Notice: This page requires JavaScript to function properly.
Please enable JavaScript in your browser settings or update your browser.Apprendre Challenge: Putting It All Together | Modeling
ML Introduction with scikit-learn
course content

Contenu du cours

ML Introduction with scikit-learn

ML Introduction with scikit-learn

1. Machine Learning Concepts
What is MLTypes of Machine LearningTraining SetTypes of DataMachine Learning Workflow
2. Preprocessing Data with Scikit-learn
Scikit-learn ConceptsGetting Familiar with DatasetDealing with Missing ValuesChallenge: Imputing Missing ValuesOrdinalEncoderOne-Hot EncoderLabelEncoderChallenge: Encoding Categorical VariablesWhy Scale the Data?StandardScaler, MinMaxScaler, MaxAbsScalerChallenge: Scaling the Features
3. Pipelines
What is PipelineColumnTransformerEfficient Data Preprocessing with PipelinesChallenge: Creating a PipelineFinal EstimatorChallenge: Creating a Complete ML Pipeline
4. Modeling
ModelsKNeighborsClassifierEvaluating the ModelCross-ValidationChallenge: Evaluating the Model with Cross-ValidationGridSearchCVThe Flaw of GridSearchCVChallenge: Tuning Hyperparameters with RandomizedSearchCVModeling SummaryChallenge: Putting It All Together

book
Challenge: Putting It All Together

In this challenge, you will apply everything you learned throughout the course from data preprocessing to training and evaluating the model.

carousel-imgcarousel-imgcarousel-imgcarousel-imgcarousel-img
Tâche

Swipe to start coding

  1. Encode the target.
  2. Split the data so that 33% is used for the test set and the remainder for the training set.
  3. Make a ColumnTransformer to encode only the 'island' and 'sex' columns. Make sure the others columns remain untouched. Use a proper encoder for nominal data.
  4. Fill the gaps in a param_grid to try the following values for the number of neighbors: [1, 3, 5, 7, 9, 12, 15, 20, 25].
  5. Create a GridSearchCV object with the KNeighborsClassifier as a model.
  6. Construct a pipeline that begins with ct as the first step, followed by imputation using the most frequent value, standardization, and concludes with GridSearchCV as the final estimator.
  7. Train the model using a pipeline on the training set.
  8. Evaluate the model on the test set. (Print its score)
  9. Get a predicted target for X_test.
  10. Print the best estimator found by grid_search.

Solution

Switch to desktopPassez à un bureau pour une pratique réelleContinuez d'où vous êtes en utilisant l'une des options ci-dessous
Tout était clair ?

Comment pouvons-nous l'améliorer ?

Merci pour vos commentaires !

Section 4. Chapitre 10
toggle bottom row

book
Challenge: Putting It All Together

In this challenge, you will apply everything you learned throughout the course from data preprocessing to training and evaluating the model.

carousel-imgcarousel-imgcarousel-imgcarousel-imgcarousel-img
Tâche

Swipe to start coding

  1. Encode the target.
  2. Split the data so that 33% is used for the test set and the remainder for the training set.
  3. Make a ColumnTransformer to encode only the 'island' and 'sex' columns. Make sure the others columns remain untouched. Use a proper encoder for nominal data.
  4. Fill the gaps in a param_grid to try the following values for the number of neighbors: [1, 3, 5, 7, 9, 12, 15, 20, 25].
  5. Create a GridSearchCV object with the KNeighborsClassifier as a model.
  6. Construct a pipeline that begins with ct as the first step, followed by imputation using the most frequent value, standardization, and concludes with GridSearchCV as the final estimator.
  7. Train the model using a pipeline on the training set.
  8. Evaluate the model on the test set. (Print its score)
  9. Get a predicted target for X_test.
  10. Print the best estimator found by grid_search.

Solution

Switch to desktopPassez à un bureau pour une pratique réelleContinuez d'où vous êtes en utilisant l'une des options ci-dessous
Tout était clair ?

Comment pouvons-nous l'améliorer ?

Merci pour vos commentaires !

Section 4. Chapitre 10
Switch to desktopPassez à un bureau pour une pratique réelleContinuez d'où vous êtes en utilisant l'une des options ci-dessous
We're sorry to hear that something went wrong. What happened?
some-alt