machine-learning-with-air-pressure-failure-data-of-scania-trucks's Introduction

Machine-Learning-Prediction-Model-Designing

Case: Machine Learning with Air Pressure Failure data of Scania trucks

Summary:

AdaptiveAlgo Systems Inc. has invited us to help them in implementing data science solutions. Our team is aiming to deleiver high performance solutions in a timely manner. AdaptiveAlgo has provided a dataset related to Air pressure system failure and operational data in Scania trucks.Our goal is to develop prediction models and to select accuarte model with minimum Total cost.

Introduction:

This part of case study consists of various elements of Machine learning. Following are the contents of this part of case study.

Part	Description
Part 1: Exploratory Data Analysis	Conduct EDA using Python libraries (plotly, seaborn, matplotlib etc.)
Part 2: Feature Engineering	Conduct thorough feature analysis and use pre-processing techniques to make the data usable.
Part 3: Prediction Algorithms	Try Logistic Regression, Random Forest, Support Vector Machine and XGBoost to build prediction models in using sklearn in Python. Compute AUC_ROC_Score for Training and Testing Datasets. Recommend a model.
Part 4: Serialization	Serialize Machine Learning Algorithms using Pickle, followed by saving the serialized format into a file.
Part 5: Final Pipeline	Luigi framework is used to build pipeline to connect data processing elements.
Part 6: Report	Put together a comprehensive report discussing analysis in pdf.

INFO:

Language Used : Python
Process Followed : Data Ingestion, Data Wrangling, Data Cleansing, Exploratory Data Analysis,Feature Engineering, Predicting Algorithm Models, Serialization, Piplelining
Tools Used : Jupyter Notebook, boto 3, boto, Amazon S3 bucket