Experiment 2, 3 from gdymind

yangyanli · Feb 13, 2018 · 5cf6786 · 5cf6786
1 parent 9fd3368
commit 5cf6786
Show file tree

Hide file tree

Showing 36 changed files with 3,607 additions and 0 deletions.
diff --git a/students/DongHuibing/Experiment1/DBSCAN/src/DBSCAN.cpp b/students/DongHuibing/Experiment1/DBSCAN/src/DBSCAN.cpp
@@ -0,0 +1,126 @@
+#include<bits/stdc++.h>
+#include<unistd.h>
+using namespace std;
+struct Node
+{
+    double x, y;
+    int truth;
+    int cluster;//-1:undefined;0:noise;
+
+    bool operator< (const Node &rhs) const
+    {
+        if (x != rhs.x) return x < rhs.x;
+        return y < rhs.y;
+    }
+};
+vector<Node> nodes;
+const int MAXN = 1e4 + 5;
+double dis[MAXN][MAXN];
+double eps;
+int minPts;
+
+void readData()
+{
+    string s = "";
+    cout << "Please enter the file name , eps and minPts:" << endl;
+    cin >> s >> eps >> minPts;
+    freopen(("../../data/synthetic_data/" + s).c_str(), "r", stdin);
+    double x, y;
+    int t;
+    while(~scanf("%lf,%lf,%d", &x, &y, &t))
+    {
+        nodes.push_back((Node){x, y, t, -1});
+    }
+}
+
+double squDistance(Node &u, Node &v)
+{
+    double dx = u.x - v.x;
+    double dy = u.y - v.y;
+    return dx * dx + dy * dy;
+}
+
+double mydistance(Node &u, Node &v)
+{
+    return sqrt(squDistance(u, v));
+}
+
+void calcDis()
+{
+    for(int i = 0; i < nodes.size(); ++i)
+    {
+        for(int j = i + 1; j < nodes.size(); ++j)
+        {
+            dis[i][j] = dis[j][i] = squDistance(nodes[i], nodes[j]);
+        }
+    }
+}
+
+void dbscan()
+{
+    int clusterId = 0;
+    for(int i = 0; i < nodes.size(); ++i)
+    {
+        Node &cur = nodes[i];
+        if(cur.cluster >= 0) continue;
+        queue<int> neighbors;
+        set<int> se;
+        se.insert(i);
+        for(int j = 0; j < nodes.size(); ++j)
+        {
+            if(i == j || nodes[j].cluster > 0) continue;
+            if(mydistance(cur, nodes[j]) <= eps)
+            {
+                neighbors.push(j);
+                se.insert(j);
+            }
+        }
+        if(neighbors.size() < minPts)
+        {
+            nodes[i].cluster = 0;
+            continue;
+        }
+        nodes[i].cluster = ++clusterId;
+        while(!neighbors.empty())
+        {
+            int tp = neighbors.front();
+            neighbors.pop();
+            nodes[tp].cluster = clusterId;
+            for(int j = 0; j < nodes.size(); ++j)
+            {
+                if(j == i || j == tp || nodes[j].cluster > 0 || se.find(j) != se.end()) continue;
+                if(mydistance(nodes[tp], nodes[j]) <= eps)
+                {
+                    se.insert(j);
+                    neighbors.push(j);
+                }
+            }
+        }
+    }
+}
+
+void out(vector<Node> &nodes)
+{
+    for(int i = 0; i < nodes.size(); ++i)
+        cout << nodes[i].x << ' ' << nodes[i].y << ' ' << nodes[i].truth << ' ' << nodes[i].cluster << endl;
+}
+
+void outputResult()
+{
+    freopen("../data/data.tsv", "w", stdout);
+    puts("x\ty\tclusters");
+    for(int i = 0; i < nodes.size(); ++i)
+    {
+        printf("%.2f\t%.2f\tCluster%d\n", nodes[i].x, nodes[i].y, nodes[i].cluster);
+    }
+}
+
+
+int main()
+{
+    readData();
+    calcDis();
+    dbscan();
+    outputResult();
+    return 0;
+}
diff --git a/students/DongHuibing/Experiment1/DBSCAN/src/index.html b/students/DongHuibing/Experiment1/DBSCAN/src/index.html
@@ -0,0 +1,114 @@
+<!DOCTYPE html>
+<meta charset="utf-8">
+<style>
+
+	body {
+	  font: 10px sans-serif;
+	}
+
+	.axis path,
+	.axis line {
+	  fill: none;
+	  stroke: #000;
+	  shape-rendering: crispEdges;
+	}
+
+	.dot {
+	  stroke: #eee;
+	}
+
+</style>
+<body>
+<script src="https://cdnjs.cloudflare.com/ajax/libs/d3/3.5.7/d3.min.js"></script>
+<!–– do not use version 4 of d3, some functions API are different ––>
+<script>
+
+var margin = {top: 20, right: 20, bottom: 30, left: 40},
+    width = 960 - margin.left - margin.right,
+    height = 500 - margin.top - margin.bottom;
+
+var x = d3.scale.linear()
+    .range([0, width]);
+
+var y = d3.scale.linear()
+    .range([height, 0]);
+
+var color = d3.scale.category10();
+var xAxis = d3.svg.axis()
+    .scale(x)
+    .orient("bottom");
+
+var yAxis = d3.svg.axis()
+    .scale(y)
+    .orient("left");
+
+var svg = d3.select("body").append("svg")
+    .attr("width", width + margin.left + margin.right)
+    .attr("height", height + margin.top + margin.bottom)
+  .append("g")
+    .attr("transform", "translate(" + margin.left + "," + margin.top + ")");
+
+d3.tsv("../data/data.tsv", function(error, data) {
+  if (error) throw error;
+
+  data.forEach(function(d) {
+    d.y = +d.y;
+    d.x = +d.x;
+  });
+
+  x.domain(d3.extent(data, function(d) { return d.x; })).nice();
+  y.domain(d3.extent(data, function(d) { return d.y; })).nice();
+
+  svg.append("g")
+      .attr("class", "x axis")
+      .attr("transform", "translate(0," + height + ")")
+      .call(xAxis)
+    .append("text")
+      .attr("class", "label")
+      .attr("x", width)
+      .attr("y", -6)
+      .style("text-anchor", "end")
+      .text("x");
+
+  svg.append("g")
+      .attr("class", "y axis")
+      .call(yAxis)
+    .append("text")
+      .attr("class", "label")
+      .attr("transform", "rotate(-90)")
+      .attr("y", 6)
+      .attr("dy", ".71em")
+      .style("text-anchor", "end")
+      .text("y")
+
+  svg.selectAll(".dot")
+      .data(data)
+    .enter().append("circle")
+      .attr("class", "dot")
+      .attr("r", 3.5)
+      .attr("cx", function(d) { return x(d.x); })
+      .attr("cy", function(d) { return y(d.y); })
+      .style("fill", function(d) { return color(d.clusters); });
+
+  var legend = svg.selectAll(".legend")
+      .data(color.domain())
+    .enter().append("g")
+      .attr("class", "legend")
+      .attr("transform", function(d, i) { return "translate(0," + i * 20 + ")"; });
+
+  legend.append("rect")
+      .attr("x", width - 18)
+      .attr("width", 18)
+      .attr("height", 18)
+      .style("fill", color);
+
+  legend.append("text")
+      .attr("x", width - 24)
+      .attr("y", 9)
+      .attr("dy", ".35em")
+      .style("text-anchor", "end")
+      .text(function(d) { return d; });
+
+});
+
+</script>
diff --git a/...ents/DongHuibing/Experiment1/SpectralClustering/results/spectral_A_0.5_10_7.png b/...ents/DongHuibing/Experiment1/SpectralClustering/results/spectral_A_0.5_10_7.png
diff --git a/...s/DongHuibing/Experiment1/SpectralClustering/results/spectral_R15_0.5_10_14.png b/...s/DongHuibing/Experiment1/SpectralClustering/results/spectral_R15_0.5_10_14.png
diff --git a/.../DongHuibing/Experiment1/SpectralClustering/results/spectral_flame_0.5_10_2.png b/.../DongHuibing/Experiment1/SpectralClustering/results/spectral_flame_0.5_10_2.png
diff --git a/students/DongHuibing/Experiment1/SpectralClustering/results/spectral_mix.png b/students/DongHuibing/Experiment1/SpectralClustering/results/spectral_mix.png
diff --git a/...s/DongHuibing/Experiment1/SpectralClustering/results/spectral_mix_0.5_10_20.png b/...s/DongHuibing/Experiment1/SpectralClustering/results/spectral_mix_0.5_10_20.png
diff --git a/...s/DongHuibing/Experiment1/SpectralClustering/results/spectral_mix_0.5_20_20.png b/...s/DongHuibing/Experiment1/SpectralClustering/results/spectral_mix_0.5_20_20.png
diff --git a/students/DongHuibing/Experiment1/SpectralClustering/src/SpectralClustering.cpp b/students/DongHuibing/Experiment1/SpectralClustering/src/SpectralClustering.cpp
@@ -0,0 +1,86 @@
+#include<bits/stdc++.h>
+#include<unistd.h>
+using namespace std;
+struct Node
+{
+    double x, y;
+    int truth;
+    int cluster;//-1:undefined;0:noise;
+
+    bool operator< (const Node &rhs) const
+    {
+        if (x != rhs.x) return x < rhs.x;
+        return y < rhs.y;
+    }
+};
+vector<Node> nodes;
+const int MAXN = 1e4 + 5;
+double sim[MAXN][MAXN], deg[MAXN][MAXN], L[MAXN][MAXN];
+double sigma;
+int k;
+
+void readData()
+{
+    string s = "";
+    cout << "Please enter the file name , sigma and k:" << endl;
+    cin >> s >> sigma >> k;
+    freopen(("../data/synthetic_data/" + s).c_str(), "r", stdin);
+    double x, y;
+    int t;
+    while(~scanf("%lf,%lf,%d", &x, &y, &t))
+        nodes.push_back((Node){x, y, t, -1});
+}
+
+double squDistance(Node &u, Node &v)
+{
+    double dx = u.x - v.x;
+    double dy = u.y - v.y;
+    return dx * dx + dy * dy;
+}
+
+
+void calcSim()
+{
+    for(int i = 0; i < nodes.size(); ++i)
+        for(int j = i; j < nodes.size(); ++j)
+            sim[i][j] = sim[j][i] = exp(-squDistance(nodes[i], nodes[j])*0.5/sigma/sigma);
+}
+
+void calcDeg()
+{
+    for(int i = 0; i < nodes.size(); ++i)
+        for(int j = i; j < nodes.size(); ++j) deg[i][j] = deg[j][i] = 0;
+    for(int i = 0; i < nodes.size(); ++i)
+        for(int j = i + 1; j < nodes.size(); ++j)
+        {
+            deg[i][i] += sim[i][j];
+            deg[j][j] += sim[i][j];
+        }
+}
+
+void calcLap()
+{
+    for(int i = 0; i < nodes.size(); ++i)
+        for(int j = 0; j < nodes.size(); ++j) L[i][j] = sim[i][j] - deg[i][j];
+}
+
+void outputResult()
+{
+    freopen("../data/data.tsv", "w", stdout);
+    puts("x\ty\tclusters");
+    for(int i = 0; i < nodes.size(); ++i)
+    {
+        printf("%.2f\t%.2f\tCluster%d\n", nodes[i].x, nodes[i].y, nodes[i].cluster);
+    }
+}
+
+
+int main()
+{
+    readData();
+    calcSim();
+    calcDeg();
+    calcLap();
+    outputResult();
+    return 0;
+}