Book Image

Python Data Analysis - Third Edition

By : Avinash Navlani, Ivan Idris
5 (1)
Book Image

Python Data Analysis - Third Edition

5 (1)
By: Avinash Navlani, Ivan Idris

Overview of this book

Data analysis enables you to generate value from small and big data by discovering new patterns and trends, and Python is one of the most popular tools for analyzing a wide variety of data. With this book, you’ll get up and running using Python for data analysis by exploring the different phases and methodologies used in data analysis and learning how to use modern libraries from the Python ecosystem to create efficient data pipelines. Starting with the essential statistical and data analysis fundamentals using Python, you’ll perform complex data analysis and modeling, data manipulation, data cleaning, and data visualization using easy-to-follow examples. You’ll then understand how to conduct time series analysis and signal processing using ARMA models. As you advance, you’ll get to grips with smart processing and data analytics using machine learning algorithms such as regression, classification, Principal Component Analysis (PCA), and clustering. In the concluding chapters, you’ll work on real-world examples to analyze textual and image data using natural language processing (NLP) and image analytics techniques, respectively. Finally, the book will demonstrate parallel computing using Dask. By the end of this data analysis book, you’ll be equipped with the skills you need to prepare data for analysis and create meaningful data visualizations for forecasting values from data.
Table of Contents (20 chapters)
1
Section 1: Foundation for Data Analysis
6
Section 2: Exploratory Data Analysis and Data Cleaning
11
Section 3: Deep Dive into Machine Learning
15
Section 4: NLP, Image Analytics, and Parallel Computing

DBSCAN clustering

Partitioning clustering methods, such as k-means, and hierarchical clustering methods, such as agglomerative clustering, are good for discovering spherical or convex clusters. These algorithms are more sensitive to noise or outliers and work for well-separated clusters:

Intuitively, we can say that a density-based clustering approach is most similar t how we as humans might instinctively group items. In all the preceding figures, we can quickly see the number of different groups or clusters due to the density of the items.

Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is based on the idea of groups and noise. The main idea behind it is that each data item of a group or cluster has a minimum number of data items in a given radius.

The main goal of DBSCAN is to discover the dense region that can be computed using minimum number of objects (minPoints) and given radius (eps). DBSCAN has the capability to generate random shapes of clusters and deal...