How harshachakravarthy/consumer-behavior-analysis-for-electric-vehicle-adoption works
This repository studies consumer behavior around Washington State EV adoption, with a stated goal of predicting the chosen EV type. Its interactive workflow is: a user uploads a CSV, inspects its structure, explores visualizations, and runs selectable regression, clustering, or classification analyses. The notebooks provide separate EDA, modeling, and final-analysis workspaces; the tree and README identify them, but sampled source does not establish their internal wiring. The supplied Excel dataset is distinct from the app’s CSV upload input.
Main entry points: app.py Data Inspection · Electric_Vehicle_Population_Data.xlsx EV Population Data · Consumer Behavior Analysis for Electric Vehicle Adoption EDA.ipynb EDA Notebook
Components 12
Project Data
- EV Population Data
Dataset/Electric_Vehicle_Population_Data.xlsx
Interactive App
- Streamlit App
streamlit.app/app.py - CSV Upload
streamlit.app/app.py - Data Inspection
streamlit.app/app.py - Exploratory Charts
streamlit.app/app.py - Regression Models
streamlit.app/app.py - K-Means Clustering
streamlit.app/app.py - RF Classification
streamlit.app/app.py
Analysis Notebooks
- EDA Notebook
ipynb files/Consumer Behavior Analysis for Electric Vehicle Adoption EDA.ipynb - Modeling Notebook
ipynb files/Consumer Behavior Analysis for Electric Vehicle Adoption Modelling.ipynb - Final Notebook
ipynb files/Consumer Behavior Analysis for Electric Vehicle Adoption Final.ipynb
Other components
- Analyst
Connections 9
- Analyst → Streamlit App: opens
- Streamlit App → CSV Upload: offers
- Analyst → CSV Upload: uploads CSV
- CSV Upload → Data Inspection: loads data
- Data Inspection → Exploratory Charts: explores data
- Data Inspection → Regression Models: selects data
- Data Inspection → K-Means Clustering: selects data
- Data Inspection → RF Classification: selects data
- EV Population Data → EDA Notebook