Merge pull request #479 from YashSachan2/yash2

Bearing Classification
abhisheks008 · Jan 3, 2024 · 03bcc72 · 03bcc72
2 parents ae05aa9 + 141fa40
commit 03bcc72
Show file tree

Hide file tree

Showing 9 changed files with 3,719 additions and 0 deletions.
diff --git a/Bearing Classification/Dataset/Faulty-bearing.csv b/Bearing Classification/Dataset/Faulty-bearing.csv
diff --git a/Bearing Classification/Dataset/Healthy-bearing.csv b/Bearing Classification/Dataset/Healthy-bearing.csv
diff --git a/Bearing Classification/Images/EDA1.png b/Bearing Classification/Images/EDA1.png
diff --git a/Bearing Classification/Images/EDA2.png b/Bearing Classification/Images/EDA2.png
diff --git a/Bearing Classification/Images/EDA3.png b/Bearing Classification/Images/EDA3.png
diff --git a/Bearing Classification/Images/Input_Dataset.png b/Bearing Classification/Images/Input_Dataset.png
diff --git a/Bearing Classification/Images/Metrics.png b/Bearing Classification/Images/Metrics.png
diff --git a/Bearing Classification/Model/bearing_classification.ipynb b/Bearing Classification/Model/bearing_classification.ipynb
diff --git a/Bearing Classification/README.md b/Bearing Classification/README.md
@@ -0,0 +1,70 @@
+# Bearing Classification using ML 
+
+## PROJECT TITLE
+
+Bearing Classification
+
+## GOAL
+
+To identify faulty and healthy bearing. 
+
+## DATASET
+
+The link for the dataset used in this project:  https://www.kaggle.com/datasets/zlemglsmklkaya/healthy-vs-faulty-bearings/data?select=Healthy-bearing.csv
+
+## EDA:
+![Alt text](Images/Input_Dataset.png)
+![Alt text](Images/EDA1.png)
+Shape: (1998,2)
+
+## DESCRIPTION
+
+This project aims to identify the faulty and helthy bearings.
+
+## WHAT I HAD DONE
+
+1. Data collection: From the link of the dataset given above. 
+2. Data preprocessing: Preprocessed the data to create valid features.
+3. Model selection: XGBC,Random Forest,Logestic Regression,Gaussian Bayes,AdaBoost Classifier.
+4. Comparative analysis: Compared the accuracy score of all the models.
+
+
+## MODELS SUMMARY
+
+- XGBC
+- Logistic Regression
+- Adaboost Classifier
+- Random Forest Classifier
+- Gaussian Bayes
+
+## LIBRARIES NEEDED
+
+The following libraries are required to run this project:
+
+- matplotlib
+- numpy
+- pandas
+- sklearn
+
+## EVALUATION METRICS
+
+The evaluation metrics I used to assess the models:
+
+- Accuracy 
+
+It is shown using Confusion Matrix in the Images folder
+
+## RESULTS
+Results on Val dataset:
+XGBC: 77.33%
+Random Forest: 77.67%
+Adaboost: 75%
+Logistic Regression: 74%
+Gaussian Bayes: 73.33%
+DTC:77.33%
+![Alt text](Images/Metrics.png)
+
+## CONCLUSION
+Based on results we can draw following conclusions:
+
+1.The Random Forest worked the best