graph-inspect/*: add
This commit is contained in:
parent
b98904e9e5
commit
3c7e3fc018
3 changed files with 1431 additions and 0 deletions
425
graph-inspect/inspect-graph-comparison.ipynb
Normal file
425
graph-inspect/inspect-graph-comparison.ipynb
Normal file
|
|
@ -0,0 +1,425 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Compare interactions graphs\n",
|
||||
"\n",
|
||||
"Inspecting interaction and comparing graphs by counting the components, determining the connectivity, clustering and various other metrics. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Import the graphs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import networkx as nx\n",
|
||||
"\n",
|
||||
"casename1 = '...'\n",
|
||||
"case1 = '...'\n",
|
||||
"\n",
|
||||
"casename2 = '...'\n",
|
||||
"case2 = '...'\n",
|
||||
"\n",
|
||||
"# Import the graph\n",
|
||||
"G1 = nx.read_graphml(f'../datasets/{case1}-dtc-graph.graphml')\n",
|
||||
"G2 = nx.read_graphml(f'../datasets/{case2}-dtc-graph.graphml')\n",
|
||||
"\n",
|
||||
"# Print nodes, edges and density of the graphs\n",
|
||||
"print(f'G1:\\nNodes: {G1.number_of_nodes()}\\nEdges: {G1.number_of_edges()}\\nDensity: {nx.density(G1):.5f}')\n",
|
||||
"print(f'G2:\\nNodes: {G2.number_of_nodes()}\\nEdges: {G2.number_of_edges()}\\nDensity: {nx.density(G2):.5f}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Remove isolated nodes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"G1.remove_nodes_from(list(nx.isolates(G1)))\n",
|
||||
"G2.remove_nodes_from(list(nx.isolates(G2)))\n",
|
||||
"\n",
|
||||
"# Print nodes, edges and density of the graphs\n",
|
||||
"print(f'G1:\\nNodes: {G1.number_of_nodes()}\\nEdges: {G1.number_of_edges()}\\nDensity: {nx.density(G1):.5f}')\n",
|
||||
"print(f'G2:\\nNodes: {G2.number_of_nodes()}\\nEdges: {G2.number_of_edges()}\\nDensity: {nx.density(G2):.5f}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Compute average degree, connectivity, clustering and degree_assortivity. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"components1 = list(nx.connected_components(G1))\n",
|
||||
"\n",
|
||||
"component_metrics1 = []\n",
|
||||
"\n",
|
||||
"for component in components1:\n",
|
||||
"\n",
|
||||
" subG = G1.subgraph(component)\n",
|
||||
"\n",
|
||||
" num_nodes = subG.number_of_nodes()\n",
|
||||
" num_edges = subG.number_of_edges()\n",
|
||||
" average_degree = (2 * num_edges) / num_nodes\n",
|
||||
" connectivity = nx.node_connectivity(subG)\n",
|
||||
" clustering = nx.average_clustering(subG)\n",
|
||||
" degree_assortivity = nx.degree_assortativity_coefficient(subG)\n",
|
||||
"\n",
|
||||
" metrics = {\n",
|
||||
" 'num_nodes': num_nodes,\n",
|
||||
" 'num_edges': num_edges,\n",
|
||||
" 'average_degree': average_degree,\n",
|
||||
" 'connectivity': connectivity,\n",
|
||||
" 'clustering': clustering,\n",
|
||||
" 'degree_assortivity': degree_assortivity,\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" component_metrics1.append(metrics)\n",
|
||||
"\n",
|
||||
"df_metric1 = pd.DataFrame(component_metrics1)\n",
|
||||
"df_metric1.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"components2 = list(nx.connected_components(G2))\n",
|
||||
"\n",
|
||||
"component_metrics2 = []\n",
|
||||
"\n",
|
||||
"for component in components2:\n",
|
||||
"\n",
|
||||
" subG = G2.subgraph(component)\n",
|
||||
"\n",
|
||||
" num_nodes = subG.number_of_nodes()\n",
|
||||
" num_edges = subG.number_of_edges()\n",
|
||||
" average_degree = (2 * num_edges) / num_nodes\n",
|
||||
" connectivity = nx.node_connectivity(subG)\n",
|
||||
" clustering = nx.average_clustering(subG)\n",
|
||||
" degree_assortivity = nx.degree_assortativity_coefficient(subG)\n",
|
||||
"\n",
|
||||
" metrics = {\n",
|
||||
" 'num_nodes': num_nodes,\n",
|
||||
" 'num_edges': num_edges,\n",
|
||||
" 'average_degree': average_degree,\n",
|
||||
" 'connectivity': connectivity,\n",
|
||||
" 'clustering': clustering,\n",
|
||||
" 'degree_assortivity': degree_assortivity,\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" component_metrics2.append(metrics)\n",
|
||||
"\n",
|
||||
"df_metric2 = pd.DataFrame(component_metrics2)\n",
|
||||
"df_metric2.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Filter out the outliers in the dataframe, based on number of edges."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_metric1_ro = df_metric1[(df_metric1['num_edges'] < 400) & (df_metric1['num_nodes'] > 10)]\n",
|
||||
"\n",
|
||||
"df_metric1_ro.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_metric2_ro = df_metric2[(df_metric2['num_edges'] < 400) & (df_metric2['num_nodes'] > 10)]\n",
|
||||
"\n",
|
||||
"df_metric2_ro.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distributions of average degree."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(8, 6))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e3\n",
|
||||
"\n",
|
||||
"# Define the number of bins\n",
|
||||
"num_bins = 20\n",
|
||||
"\n",
|
||||
"# Calculate the combined range for both datasets\n",
|
||||
"min_value = min(df_metric1_ro['average_degree'].min(), df_metric2_ro['average_degree'].min())\n",
|
||||
"max_value = max(df_metric1_ro['average_degree'].max(), df_metric2_ro['average_degree'].max())\n",
|
||||
"\n",
|
||||
"# Create bin edges\n",
|
||||
"bins = np.linspace(min_value, max_value, num_bins + 1)\n",
|
||||
"\n",
|
||||
"# Create a single plot\n",
|
||||
"sns.histplot(df_metric1_ro['average_degree'], bins=bins, color='blue', alpha=0.5, label=f'{casename1.title()} case')\n",
|
||||
"sns.histplot(df_metric2_ro['average_degree'], bins=bins, color='orange', alpha=0.5, label=f'{casename2.title()} case')\n",
|
||||
"\n",
|
||||
"# Set y-axis to logarithmic scale\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"\n",
|
||||
"# Set titles and labels\n",
|
||||
"plt.title('Distribution of average degree (nodes > 10, edges < 400)', fontsize=16)\n",
|
||||
"plt.xlabel('Average degree')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
"\n",
|
||||
"# Add a legend\n",
|
||||
"plt.legend()\n",
|
||||
"\n",
|
||||
"# Show the plot\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distributions of connectivity."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(8, 6))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e3\n",
|
||||
"\n",
|
||||
"# Define the number of bins\n",
|
||||
"num_bins = 20\n",
|
||||
"\n",
|
||||
"# Calculate the combined range for both datasets\n",
|
||||
"min_value = min(df_metric1_ro['connectivity'].min(), df_metric2_ro['connectivity'].min())\n",
|
||||
"max_value = max(df_metric1_ro['connectivity'].max(), df_metric2_ro['connectivity'].max())\n",
|
||||
"\n",
|
||||
"# Create bin edges\n",
|
||||
"bins = np.linspace(min_value, max_value, num_bins + 1)\n",
|
||||
"\n",
|
||||
"# Create a single plot\n",
|
||||
"sns.histplot(df_metric1_ro['connectivity'], bins=bins, color='blue', alpha=0.5, label=f'{casename1.title()} case')\n",
|
||||
"sns.histplot(df_metric2_ro['connectivity'], bins=bins, color='orange', alpha=0.5, label=f'{casename2.title()} case')\n",
|
||||
"\n",
|
||||
"# Set y-axis to logarithmic scale\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"\n",
|
||||
"# Set titles and labels\n",
|
||||
"plt.title('Distribution of connectivity (nodes > 10, edges < 400)', fontsize=16)\n",
|
||||
"plt.xlabel('Connectivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
"\n",
|
||||
"# Add a legend\n",
|
||||
"plt.legend()\n",
|
||||
"\n",
|
||||
"# Show the plot\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distributions of clustering."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(8, 6))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e3\n",
|
||||
"\n",
|
||||
"# Define the number of bins\n",
|
||||
"num_bins = 20\n",
|
||||
"\n",
|
||||
"# Calculate the combined range for both datasets\n",
|
||||
"min_value = min(df_metric1_ro['clustering'].min(), df_metric2_ro['clustering'].min())\n",
|
||||
"max_value = max(df_metric1_ro['clustering'].max(), df_metric2_ro['clustering'].max())\n",
|
||||
"\n",
|
||||
"# Create bin edges\n",
|
||||
"bins = np.linspace(min_value, max_value, num_bins + 1)\n",
|
||||
"\n",
|
||||
"# Create a single plot\n",
|
||||
"sns.histplot(df_metric1_ro['clustering'], bins=bins, color='blue', alpha=0.5, label=f'{casename1.title()} case')\n",
|
||||
"sns.histplot(df_metric2_ro['clustering'], bins=bins, color='orange', alpha=0.5, label=f'{casename2.title()} case')\n",
|
||||
"\n",
|
||||
"# Set y-axis to logarithmic scale\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"\n",
|
||||
"# Set titles and labels\n",
|
||||
"plt.title('Distribution of clustering (nodes > 10, edges < 400)', fontsize=16)\n",
|
||||
"plt.xlabel('Clustering')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
"\n",
|
||||
"# Add a legend\n",
|
||||
"plt.legend()\n",
|
||||
"\n",
|
||||
"# Show the plot\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distributions of degree assortivity."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(8, 6))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e3\n",
|
||||
"\n",
|
||||
"# Define the number of bins\n",
|
||||
"num_bins = 20\n",
|
||||
"\n",
|
||||
"# Calculate the combined range for both datasets\n",
|
||||
"min_value = min(df_metric1_ro['degree_assortivity'].min(), df_metric2_ro['degree_assortivity'].min())\n",
|
||||
"max_value = max(df_metric1_ro['degree_assortivity'].max(), df_metric2_ro['degree_assortivity'].max())\n",
|
||||
"\n",
|
||||
"# Create bin edges\n",
|
||||
"bins = np.linspace(min_value, max_value, num_bins + 1)\n",
|
||||
"\n",
|
||||
"# Create a single plot\n",
|
||||
"sns.histplot(df_metric1_ro['degree_assortivity'], bins=bins, color='blue', alpha=0.5, label=f'{casename1.title()} case')\n",
|
||||
"sns.histplot(df_metric2_ro['degree_assortivity'], bins=bins, color='orange', alpha=0.5, label=f'{casename2.title()} case')\n",
|
||||
"\n",
|
||||
"# Set y-axis to logarithmic scale\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"\n",
|
||||
"# Set titles and labels\n",
|
||||
"plt.title('Distribution of degree assortivity (nodes > 10, edges < 400)', fontsize=16)\n",
|
||||
"plt.xlabel('Degree assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
"\n",
|
||||
"# Add a legend\n",
|
||||
"plt.legend()\n",
|
||||
"\n",
|
||||
"# Show the plot\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"plt.show()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"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": "3.14.6"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "8c75c0fdd1a718867cdcb84b32adcfdbeaad00b3a4e00a59385211aeed084d4c"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
335
graph-inspect/inspect-graph-user.ipynb
Normal file
335
graph-inspect/inspect-graph-user.ipynb
Normal file
|
|
@ -0,0 +1,335 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Inspect user interactions\n",
|
||||
"\n",
|
||||
"Inspecting the user interactions obtained from the NN, DTC and TC graphs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Import the dataset."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"casename = '...'\n",
|
||||
"case = '...'\n",
|
||||
"\n",
|
||||
"df_data = pd.read_csv(f'../datasets/{case}-closed-s-users.csv')\n",
|
||||
"\n",
|
||||
"df_data.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distributions."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(15, 10))\n",
|
||||
"\n",
|
||||
"plt.subplot(2,3,1)\n",
|
||||
"sns.histplot(df_data['nn-count'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.title('Distribution of NN interactions')\n",
|
||||
"plt.xlabel('NN interactions')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(2,3,2)\n",
|
||||
"sns.histplot(df_data['dtc-count'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.title('Distribution of DTC interactions')\n",
|
||||
"plt.xlabel('DTC interactions')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(2,3,3)\n",
|
||||
"sns.histplot(df_data['tc-count'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.title('Distribution of TC interactions')\n",
|
||||
"plt.xlabel('TC interactions')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(2,3,4)\n",
|
||||
"sns.histplot(df_data['post-count'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.title('Distribution of posts')\n",
|
||||
"plt.xlabel('Number of posts')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(2,3,5)\n",
|
||||
"sns.histplot(df_data['mean-sentiment'], bins=20, kde=True)\n",
|
||||
"plt.title('Distribution of mean sentiment')\n",
|
||||
"plt.xlabel('Mean sentiment')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(2,3,6)\n",
|
||||
"sns.histplot(df_data['std-sentiment'], bins=20, kde=True)\n",
|
||||
"plt.title('Distribution of SD sentiment')\n",
|
||||
"plt.xlabel('SD sentiment')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.suptitle(f'Distribution of user metrics {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"plt.savefig(f'../datasets/{case}-user-metrics.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot interaction count against mean sentiment, SD sentiment and post count."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import seaborn as sns\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"\n",
|
||||
"# Define the pairs of variables for the subplots\n",
|
||||
"variables = [\n",
|
||||
" (\"nn-count\", \"mean-sentiment\"),\n",
|
||||
" (\"dtc-count\", \"mean-sentiment\"),\n",
|
||||
" (\"tc-count\", \"mean-sentiment\"),\n",
|
||||
" (\"nn-count\", \"std-sentiment\"),\n",
|
||||
" (\"dtc-count\", \"std-sentiment\"),\n",
|
||||
" (\"tc-count\", \"std-sentiment\"),\n",
|
||||
" (\"nn-count\", \"post-count\"),\n",
|
||||
" (\"dtc-count\", \"post-count\"),\n",
|
||||
" (\"tc-count\", \"post-count\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"# Create the figure\n",
|
||||
"plt.figure(figsize=(15, 15))\n",
|
||||
"\n",
|
||||
"# Loop through the variables and create subplots\n",
|
||||
"for i, (x_var, y_var) in enumerate(variables):\n",
|
||||
" plt.subplot(3, 3, i + 1)\n",
|
||||
" \n",
|
||||
" # Drop NaN values for the current pair of variables\n",
|
||||
" df_nonan = df_data.dropna(subset=[x_var, y_var])\n",
|
||||
" \n",
|
||||
" # Create scatter plot\n",
|
||||
" sns.scatterplot(x=x_var, y=y_var, data=df_nonan, alpha=0.4, color=\"black\", edgecolor=None)\n",
|
||||
" \n",
|
||||
" # Create Lowess regression plot\n",
|
||||
" sns.regplot(x=x_var, y=y_var, data=df_nonan, scatter=False, lowess=True, line_kws={'color': 'blue', 'linewidth': 2}, label=\"Lowess fit\")\n",
|
||||
" \n",
|
||||
" # Set logarithmic scale for x-axis\n",
|
||||
" plt.xscale(\"log\")\n",
|
||||
" \n",
|
||||
" # Set labels and grid\n",
|
||||
" plt.xlabel(x_var.replace('-', ' '))\n",
|
||||
" plt.ylabel(y_var.replace('-', ' '))\n",
|
||||
" plt.grid()\n",
|
||||
" plt.legend()\n",
|
||||
" plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
"\n",
|
||||
"# Set the overall title and layout\n",
|
||||
"plt.suptitle(f'Scatter plot of user metrics against interaction count {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"# Save the figure\n",
|
||||
"plt.savefig(f'../datasets/{case}-user-interaction-scatter.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot (simplified) interaction count against mean sentiment, SD sentiment and post count. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import seaborn as sns\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"from scipy import stats\n",
|
||||
"\n",
|
||||
"# Assuming df_data is your DataFrame and casename and case are defined\n",
|
||||
"plt.figure(figsize=(15, 15))\n",
|
||||
"\n",
|
||||
"# Define the pairs of variables for the subplots\n",
|
||||
"variables = [\n",
|
||||
" (\"nn-count\", \"mean-sentiment\"),\n",
|
||||
" (\"dtc-count\", \"mean-sentiment\"),\n",
|
||||
" (\"tc-count\", \"mean-sentiment\"),\n",
|
||||
" (\"nn-count\", \"std-sentiment\"),\n",
|
||||
" (\"dtc-count\", \"std-sentiment\"),\n",
|
||||
" (\"tc-count\", \"std-sentiment\"),\n",
|
||||
" (\"nn-count\", \"post-count\"),\n",
|
||||
" (\"dtc-count\", \"post-count\"),\n",
|
||||
" (\"tc-count\", \"post-count\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"# Loop through the variables and create subplots\n",
|
||||
"for i, (x_var, y_var) in enumerate(variables):\n",
|
||||
" plt.subplot(3, 3, i + 1)\n",
|
||||
" \n",
|
||||
" # Drop NaN values for the current pair of variables\n",
|
||||
" df_nonan = df_data.dropna(subset=[x_var, y_var])\n",
|
||||
" \n",
|
||||
" # Create the regression plot\n",
|
||||
" sns.regplot(x=x_var, y=y_var, data=df_nonan, scatter=False, ci=68, line_kws={'color': 'blue', 'linewidth': 2})\n",
|
||||
" \n",
|
||||
" # Fit the regression model and get r and p values\n",
|
||||
" slope, intercept, r_value, p_value, std_err = stats.linregress(df_nonan[x_var], df_nonan[y_var])\n",
|
||||
" \n",
|
||||
" # Add labels and grid\n",
|
||||
" plt.xlabel(x_var.replace('-', ' '))\n",
|
||||
" plt.ylabel(y_var.replace('-', ' '))\n",
|
||||
" plt.grid()\n",
|
||||
" plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
" \n",
|
||||
" # Add text annotation for r and p values\n",
|
||||
" plt.text(0.05, 0.95, f'r = {r_value:.4f}\\np = {max(p_value, 0.0001):.4f}', transform=plt.gca().transAxes, fontsize=12, verticalalignment='top', bbox=dict(facecolor='white', alpha=0.5))\n",
|
||||
"\n",
|
||||
"# Set the overall title and layout\n",
|
||||
"plt.suptitle(f'Regression plot of user metrics against interaction count {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"# Save the figure\n",
|
||||
"plt.savefig(f'../datasets/{case}-user-interaction-regression.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Take out change in sentiment regressions."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import seaborn as sns\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"from scipy import stats\n",
|
||||
"\n",
|
||||
"# Assuming df_data is your DataFrame and casename and case are defined\n",
|
||||
"fig, axes = plt.subplots(1, 3, figsize=(15, 6), sharey=True)\n",
|
||||
"\n",
|
||||
"# Define the variables for std-sentiment plots\n",
|
||||
"variables = [\n",
|
||||
" (\"nn-count\", \"std-sentiment\"),\n",
|
||||
" (\"dtc-count\", \"std-sentiment\"),\n",
|
||||
" (\"tc-count\", \"std-sentiment\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"# Loop through the variables and create subplots\n",
|
||||
"for i, (ax, (x_var, y_var)) in enumerate(zip(axes, variables)):\n",
|
||||
" # Drop NaN values for the current pair of variables\n",
|
||||
" df_nonan = df_data.dropna(subset=[x_var, y_var])\n",
|
||||
" \n",
|
||||
" # Create the regression plot\n",
|
||||
" sns.regplot(x=x_var, y=y_var, data=df_nonan, scatter=False, ci=68, line_kws={'color': 'blue', 'linewidth': 2}, ax=ax)\n",
|
||||
" \n",
|
||||
" # Fit the regression model and get r and p values\n",
|
||||
" slope, intercept, r_value, p_value, std_err = stats.linregress(df_nonan[x_var], df_nonan[y_var])\n",
|
||||
" \n",
|
||||
" # Add labels and grid\n",
|
||||
" ax.set_xlabel(x_var.replace('-', ' '))\n",
|
||||
" if i == 0:\n",
|
||||
" ax.set_ylabel(y_var.replace('-', ' '))\n",
|
||||
" else:\n",
|
||||
" ax.set_ylabel('')\n",
|
||||
" ax.grid()\n",
|
||||
" ax.tick_params(axis='both', direction='in', top=True, right=True)\n",
|
||||
" \n",
|
||||
" # Add text annotation for r and p values\n",
|
||||
" ax.text(0.05, 0.95, f'r = {r_value:.4f}\\np = {max(p_value, 0.0001):.4f}', transform=ax.transAxes, fontsize=12, verticalalignment='top', bbox=dict(facecolor='white', alpha=0.5))\n",
|
||||
"\n",
|
||||
"# Set the overall title and layout\n",
|
||||
"plt.suptitle(f'Regression plot of standard deviation of sentiment against interaction count {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.95])\n",
|
||||
"\n",
|
||||
"# Save the figure\n",
|
||||
"plt.savefig(f'../datasets/{case}-user-std-sentiment-regression.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"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": "3.14.6"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "8c75c0fdd1a718867cdcb84b32adcfdbeaad00b3a4e00a59385211aeed084d4c"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
671
graph-inspect/inspect-graph.ipynb
Normal file
671
graph-inspect/inspect-graph.ipynb
Normal file
|
|
@ -0,0 +1,671 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Inspect interaction graphs\n",
|
||||
"\n",
|
||||
"Inspecting interaction graphs by counting the components, determining the connectivity, clustering and various other metrics. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Import the graph."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import networkx as nx\n",
|
||||
"\n",
|
||||
"casename = '...'\n",
|
||||
"case = '...'\n",
|
||||
"\n",
|
||||
"# Import the graph\n",
|
||||
"G = nx.read_graphml(f'../datasets/{case}-dtc-graph.graphml')\n",
|
||||
"\n",
|
||||
"# Print nodes, edges and density of the graph\n",
|
||||
"print(f'Nodes: {G.number_of_nodes()}\\nEdges: {G.number_of_edges()}\\nDensity: {nx.density(G):.5f}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Remove isolated nodes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"G.remove_nodes_from(list(nx.isolates(G)))\n",
|
||||
"print(f'Nodes: {G.number_of_nodes()}\\nEdges: {G.number_of_edges()}\\nDensity: {nx.density(G):.5f}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Compute number of connected components."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"nx.number_connected_components(G)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Compute metrics of each component."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"components = list(nx.connected_components(G))\n",
|
||||
"\n",
|
||||
"component_metrics = []\n",
|
||||
"\n",
|
||||
"for component in components:\n",
|
||||
"\n",
|
||||
" subG = G.subgraph(component)\n",
|
||||
"\n",
|
||||
" num_nodes = subG.number_of_nodes()\n",
|
||||
" num_edges = subG.number_of_edges()\n",
|
||||
" diameter = nx.diameter(subG)\n",
|
||||
" average_degree = (2 * num_edges) / num_nodes\n",
|
||||
" density = nx.density(subG)\n",
|
||||
" connectivity = nx.node_connectivity(subG)\n",
|
||||
" clustering = nx.average_clustering(subG)\n",
|
||||
" degree_assortivity = nx.degree_assortativity_coefficient(subG)\n",
|
||||
" sentiment_assortivity = nx.numeric_assortativity_coefficient(subG, 'sentiment')\n",
|
||||
"\n",
|
||||
" metrics = {\n",
|
||||
" 'num_nodes': num_nodes,\n",
|
||||
" 'num_edges': num_edges,\n",
|
||||
" 'diameter': diameter,\n",
|
||||
" 'average_degree': average_degree,\n",
|
||||
" 'density': density,\n",
|
||||
" 'connectivity': connectivity,\n",
|
||||
" 'clustering': clustering,\n",
|
||||
" 'degree_assortivity': degree_assortivity,\n",
|
||||
" 'sentiment_assortivity': sentiment_assortivity\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" component_metrics.append(metrics)\n",
|
||||
"\n",
|
||||
"df_metric = pd.DataFrame(component_metrics)\n",
|
||||
"df_metric.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distribution of the metrics."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(15, 15))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e5\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 1)\n",
|
||||
"sns.histplot(df_metric['num_nodes'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of nodes')\n",
|
||||
"plt.xlabel('Number of nodes')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 2)\n",
|
||||
"sns.histplot(df_metric['num_edges'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of edges')\n",
|
||||
"plt.xlabel('Number of edges')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 3)\n",
|
||||
"sns.histplot(df_metric['diameter'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of diameter')\n",
|
||||
"plt.xlabel('Diameter')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 4)\n",
|
||||
"sns.histplot(df_metric['average_degree'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of average degree')\n",
|
||||
"plt.xlabel('Average degree')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 5)\n",
|
||||
"sns.histplot(df_metric['density'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(1e1, upper_limit)\n",
|
||||
"plt.title('Distribution of density')\n",
|
||||
"plt.xlabel('Density')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 6)\n",
|
||||
"sns.histplot(df_metric['connectivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of connectivity')\n",
|
||||
"plt.xlabel('Connectivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 7)\n",
|
||||
"sns.histplot(df_metric['clustering'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of clustering')\n",
|
||||
"plt.xlabel('Clustering')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 8)\n",
|
||||
"sns.histplot(df_metric['degree_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of degree assortivity')\n",
|
||||
"plt.xlabel('Degree assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 9)\n",
|
||||
"sns.histplot(df_metric['sentiment_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of sentiment assortivity')\n",
|
||||
"plt.xlabel('Sentiment assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.suptitle(f'Metrics {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"plt.savefig(f'../datasets/{case}-metrics.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Filter out the outliers in the dataframe, based on number of edges."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_metric_ro = df_metric[df_metric['num_edges'] < 400]\n",
|
||||
"\n",
|
||||
"df_metric_ro.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distribution of the metrics of the outlier filtered dataframe."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Set up the matplotlib figure\n",
|
||||
"plt.figure(figsize=(15, 15))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e5\n",
|
||||
"\n",
|
||||
"# Plot distributions\n",
|
||||
"plt.subplot(3, 3, 1)\n",
|
||||
"sns.histplot(df_metric_ro['num_nodes'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of nodes')\n",
|
||||
"plt.xlabel('Number of nodes')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 2)\n",
|
||||
"sns.histplot(df_metric_ro['num_edges'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of edges')\n",
|
||||
"plt.xlabel('Number of edges')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 3)\n",
|
||||
"sns.histplot(df_metric_ro['diameter'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of diameter')\n",
|
||||
"plt.xlabel('Diameter')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 4)\n",
|
||||
"sns.histplot(df_metric_ro['average_degree'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of average degree')\n",
|
||||
"plt.xlabel('Average degree')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 5)\n",
|
||||
"sns.histplot(df_metric_ro['density'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(1e1, upper_limit)\n",
|
||||
"plt.title('Distribution of density')\n",
|
||||
"plt.xlabel('Density')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 6)\n",
|
||||
"sns.histplot(df_metric_ro['connectivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of connectivity')\n",
|
||||
"plt.xlabel('Connectivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 7)\n",
|
||||
"sns.histplot(df_metric_ro['clustering'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of clustering')\n",
|
||||
"plt.xlabel('Clustering')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 8)\n",
|
||||
"sns.histplot(df_metric_ro['degree_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of degree assortivity')\n",
|
||||
"plt.xlabel('Degree assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 9)\n",
|
||||
"sns.histplot(df_metric_ro['sentiment_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of sentiment assortivity')\n",
|
||||
"plt.xlabel('Sentiment assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.suptitle(f'Metrics (edges < 400) {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"plt.savefig(f'../datasets/{case}-metrics-ro.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Filter metrics on number of nodes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_metric_ls = df_metric[df_metric['num_nodes'] > 10]\n",
|
||||
"\n",
|
||||
"df_metric_ls.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Plot the distribution of the metrics of the large structures set."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Set up the matplotlib figure\n",
|
||||
"plt.figure(figsize=(15, 15))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e3\n",
|
||||
"\n",
|
||||
"# Plot distributions\n",
|
||||
"plt.subplot(3, 3, 1)\n",
|
||||
"sns.histplot(df_metric_ls['num_nodes'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of nodes')\n",
|
||||
"plt.xlabel('Number of nodes')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 2)\n",
|
||||
"sns.histplot(df_metric_ls['num_edges'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of edges')\n",
|
||||
"plt.xlabel('Number of edges')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 3)\n",
|
||||
"sns.histplot(df_metric_ls['diameter'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of diameter')\n",
|
||||
"plt.xlabel('Diameter')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 4)\n",
|
||||
"sns.histplot(df_metric_ls['average_degree'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of average degree')\n",
|
||||
"plt.xlabel('Average degree')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 5)\n",
|
||||
"sns.histplot(df_metric_ls['density'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(1e1, upper_limit)\n",
|
||||
"plt.title('Distribution of density')\n",
|
||||
"plt.xlabel('Density')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 6)\n",
|
||||
"sns.histplot(df_metric_ls['connectivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of connectivity')\n",
|
||||
"plt.xlabel('Connectivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 7)\n",
|
||||
"sns.histplot(df_metric_ls['clustering'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of clustering')\n",
|
||||
"plt.xlabel('Clustering')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 8)\n",
|
||||
"sns.histplot(df_metric_ls['degree_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of degree assortivity')\n",
|
||||
"plt.xlabel('Degree assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 9)\n",
|
||||
"sns.histplot(df_metric_ls['sentiment_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of sentiment assortivity')\n",
|
||||
"plt.xlabel('Sentiment assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.suptitle(f'Metrics (nodes > 10) {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"plt.savefig(f'../datasets/{case}-metrics-ls.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Filter out the outliers in the large structures dataset, based on number of edges."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_metric_ls_ro = df_metric_ls[df_metric_ls['num_edges'] < 400]\n",
|
||||
"\n",
|
||||
"df_metric_ls_ro.describe()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Set up the matplotlib figure\n",
|
||||
"plt.figure(figsize=(15, 15))\n",
|
||||
"\n",
|
||||
"upper_limit = 1e3\n",
|
||||
"\n",
|
||||
"# Plot distributions\n",
|
||||
"plt.subplot(3, 3, 1)\n",
|
||||
"sns.histplot(df_metric_ls_ro['num_nodes'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of nodes')\n",
|
||||
"plt.xlabel('Number of nodes')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 2)\n",
|
||||
"sns.histplot(df_metric_ls_ro['num_edges'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of edges')\n",
|
||||
"plt.xlabel('Number of edges')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 3)\n",
|
||||
"sns.histplot(df_metric_ls_ro['diameter'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of diameter')\n",
|
||||
"plt.xlabel('Diameter')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 4)\n",
|
||||
"sns.histplot(df_metric_ls_ro['average_degree'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of average degree')\n",
|
||||
"plt.xlabel('Average degree')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 5)\n",
|
||||
"sns.histplot(df_metric_ls_ro['density'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(1e1, upper_limit)\n",
|
||||
"plt.title('Distribution of density')\n",
|
||||
"plt.xlabel('Density')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 6)\n",
|
||||
"sns.histplot(df_metric_ls_ro['connectivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of connectivity')\n",
|
||||
"plt.xlabel('Connectivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 7)\n",
|
||||
"sns.histplot(df_metric_ls_ro['clustering'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of clustering')\n",
|
||||
"plt.xlabel('Clustering')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 8)\n",
|
||||
"sns.histplot(df_metric_ls_ro['degree_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of degree assortivity')\n",
|
||||
"plt.xlabel('Degree assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.subplot(3, 3, 9)\n",
|
||||
"sns.histplot(df_metric_ls_ro['sentiment_assortivity'], bins=20)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.ylim(0.9, upper_limit)\n",
|
||||
"plt.title('Distribution of sentiment assortivity')\n",
|
||||
"plt.xlabel('Sentiment assortivity')\n",
|
||||
"plt.ylabel('Count')\n",
|
||||
"plt.grid()\n",
|
||||
"plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
|
||||
"\n",
|
||||
"plt.suptitle(f'Metrics (nodes > 10, edges < 400) {casename} case', fontsize=16)\n",
|
||||
"plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
|
||||
"\n",
|
||||
"plt.savefig(f'../datasets/{case}-metrics-ls-ro.png')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"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": "3.14.6"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "8c75c0fdd1a718867cdcb84b32adcfdbeaad00b3a4e00a59385211aeed084d4c"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue