How sifat192/social-network-ads-ml works
This repository is a notebook-based classification project that predicts ad purchases from demographic data. Its documented workflow runs from loading the Social Network Ads dataset through preparation and exploration to logistic-regression training and evaluation. The README identifies accuracy, confusion matrix, and F1 score as evaluation measures. The notebook is not included in the excerpts, so the graph represents documented stages and does not assert implementation details beyond them.
Main entry points: Social_Network_Ads_model.ipynb Logistic regression · Social_Network_Ads.csv Ads dataset
Components 9
Data preparation
- Ads dataset
Social_Network_Ads.csv - Data loading
Social_Network_Ads_model.ipynb - Data cleaning
Social_Network_Ads_model.ipynb - Exploratory analysis
Social_Network_Ads_model.ipynb - Feature engineering
Social_Network_Ads_model.ipynb
Modeling
- Train-test split
Social_Network_Ads_model.ipynb - Logistic regression
Social_Network_Ads_model.ipynb
Evaluation
- Model evaluation
Social_Network_Ads_model.ipynb - Purchase prediction
Social_Network_Ads_model.ipynb
Connections 8
- Data loading → Ads dataset: reads
README.md - Data loading → Data cleaning: passes data
README.md - Data cleaning → Exploratory analysis: precedes
README.md - Exploratory analysis → Feature engineering: precedes
README.md - Feature engineering → Train-test split: precedes
README.md - Train-test split → Logistic regression: precedes
README.md - Logistic regression → Model evaluation: evaluated by
README.md - Logistic regression → Purchase prediction: predicts
README.md