Upload folder using huggingface_hub
Browse files- README.md +25 -0
- best_model.joblib +3 -0
- best_model_metrics.json +9 -0
- best_model_params.json +4 -0
- experiment_tracking_log.csv +5 -0
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# Predictive Maintenance Model
|
| 3 |
+
|
| 4 |
+
## Overview
|
| 5 |
+
This repository contains the best-performing machine learning model for the predictive maintenance project.
|
| 6 |
+
|
| 7 |
+
## Problem Statement
|
| 8 |
+
The objective of the model is to classify whether an engine is operating normally or may require maintenance based on sensor readings.
|
| 9 |
+
|
| 10 |
+
## Input Features
|
| 11 |
+
- Engine_RPM
|
| 12 |
+
- Lub_Oil_Pressure
|
| 13 |
+
- Fuel_Pressure
|
| 14 |
+
- Coolant_Pressure
|
| 15 |
+
- Lub_Oil_Temperature
|
| 16 |
+
- Coolant_Temperature
|
| 17 |
+
|
| 18 |
+
## Selected Model
|
| 19 |
+
AdaBoost
|
| 20 |
+
|
| 21 |
+
## Evaluation Summary
|
| 22 |
+
{'Model': 'AdaBoost', 'Best_Parameters': "{'learning_rate': 0.05, 'n_estimators': 100}", 'CV_Best_F1': 0.7752, 'Test_Accuracy': 0.6304, 'Test_Precision': 0.6304, 'Test_Recall': 1.0, 'Test_F1': 0.7733}
|
| 23 |
+
|
| 24 |
+
## Notes
|
| 25 |
+
This model was selected after comparing multiple tree-based classification algorithms using cross-validation and test-set evaluation.
|
best_model.joblib
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c93788dcb2a026a9b78690d25140233dc908baae3a2c21232dad97051b09c55
|
| 3 |
+
size 65796
|
best_model_metrics.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Model": "AdaBoost",
|
| 3 |
+
"Best_Parameters": "{'learning_rate': 0.05, 'n_estimators': 100}",
|
| 4 |
+
"CV_Best_F1": 0.7752,
|
| 5 |
+
"Test_Accuracy": 0.6304,
|
| 6 |
+
"Test_Precision": 0.6304,
|
| 7 |
+
"Test_Recall": 1.0,
|
| 8 |
+
"Test_F1": 0.7733
|
| 9 |
+
}
|
best_model_params.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Model": "AdaBoost",
|
| 3 |
+
"Best_Parameters": "{'learning_rate': 0.05, 'n_estimators': 100}"
|
| 4 |
+
}
|
experiment_tracking_log.csv
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Model,Best_Parameters,CV_Best_F1,Test_Accuracy,Test_Precision,Test_Recall,Test_F1
|
| 2 |
+
AdaBoost,"{'learning_rate': 0.05, 'n_estimators': 100}",0.7752,0.6304,0.6304,1.0,0.7733
|
| 3 |
+
Gradient Boosting,"{'learning_rate': 0.05, 'max_depth': 2, 'n_estimators': 100, 'subsample': 0.8}",0.7684,0.6642,0.6857,0.8628,0.7641
|
| 4 |
+
Random Forest,"{'max_depth': 10, 'min_samples_leaf': 4, 'min_samples_split': 10, 'n_estimators': 100}",0.7625,0.665,0.6904,0.8494,0.7617
|
| 5 |
+
Decision Tree,"{'criterion': 'gini', 'max_depth': 5, 'min_samples_leaf': 1, 'min_samples_split': 2}",0.7603,0.6598,0.6895,0.8376,0.7564
|