library("quanteda")
## Package version: 4.1.0
## Unicode version: 15.1
## ICU version: 74.2
## Parallel computing: disabled
## See https://quanteda.io for tutorials and examples.
library("quanteda.textmodels")
quanteda.textmodels implements fast methods for fitting and predicting Naive Bayes textmodels built especially for sparse document-feature matrices from textual data. It implements two models: multinomial and Bernoulli. (See Manning, Raghavan, and Schütze 2008, Chapter 13.)
Here, we compare performance for the two models, and then to the performance from two other packages for fitting these models.
For these tests, we will choose the dataset of 50,000 movie reviews from Maas et. al. (2011). We will use their partition into test and training sets for training and fitting our models.
# large movie review database of 50,000 movie reviews
load(url("https://quanteda.org/data/data_corpus_LMRD.rda"))
dfmat <- tokens(data_corpus_LMRD) %>%
dfm()
dfmat_train <- dfm_subset(dfmat, set == "train")
dfmat_test <- dfm_subset(dfmat, set == "test")
Comparing the performance of fitting the model:
library("microbenchmark")
microbenchmark(
multi = textmodel_nb(dfmat_train, dfmat_train$polarity, distribution = "multinomial"),
bern = textmodel_nb(dfmat_train, dfmat_train$polarity, distribution = "Bernoulli"),
times = 20
)
## Unit: milliseconds
## expr min lq mean median uq max neval
## multi 80.34769 81.24196 94.81686 85.06151 94.92649 237.2582 20
## bern 87.78628 100.25074 109.23630 102.04394 103.43905 254.2195 20
And for prediction:
microbenchmark(
multi = predict(textmodel_nb(dfmat_train, dfmat_train$polarity, distribution = "multinomial"),
newdata = dfmat_test),
bern = predict(textmodel_nb(dfmat_train, dfmat_train$polarity, distribution = "Bernoulli"),
newdata = dfmat_test),
times = 20
)
## Unit: milliseconds
## expr min lq mean median uq max neval
## multi 90.81255 91.47726 105.0432 92.15665 105.0006 258.8233 20
## bern 118.57058 131.24771 134.3562 133.07991 137.1816 157.0198 20
Now let’s see how textmodel_nb()
compares to equivalent
functions from other packages. Multinomial:
library("fastNaiveBayes")
library("naivebayes")
## naivebayes 1.0.0 loaded
## For more information please visit:
## https://majkamichal.github.io/naivebayes/
microbenchmark(
textmodels = {
tmod <- textmodel_nb(dfmat_train, dfmat_train$polarity, smooth = 1, distribution = "multinomial")
pred <- predict(tmod, newdata = dfmat_test)
},
fastNaiveBayes = {
tmod <- fnb.multinomial(as(dfmat_train, "dgCMatrix"), y = dfmat_train$polarity, laplace = 1, sparse = TRUE)
pred <- predict(tmod, newdata = as(dfmat_test, "dgCMatrix"))
},
naivebayes = {
tmod = multinomial_naive_bayes(as(dfmat_train, "dgCMatrix"), dfmat_train$polarity, laplace = 1)
pred <- predict(tmod, newdata = as(dfmat_test, "dgCMatrix"))
},
times = 20
)
## Unit: milliseconds
## expr min lq mean median uq max neval
## textmodels 91.2692 91.95058 98.3551 96.38518 105.2213 108.3261 20
## fastNaiveBayes 135.5703 147.66605 159.2900 150.64573 160.1106 300.7710 20
## naivebayes 104.0532 114.89914 121.0378 119.41170 123.8959 163.4573 20
And Bernoulli. Note here that while we are supplying the Boolean
matrix to textmodel_nb()
, this re-weighting from the count
matrix would have been performed automatically within the function had
we not done so in advance - it’s done here just for comparison.
dfmat_train_bern <- dfm_weight(dfmat_train, scheme = "boolean")
dfmat_test_bern <- dfm_weight(dfmat_test, scheme = "boolean")
microbenchmark(
textmodel_nb = {
tmod <- textmodel_nb(dfmat_train_bern, dfmat_train$polarity, smooth = 1, distribution = "Bernoulli")
pred <- predict(tmod, newdata = dfmat_test)
},
fastNaiveBayes = {
tmod <- fnb.bernoulli(as(dfmat_train_bern, "dgCMatrix"), y = dfmat_train$polarity, laplace = 1, sparse = TRUE)
pred <- predict(tmod, newdata = as(dfmat_test_bern, "dgCMatrix"))
},
naivebayes = {
tmod = bernoulli_naive_bayes(as(dfmat_train_bern, "dgCMatrix"), dfmat_train$polarity, laplace = 1)
pred <- predict(tmod, newdata = as(dfmat_test_bern, "dgCMatrix"))
},
times = 20
)
## Unit: milliseconds
## expr min lq mean median uq max neval
## textmodel_nb 119.8218 134.7251 153.5484 136.0846 147.1434 304.1643 20
## fastNaiveBayes 147.3500 163.8354 174.5313 175.8139 184.9254 197.0339 20
## naivebayes 116.3560 128.1979 135.7817 136.2872 141.6194 153.6593 20
Maas, Andrew L., Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts (2011). “Learning Word Vectors for Sentiment Analysis”. The 49th Annual Meeting of the Association for Computational Linguistics (ACL 2011).
Majka M (2020). naivebayes: High Performance Implementation of the Naive Bayes Algorithm in R. R package version 0.9.7, <URL: https://CRAN.R-project.org/package=naivebayes>. Date: 2020-03-08.
Manning, Christopher D., Prabhakar Raghavan, and Hinrich Schütze (2008). Introduction to Information Retrieval. Cambridge University Press.
Skogholt, Martin (2020). fastNaiveBayes: Extremely Fast Implementation of a Naive Bayes Classifier. R package version 2.2.1. https://github.com/mskogholt/fastNaiveBayes. Date: 2020-05-04.