Icon

Titanic - ML Project

This will be the first dataset everyone starts for kaggle competitions. The dataset is easy to interpret and can start with the basic libraries like numpy, pandas, seaborn and matplotlib in Python. The objective is to predict whether a passenger in titanic survived or not survived based on the features or predictor variables.

In KNIME Analytics Platform, we can do this ML project without coding or without using python. Everything from EDA, Data Cleaning, Normalization, Variable encoding, Data Partioning, Model Building & Sample File submission is covered. More can be done but this project is aimed for beginners.

Download KNIME and this workflow from my KNIME hub.

(Titanic Data - Notes)-Dimension (1309 rows, 12 columns)-High skewness for variables Sibsp,Parch & Fare-Missing value in variable Age, Cabin &Embarked.-Zero value in varibale Fare. (Outlier Treatment)Try using the same workflow shownbelow after outlier treament & check anymodel performance improvement (Gray Nodes)Gray color nodes are components, whichmeans two or more nodes are combined toform one component. Open each to view thesub workflows in each component nodes (Sample File Submission)Export the sample submission csv tothe local path. Upload the file in Kaggleto see the model score. Train DataJoining Train & TestTest DataCorrelation CheckTrain & TestTrain & ValidationSample SubmissionSelect Columns CSV Reader Concatenate CSV Reader Scatter Plot(JFreeChart) Outlier Treatment Data Cleaning Data EDA Partitioning Variable Encoding Normalization Partitioning Modelling (FindingBest Model) CSV Writer Best Model (LogisticsRegression) Column Filter (Titanic Data - Notes)-Dimension (1309 rows, 12 columns)-High skewness for variables Sibsp,Parch & Fare-Missing value in variable Age, Cabin &Embarked.-Zero value in varibale Fare. (Outlier Treatment)Try using the same workflow shownbelow after outlier treament & check anymodel performance improvement (Gray Nodes)Gray color nodes are components, whichmeans two or more nodes are combined toform one component. Open each to view thesub workflows in each component nodes (Sample File Submission)Export the sample submission csv tothe local path. Upload the file in Kaggleto see the model score. Train DataJoining Train & TestTest DataCorrelation CheckTrain & TestTrain & ValidationSample SubmissionSelect ColumnsCSV Reader Concatenate CSV Reader Scatter Plot(JFreeChart) Outlier Treatment Data Cleaning Data EDA Partitioning Variable Encoding Normalization Partitioning Modelling (FindingBest Model) CSV Writer Best Model (LogisticsRegression) Column Filter

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: user
Created at: 2021-08-20
On NodePit since: 2025-10-16
Last update: 2026-01-06
Created with KNIME version: v4.3.4
Tags: KNIMETitanicMachine LearningKaggle

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!