#_ important Scikit-learn Operations [ +100 ]

General Operations:

● sklearn.datasets.load_iris(): Load the iris dataset.

● sklearn.datasets.load_digits(): Load the hand-written digits
dataset.
● sklearn.model_selection.train_test_split(): Split datasets into
training and testing subsets.

Preprocessing:

● sklearn.preprocessing.StandardScaler(): Standardize features by

removing the mean and scaling to unit variance.
● sklearn.preprocessing.MinMaxScaler(): Transform features by scaling
them to a given range.
● sklearn.preprocessing.LabelEncoder(): Encode labels with value
between 0 and n_classes-1.
● sklearn.preprocessing.OneHotEncoder(): Convert categorical
variable(s) into dummy/indicator variables.

Supervised Learning Algorithms:

Linear Models:

● sklearn.linear_model.LinearRegression(): Ordinary least squares

linear regression.
● sklearn.linear_model.LogisticRegression(): Logistic regression
(classification).
● sklearn.linear_model.Ridge(): Linear least squares with l2
regularization.

Support Vector Machines (SVM):

● sklearn.svm.SVC(): C-Support Vector Classification.

● sklearn.svm.SVR(): Epsilon-Support Vector Regression.

By: Waleed Mousa

Nearest Neighbors:

● sklearn.neighbors.KNeighborsClassifier(): Classifier implementing

the k-nearest neighbors vote.
● sklearn.neighbors.KNeighborsRegressor(): Regression based on
k-nearest neighbors.

Gaussian Processes:

● sklearn.gaussian_process.GaussianProcessRegressor(): Gaussian
process regression (GPR).
● sklearn.gaussian_process.GaussianProcessClassifier(): Gaussian
process classification (GPC).

Decision Trees:

● sklearn.tree.DecisionTreeClassifier(): Decision tree classifier.

● sklearn.tree.DecisionTreeRegressor(): Decision tree regressor.

Ensemble Methods:

● sklearn.ensemble.RandomForestClassifier(): Random forest classifier.

● sklearn.ensemble.RandomForestRegressor(): Random forest regressor.
● sklearn.ensemble.GradientBoostingClassifier(): Gradient boosting
classifier.
● sklearn.ensemble.GradientBoostingRegressor(): Gradient boosting
regressor.

Neural Network Models:

● sklearn.neural_network.MLPClassifier(): Multi-layer perceptron

classifier.
● sklearn.neural_network.MLPRegressor(): Multi-layer perceptron
regressor.

Unsupervised Learning Algorithms:

Clustering:

● sklearn.cluster.KMeans(): K-Means clustering.

By: Waleed Mousa

 ● sklearn.cluster.DBSCAN(): Density-based spatial clustering of
applications with noise.
● sklearn.cluster.AgglomerativeClustering(): Agglomerative
clustering.

Dimensionality Reduction:

● sklearn.decomposition.PCA(): Principal component analysis.

● sklearn.decomposition.NMF(): Non-negative matrix factorization.
● sklearn.manifold.TSNE(): t-distributed Stochastic Neighbor
Embedding.

Model Selection and Evaluation:

● sklearn.model_selection.cross_val_score(): Evaluate a score by

cross-validation.
● sklearn.model_selection.GridSearchCV(): Exhaustive search over
specified parameter values for an estimator.
● sklearn.model_selection.RandomizedSearchCV(): Randomized search on
hyperparameters.
● sklearn.metrics.accuracy_score(): Accuracy classification score.
● sklearn.metrics.mean_squared_error(): Mean squared error regression
loss.
● sklearn.metrics.confusion_matrix(): Compute confusion matrix to
evaluate the accuracy of a classification.
● sklearn.metrics.roc_curve(): Compute Receiver operating
characteristic (ROC).
● sklearn.metrics.auc(): Compute Area Under the Curve (AUC) from
prediction scores.

Pipeline:

● sklearn.pipeline.Pipeline(): Pipeline of transforms and a final

estimator.
● sklearn.pipeline.make_pipeline(): Construct a Pipeline from the
given estimators.

By: Waleed Mousa

Feature Extraction:

● sklearn.feature_extraction.text.CountVectorizer(): Convert a
collection of text documents to a matrix of token counts.
● sklearn.feature_extraction.text.TfidfVectorizer(): Convert a
collection of raw documents to a matrix of TF-IDF features.

Feature Selection:

● sklearn.feature_selection.SelectKBest(): Select features according

to the k highest scores.
● sklearn.feature_selection.RFE(): Feature ranking with recursive
feature elimination.

Imbalanced Datasets:

● sklearn.utils.class_weight.compute_class_weight(): Estimate class

weights for unbalanced datasets.

Decomposition:

● sklearn.decomposition.TruncatedSVD(): Dimensionality reduction

using truncated SVD (aka LSA).
● sklearn.decomposition.FastICA(): Fast algorithm for Independent
Component Analysis.

Manifold Learning:

● sklearn.manifold.Isomap(): Isomap embedding.

● sklearn.manifold.MDS(): Multi-dimensional scaling.

Dataset Transformations:

● sklearn.preprocessing.PolynomialFeatures(): Generate polynomial and

interaction features.
● sklearn.preprocessing.Binarizer(): Binarize data (set feature
values to 0 or 1) according to a threshold.

By: Waleed Mousa

Validation:

● sklearn.model_selection.StratifiedKFold(): Stratified K-Folds

cross-validator.
● sklearn.model_selection.LeaveOneOut(): Leave-One-Out
cross-validator.

Calibration:

● sklearn.calibration.CalibratedClassifierCV(): Probability
calibration with isotonic regression or logistic regression.

Semi-Supervised Learning:

● sklearn.semi_supervised.LabelPropagation(): Label Propagation

classifier.
● sklearn.semi_supervised.LabelSpreading(): Label Spreading
classifier.

Kernel Ridge Regression:

● sklearn.kernel_ridge.KernelRidge(): Kernel ridge regression.

Pairwise Metrics:

● sklearn.metrics.pairwise.cosine_similarity(): Compute cosine

similarity between samples in X and Y.

Discriminant Analysis:

● sklearn.discriminant_analysis.LinearDiscriminantAnalysis(): Linear
Discriminant Analysis.
● sklearn.discriminant_analysis.QuadraticDiscriminantAnalysis():
Quadratic Discriminant Analysis.

Isolation Forest:

● sklearn.ensemble.IsolationForest(): Isolation Forest Algorithm.

By: Waleed Mousa

Naive Bayes:

● sklearn.naive_bayes.GaussianNB(): Gaussian Naive Bayes.

● sklearn.naive_bayes.MultinomialNB(): Multinomial Naive Bayes.

Cross Decomposition:

● sklearn.cross_decomposition.PLSRegression(): PLS regression.

Nearest Centroid Classifier:

● sklearn.neighbors.NearestCentroid(): Nearest centroid classifier.

Neural network utilities:

● sklearn.neural_network.BernoulliRBM(): Bernoulli Restricted

Boltzmann Machine.

Stochastic Gradient Descent:

● sklearn.linear_model.SGDClassifier(): Linear classifiers with SGD

training.
● sklearn.linear_model.SGDRegressor(): Linear model fitted by
minimizing a regularized empirical loss with SGD.

Multi-class and multi-label algorithms:

● sklearn.multiclass.OneVsRestClassifier(): One-vs-the-rest (OvR)

multiclass/multilabel strategy.

Multioutput regression:

● sklearn.multioutput.MultiOutputRegressor(): Multioutput regression.

Multiclass-multioutput algorithms:

● sklearn.multioutput.ClassifierChain(): Classifier Chain.

By: Waleed Mousa

Sparse coding:

● sklearn.decomposition.SparseCoder(): Sparse coding.

Covariance estimators:

● sklearn.covariance.EmpiricalCovariance(): Maximum likelihood

covariance estimator.

Gaussian Mixture Models:

● sklearn.mixture.GaussianMixture(): Gaussian Mixture.

Model Evaluation & Selection:

● sklearn.model_selection.permutation_test_score(): Permutation test

for score.

Cluster Biclustering:

● sklearn.cluster.bicluster.SpectralBiclustering(): Spectral
Biclustering.

Sparse PCA:

● sklearn.decomposition.SparsePCA(): Sparse Principal Components

Analysis (SparsePCA).

Voting regressor:

● sklearn.ensemble.VotingRegressor(): Voting regressor.

Bagging regressor:

● sklearn.ensemble.BaggingRegressor(): Bagging regressor.

Impute:

● sklearn.impute.SimpleImputer(): Basic imputation transformer.

By: Waleed Mousa

Checking:

● sklearn.utils.check_X_y(): Ensure X and y have compatible shapes.

Checking Estimators:

● sklearn.utils.estimator_checks.check_estimator(): Check if
estimator adheres to scikit-learn conventions.

Multilabel Binarizer:

● sklearn.preprocessing.MultiLabelBinarizer(): Transform between

iterable of iterables and a multilabel format.

Cross Decomposition:

● sklearn.cross_decomposition.CCA(): Canonical Correlation Analysis.

Loading datasets:

● sklearn.datasets.load_breast_cancer(): Load breast cancer dataset.

● sklearn.datasets.load_diabetes(): Load diabetes dataset.
● sklearn.datasets.load_linnerud(): Load Linnerud dataset.

Binarize labels:

● sklearn.preprocessing.label_binarize(): Binarize labels in a

one-vs-all fashion.

Metrics:

● sklearn.metrics.log_loss(): Logarithmic loss.

● sklearn.metrics.mean_absolute_error(): Mean absolute error
regression loss.
● sklearn.metrics.mean_squared_log_error(): Mean squared logarithmic
error regression loss.

By: Waleed Mousa

Partial dependence plots:

● sklearn.inspection.plot_partial_dependence(): Partial dependence

plots.

Unsupervised Neural Network:

● sklearn.neural_network.BernoulliRBM(): Bernoulli Restricted

Boltzmann Machine.

Load sample images:

● sklearn.datasets.load_sample_images(): Load sample images for image

manipulation.

Metrics:

● sklearn.metrics.precision_recall_curve(): Compute precision-recall

pairs for different probability thresholds.
● sklearn.metrics.average_precision_score(): Compute average
precision (AP) from prediction scores.

Checking:

● sklearn.utils.check_random_state(): Turn random state into a numpy

random number generator.

Output Code:

● sklearn.utils.murmurhash3_32(): Hash a Python object into a 32-bit

integer.

Metrics:

● sklearn.metrics.classification_report(): Build a text report

showing the main classification metrics.
● sklearn.metrics.cohen_kappa_score(): Cohen's kappa: a statistic
that measures inter-annotator agreement.

By: Waleed Mousa

● sklearn.metrics.confusion_matrix(): Compute confusion matrix to
evaluate the accuracy of a classification.
● sklearn.metrics.hinge_loss(): Compute (average) hinge loss.
● sklearn.metrics.matthews_corrcoef(): Compute the Matthews
correlation coefficient (MCC) for binary classes.

By: Waleed Mousa