Driverless Machine Learning Web App
- 1. DRIVERLESS ML Automation of ML using Driverless API Sayantan Ghosh Kalinga Institute Of Industrial technology
- 2. What is Driverless API? Driverless API is a automation Software to process large amount of datasets(Preprocessing & Cleaning) in few seconds. It has the capability to apply Machine Learning Algorithms (Logistic Regerssion,KNN,Decision Tree,Naive Bayes,SVM) and ANN autonomously in the dataset without human interface and to visualize the accuracies of the algorithms,Features' Importance,F1 score,recall score. 2
- 3. Key Capabilities of Driverless API 1 2 It can produce interactive graphical visualization using advanced pygal library. It can preprocess the dataset very efficiently.( Ex-It can handle categorical Data as well as NaN or missing Values). It can do Feature Scaling very efficienty to increase accuracy and acceptbility. The API can process dataset analization in a very less amount of time. 3 4 It can be used for Binary as well as Multiclass Classification, Churn Modeling, Credit Card Fraud Detection, Marketing Analysis. It generates Dataset info as well as the features that are irelevant for the model prediction. Data Preprocessingt Visualization Time Efficient Feature Scaling 5 6 3
- 4. Data Collection Phase Feature Selection. Data Preprocessing Algorithm Implementation. Development Process of the Driverless API Input Dataset • The Flask API consists of a 5-Stage pipeline process from user Input to Output Phase. • It uses Flask framework to implement python scripts. • The API web Interface is developed using HTML5 & CSS3. • The 5 stages are- 5 Output Visualization Phase.Output 4
- 5. Methodology & Implementations WorkFlow Diagram of the API 5 Data Collection Stage .csv Split Amount Epoch Feature Selection & Dimensionality Reduction Compute the featurs' Importance and select the relevant features based on the features' importance. Data Preprocessing (Categorical,Missing Value Handling) Classification Algorithms All the ML Classifiers are implemented into the dataset through K-Fold Cross Validation and results are stored. Analyzation Report & Visualization of Predicted results using pygal All the Categorical datas are One Hot Encoded and Missing Values are handed using mean values. At the Input Phase the user will Provide the .csv file, Split amount of the dataset and the epoch Count and the optimizer Algorithms.
- 6. Keras 2 Flask 3 Scikit-Learn Keras is used for implementing the Artificial Neural Network. Flask is used for implementing the Web API. Scikit-lEarn is used for Implementing the overall Classification Algorithms and overall inn the preprocessing Phase. TECHNOLOGIES USED 6 Pygal is used for implementing the visualizations using Support Vector Graphics 1 4 Pygal Numpy is used for computing the numeracal Operations. 5 Numpy5 Pandas is used for Implementing all the DataFrame processing. 6 Pandas
- 7. Automation Of Classification Algorithms 7 For the Automation Process I have used 6 Classification Algorithms and each Algorithm is feed into the K-Fold Cross Validation into 10 Splits. Accuracy ,Recall,F1 Score Distribution of Classification Algorithms which can help to choose proper classifiers in less amount of Time. K-Fold Cross Validation (10 splits)
- 8. Result Analysis On Various Datasets Dataset : titanic_train.csv Target Column : Survived Split Amount: 0.3 Epoch Count: 100 8 79.01 80.36 73.63 80.26 62.86 82.27 0 10 20 30 40 50 60 70 80 90 Logistic Regression KNN Decision Tree Random Forest Naive Bayes SVM Logistic Regression KNN Decision Tree Random Forest Naive Bayes SVM 79.01 80.36 73.63 80.26 62.86 82.27 0 10 20 30 40 50 60 70 80 90 Logistic Regression KNN Decision Tree Random Forest Naive Bayes SVM Accuracies of Classifiers on titanic datset. Logistic Regression KNN Decision Tree Random Forest Naive Bayes SVM Dataset : brain_tumour_classification.csv Target Column : diagnosis Split Amount: 0.3 Epoch Count: 100
- 9. Auto-Visualization of Feature Importance and Data details The API is proved to analyze and visualize the feature- Importances much more efficiently. It is the Feature Importance Report of the titanic Datset. 9 Dataset Info Table Feature ColumnsImportances
- 10. Future Applications of the API 10 Financial Analysis and Bank Churn Model Business Modeling Health Care Applications Weather Prediction
- 11. Further Improvements 11 01 02 03 04 Integrating CNN and OpenCV so that it can perform Image Classification. Image Processing and Disease Recognition Natural Language Processing.Text Data Classification,Spam filter Detection Audio Generation & Processing
- 12. CONCLUSION Machine learning has become one of the main engines of the current era. The production pipeline of a machine learning models passe through different phases and stages that require wide knowledge of several available tools, and algorithms. However, as the scale of data produced daily is increasing continuously at an exponential scale, it has become essential to automate this process. In this project, I have covered comprehensively the state-of-the-art research effort in the domain of Driverless ML frameworks. 12
- 14. THANK YOU! Sayantan Ghosh Kalinga Institute Of Industrial Technology Email [email protected]