Tokenização e remoção de palavras irrelevantes

library(tidytext)
library(dplyr)

# A simple text corpus
text_df <- tibble::tibble(
  doc_id = 1:3,
  text   = c(
    'The quick brown fox jumps over the lazy dog.',
    'Text mining with R is powerful and fun.',
    'Natural language processing enables many applications.'
  )
)

cat('Input: ', nrow(text_df), 'documents\n')
cat('Columns:', names(text_df), '\n')

library(tidytext)
library(dplyr)

text_df <- tibble::tibble(
  doc_id = 1:2,
  text   = c(
    'R is a great language for data analysis.',
    'Text mining reveals hidden patterns in documents.'
  )
)

# Tokenise into words
tokens <- text_df |>
  unnest_tokens(word, text)

cat('Tokens extracted:', nrow(tokens), '\n')
print(tokens)

library(tidytext)
library(dplyr)

# Inspect the stop_words dataset
cat('Total stop words:', nrow(stop_words), '\n')
cat('Lexicons:', paste(unique(stop_words$lexicon), collapse = ', '), '\n')

# First few stop words from each lexicon
stop_words |>
  group_by(lexicon) |>
  slice_head(n = 3) |>
  print()

library(tidytext)
library(dplyr)

text_df <- tibble::tibble(
  doc_id = 1:3,
  text   = c(
    'The quick brown fox jumps over the lazy dog',
    'A stitch in time saves nine important words',
     'To be or not to be that is the question'
  )
)

tokens <- text_df |>
  unnest_tokens(word, text)

cat('Before removing stop words:', nrow(tokens), '\n')

tokens_clean <- tokens |>
  anti_join(stop_words, by = 'word')

cat('After removing stop words:', nrow(tokens_clean), '\n')
print(tokens_clean)

library(tidytext)
library(dplyr)

# Use Jane Austen's novels from janeaustenr package
# For demo: simulate a small corpus
corpus <- tibble::tibble(
  text = c(
    'data science involves statistics programming analysis',
    'machine learning algorithms data patterns training',
    'statistics probability distributions random variables data',
    'programming languages python r julia statistics',
    'analysis patterns distributions algorithms science'
  )
)

word_counts <- corpus |>
  unnest_tokens(word, text) |>
  anti_join(stop_words, by = 'word') |>
  count(word, sort = TRUE)

cat('Top 8 words:\n')
print(head(word_counts, 8))

library(tidytext)
library(dplyr)

# Domain-specific words to remove
custom_stops <- tibble::tibble(
  word   = c('data', 'analysis', 'r', 'using', 'also'),
  lexicon = 'custom'
)

# Combine with built-in stop words
all_stops <- bind_rows(stop_words, custom_stops)
cat('Total stop words after custom:', nrow(all_stops), '\n')

corpus <- tibble::tibble(
  text = c(
    'Using R for data analysis and machine learning models',
    'Statistical data analysis also involves data visualisation'
  )
)

clean_tokens <- corpus |>
  unnest_tokens(word, text) |>
  anti_join(all_stops, by = 'word') |>
  count(word, sort = TRUE)

print(clean_tokens)

library(tidytext)
library(dplyr)

corpus <- tibble::tibble(
  doc_id = 1:2,
  text = c(
    'machine learning and deep learning are powerful techniques',
    'natural language processing uses machine learning methods'
  )
)

bigrams <- corpus |>
  unnest_tokens(bigram, text, token = 'ngrams', n = 2)

cat('Bigrams extracted:', nrow(bigrams), '\n')
print(bigrams)

# Count most common bigrams
bigram_counts <- bigrams |> count(bigram, sort = TRUE)
cat('\nTop bigrams:\n')
print(head(bigram_counts, 5))

library(tidytext)
library(dplyr)
library(tidyr)

corpus <- tibble::tibble(
  text = c(
    'the field of machine learning and deep learning is growing',
    'natural language processing is a subfield of artificial intelligence'
  )
)

bigrams_filtered <- corpus |>
  unnest_tokens(bigram, text, token = 'ngrams', n = 2) |>
  separate(bigram, into = c('word1', 'word2'), sep = ' ') |>
  filter(
    !word1 %in% stop_words$word,
    !word2 %in% stop_words$word
  ) |>
  unite(bigram, word1, word2, sep = ' ') |>
  count(bigram, sort = TRUE)

print(bigrams_filtered)

library(tidytext)
library(dplyr)
library(ggplot2)

corpus <- tibble::tibble(
  text = c(
    'statistics probability machine learning algorithms patterns',
    'data science programming analysis visualisation models',
    'machine learning deep learning neural networks patterns',
    'probability statistics hypothesis testing distributions',
    'algorithms optimisation gradient descent models training'
  )
)

top_words <- corpus |>
  unnest_tokens(word, text) |>
  anti_join(stop_words, by = 'word') |>
  count(word, sort = TRUE) |>
  slice_head(n = 10)

ggplot(top_words, aes(reorder(word, n), n)) +
  geom_col(fill = 'steelblue') +
  coord_flip() +
  labs(x = 'Word', y = 'Count', title = 'Top 10 Terms') +
  theme_minimal()

library(tidytext)
library(dplyr)

docs <- tibble::tibble(
  doc_id = c(1, 1, 1, 2, 2, 2, 3, 3, 3),
  text   = c(
    'machine learning models training',
    'neural networks deep learning',
    'algorithms gradient descent optimisation',
    'statistical analysis probability distributions',
    'hypothesis testing confidence intervals regression',
    'bayesian inference prior posterior likelihood',
    'data visualisation plots charts dashboards',
    'ggplot2 ggvis plotly interactive graphics',
    'colour scales aesthetics themes layers'
  )
)

word_counts <- docs |>
  unnest_tokens(word, text) |>
  anti_join(stop_words, by = 'word') |>
  count(doc_id, word, sort = TRUE)

cat('Word-doc pairs:', nrow(word_counts), '\n')
print(head(word_counts, 10))

library(tidytext)
library(dplyr)

doc <- tibble::tibble(
  id   = 1L,
  text = paste(
    'R is a statistical programming language.',
    'It is widely used in data science and machine learning.',
    'The tidyverse makes data manipulation easy.',
    'Text mining with tidytext is elegant and powerful.'
  )
)

sentences <- doc |>
  unnest_tokens(sentence, text, token = 'sentences')

cat('Sentences found:', nrow(sentences), '\n')
print(sentences$sentence)

library(tidytext)
library(dplyr)

tibble::tibble(text = 'The quick brown fox jumps over the lazy dog') |>
  unnest_tokens(word, text) |>
  anti_join(stop_words, by = 'word') |>
  count(word, sort = TRUE) |>
  print()