Downloads · 30 days
13
23% of all-time downloads
p2-spam-classification-keras-mlp32-bs16
neck392/p2-spam-classification-keras-mlp32-bs16
p2-spam-classification-keras-mlp32-bs16 is a machine learning model from neck392. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for keras. The card lists the license as mit.
Keras classification model with: - Dense(32, relu) - Dense(1, sigmoid)
All-time downloads
57
Public
Repo size
3.2 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.keras43.6 KB · 82%
At a glance
- Library
- keras
- License
- mit
- Access
- Public
- Created
- Apr 24, 2026
- Updated
- Apr 24, 2026
- SHA
- cb5dd5d2
Model card
From the Hugging Face model README
P2 Spam Classification
Model
Keras classification model with:
- Dense(32, relu)
- Dense(1, sigmoid)
Task
Predict whether an email is spam (1) or ham (0) from tabular features.
Input Features
This model uses 57 tabular features based on:
- word frequency
- character frequency
- capital letter patterns
Preprocessing
- clipping on:
- capital_run_length_average
- capital_run_length_longest
- capital_run_length_total
log1pon all input featuresStandardScaler
Threshold
- Selected threshold: 0.50
Validation Metrics
- Accuracy: 0.9587
- Precision: 0.9426
- Recall: 0.9530
- F1-score: 0.9478
Test Metrics
- Accuracy: 0.9425
- Precision: 0.9212
- Recall: 0.9339
- F1-score: 0.9275
Files
model.kerasscaler.joblibfeature_names.jsonpreprocess.jsonmetrics.json
Notes
This repository contains the trained model and preprocessing metadata.
- Library
- keras
- License
- mit
- Created
- Apr 24, 2026
- Updated
- Apr 24, 2026