Fraud risk propagation in large scale network

What's the best approach to do some graph analytics and risk propagation in a network using python where multiple accounts are connected through a relationship and few of the accounts in the network are marked as bad accounts and the rest are unknown? I tried using networkx but it seems to run forever. I have about 8MM edges and 40K nodes
Category: Data Science

Visualization library for networks and dependencies

this is a more general question asking about Python libraries that are able to showcase networks with following criterias: Different size of the nodes depending on a metric (e.g. sum of some variable X received by all other nodes) Direction of the connection between the nodes (e.g. Node A sends X units to Node B, while Node B sends Y units to Node A and Q units to Node C) - So a node can receive and send at the …
Category: Data Science

Community detection for selected nodes

I'm new to graph theory and reached a point of doing community detection successfully.My next problem is to perform a community detection for specific nodes on the network (dividing set of nodes on the network into communities). To understand the needs, i do have a a network of all roads in a city. Also, I have 5 buses and need to deliver workers to 50 (lets say +/- 10) dynamic locations. Each morning, i need to assign workers to clients …
Category: Data Science

Node eigenvector centrality

I recently started using networkx and i have the folowing problem. I have a weighted graph: Each node have a weight and represent a person Nodes are interlinked with weighted edges I would like to assign a score for nodes, and in order to do so i would like to use the eigen vector centrality. However, eigen vector centrality take only into consederation weights of the edges and not the weights of nodes. Anyone know how to use eigenvector centrality …
Category: Data Science

How to create a graph network (Networkx) from the solution of Ordinary differential equations?

I have a list of Nodes. Suppose, N =["1","2","3","4"] # there can be different number of nodes And I have solved the differential equation which is a relation to anything(let us consider) using odeint From the solution of the differential equation, I have the relation between C and t result = odeint(model,C0,t) Now, assuming the edges are created from the solution of the differential equation between C and t. I want to create a graph network using Networkx. Is there …
Category: Data Science

Reduce size of a network graph for bipartite projection

I have a graph that I created from a pandas data frame. The length of the graph is ~450k edges. When I try to run the weighted_projected_graph function, it runs for a long time (I have not seen it finish), presumably because of the size of this data set. What is a good method for reducing the size of this data set before creating the bipartite graph? I have tried narrowing it down by using the most connected components: trim1 …
Category: Data Science

How to write a code on Link prediction on dynamic network in python?

I have read plenty of papers on link prediction on dynamic networks, but I am getting confusion on how to do it. I know link prediction on dynamic networks is different from static network.In dynamic network your given a series of snapshots of the graphs(G=(G1, G2....Gn)) and trying to predict link in time T+1 For example, I have a file with a bunch of edge lists (link here) each edge list is associated with the time in which the edge …
Category: Data Science

Create Nodes/Edges From CSV (latitude and longitude) for Graphs

The Ultimate Goal: I want to find the shortest and coolest (in terms of temperature) path between two points (for a given pair of latitudes and longitudes on the map)! I am aware of algorithms like Dijkstra or A*, which are apparently the ones are used in navigation systems. In fact I was able to successfully create a dummy graph using NetworkX in Python and find the shortest path easily: import matplotlib.pyplot as plt import networkx as nx %matplotlib inline …
Category: Data Science

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.