CSUMB Learning Journal 2025

This week in class I spent a lot of time working with NumPy, Pandas, and data visualization in Python. Early in the week I focused on NumPy arrays, indexing, boolean masks, and vectorized operations. I also practiced using list comprehensions and learned more about the differences between Python lists and NumPy arrays. One thing I noticed is that NumPy operations become much cleaner and more efficient once you stop thinking in terms of loops and start thinking in terms of whole-array operations. Later in the week we moved into Pandas Series and DataFrames. I learned how to select columns, filter rows with boolean conditions, group data, compute statistics, and rename columns. I also became more comfortable reading dataframe summaries with functions like info() and describe(). At first I mixed up when operations returned a Series versus a DataFrame, but after working through the labs I feel much more confident about it. The visualization part of the labs was especially interesting. We c...

  This week focused heavily on using Pandas and NumPy for data analysis and aggregation. I practiced working with Pandas Series and DataFrames, including creating columns, renaming columns, filtering rows with boolean masks, and using .loc and .iloc for indexing. I also worked with aggregation functions such as mean(), median(), value_counts(), and groupby() to analyze datasets like heart disease data, census data, penguin body mass data, and Lyft bike-sharing data. One important idea I learned is that Pandas automatically aligns data using indexes, which can be very powerful but also confusing when values are missing or indexes do not match. A concept I am still working on fully understanding is when to use groupby() versus value_counts(). I understand that value_counts() is useful for counting categories quickly, while groupby() is more flexible for computing statistics, but sometimes the two approaches seem similar. Another topic that took practice was combining boolean masks wi...

This was the first week of CST383 and we focused on building a strong foundation in Python for data science, especially working with NumPy and basic scripting tools. I practiced creating and manipulating arrays, including slicing, fancy indexing, and boolean masking. I also learned how vectorized operations allow computations to be performed efficiently across entire arrays without using loops. Working with both 1D and 2D arrays helped me better understand how to access specific rows and columns, as well as how to compute statistics like mean and median along different axes. In addition, I explored filtering data using conditions and using those filters to extract subsets of interest. One concept that I found a bit confusing at first was how boolean masks need to match the shape of the array they are indexing. For example, trying to index an array with a mask of a different length results in an error, which made me realize how important array dimensions are in NumPy. This made me ask: ...

     One thing that went well during our service-learning project was our ability to build meaningful full-stack functionality that contributed to a real application rather than just completing isolated assignments. As a team, we developed useful features such as availability scheduling, time entry reporting, and backend APIs to support booking functionality. Collaboration improved over time as we became more comfortable using Git, resolving merge conflicts, and coordinating contributions through pull requests. A major success was moving portions of the project away from hardcoded or mock data toward real frontend-backend integration. We also made significant progress through debugging, identifying issues involving authentication, CORS, and data persistence that led to real improvements in the application.      One area I would improve is communication and coordination earlier in the development process. There were times when better communication about bran...

 This week in CST370 introduced several advanced algorithm techniques for optimization and graph problems. We began with non-comparison sorting , such as counting sort or radix sort, which sort data without directly comparing elements. These algorithms can achieve linear time under certain conditions, making them faster than traditional comparison-based sorts. We then studied dynamic programming , a method that solves complex problems by breaking them into overlapping subproblems and storing solutions to avoid repeated work. This approach is powerful for optimization problems like shortest paths or resource allocation. Next, we covered Warshall’s algorithm , which computes the transitive closure of a graph. It determines which vertices are reachable from others, helping analyze connectivity. Related to this, Floyd’s algorithm finds the shortest paths between all pairs of vertices in a weighted graph, improving efficiency compared to running single-source algorithms repeatedly. ...

 This week in CST370, we focused on advanced data structures designed to improve efficiency. We started with AVL Trees , which are self-balancing binary search trees. I learned how rotations help maintain balance after insertions and deletions, ensuring operations like search, insert, and delete stay at  O ( log ⁡ n ) O(\log n) O ( log n ) . Next, we studied 2-3 Trees , another balanced search tree structure. Unlike binary trees, nodes can store one or two keys, which helps keep the tree perfectly balanced. This guarantees efficient operations and deepened my understanding of how balancing improves performance. We then covered Heaps and Heapsort . A heap is a complete binary tree that satisfies the heap property (max-heap or min-heap). I learned how heaps are useful for priority queues and how Heapsort uses the heap structure to sort elements in O ( n log ⁡ n ) O(n \log n) O ( n log n ) time without needing extra space like merge sort. Finally, we explored Hashing , which ...