Questions marquées «supervised-learning»

29
Pourquoi xgboost est-il tellement plus rapide que sklearn GradientBoostingClassifier?

J'essaie de former un modèle d'augmentation de gradient sur plus de 50k exemples avec 100 fonctionnalités numériques. XGBClassifiergère 500 arbres en 43 secondes sur ma machine, alors qu'il GradientBoostingClassifierne gère que 10 arbres (!) en 1 minute et 2 secondes :( Je n'ai pas pris la peine...

scikit-learn xgboost gbm data-mining classification data-cleaning machine-learning reinforcement-learning data-mining bigdata dataset nlp language-model stanford-nlp machine-learning neural-network deep-learning randomized-algorithms machine-learning beginner career xgboost loss-function neural-network software-recommendation naive-bayes-classifier classification scikit-learn feature-selection r random-forest cross-validation data-mining python scikit-learn random-forest churn python clustering k-means machine-learning nlp sentiment-analysis machine-learning programming python scikit-learn nltk gensim visualization data csv neural-network deep-learning descriptive-statistics machine-learning supervised-learning text-mining orange data parameter-estimation python pandas scraping r clustering k-means unsupervised-learning
16
agrandir la carte thermique de Seaborn

Je crée un corr()df à partir d'un df d'origine. Le corr()df est sorti 70 X 70 et il est impossible de visualiser le heatmap ... sns.heatmap(df). Si j'essaie d'afficher le corr = df.corr(), le tableau ne correspond pas à l'écran et je peux voir toutes les corrélations. Est-ce un moyen d'imprimer...

visualization pandas plotting machine-learning neural-network svm decision-trees svm efficiency python linear-regression machine-learning nlp topic-model lda named-entity-recognition naive-bayes-classifier association-rules fuzzy-logic kaggle deep-learning tensorflow inception classification feature-selection feature-engineering machine-learning scikit-learn tensorflow keras encoding nlp text-mining nlp rnn python neural-network feature-extraction machine-learning predictive-modeling python r linear-regression clustering r ggplot2 neural-network neural-network training python neural-network deep-learning rnn predictive-modeling databases sql programming distribution dataset cross-validation neural-network deep-learning rnn machine-learning machine-learning python deep-learning data-mining tensorflow visualization tools sql embeddings orange feature-extraction unsupervised-learning gan machine-learning python data-mining pandas machine-learning data-mining bigdata apache-spark apache-hadoop deep-learning python convnet keras aggregation clustering k-means r random-forest decision-trees reference-request visualization data pandas plotting neural-network keras rnn theano deep-learning tensorflow inception predictive-modeling deep-learning regression sentiment-analysis nlp encoding deep-learning python scikit-learn lda convnet keras predictive-modeling regression overfitting regression svm prediction machine-learning similarity word2vec information-retrieval word-embeddings neural-network deep-learning rnn
10
Quand choisir la régression linéaire ou l'arbre de décision ou la régression de forêt aléatoire? [fermé]

Fermé . Cette question doit être plus ciblée . Il n'accepte pas actuellement de réponses. Voulez-vous améliorer cette question? Mettez à jour la question pour qu'elle se concentre sur un seul problème en modifiant ce post . Fermé il y a 4 ans . Je travaille sur un projet et j'ai du mal à décider...

machine-learning algorithms random-forest linear-regression decision-trees machine-learning predictive-modeling forecast r clustering similarity data-mining dataset statistics text-mining text-mining data-cleaning data-wrangling machine-learning classification algorithms xgboost data-mining dataset dataset regression graphs svm unbalanced-classes cross-validation optimization hyperparameter genetic-algorithms visualization predictive-modeling correlation machine-learning predictive-modeling apache-spark statistics normalization apache-spark map-reduce r correlation confusion-matrix r data-cleaning classification terminology dataset image-classification machine-learning regression apache-spark machine-learning data-mining nlp parsing machine-learning dimensionality-reduction visualization clustering multiclass-classification evaluation unsupervised-learning machine-learning machine-learning data-mining supervised-learning unsupervised-learning machine-learning data-mining classification statistics predictive-modeling data-mining clustering python pandas machine-learning dataset data-cleaning data bigdata software-recommendation
10
Comment faire un produit intérieur par lots dans Tensorflow?

J'ai deux tenseur a:[batch_size, dim] b:[batch_size, dim]. Je veux faire un produit intérieur pour chaque paire du lot, en générant c:[batch_size, 1], où c[i,0]=a[i,:].T*b[i,:].

tensorflow scikit-learn svm cross-validation feature-selection bayesian machine-learning decision-trees parameter-estimation neural-network convnet neural-network regularization visualization machine-learning similarity python pandas indexing r data-cleaning machine-learning predictive-modeling data-cleaning recommender-system python sequential-pattern-mining software-recommendation r visualization gaussian distribution machine-learning data-mining bigdata apache-hadoop predictive-modeling logistic-regression sampling machine-learning regression feature-selection mongodb neural-network inception machine-learning classification dataset databases logistic-regression deep-learning backpropagation classification data-mining multilabel-classification text-mining data-cleaning unsupervised-learning anomaly-detection python r python pandas