Uber Data Analysis With Python

I would like to present to you the findings of my recent exploration of the Uber dataset, which I have undertaken as part of this project. Throughout my analysis, I delved into several key aspects, including the highest month, date, and pick-up locations. The primary objective was to enhance my comprehension of the dataset and extract valuable insights that I can now share with you. By examining the Uber dataset, I aimed to provide you with a comprehensive understanding of its nuances. I believe that the knowledge gained from this analysis will prove valuable in your own exploration of the dataset. These techniques can also be applied to other datasets you may encounter, allowing you to enhance your understanding further. I warmly welcome any valuable comments and feedback you may have to help me improve my analysis. Your time and support are greatly appreciated. Thank you for considering my work.

Credit Card Fraud Detection

This research evaluates multiple advanced machine learning algorithms using the CCF Kaggle dataset to determine the most accurate prediction model for credit card fraud detection. The author analyzes eight algorithms, including logistic regression, decision trees, random forests, multi-layer perceptions, Naive Bayes, XGBoost, KNN, and SVM. To improve accuracy and efficacy, the author also implements PCA for dimensionality reduction. The findings indicate that XGBoost presents the highest accuracy when compared to other models, with emphasis on precision, recall, f1-score, and accuracy. Furthermore, Cross-validation using three algorithms (LG, DT, RF) indicates that RF performs better than the others. The performance of RF is significantly higher in cases of underdamping and oversampling.

Movie Correlation in Python

In this Data Analyst Portfolio Project, I will detect correlations between variables using Python. I collected a dataset of Hollowood films from 2002 to 2018 for this project, where I attempted to demonstrate various types of data interrelationships. I utilised Python Jupyter notebook and numerous different types of functions to complete my job. As a programmer with a programming background, I have watched numerous YouTube videos about Python in preparation for this assignment, which has made it easier for me to complete. I have utilised many types of PHP functions, and the scripts are provided in the links below. ThankYou

Python Project of World Cup Dataset

In this Python project, I have compiled a dataset of world cup matches from 1930 to 2018, demonstrating the countries that have played the most and won the most football matches and world cups. During the same interval, # This data will be used to determine the country that has participated in the most World Cup matches, the top 10 countries that have participated in the most World Cup matches, to create a bar chart for the top five countries, and to determine the countries with the highest number of goals and winning teams from 1930 to 2018. Throughout the duration of the project, I have learned numerous functions, and I continue to learn and enjoy the Python programming language.