H2O Example

This is a template notebook that will allow you to replicate an H2O workspace. If you want to take a look at the installation then take a look at the dockerfile in Environment > Dockerfile.

Click on the Duplicate button to get you started and feel free to delete all the cells here. From there, import H2O as you normally would.

import h2o h2o.init()

from h2o.estimators.kmeans import H2OKMeansEstimator iris = h2o.import_file("iris.csv") # Define target class iris['class'] = iris['class'].asfactor() # Set the predictor names and the response column name predictors = iris.columns[:-1] # Split into train and validation sets train, valid = iris.split_frame(ratios=[.75], seed=1234) print('\nTrain Dataframe') print(train.as_data_frame().sample(10)) print('\nValidation Dataframe') print(valid.as_data_frame().sample(10))

# Initialize the estimator then train the model iris_kmeans = H2OKMeansEstimator(k=3, seed=1234) iris_kmeans.train(x=predictors, training_frame=iris) # Bind predictions to validation df predictions = iris_kmeans.predict(valid) results = valid.cbind(predictions)

# Change clusters names and then show results as a dataframe results_df = results.as_data_frame() results_df.predict.replace({0: 'Versicolor', 1: 'Setosa', 2: 'Virginica'}, inplace=True) results_df

H2O Example

Recommended on Deepnote

Stock Market Analysis

The 10 Best Ways to Create NumPy Arrays

Wide Residual Networks