Social Network Analysis(SNA) and Graph Analysis using Python

Explore the history of graph theory through the classic seven bridges puzzle set in an 18th-century city, highlighting crossing each bridge exactly once and the 1735 solution.

Define graphs and explore how nodes and connections form networks, illustrated by airport and political network examples, highlighting how graph analysis reveals connectivity and patterns.

Load and clean data for graph foundations, convert numeric and categorical columns, perform descriptive analysis, and set up reproducible workflows using python tools for SNA and graph analysis.

Explore undirectional graphs by building and visualizing nodes and edges, measuring connectivity, density, and degree, and interpreting line thickness and color to reveal relationships.

Explore the small world concept of six degrees of separation through a chain of friends. See how modern networks like Facebook and LinkedIn reduce degrees to two to four.

Analyze the small world phenomenon by examining six degrees of separation, clustering, and average shortest paths in networks and random graphs, using sigma to assess small-world behavior with Python.

Discover how diameter, transitivity, subtree structures, and eccentricity reveal network connectivity; identify influential nodes with closeness centrality and explore distance-based measures across sample graphs.

Examine betweenness centrality, communities, and cliques, and see how adjacency matrices illustrate which individuals connect groups and enable cross-group communication.

Learn how directional graphs model asymmetric relations in social networks, when edge direction matters, and how multiple interactions imply connectivity, sometimes converted to undirected for analysis.

Explore how to collect, prepare, and analyze social network data with graphs built from source and target nodes, including data conversion and practical crawling workflows in Python.

Explore preprocessing of airline data for graph analysis: download, clean, and select key columns, handle missing values, drop duplicates, and prepare a scalable dataset for social network analysis in Python.

Learn to analyze social networks with Python by exploring density and transitivity, evaluating layouts, and calculating diameter and shortest paths to reveal network connectivity.

Analyze social networks and graph structures using Python, focusing on degree, subtree, eccentricity, closeness, eigenvector and betweenness centrality, and community connectivity.

Engage with practical questions and answers in social network analysis and graph analysis using Python, featuring hands-on practice, discussion forums, and guided problem solving.

Analyze fraudulent network data by preparing and transforming graphs, applying distance and degree metrics, and using unsupervised machine learning to detect fraud patterns.

Explore transitivity, closeness, eigenvector, betweenness, communities, and directional aspects in social networks using Python, analyzing density and distances to reveal key structures.

Explore k-means clustering to group data points by similarity using features and distances, determine optimal cluster numbers with the elbow method, and apply these ideas in Python for SNA.

Explore advanced statistics to compute a fraud score, using descriptive analysis, correlations, and unsupervised analysis, with emphasis on validating scores through graphs and data insights.

Apply supervised analytics to fraud detection with a random forest model on production data, selecting essential independent features and generating predictive scores and descriptive insights from graphs.

Explore Enron e-mail analysis by detailing data loading from Kaggle, handling large 1.3 GB CSV files, and cleaning messages for scalable analysis.

Learn to clean and prepare email data for a unidirectional graph by grouping records, creating a new column, and filtering for clear social network analysis and graph analysis.

Explore density, transitivity, and layouts in social network graphs using Python and nx visualization, with hands-on guidance on graph analysis and interpreting network structures.

Analyze how to navigate social networks using degree, closeness, betweenness, and eigenvector centrality. Detect communities and identify influential nodes with Python.

Practice line-by-line exploration of social network analysis and graph analysis in Python, focusing on visualisations, clustering activity, basic statistics, and building a model to predict new connections.

Explore PageRank, Google's link-analysis algorithm, and its relation to hyperlink-induced topic search (HITS), including hub and authority concepts and the role of citations and links in ranking.

Learn to implement PageRank in Python for social network graphs, performing link analysis and graph-based ranking to evaluate node importance.

Explore node embeddings prerequisites for social network analysis and graph analysis using Python, establishing foundational building blocks and descriptive definitions to prepare for advanced techniques.

Explore word embedding fundamentals, with high-dimensional word vectors (around 300 dimensions), capturing global semantics and word similarity for document classification and clustering in Python.

Learn node embedding for graphs using random walk based methods like deep walk to capture context and generate vector representations of network structure.

Explore node embedding using deep walk to capture structural similarity in graphs. Learn how random walks generate representations useful for social network analysis with Python.

Explore node embedding with Node2Vec to capture network similarity through biased random walks and window-based context, applying Python-based social network analysis and graph techniques.

Explore how to apply social network analysis and graph analysis in Python to uncover network relationships, predict interactions, and derive graph-based features within a CRISP-DM data science workflow.