Index
A
- Altman's Z-score / How to do it…
- attributes, random forest
- rf.criterion / How to do it…
- rf.bootstrap / How to do it…
- rf.n_jobs / How to do it…
- rf.max_features / How to do it…
- rf.compute_idportances / How to do it…
- rf.max_depth / How to do it…
- attributes, support vector classifier (SVC)
- C / How to do it…
- class_weight / How to do it…
- gamma / How to do it…
- kernel / How to do it…
- automatic cross validation
- about / Getting ready, How it works...
B
- Bayesian Ridge Regression
- Bayesian ridge regression
- applying, directly / Directly applying Bayesian ridge regression, How it works..., There's more...
- binary features
- creating, through thresholding / Creating binary features through thresholding, How it works...
- bootstrapping
- about / There's more...
- boston dataset
- about / Getting ready, Getting ready
- Brute force grid search
- about / Brute force grid search
- performing / Getting ready, How it works...
- Bunch object
- about / How it works…
C
- categorical variables
- about / Working with categorical variables
- working with / Getting ready, There's more...
- centroids
- about / Optimizing the number of centroids
- optimizing / Getting ready, How to do it…, How it works…
- classification
- linear methods, using for / Using linear methods for classification – logistic regression, How to do it..., There's more...
- about / Introduction
- LDA, using for / How to do it…, How it works…
- Stochastic Gradient Descent, using for / Getting ready, How to do it…
- classifications
- performing, with Decision Trees / Doing basic classifications with Decision Trees, How to do it…, How it works…
- closest object
- finding, in feature space / Getting ready, How to do it..., How it works...
- cluster
- correctness, assessing / Assessing cluster correctness, How to do it...
- clustering
- about / Introduction, Using KMeans to cluster data
- compute_importances parameter / How to do it…
- correlation functions, scikit-learn / How it works…
- cosine kernel
- about / How to do it...
- cross validation
- about / How it works...
- cross validation, with ShuffleSplit / Getting ready, How to do it...
D
- data
- scaling, to standard normal / Scaling data to the standard normal, How it works...
- line, fitting through / Fitting a line through data, How to do it..., How it works...
- clustering, KMeans used / Getting ready, How to do it…, How it works...
- handling, MiniBatch KMeans used / How to do it..., How it works...
- classifying, with Support Vector Machines (SVM) / Getting ready, How it works…
- data imputation
- datasets module
- about / How to do it…
- decision boundary / How it works…
- decision tree, versus random forest
- size, checking / There's more...
- Decision Tree model
- tuning / Tuning a Decision Tree model, How to do it…
- Decision Trees
- used, for performing classifications / Doing basic classifications with Decision Trees, How to do it…, How it works…
- decomposition
- factor analysis, using for / Getting ready, How to do it...
- DictionaryLearning
- about / Decomposition to classify with DictionaryLearning
- decomposition, performing for classification / Getting ready, How to do it..., How it works...
- DictVectorizer option / DictVectorizer
- dimensionality
- reducing, with PCA / Getting ready, How it works...
- reducing, truncated SVD used / Getting ready, How to do it..., How it works...
- distance functions
- about / How it works...
- documents
- classifying, with Naïve Bayes / Getting ready, How to do it…
- dummy estimators
- used, for comparing results / Using dummy estimators to compare results, How to do it..., How it works...
- dunder / There's more...
E
- effective rank
- about / How to do it...
- entropy
- versus Gini impurity / How it works…
- external sources
- sample data, obtaining from / Getting sample data from external sources, How to do it…, There's more…
F
- factor analysis
- about / Using factor analysis for decomposition
- using, for decomposition / Getting ready, How to do it...
- feature importance / There's more…
- feature selection
- about / Feature selection, How to do it..., How it works...
- feature selection, on L1 norms / Feature selection on L1 norms, How to do it..., How it works...
- feature space
- closest objects, finding in / Getting ready, How to do it..., How it works...
- feature_selection module
- importing / How to do it...
- fit method
- about / The fit method
G
- Gauss-Markov theorem
- about / How it works...
- Gaussian Mixture Models
- probabilistic clustering, performing with / Getting ready, How to do it..., How it works...
- Gaussian process
- about / Using Gaussian processes for regression
- using, for regression / Using Gaussian processes for regression, How to do it…, How it works…
- GaussianProcess object
- beta0 / How to do it…
- corr / How to do it…
- regr / How to do it…
- nugget / How to do it…
- normalize / How to do it…
- Gaussian process object
- defining / How to do it…
- gaussian_process module
- about / Getting ready
- Gini impurity
- versus entropy / How it works…
- about / How it works…
- gradient boosting regression
- about / Getting ready
- working / How to do it..., How it works...
- grid search
- performing / Getting ready, How to do it...
I
- idempotent scalar objects
- creating / Creating idempotent scalar objects
- image
- quantizing, with KMeans clustering / Getting ready, How do it…
- imputation, scikit-learn
- idempotent scalar objects. creating / Creating idempotent scalar objects
- sparse imputations, handling / Handling sparse imputations
- inertia
- about / There's more...
- Information Gain (IG) / How it works…
J
- joblib
- models, persisting with / Persisting models with joblib, How it works...
K
- k-fold cross validation
- about / K-fold cross validation, How it works...
- k-NN
- using, for regression / Getting ready, How to do it…
- kernel PCA, nonlinear dimensionality reduction / Kernel PCA for nonlinear dimensionality reduction, How to do it..., How it works...
- KMeans
- about / Using KMeans to cluster data, Using MiniBatch KMeans to handle more data
- used, for clustering data / Getting ready, How to do it…, How it works...
- using, for outlier detection / Getting ready, How to do it..., How it works...
- KMeans clustering
- image, quantizing with / Getting ready, How do it…
L
- LabelBinarizer() method / How to do it...
- label features
- binarizing / Binarizing label features, How it works..., There's more...
- label propagation
- label propagation, semi-supervised learning / Getting ready, How to do it…
- LARS
- about / Getting ready
- Lasso, feature selection
- about / Lasso for feature selection
- Lasso cross-validation
- about / Lasso cross-validation
- LDA
- using, for classification / How to do it…, How it works…
- least absolute shrinkage and selection operator (LASSO)
- leave-one-out cross-validation (LOOCV)
- about / How to do it...
- line
- fitting, through data / Fitting a line through data, How to do it..., How it works...
- linear methods
- using, for classification / Using linear methods for classification – logistic regression, Getting ready, How to do it..., There's more...
- linear models
- about / Introduction
- linear regression
- about / Fitting a line through data
- linear regression model
- LinearRegression object
- about / There's more...
- linear_models module / How to do it...
- logistic regression
- LogisticRegression classifier / How to do it…
- LogisticRegression object
- about / How to do it...
- loss function / How it works...
- lr object
- about / Getting ready
- ls parameter / How it works...
M
- %matplotlib inline command / Getting sample data from external sources
- machine learning (ML) / Introduction
- max_depth parameter / How it works..., How to do it…
- mean absolute deviation (MAD)
- about / How to do it..., How it works...
- mean squared error (MSE)
- about / How to do it..., How it works...
- MiniBatch KMeans
- used, for handling data / How to do it..., How it works...
- missing values
- imputing, through various strategies / Getting ready, How to do it..., How it works..., There's more...
- models
- regularizing, sparsity used / Using sparsity to regularize models, How it works...
- persisting, with joblib / Persisting models with joblib, How it works...
- multiclass classification
- generalizing with / Getting ready, How it works…
- multiple preprocessing steps
- Pipelines, using for / Getting ready, How to do it..., How it works...
N
- Naïve Bayes
- about / Classifying documents with Naïve Bayes
- documents, classifying with / Getting ready, How to do it…
- extending / There's more…
- normalization
- about / How it works...
- NP-hard
- about / Getting ready
O
- OneVsRestClassifier / Getting ready
- outlier detection
- KMeans, using for / Getting ready, How to do it..., How it works...
P
- pairwise distances
- about / There's more...
- pairwise_distances function
- about / How to do it...
- patsy option / Patsy
- PCA
- about / Reducing dimensionality with PCA
- dimensionality, reducing with / Getting ready, How it works...
- PCA object
- about / There's more...
- Pipelines
- about / Using Pipelines for multiple preprocessing steps
- using, for multiple preprocessing steps / Getting ready, How to do it..., How it works...
- working / Getting ready, How to do it..., How it works..., There's more...
- precision parameter / How to do it…
- preprocessing module
- about / Getting ready
- probabilistic clustering
- performing, with Gaussian Mixture Models / Getting ready, How to do it..., How it works...
- pydot / Getting ready
Q
- QDA
- about / Working with QDA – a nonlinear LDA
- working with / How to do it…, How it works…
R
- radial basis function
- using / There's more…
- random forest model
- tuning / Tuning a random forest model, How to do it…
- random forests
- recall parameter / How to do it…
- regression
- Gaussian process, using for / Using Gaussian processes for regression, How to do it…, How it works…
- Stochastic Gradient Descent (SGD), using for / Getting ready, How to do it…, How it works…
- about / Using k-NN for regression
- k-NN, using for / Getting ready, How to do it…
- regression model
- evaluating / Regression model evaluation, How to do it..., How it works...
- regularization, LARS
- about / How to do it..., How it works...
- residuals
- about / How to do it...
- results
- comparing, dummy estimators used / Using dummy estimators to compare results, How to do it..., How it works...
- ridge cross-validation
- about / How to do it...
- RidgeCV object / How to do it...
- ridge regression
- used, for overcoming linear regression's shortfalls / Using ridge regression to overcome linear regression's shortfalls, How to do it..., How it works...
- ridge regression parameter
- root-mean-square deviation (RMSE)
- about / How it works...
S
- sample data
- obtaining, from external sources / Getting sample data from external sources, How to do it…, There's more…
- creating, for toy analysis / Getting ready, How to do it..., How it works...
- scikit-image
- scikit-learn
- URL / How it works…
- semi-supervised technique / Label propagation with semi-supervised learning
- ShuffleSplit
- about / Cross validation with ShuffleSplit
- used, for performing cross validation / Getting ready, How to do it...
- silhouette distance
- about / How to do it…
- sklearn.metrics.pairwise
- about / Getting ready
- sklearn package
- about / How to do it…
- sparse imputations
- handling / Handling sparse imputations
- sparse matrices
- about / Sparse matrices
- sparsity
- used, for regularizing models / Getting ready, How it works...
- spherical clusters
- about / Getting ready
- standard normal
- about / Scaling data to the standard normal
- data, scaling to / Scaling data to the standard normal, How it works...
- Stochastic Gradient Descent
- using, for classification / Getting ready, How to do it…
- Stochastic Gradient Descent (SGD)
- using, for regression / Getting ready, How to do it…, How it works…
- strategies
- missing values, imputing through / Getting ready, How to do it..., How it works..., There's more...
- stratified k-fold valuation
- viewing / Stratified k-fold, How to do it..., How it works...
- support vector classifier (SVC)
- about / How to do it…
- Support Vector Machines (SVM)
- about / Classifying data with support vector machines
- data, classifying with / Getting ready, How it works…
- support vectors
T
- thresholding
- binary features, creating through / Creating binary features through thresholding, How it works...
- toy analysis
- sample data, creating for / Getting ready, How to do it..., How it works...
- TrucatedSVD
- about / There's more...
- sign flipping / Sign flipping
- sparse matrices / Sparse matrices
- truncated SVD
- used, for reducing dimensionality / Getting ready, How to do it..., How it works...
U
- UCI Machine Learning Repository / See also
- univariate selection
- about / Feature selection
V
- VarianceThreshold object / How to do it...
Z
- z-scores