CS-GO Professionals
Scrape the Dataset of all CSGO Athletes from the hltv website, and perform Feature Engineering and Exploratory Data Analysis to create insights.
Created on 17th March 2023
•
CS-GO Professionals
Scrape the Dataset of all CSGO Athletes from the hltv website, and perform Feature Engineering and Exploratory Data Analysis to create insights.
The problem CS-GO Professionals solves
The dataset of CSGO Athletes, which is scraped and processed in this project, can be a valuable resource for anyone interested in the eSports industry or competitive gaming. By performing feature engineering and exploratory data analysis on the dataset, we can gain insights into the performance of individual athletes, teams, and the eSports ecosystem as a whole.
Some potential use cases for this dataset and analysis include:
Player evaluation: Teams can use the insights gained from the analysis to evaluate potential recruits, identify areas for improvement in existing players, and make strategic decisions about their rosters. Game strategy: By analyzing player and team performance data, game analysts and coaches can develop new strategies to gain an edge in gameplay. Sponsorship and marketing: With the rise of eSports as a mainstream industry, sponsors and advertisers can use the dataset and analysis to identify high-performing athletes and teams to partner with and promote their brands. Fan engagement: The analysis can provide valuable insights to game fans, allowing them to follow the performance of their favourite athletes and teams more closely and engage in more meaningful discussions and debates about the game.
Overall, the dataset and analysis created in this project can make existing tasks, such as player evaluation, game strategy development, and fan engagement, easier, more accurate, and more data-driven. By providing insights into the performance of individual players and teams, as well as trends and patterns in the eSports industry, the analysis can help stakeholders make informed decisions that lead to better outcomes.
In summary, the scraping and analysis of the CSGO Athletes dataset can provide valuable insights and benefits to a wide range of stakeholders in the eSports industry, including teams, players, sponsors, advertisers, fans, and industry regulators.
Challenges I ran into
During the project, I faced several difficulties that presented some significant challenges. To overcome these challenges, I used the following strategies:
Data preprocessing: To clean, format, and transform the data into an appropriate format for the ML algorithms, I spent a considerable amount of time researching and experimenting with different data preprocessing techniques. I also consulted with my mentors for their feedback and suggestions on how to best approach the task. Model selection: I conducted extensive research and experimentation with different machine learning and clustering algorithms to choose the most appropriate algorithm and model for a given task. I also consulted with my mentors for their feedback and suggestions on which models would be most suitable for the task. Lack of domain expertise: To overcome my lack of domain expertise in CS:GO, I read several articles and watched videos to learn more about the game, players, playing patterns, roles, etc. I also consulted with my mentors, who had more experience in the field, to get their feedback and insights. Data scraping from the website: To learn the basics of web scraping and successfully scrape data from the website, I researched different web scraping tools and techniques. I also consulted with my mentors for advice on which tools and techniques would be most effective. Defining player roles: I conducted extensive research and consulted with experts in the field to categorise players into different roles in the game. However, due to the loosely defined nature of player roles in CS:GO, I ultimately had to drop the issue and focus on other aspects of the analysis.
Overall, I overcame the challenges I faced during the project by using a combination of research, experimentation, and collaboration with my mentors to develop effective solutions. Through this process, I was able to complete the project and gain valuable experience successfully.
Technologies used