network-graph-analysis

Network Graph Analysis

Overview

Graph and network analysis extracts structural information from relational data. Use this skill when your data describes connections between entities — citations, protein interactions, social ties, trade flows, co-occurrence matrices, or any adjacency structure. The key insight: if relationships carry information that tabular rows cannot, model the structure explicitly.

When to Use This Skill

Use this skill when:

• Your data is fundamentally relational (entities linked by edges)
• You need to identify influential nodes, bridging nodes, or tightly-knit communities
• You are building or evaluating a graph neural network (GNN)
• You need to visualize network structure for publication or exploration
• Your dataset is a co-occurrence matrix, adjacency matrix, or edge list

Do not reach for graph methods if rows in your tabular dataset are independent (no meaningful pairwise relationships). First run EDA (EDA skill) to understand data shape, then apply this skill.

---

Graph Construction from Data

From a NumPy/SciPy Adjacency Matrix

import numpy as np
import networkx as nx
import scipy.sparse as sp

# Dense adjacency matrix
A = np.array([[0, 1, 0],
              [1, 0, 1],
              [0, 1, 0]])

G = nx.from_numpy_array(A)                          # undirected
G_directed = nx.from_numpy_array(A, create_using=nx.DiGraph())  # directed

# SciPy sparse matrix (memory-efficient for large graphs)
A_sparse = sp.csr_matrix(A)
G_sparse = nx.from_scipy_sparse_array(A_sparse)

From an Edge List CSV

import pandas as pd

# CSV with columns: source, target (and optionally weight)
edges_df = pd.read_csv('edges.csv')

# Unweighted, undirected
G = nx.from_pandas_edgelist(edges_df, source='source', target='target')

# Weighted, directed
G_weighted = nx.from_pandas_edgelist(
    edges_df,
    source='source',
    target='target',
    edge_attr='weight',
    create_using=nx.DiGraph()
)

From Bipartite Data (e.g., users x items)