juneja-codebase 0.1.3__py3-none-any.whl

juneja_codebase/templates/social_network_analysis/2_try.ipynb

@@ -0,0 +1,352 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "36b05a3b",
+   "metadata": {},
+   "source": [
+    "# **Q2(A) Compute and plot the degree distribution, cumulative degree distributions of four real-world networks(networks with approx 100, 1000, 10,000, 100,000 nodes).Also compute local and global properties of the network.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4cd11209",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# KARATE CLUB\n",
+    "\n",
+    "import networkx as nx\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "G = nx.karate_club_graph()\n",
+    "\n",
+    "print(\"Nodes:\", G.number_of_nodes())\n",
+    "print(\"Edges:\", G.number_of_edges())\n",
+    "\n",
+    "degrees = [d for _, d in G.degree()]\n",
+    "\n",
+    "plt.figure(figsize=(12,5))\n",
+    "plt.subplot(1,2,1)\n",
+    "plt.hist(degrees, bins=range(1, max(degrees)+2), color='pink', edgecolor='black')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Frequency')\n",
+    "plt.title('Degree Distribution')\n",
+    "\n",
+    "plt.subplot(1,2,2)\n",
+    "sorted_deg = sorted(set(degrees))\n",
+    "cum = [sum(i <= x for i in degrees)/len(degrees) for x in sorted_deg]\n",
+    "plt.plot(sorted_deg, cum, marker='o', color='darkblue')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Cumulative Probability')\n",
+    "plt.title('Cumulative Degree Distribution')\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "\n",
+    "avg_deg = sum(degrees)/len(degrees)\n",
+    "clustering = nx.average_clustering(G)\n",
+    "density = nx.density(G)\n",
+    "avg_dist = nx.average_shortest_path_length(G)\n",
+    "radius = nx.radius(G)\n",
+    "diameter = nx.diameter(G)\n",
+    "\n",
+    "print(\"\\nNetwork Properties:\")\n",
+    "print(f\"Average Degree: {avg_deg:.2f}\")\n",
+    "print(f\"Clustering Coefficient: {clustering:.3f}\")\n",
+    "print(f\"Density: {density:.3f}\")\n",
+    "print(f\"Average Distance: {avg_dist:.3f}\")\n",
+    "print(f\"Radius: {radius}\")\n",
+    "print(f\"Diameter: {diameter}\")\n",
+    "\n",
+    "plt.figure(figsize=(8,6))\n",
+    "#other layouts\n",
+    "# pos = nx.spring_layout(G, seed=42)\n",
+    "# pos = nx.circular_layout(G)\n",
+    "pos = nx.kamada_kawai_layout(G)\n",
+    "nx.draw(G, pos, with_labels=True, node_color='pink', edge_color='blue',\n",
+    "        node_size=800, font_color='black', font_size=8)\n",
+    "plt.title(\"Karate Club Network\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f4d1fbc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# POLITICAL BOOKS\n",
+    "\n",
+    "import pandas as pd\n",
+    "import networkx as nx\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "df = pd.read_csv('PoliticalBooks.txt', sep='\\t', names=['Source', 'Target'], header=0)\n",
+    "G = nx.from_pandas_edgelist(df, source='Source', target='Target', create_using=nx.Graph())\n",
+    "\n",
+    "print(\"Nodes:\", G.number_of_nodes())\n",
+    "print(\"Edges:\", G.number_of_edges())\n",
+    "\n",
+    "degrees = [d for _, d in G.degree()]\n",
+    "\n",
+    "plt.figure(figsize=(12,5))\n",
+    "plt.subplot(1,2,1)\n",
+    "plt.hist(degrees, bins=range(1, max(degrees)+2), color='pink', edgecolor='black')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Frequency')\n",
+    "plt.title('Degree Distribution')\n",
+    "\n",
+    "plt.subplot(1,2,2)\n",
+    "sorted_deg = sorted(set(degrees))\n",
+    "cum = [sum(i <= x for i in degrees)/len(degrees) for x in sorted_deg]\n",
+    "plt.plot(sorted_deg, cum, marker='o', color='darkblue')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Cumulative Probability')\n",
+    "plt.title('Cumulative Degree Distribution')\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "\n",
+    "avg_deg = sum(degrees)/len(degrees)\n",
+    "clustering = nx.average_clustering(G)\n",
+    "density = nx.density(G)\n",
+    "avg_dist = nx.average_shortest_path_length(G)\n",
+    "radius = nx.radius(G)\n",
+    "diameter = nx.diameter(G)\n",
+    "\n",
+    "print(\"\\nNetwork Properties:\")\n",
+    "print(f\"Average Degree: {avg_deg:.2f}\")\n",
+    "print(f\"Clustering Coefficient: {clustering:.3f}\")\n",
+    "print(f\"Density: {density:.3f}\")\n",
+    "print(f\"Average Distance: {avg_dist:.3f}\")\n",
+    "print(f\"Radius: {radius}\")\n",
+    "print(f\"Diameter: {diameter}\")\n",
+    "\n",
+    "plt.figure(figsize=(8,6))\n",
+    "#pos = nx.spring_layout(G, seed=42)\n",
+    "# pos = nx.kamada_kawai_layout(G)\n",
+    "pos = nx.circular_layout(G)\n",
+    "\n",
+    "nx.draw(G, pos, with_labels=True, node_color='pink', edge_color='blue',\n",
+    "        node_size=800, font_color='black', font_size=8)\n",
+    "plt.title(\"Political Books Network\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f59953fe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# HAMSTER DATASET\n",
+    "\n",
+    "import pandas as pd\n",
+    "import networkx as nx\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "df = pd.read_csv('soc-hamsterster.edges', sep=' ', names=['Source', 'Target'])\n",
+    "G = nx.from_pandas_edgelist(df, source='Source', target='Target', create_using=nx.Graph())\n",
+    "\n",
+    "print(\"Nodes:\", G.number_of_nodes())\n",
+    "print(\"Edges:\", G.number_of_edges())\n",
+    "\n",
+    "degrees = [d for _, d in G.degree()]\n",
+    "\n",
+    "plt.figure(figsize=(12,5))\n",
+    "plt.subplot(1,2,1)\n",
+    "plt.hist(degrees, bins=range(1, max(degrees)+2), color='pink', edgecolor='black')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Frequency')\n",
+    "plt.title('Degree Distribution')\n",
+    "\n",
+    "plt.subplot(1,2,2)\n",
+    "sorted_deg = sorted(set(degrees))\n",
+    "cum = [sum(i <= x for i in degrees)/len(degrees) for x in sorted_deg]\n",
+    "plt.plot(sorted_deg, cum, marker='o', color='darkblue')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Cumulative Probability')\n",
+    "plt.title('Cumulative Degree Distribution')\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "\n",
+    "avg_deg = sum(degrees)/len(degrees)\n",
+    "clustering = nx.average_clustering(G)\n",
+    "density = nx.density(G)\n",
+    "#avg_dist = nx.average_shortest_path_length(G) # This might be slow for large graphs\n",
+    "#radius = nx.radius(G) # This might be slow for large graphs\n",
+    "#diameter = nx.diameter(G) # This might be slow for large graphs\n",
+    "\n",
+    "print(\"\\nNetwork Properties:\")\n",
+    "print(f\"Average Degree: {avg_deg:.2f}\")\n",
+    "print(f\"Clustering Coefficient: {clustering:.3f}\")\n",
+    "print(f\"Density: {density:.3f}\")\n",
+    "#print(f\"Average Distance: {avg_dist:.3f}\")\n",
+    "#print(f\"Radius: {radius}\")\n",
+    "#print(f\"Diameter: {diameter}\")\n",
+    "\n",
+    "\n",
+    "plt.figure(figsize=(8,6))\n",
+    "#pos = nx.spring_layout(G, seed=42)\n",
+    "# pos = nx.kamada_kawai_layout(G)\n",
+    "pos = nx.circular_layout(G)\n",
+    "\n",
+    "nx.draw(G, pos, with_labels=True, node_color='pink', edge_color='blue',\n",
+    "        node_size=800, font_color='black', font_size=8)\n",
+    "plt.title(\"Hamsterster Social Network\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fef12822",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# EUROROAD DATASET\n",
+    "\n",
+    "import pandas as pd\n",
+    "import networkx as nx\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "df = pd.read_csv('road-euroroad.edges', sep=' ', names=['Source', 'Target'], header=0)\n",
+    "G = nx.from_pandas_edgelist(df, source='Source', target='Target', create_using=nx.Graph())\n",
+    "\n",
+    "print(\"Nodes:\", G.number_of_nodes())\n",
+    "print(\"Edges:\", G.number_of_edges())\n",
+    "\n",
+    "degrees = [d for _, d in G.degree()]\n",
+    "\n",
+    "plt.figure(figsize=(12,5))\n",
+    "plt.subplot(1,2,1)\n",
+    "plt.hist(degrees, bins=range(1, max(degrees)+2), color='pink', edgecolor='black')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Frequency')\n",
+    "plt.title('Degree Distribution')\n",
+    "\n",
+    "plt.subplot(1,2,2)\n",
+    "sorted_deg = sorted(set(degrees))\n",
+    "cum = [sum(i <= x for i in degrees)/len(degrees) for x in sorted_deg]\n",
+    "plt.plot(sorted_deg, cum, marker='o', color='darkblue')\n",
+    "plt.xlabel('Degree')\n",
+    "plt.ylabel('Cumulative Probability')\n",
+    "plt.title('Cumulative Degree Distribution')\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "\n",
+    "avg_deg = sum(degrees)/len(degrees)\n",
+    "clustering = nx.average_clustering(G)\n",
+    "density = nx.density(G)\n",
+    "#avg_dist = nx.average_shortest_path_length(G)\n",
+    "#radius = nx.radius(G)\n",
+    "#diameter = nx.diameter(G)\n",
+    "\n",
+    "print(\"\\nNetwork Properties:\")\n",
+    "print(f\"Average Degree: {avg_deg:.2f}\")\n",
+    "print(f\"Clustering Coefficient: {clustering:.3f}\")\n",
+    "print(f\"Density: {density:.3f}\")\n",
+    "#print(f\"Average Distance: {avg_dist:.3f}\")\n",
+    "#print(f\"Radius: {radius}\")\n",
+    "#print(f\"Diameter: {diameter}\")\n",
+    "\n",
+    "\n",
+    "plt.figure(figsize=(8,6))\n",
+    "#pos = nx.spring_layout(G, seed=42)\n",
+    "# pos = nx.kamada_kawai_layout(G)\n",
+    "pos = nx.circular_layout(G)\n",
+    "\n",
+    "nx.draw(G, pos, with_labels=True, node_color='pink', edge_color='blue',\n",
+    "        node_size=800, font_color='black', font_size=8)\n",
+    "plt.title(\"road-euroroad\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cccc0f61",
+   "metadata": {},
+   "source": [
+    "# **Q2(B) Implement page rank algorithm and calculate the number of iteration to determine the convergence point and indicate your result with a pre defined page rank function.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85c29c9e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import networkx as nx\n",
+    "import numpy as np\n",
+    "\n",
+    "G = nx.DiGraph()\n",
+    "\n",
+    "G.add_nodes_from([1, 2, 3, 4])\n",
+    "\n",
+    "edges = [(1, 2), (1, 3), (2, 3), (4, 1), (3, 4), (4, 2)]\n",
+    "G.add_edges_from(edges)\n",
+    "\n",
+    "print(\"Nodes:\", G.nodes())\n",
+    "print(\"Edges:\", G.edges())\n",
+    "\n",
+    "d = 0.85                      # Damping factor\n",
+    "N = len(G)                    # Number of nodes\n",
+    "PR = np.ones(N) / N           # Initial PageRank\n",
+    "M = nx.to_numpy_array(G).T    # Adjacency matrix\n",
+    "\n",
+    "# Normalize columns\n",
+    "for i in range(N):\n",
+    "    if M[:, i].sum() != 0:\n",
+    "        M[:, i] = M[:, i] / M[:, i].sum()\n",
+    "\n",
+    "# Iterative PageRank computation\n",
+    "tolerance = 1e-6\n",
+    "iteration = 0\n",
+    "while True:\n",
+    "    iteration += 1\n",
+    "    new_PR = (1 - d) / N + d * np.dot(M, PR)\n",
+    "    if np.linalg.norm(new_PR - PR, 1) < tolerance:\n",
+    "        break\n",
+    "    PR = new_PR\n",
+    "\n",
+    "# results\n",
+    "manual_pagerank = {node + 1: round(rank, 4) for node, rank in enumerate(PR)}\n",
+    "print(\"\\nManual PageRank Results:\")\n",
+    "for node, value in manual_pagerank.items():\n",
+    "    print(f\"Node {node}: {value}\")\n",
+    "\n",
+    "print(f\"\\n Converged after {iteration} iterations\")\n",
+    "\n",
+    "# Compare with NetworkX predefined PageRank\n",
+    "nx_pagerank = nx.pagerank(G, alpha=0.85)\n",
+    "print(\"\\nNetworkX PageRank Results:\")\n",
+    "for node, value in nx_pagerank.items():\n",
+    "    print(f\"Node {node}: {round(value, 4)}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}