Icon

BloodPressure

Run Jupyter in KNIME

This Workflow showcases how the Jupyter Notebooks can be integrated in KNIME. The Jupyter Notebook is responsible for feature transformation.

The Reading Data and Pre-processing block is responsible for loading the data and performing the preprocessing using Python Script Node. The Node loads the Jupyter Notebook. The Jupyter Notebook Path block can be used to provide the location of the Jupyter Notebook. The rest of the blocks are responsible for Training and evaluating the Decision Tree.

URL: Jupyter and KNIME https://www.knime.com/blog/knime-and-jupyter
URL: KNIME Python Integration Guide https://docs.knime.com/latest/python_installation_guide/#_introduction
URL: Data Transfer between KNIME and Python Just Got Faster https://www.knime.com/blog/python-integration-for-fast-data-transfer
URL: KNIME Python API Documentation https://docs.knime.com/latest/python_installation_guide/#jupyter-notebooks

Blood Pressure Linear Regression Pipeline
This workflow implements the logic from predicting-the-hard-disease-using-linear-rgrssn.ipynb using KNIME nodes. Steps:

  1. CSV Reader: Reads heart_disease.csv (corresponds to data import in the notebook).

  2. Missing Value: Handles missing values (data cleaning step in notebook).

  3. Binner: Encodes categorical variables (feature engineering step in notebook).

  4. X-Partitioner: Splits data into training and test sets (train/test split in notebook).

  5. Linear Regression Learner: Trains the regression model (model training in notebook).

  6. Regression Predictor: Applies the model to test data (prediction step in notebook).

  7. Numeric Scorer: Evaluates model performance (evaluation step in notebook).

1. Data Import

2. Data Cleaning
.

3. Feature Engineering

4. Data Splitting

5. Model Training

6. Prediction

7. Evaluation

Results Display

Display predicted values and evaluation results
Table View
Handle missing values in heart_disease.csv
Missing Value
Encode categorical variables (binning if needed)
Binner
CSV Reader
Apply regression model to test data
Regression Predictor
Evaluate regression model performance (RMSE, R², etc.)
Numeric Scorer
Split data into training and test sets
X-Partitioner
Train linear regression model
Linear Regression Learner

Nodes

Extensions

Links