Ankit Singh

Ankit Singh

Data Scientist & Astrophysicist

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Exploring UK Road Accidents: What 104K Collisions Tell You Before You Model

Published:

Before building any model, you need to understand the data well enough to make defensible modeling decisions. This post walks through how I approached exploratory data analysis on the UK Department for Transport’s 2023 road accident dataset — 104,258 collisions and 189,815 vehicle records. The EDA directly shaped the dual-model strategy I describe in my class imbalance post.

Tackling Extreme Class Imbalance: UK Road Accident Severity with LightGBM

Published:

When 76% of your labels belong to a single class and the rarest class sits at 1.4%, standard classifiers will happily predict the majority class every time and report impressive accuracy. This post walks through what I learned building a severity classifier on 104,258 UK road collisions from the Department for Transport’s 2023 STATS19 data, and why the numbers that looked great at first turned out to be completely wrong.

LatexForLLM: Turning LaTeX Papers into Graphs for Smarter LLM Retrieval

Published:

If you have ever pasted an entire research paper into ChatGPT or Claude and watched your token budget evaporate, you know the problem. A typical 10-page paper burns 8,000-12,000 tokens, yet the model only needs a few hundred to answer most questions about it. I built LatexForLLM to fix this. It parses LaTeX documents into a typed graph and retrieves only the sections, equations, and figures that matter. On benchmark tasks against a realistic 200-line paper, graph-based retrieval cuts word count by ~54% on average (up to ~80% for focused queries) compared to pasting the full document.

Leveraging Pandas to Interact with SQL

Published:

Most data work involves going back and forth between SQL databases and Python. You write a query to pull what you need, load it into a DataFrame, do your analysis, maybe write results back. Pandas has built-in support for this workflow, and once you set it up, you rarely need to leave Python to interact with your database.

Stock analysis

Published:

In this notebook we will carry the trend analysis of technology stocks.

Time series analysis

Published:

We will discuss the time series analysis using finance data. The techniques like Moving Average (MA) , Autoregressive (AR) and Autoregressive Integrated Moving Average Model (ARIMA) will be dicussed. For modelling the time series we will be using the statsmodel library for the data acquired using Yahoo finance api.

Portfolio Analysis

Published:

We create a portfolio of stocks from American markets, analyze their performance and try to acess the risk in future.

organization

outreach

publications

Ultraviolet and optical view of galaxies in the Coma supercluster

Published in Monthly Notices of the Royal Astronomical Society, 2018

This paper presents an ultraviolet and optical view of galaxies in the Coma supercluster.

Recommended citation: Mahajan, S., Singh, A., & Shobhana, D. (2018). "Ultraviolet and optical view of galaxies in the Coma supercluster." Monthly Notices of the Royal Astronomical Society, 478(4), 4336-4347. [DOI](https://doi.org/10.1093/mnras/sty1370) https://doi.org/10.1093/mnras/sty1370

Caught in the web: A tale of filament galaxies

Published in Proceedings of the International Astronomical Union, 2019

This paper presents a tale of filament galaxies.

Recommended citation: Singh, A., Mahajan, S., & Shobhana, D. (2019). "Caught in the web: A tale of filament galaxies." Proceedings of the International Astronomical Union, 15(S341), 304-306. [DOI](https://doi.org/10.1017/S1743921319001406) https://doi.org/10.1017/S1743921319001406

Ram pressure stripping: an analytical approach

Published in Monthly Notices of the Royal Astronomical Society, 2019

This paper presents an analytical approach to ram pressure stripping.

Recommended citation: Singh, A., Gulati, M., & Bagla, J. S. (2019). "Ram pressure stripping: an analytical approach." Monthly Notices of the Royal Astronomical Society, 489(4), 5582-5593. [DOI](https://doi.org/10.1093/mnras/stz2523) https://doi.org/10.1093/mnras/stz2523

Study of galaxies on large-scale filaments in simulations

Published in Monthly Notices of the Royal Astronomical Society, 2020

This paper presents a study of galaxies on large-scale filaments in simulations.

Recommended citation: Singh, A., Mahajan, S., & Bagla, J. S. (2020). "Study of galaxies on large-scale filaments in simulations." Monthly Notices of the Royal Astronomical Society, 497(2), 2265-2275. [DOI](https://doi.org/10.1093/mnras/staa1913) https://doi.org/10.1093/mnras/staa1913

On the Effects of Local Environment on Active Galactic Nucleus (AGN) in the Horizon Run 5 Simulation

Published in The Astrophysical Journal, 2023

This paper explores the effects of local environment on Active Galactic Nuclei (AGN) in the Horizon Run 5 Simulation.

Recommended citation: Singh, A., Park, C., Choi, E., Kim, J., Jun, H., Gibson, B. K., Kim, Y., Lee, J., & Snaith, O. (2023). "On the Effects of Local Environment on Active Galactic Nucleus (AGN) in the Horizon Run 5 Simulation." The Astrophysical Journal, 953(1), 64. [DOI](https://doi.org/10.3847/1538-4357/acdd6b) https://doi.org/10.3847/1538-4357/acdd6b

Spatial Distribution of Intracluster Light versus Dark Matter in Horizon Run 5

Published in ApJ, 965, 145, 2024

This paper investigates the spatial distribution of intracluster light versus dark matter in Horizon Run 5.

Recommended citation: Yoo J., Park C., Sabiu C. G., Singh A., Ko J., Lee J., Pichon C., Jee M. J., Gibson B. K., Kim J., Shin J., Kim Y., Kim H., 2024, "Spatial Distribution of Intracluster Light versus Dark Matter in Horizon Run 5", ApJ, 965, 145. https://doi.org/10.48550/arXiv.2402.17958

The Environmental Dependence of the Stellar Mass - Gas Metallicity Relation in Horizon Run 5

Published in MNRAS, 531, 3858-3875, 2024

This paper investigates the dependence of the Stellar Mass - Gas Metallicity Relation using HR5.

Recommended citation: Rowntree A. R., Singh A., Vincenzo F., Gibson B. K., Gouin C., Galarraga-Espinosa D., Lee J., Kim J., Laigle C., Park C., Pichon C., Few G., Hong S. E., Kim Y., 2024, "The Environmental Dependence of the Stellar Mass - Gas Metallicity Relation in Horizon Run 5", MNRAS, 531, 3858-3875. https://arxiv.org/abs/2404.10055

Impact of different physical processes in cosmic web on the scatter in mass-metallicity relation

Published in submitted to MNRAS, 2026

Investigates the impact of different physical processes in the cosmic web on the scatter in the mass-metallicity relation.

Recommended citation: Rowntree A. R., Singh A., Vincenzo F., et al., 2026, "Impact of different physical processes in cosmic web on the scatter in mass-metallicity relation", submitted to MNRAS, arXiv:2603.03951. https://arxiv.org/abs/2603.03951

The Role of Large-Scale Environment in Shaping the Stellar Mass-Gas Metallicity Relation Across Time

Published in MNRAS, 546, stag199, 2026

Explores how the large-scale environment shapes the stellar mass-gas metallicity relation across cosmic time.

Recommended citation: Rowntree A. R., Vincenzo F., Singh A., Park C., Lee J., Pichon C., Dubois Y., Few G., Gibson B., Snaith O., Kim Y., 2026, "The Role of Large-Scale Environment in Shaping the Stellar Mass-Gas Metallicity Relation Across Time", MNRAS, 546, stag199.

talks

teaching