textmodel Performance Comparisons

library("quanteda")
## Package version: 4.1.0
## Unicode version: 15.1
## ICU version: 74.2
## Parallel computing: 4 of 4 threads used.
## See https://quanteda.io for tutorials and examples.
library("quanteda.textmodels")

Naive Bayes

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 79.58887 79.82042  84.10156  80.20437  89.64562  97.68959    20
##   bern 86.56513 99.88759 114.79154 100.36895 103.52609 254.16360    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  89.62755  89.98453 102.0828  90.20028 103.1618 249.2568    20
##   bern 129.03474 130.86109 135.5513 131.95669 143.3328 145.7439    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  90.14678  90.79273 104.6843  93.53022 104.9313 258.9628    20
##  fastNaiveBayes 132.93599 143.01086 146.6801 144.79854 151.5748 159.6089    20
##      naivebayes 104.04558 107.43844 116.5664 118.10041 121.1103 143.5285    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 119.2177 132.4640 144.4594 135.1591 148.1621 283.4056    20
##  fastNaiveBayes 141.9869 157.6556 166.4567 168.7516 175.2655 185.5722    20
##      naivebayes 114.3093 126.2507 155.6713 131.1527 145.7930 304.5695    20

References

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.

- Naive Bayes
- References