How aadip-thapaliya/advance_time_series works
Project type and purpose
• This is a data-science/time-series forecasting project implemented as a single Jupyter notebook (“lstm_arima_prophet.ipynb”) with a short README (# Advance_Time_Series).
• The purpose is to demonstrate and compare three forecasting approaches—LSTM, ARIMA, and Prophet—on one or more time-series datasets.
File structure
• Top level:
• README.md (project title and potentially usage notes)
• lstm_arima_prophet.ipynb (all code, data ingestion, model training, evaluation, and visualization live in one notebook)
• No subdirectories or separate modules/services—everything is monolithic in a notebook.
• No deployment or configuration files—this is exploratory/analytical work, not a service.
README for additional insights
• The notebook likely contains comments, import statements (Pandas, NumPy, statsmodels, fbprophet, TensorFlow/Keras, Matplotlib/Seaborn), and step-by-step forecasting code.