Analysis Projects
🔥 Check out ⇒ My Kaggle page ⇐ for more!
- Capstone project for Python Data Products for Predictive Analytics Specialization
- Focused on Data Processing, Classification, Regression, and Recommender Systems
- Extracted basic statistics
- Computed Model accuracy and Balanced Error Rate
- Applied word processing methods such as stemming on User Reviews
- Computed baseline MSE value and optimizing this value
- Simple recommender system based on item similarities
- Utilized Jaccard Similarity Measure
- Focused on data exploration
- Performed univariate and bivariate analysis
- Applied missing value treatment and outlier treatment
- Focused on model evaluation, Logistic Regression Model in particular
- Splits training dataset at 60/20/20 ratio
- Validates and fine-tune the model to avoid overfitting
- Performed appropriate model diagnotics
- Practice project on making sales prediction using Linear Regression model
- Explore different ways to visualize one of the COVID-19 dataset
- R packages used in this report includes Tidyverse, scales, reactable, htmltools, gganimate, ggthemes, and coronavirus
- the coronavirus dataset used in this project is current as of July 12, 2020
- A small project for Python course Basic Data Processing and Visualization
- Utilized Jupyter Notebook and basic Python libraries such as Pandas and Matplotlib for importing and visualizaing the Goodreads-book dataset