alvarodemig / Algorithms-Performance-Comparison Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

Algorithms' (Logistic Regression, Random Forest, KNN, Naive Bayes, AdaBoost, LDA, Gradient Boosting and MultiLayer Perceptron) with and without PCA performance comparison (train and prediction time, area under ROC curve) in the Criteo's prediction CTR dataset

1 star 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
.gitignore		.gitignore
AlgPerformComparison.py		AlgPerformComparison.py
LICENSE		LICENSE
README.md		README.md
mlp_train.py		mlp_train.py

Repository files navigation

Algorithms Performance Comparison

Dataset: Criteo's CTR prediction challenge

Dataset with all the variables
Dataset with dimensionality reduction (PCA)

Algorithms:

Logistic Regression
Random Forest
KNearest Neighbors
Naive Bayes
AdaBoost
Linear Discriminant Analysis
Gradient Boosting
Neural Networks (MultiLayer Perceptron)

Parameter tuning: YES

Output:

ROC curves (png)
Summary performances information of each algorithm (csv)

Programming Language: Python

Main Libraries:

Pandas
Numpy
Sklearn
Keras
Matplotlib

About

Algorithms' (Logistic Regression, Random Forest, KNN, Naive Bayes, AdaBoost, LDA, Gradient Boosting and MultiLayer Perceptron) with and without PCA performance comparison (train and prediction time, area under ROC curve) in the Criteo's prediction CTR dataset

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%