Data science

The internship started with learning the basic concepts of statistics and probability, which are the backbone of data analysis. I learned how to interpret data using mean, median, mode, standard deviation, and correlation. These concepts helped me understand the distribution and relationships within data, which is crucial before applying any machine learning algorithms. Probability concepts further enabled me to model uncertainty and understand outcomes in classification problems and decision-making processes. Python I learned to write basic scripts, handle data structures like lists and dictionaries, and build logic using loops and conditions. Working in Jupyter Notebook allowed me to write and test my code while documenting it clearly. One of the most valuable skills I gained was working with NumPy and Pandas, two powerful Python libraries. NumPy helped me handle numerical data and perform fast mathematical computations using arrays. Pandas, on the other hand, allowed me to work with tabular data in the form of Data Frames. I learned to read datasets from CSV, Excel files, inspect the structure, clean missing values, rename columns, filter rows, and sort the data efficiently. Data visualization, which I explored using Matplotlib and Seaborn. These tools helped me turn raw numbers into meaningful visual stories. I created bar charts, line plots, histograms, pie charts, and scatter plots to understand patterns and distributions. With Seaborn, I was able to create aesthetically pleasing and informative charts like heatmaps, box plots, and pair plots.