Ranja's Projects
Datasets to build classification and regression models optimized via random search and grid search algorithms.
An exploration of retail data for price-volume relationship, also called the demand curve.
PDF files can be read using various python library packages viz., tabula, pdfplumber etc. Here I've defined a class to parse files from a directory and save/store their information using pdfplumber in an output file.
PDF files can be parsed for their images using various python packages. Here I've defined a method to read the file, save/store the extracted images in a dir/folder using fitz (PyMuPDF module), and pillow (PIL - Python Imaging Library) used to view extracted images.
Feature engineering package with sklearn like functionality
Logistic regression for classification using pyspark
PCA for anomaly detection
A network of flight routes, your social network, knowledge graphs from text visualized with the networkx library are different graph (directed, weighted etc.) types. There're biomolecular systems (proteins) as networks which can be visualised with VMD (visual molecular dynamics).
Physics informed neural network
Config files for my GitHub profile.
How much training data is required to build a ML model?
Basic Statistics for Data Sciences
Explore the components of timeseries (univariate and multivariate) data using statsmodels library, build baseline models and compare with advanced forecasting models.