A cloud-native behavioral analytics project exploring introvert vs. extrovert patterns using Google BigQuery, Databricks, and Google Cloud Platform.
IntroExtroScope analyzes patterns of introversion and extroversion through a structured data science pipeline:
- 🔍 Exploratory Data Analysis (EDA)
- 🔮 Predictive Modeling
- 📈 Data Visualization
The entire pipeline is deployed using BigQuery SQL for analytics, Databricks for processing, and GCP for scalability.
- Understand behavioral trends in personality types.
- Build models to predict introversion/extroversion from features.
- Create visualizations to support data storytelling.
Component | Tool/Service |
---|---|
Data Storage | Google Cloud Storage |
Data Processing | Databricks + Big Query |
Visualization | Databricks + Looker Studio |
Train AUC | Validation AUC | Test AUC |
---|---|---|
0.911 | 0.870 | 0.92 |
# Clone repo
git clone https://github.com/yourusername/introextroscope.git
cd introextroscope
- Download the following
dependencies
Software |
Version |
---|---|
Python |
3.13.2 |
pip |
25.0 |
- Download the
python
dependecies required to run thenotebook
locally
python -m pip install -r requirements.txt
- Run the
jupyter lab
notebook
cd ./notebooks
jupyter lab