- Developed strong communication skills as a food bank assistant by building rapport with co-workers, empathizing with employees, and resolving conflicts in a stressful environment

- Developed an object-oriented program that simulates poker hand drawings and identifies the many types of poker hands, from high cards to royal flushes
- Performed 50 simulations of 10000 trials each, tracking hand occurrences, skewness, and other statistics related to the label, allowing for ample training and testing data
- Utilized pandas to store simulated information in a data frame and later read CSV files, extracting the feature matrix necessary to form an accurate linear model
- Trained a linear regression model using scikit-learn with the appropriate attributes to strengthen prediction precision and produce strong performance metrics like MSE and MAE
- Predicts the empirical probability variance of poker hands with 94.4% accuracy
- Created scatter plots using Matplotlib to visualize the comparison between residuals, actual values, and predictions

- Scraped NCAA Men's Big 12 Conference player statistics from basketball reference using selenium and compiled all the information into a pandas data frame
- Implemented a one-hot encoder to re-create the class columns in binary, allowing for its use in the test data
- Trained multiple logistic regression models using scikit-learn to classify players based on features like assists and field goal percentage, ultimately predicting player position with 91.7% accuracy
- Produced classification reports and visualized confusion matrices using Matplotlib and Seaborn

- Filled null values for quantitative and categorical variables, using both mean and mode imputations
- Visualized the age distribution of passengers, along with the relationship between social class and survival rate using barplots in Seaborn
- Implemented the chi-squared test using SciPy, concluding with 95% confidence that the survival rate and passenger class are significantly related, as the calculated chi-squared statistic is far greater than the critical value, thus rejecting the null hypothesis

- Cleaned roller coaster data using pandas by dropping irrelevant columns, appropriately converting attribute datatypes, and handling duplicate rows or null values
- Observed the relationship between coaster height and speed using the pearson correlation method, determining the certainty in their association through the correlation coefficient and the p-value