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.
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. |
- 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
For further Details please refer the ADS_Assignment3_Report.pdf file