US Electric Rate Prediction
This project aims to predict electric rates in the United States using various machine learning models. The dataset used for this analysis is sourced from "/content/sample_data/iouzipcodes2018.csv". The code implements data preprocessing, feature engineering, model training, and evaluation.
To run this code, you need the following dependencies:
Pandas Seaborn Matplotlib Scikit-learn
Clone the repository or download the code files.
Ensure all required libraries are installed using pip install -r requirements.txt.
Place the dataset file iouzipcodes2018.csv in the appropriate directory.
Execute the provided Python script US_ELECTRIC_RATE.ipynb in a Jupyter Notebook environment or any Python IDE supporting Jupyter notebooks.
Follow the instructions provided in the notebook for interaction.
Run the provided Python script US_ELECTRIC_RATE.ipynb.
Follow the instructions within the notebook for visualizing data, selecting variables, and training models.
The notebook allows for data visualization, preprocessing, feature selection, model training, and evaluation.
Once the best model is determined, it is serialized and saved as us.pkl.
Jupyter notebook containing the Python code for data analysis, model training, and evaluation. iouzipcodes2018.csv: Dataset containing electric rate information. requirements.txt: File listing the required Python libraries and their versions.
The trained model's performance metrics and the best-performing model are displayed within the notebook. Visualization of data and model predictions is provided.
A.Sushiiel