Danfo.js has something similar to "sklearn.model_selection.train_test_split" in scikit-learn/Python
#660
Replies: 1 comment
-
|
Danfojs does not have an exact equivalent of sklearn's train_test_split, you can achieve the same functionality by combining the sample() method with some data manipulation. for example: const dfd = require('danfojs-node')
async function train_test_split(df, testSize = 0.2, seed = 42) {
// Calculate the number of samples for test
const numTest = Math.round(df.shape[0] * testSize)
const numTrain = df.shape[0] - numTest
// Randomly sample for test set
const testDf = await df.sample(numTest, { seed: seed })
// Get the indices not in test set for training
const testIndices = new Set(testDf.index)
const trainIndices = df.index.filter(idx => !testIndices.has(idx))
// Create train set using iloc
const trainDf = df.iloc({ rows: trainIndices })
return [trainDf, testDf]
}
// Example usage:
async function example() {
// Create or load your DataFrame
const data = {
'feature1': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'feature2': [10, 20, 30, 40, 50, 60, 70, 80, 90, 100],
'target': [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]
}
const df = new dfd.DataFrame(data)
// Split features and target
const X = df.drop({ columns: ['target'] })
const y = df['target']
// Perform train-test split
const [X_train, X_test] = await train_test_split(X)
const [y_train, y_test] = await train_test_split(y)
// Now you have your training and testing sets
console.log("Training set shape:", X_train.shape)
console.log("Testing set shape:", X_test.shape)
} |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi all,
Does Danfo.js has something similar to "sklearn.model_selection.train_test_split" in scikit-learn/Python?
[https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html]
What function most close to it in Danfo.js ? Example?
Thank you
Beta Was this translation helpful? Give feedback.
All reactions