nearest is not None:\n", " tree.add_edge((tree.root, nearest))\n", " tree.visited[nearest] = True\n", " tree.root = nearest\n", " else: \n", " raise ValueError(\"No unvisited points left\")\n", " return tree\n", "\n", "def cluster(points: list[Point], k: int) -> list[Point]:\n", "\n", " print(\"Number of points: \", len(points))\n", " print(\"Building MST...\")\n", " tree = mst(points)\n", " print(\"MST edge count: \", len(tree.edges))\n", "\n", " for _ in range(k-1):\n", " longest_edge = tree.find_longest_edge()\n", " tree.edges.remove(longest_edge)\n", " \n", "\n", " # cluster 0 doesn't exist, starting from 1\n", "\n", " cluster_id = 1\n", "\n", " print(\"Clustering...\")\n", " while True:\n", " # go through all points connected to the first unclustered point\n", " unclustered = None\n", " for i, pt in enumerate(tree.points):\n", " if pt.cluster == 0:\n", " unclustered = i\n", " break\n", " \n", " if unclustered is None:\n", " break\n", " \n", " print(\"Cluster ID: \", cluster_id)\n", " \n", " print(\"Unclustered point: \", tree.points[unclustered].x, tree.points[unclustered].y)\n", " print(\"Finding connected points...\")\n", " connected = tree.find_all_connected(unclustered)\n", " print(\"Connected points: \", len(connected))\n", " for pt in connected:\n", " tree.points[pt].cluster = cluster_id\n", " cluster_id += 1\n", " \n", "\n", " return tree.points" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "*Note*: Please download spiral.txt and upload it into your *work* folder here on Jupyterhub.\n", "\n", "Now we setup the parameters:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "K = 6" ] }, { "cell_type": "code", "execution_count": 179, "metadata": {}, "outputs": [], "source": [ "K=3" ] }, { "cell_type": "code", "execution_count": 180, "metadata": { "collapsed": true }, "outputs": [], "source": [ "filepath = \"./clustering_datasets/\"\n", "filenames = [\"spiral\"]\n", "fileextension = \".txt\"" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 181, "metadata": { "collapsed": true }, "outputs": [], "source": [ "#TODO Think about a good criterium/parameter to determine the clusters" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Finally, we can cluster the data using MST-Clustering:" ] }, { "cell_type": "code", "execution_count": 182, "metadata": { "collapsed": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Number of points: 312\n", "Building MST...\n", "311\n", "MST edge count: 311\n", "Clustering...\n", "Cluster ID: 1\n", "Unclustered point: 31.95 7.95\n", "Finding connected points...\n", "Connected points: 106\n", "Cluster ID: 2\n", "Unclustered point: 19.35 31.65\n", "Finding connected points...\n", "Connected points: 101\n", "Cluster ID: 3\n", "Unclustered point: 3.9 9.6\n", "Finding connected points...\n", "Connected points: 105\n", "Finished clustering dataset: spiral\n" ] } ], "source": [ "results = {}\n", "\n", "for p in range(0,len(filenames)):\n", " datapoints = []\n", " f = filepath+filenames[p]+fileextension\n", " file = open(f,\"r\")\n", " line = file.readline()\n", " while(line != \"\"):\n", " a = line[:-1].split()\n", " x = float(a[0])\n", " y = float(a[1])\n", " datapoints.append(Point(x,y))\n", " line = file.readline()\n", " file.close()\n", " points = cluster(datapoints, k=K)\n", " results[filenames[p]] = points\n", " print(\"Finished clustering dataset: \" + filenames[p])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "And visualize the result: (You might want to execute the plot function a couple of times if the random colors are too similar.)" ] }, { "cell_type": "code", "execution_count": 183, "metadata": { "collapsed": true }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot(results[\"spiral\"])" ] } ], "metadata": { "anaconda-cloud": {}, "kernelspec": { "display_name": ".venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 1 }