Instruction :

# Load dplyr and tidytext
library(dplyr)
library(tidytext)

# Choose the bing lexicon
get_sentiments("bing")

# Choose the nrc lexicon
get_sentiments("nrc") %>%
  count(sentiment) # Count words by sentiment

Instruction :

# geocoded_tweets has been pre-defined
geocoded_tweets

# Access bing lexicon: bing
bing <- get_sentiments("bing")

# Use data frame with text data
geocoded_tweets %>%
  # With inner join, implement sentiment analysis using `bing`
  inner_join(bing)

Instruction :

# tweets_nrc has been pre-defined
tweets_nrc

tweets_nrc %>%
  # Filter to only choose the words associated with sadness
  filter(sentiment == 'sadness') %>%
  # Group by word
  group_by(word) %>%
  # Use the summarize verb to find the mean frequency
  summarize(freq = mean(freq)) %>%
  # Arrange to sort in order of descending frequency
  arrange(desc(freq))

Instruction :

# tweets_nrc has been pre-defined
tweets_nrc

joy_words <- tweets_nrc %>%
  # Filter to choose only words associated with joy
  filter(sentiment == 'joy') %>%
  # Group by each word
  group_by(word) %>%
  # Use the summarize verb to find the mean frequency
  summarize(freq = mean(freq)) %>%
  # Arrange to sort in order of descending frequency
  arrange(desc(freq))    

joy_words %>%
  top_n(20) %>%
  mutate(word = reorder(word, freq)) %>%
  # Use aes() to put words on the x-axis and frequency on the y-axis
  ggplot(aes(x = word, y = freq)) +
  # Make a bar chart with geom_col()
  geom_col() +
  coord_flip()

Instruction :

# tweets_nrc has been pre-defined
tweets_nrc

tweets_nrc %>%
  # Find only the words for the state of Utah and associated with joy
  filter(state == "utah",
      sentiment == "joy") %>%
  # Arrange to sort in order of descending frequency
  arrange(desc(freq))

tweets_nrc %>%
  # Find only the words for the state of Louisiana and associated with joy
  filter(state == "louisiana",
      sentiment == "joy") %>%
  # Arrange to sort in order of descending frequency
  arrange(desc(freq))

Instruction :

# tweets_bing has been pre-defined
tweets_bing

tweets_bing %>% 
  # Group by two columns: state and sentiment
  group_by(state, sentiment) %>%
  # Use summarize to calculate the mean frequency for these groups
  summarize(freq = mean(freq)) %>%
  spread(sentiment, freq) %>%
  ungroup() %>%
  # Calculate the ratio of positive to negative words
  mutate(ratio = positive / negative,
         state = reorder(state, ratio)) %>%
  # Use aes() to put state on the x-axis and ratio on the y-axis
  ggplot(aes(x = state, y = ratio)) +
  # Make a plot with points using geom_point()
  geom_point() +
  coord_flip()

Instruction :

# The data set shakespeare in available in the workspace
shakespeare

# Pipe the shakespeare data frame to the next line
shakespeare %>% 
  # Use count to find out how many titles/types there are
  count(title, type)

Instruction :

# Load tidytext
library(tidytext)

tidy_shakespeare <- shakespeare %>%
  # Group by the titles of the plays
  group_by(title) %>%
  # Define a new column linenumber
  mutate(linenumber = row_number()) %>%
  # Transform the non-tidy text data to tidy text data
  unnest_tokens(word, text) %>%
  ungroup()

# Pipe the tidy Shakespeare data frame to the next line
tidy_shakespeare %>% 
  # Use count to find out how many times each word is used
  count(word, sort = TRUE)

Instruction :

shakespeare_sentiment <- tidy_shakespeare %>%
  # Implement sentiment analysis with the "bing" lexicon
  inner_join(get_sentiments("bing")) 

shakespeare_sentiment %>%
  # Find how many positive/negative words each play has
  count(title, sentiment)

Instruction :

sentiment_counts <- tidy_shakespeare %>%
    # Implement sentiment analysis using the "bing" lexicon
    inner_join(get_sentiments("bing")) %>%
    # Count the number of words by title, type, and sentiment
    count(title, type, sentiment)

sentiment_counts %>%
    # Group by the titles of the plays
    group_by(title) %>%
    # Find the total number of words in each play
    mutate(total = sum(n),
    # Calculate the number of words divided by the total
           percent = n / total) %>%
    # Filter the results for only negative sentiment
    filter(sentiment == "negative") %>%
    arrange(percent)

Instruction :

word_counts <- tidy_shakespeare %>%
  # Implement sentiment analysis using the "bing" lexicon
  inner_join(get_sentiments("bing")) %>%
  # Count by word and sentiment
  count(word, sentiment)

top_words <- word_counts %>%
  # Group by sentiment
  group_by(sentiment) %>%
  # Take the top 10 for each sentiment
  top_n(10) %>%
  ungroup() %>%
  # Make word a factor in order of n
  mutate(word = reorder(word, n))

# Use aes() to put words on the x-axis and n on the y-axis
ggplot(top_words, aes(x = word, y = n, fill = sentiment)) +
  # Make a bar chart with geom_col()
  geom_col(show.legend = FALSE) +
  facet_wrap(~sentiment, scales = "free") +  
  coord_flip()

Instruction :

tidy_shakespeare %>%
  # Count by title and word
  count(title, word, sort = TRUE) %>%
  # Implement sentiment analysis using the "afinn" lexicon
  inner_join(get_sentiments("afinn")) %>%
  # Filter to only examine the values for Macbeth that are negative
  filter(title == "The Tragedy of Macbeth", value < 0)

Instruction :

sentiment_contributions <- tidy_shakespeare %>%
  # Count by title and word
  count(title, word, sort = TRUE) %>%
  # Implement sentiment analysis using the "afinn" lexicon
  inner_join(get_sentiments("afinn")) %>%
  # Group by title
  group_by(title) %>%
  # Calculate a contribution for each word in each title
  mutate(contribution = value * n / sum(n)) %>%
  ungroup()
    
sentiment_contributions

Instruction :

sentiment_contributions %>%
  # Filter for Hamlet
  filter(title == "Hamlet, Prince of Denmark") %>%
  # Arrange to see the most negative words
  arrange(contribution)

sentiment_contributions %>%
  # Filter for The Merchant of Venice
  filter(title == "The Merchant of Venice") %>%
  # Arrange to see the most positive words
  arrange(desc(contribution))

Instruction :

tidy_shakespeare %>%
  # Implement sentiment analysis using "bing" lexicon
  inner_join(get_sentiments("bing")) %>%
  # Count using four arguments
  count(title, type, index = linenumber %/% 70,  sentiment)

Instruction :

# Load the tidyr package
library(tidyr)

tidy_shakespeare %>%
  inner_join(get_sentiments("bing")) %>%
  count(title, type, index = linenumber %/% 70, sentiment) %>%
  # Spread sentiment and n across multiple columns
  spread(sentiment, n, fill = 0) %>%
  # Use mutate to find net sentiment
  mutate(sentiment = positive - negative)

Instruction :

library(tidyr)
# Load the ggplot2 package
library(ggplot2)

tidy_shakespeare %>%
  inner_join(get_sentiments("bing")) %>%
  count(title, type, index = linenumber %/% 70, sentiment) %>%
  spread(sentiment, n, fill = 0) %>%
  mutate(sentiment = positive - negative) %>%
  # Put index on x-axis, sentiment on y-axis, and map comedy/tragedy to fill
  ggplot(aes(x = index, y = sentiment, fill = type)) +
  # Make a bar chart with geom_col()
  geom_col() +
  # Separate panels for each title with facet_wrap()
  facet_wrap(~title, scales = "free_x")

Instruction :

# Load the tidytext package
library(tidytext)

# Pipe the climate_text dataset to the next line
tidy_tv <- climate_text %>%
    # Transform the non-tidy text data to tidy text data
    unnest_tokens(word, text)

Instruction :

tidy_tv %>% 
    anti_join(stop_words) %>%
    # Count by word with sort = TRUE
    count(word, sort = TRUE)
    
tidy_tv %>%
    # Count by station
    count(station) %>%
    # Rename the new column station_total
    rename(station_total = n)

Instruction :

tv_sentiment <- tidy_tv %>% 
    # Group by station
    group_by(station) %>% 
    # Define a new column station_total
    mutate(station_total = n()) %>%
    ungroup() %>%
    # Implement sentiment analysis with the NRC lexicon
    inner_join(get_sentiments("nrc"))

Instruction :

# Which stations use the most negative words?
tv_sentiment %>% 
    count(station, sentiment, station_total) %>%
    # Define a new column percent
    mutate(percent = n / station_total) %>%
    # Filter only for negative words
    filter(sentiment == "negative") %>%
    # Arrange by percent
    arrange(percent)
    
# Now do the same but for positive words
tv_sentiment %>% 
    count(station, sentiment, station_total) %>%
    # Define a new column percent
    mutate(percent = n / station_total) %>%
    # Filter only for negative words
    filter(sentiment == "positive") %>%
    # Arrange by percent
    arrange(percent)

Instruction :

tv_sentiment %>%
    # Count by word and sentiment
    count(word, sentiment) %>%
    # Group by sentiment
    group_by(sentiment) %>%
    # Take the top 10 words for each sentiment
    top_n(10, wt = n) %>%
    ungroup() %>%
    mutate(word = reorder(word, n)) %>%
    # Set up the plot with aes()
    ggplot(aes(x = word, y = n, fill = sentiment)) +
    geom_col(show.legend = FALSE) +
    facet_wrap(~ sentiment, scales = "free") +
    coord_flip()

Instruction :

tv_sentiment %>%
    # Filter for only negative words
    filter(sentiment == "negative") %>%
    # Count by word and station
    count(word, station) %>%
    # Group by station
    group_by(station) %>%
    # Take the top 10 words for each station
    top_n(10, wt = n) %>%
    ungroup() %>%
    mutate(word = reorder(paste(word, station, sep = "__"), n)) %>%
    # Set up the plot with aes()
    ggplot(aes(x = word, y = n, fill = station)) +
    geom_col(show.legend = FALSE) +
    scale_x_discrete(labels = function(x) gsub("__.+$", "", x)) +
    facet_wrap(~ station, nrow = 2, scales = "free") +
    coord_flip()

Instruction :

# Load the lubridate package
library(lubridate)

sentiment_by_time <- tidy_tv %>%
    # Define a new column using floor_date()
    mutate(date = floor_date(show_date, unit = "6 months")) %>%
    # Group by date
    group_by(date) %>%
    mutate(total_words = n()) %>%
    ungroup() %>%
    # Implement sentiment analysis using the NRC lexicon
    inner_join(get_sentiments("nrc"))

sentiment_by_time %>%
    # Filter for positive and negative words
    filter(sentiment %in% c("positive"
,
"negative")) %>%
    # Count by date, sentiment, and total_words
    count(date, sentiment, total_words) %>%
    ungroup() %>%
    mutate(percent = n / total_words) %>%
    # Set up the plot with aes()
    ggplot(aes(x = date, y =percent, color = sentiment)) +
    geom_line(size = 1.5) +
    geom_smooth(method = "lm", se = FALSE, lty = 2) +
    expand_limits(y = 0)

Instruction :

tidy_tv %>%
    # Define a new column that rounds each date to the nearest 1 month
    mutate(date = floor_date(show_date, unit = "1 months")) %>%
    filter(word %in% c("threat", "hoax", "denier",
                       "real", "warming", "hurricane")) %>%
    # Count by date and word
    count(date, word) %>%
    ungroup() %>%
    # Set up your plot with aes()
    ggplot(aes(x = date, y = n, color = word)) +
    # Make facets by word
    facet_wrap(~ word) +
    geom_line(size = 1.5, show.legend = FALSE) +
    expand_limits(y = 0)

Instruction :

# Load the tidytext package
library(tidytext)

# Pipe song_lyrics to the next line
tidy_lyrics <- song_lyrics %>% 
  # Transform the lyrics column to a word column
  unnest_tokens(word, lyrics)

# Print tidy_lyrics
tidy_lyrics

Instruction :

totals <- tidy_lyrics %>%
  # Count by song to find the word totals for each song
  count(song) %>%
  # Rename the new column
  rename(total_words = n)

# Print totals    
totals

lyric_counts <- tidy_lyrics %>%
  # Combine totals with tidy_lyrics using the "song" column
  left_join(totals, by = "song")

Instruction :

lyric_sentiment <- lyric_counts %>%
    # Implement sentiment analysis with the "nrc" lexicon
    inner_join(get_sentiments("nrc"))

lyric_sentiment %>%
    # Find how many sentiment words each song has
    count(song, sentiment, sort = TRUE)

Instruction :

# What songs have the highest proportion of negative words?
lyric_sentiment %>%
    # Count using three arguments
    count(song, sentiment, total_words) %>%
    ungroup() %>%
    # Make a new percent column with mutate 
    mutate(percent = n / total_words) %>%
    # Filter for only negative words
    filter(sentiment == "negative") %>%
    # Arrange by descending percent
    arrange(desc(percent))

# What songs have the highest proportion of positive words?
lyric_sentiment %>%
    count(song, sentiment, total_words) %>%
    ungroup() %>%
    mutate(percent = n / total_words) %>%
    filter(sentiment == "positive") %>%
    arrange(desc(percent))

Instruction :

lyric_sentiment %>%
    filter(sentiment == "positive") %>%
    # Count by song, Billboard rank, and the total number of words
    count(song, rank, total_words) %>%
    ungroup() %>%
    # Use the correct dplyr verb to make two new columns
    mutate(percent = n / total_words,
           rank = 10 * floor(rank / 10)) %>%
    ggplot(aes(as.factor(rank), percent)) +
    # Make a boxplot
    geom_boxplot()

Instruction :

lyric_sentiment %>%
    # Filter for only negative words
    filter(sentiment == "negative") %>%
    # Count by song, Billboard rank, and the total number of words
    count(song, rank, total_words) %>%
    ungroup() %>%
    # Mutate to make a percent column
    mutate(percent = n / total_words,
           rank = 10 * floor(rank / 10)) %>%
    # Use ggplot to set up a plot with rank and percent
    ggplot(aes(as.factor(rank), percent)) +
    # Make a boxplot
    geom_boxplot()

Instruction :

# How is negative sentiment changing over time?
lyric_sentiment %>%
    # Filter for only negative words
    filter(sentiment == "negative") %>%
    # Count by song, year, and the total number of words
    count(song, year, total_words) %>%
    ungroup() %>%
    mutate(percent = n / total_words,
           year = 10 * floor(year / 10)) %>%
    # Use ggplot to set up a plot with year and percent
    ggplot(aes(as.factor(year), percent)) +
    geom_boxplot()
    
# How is positive sentiment changing over time?
lyric_sentiment %>%
    filter(sentiment == "positive") %>%
    count(song, year, total_words) %>%
    ungroup() %>%
    mutate(percent = n / total_words,
           year = 10 * floor(year / 10)) %>%
    ggplot(aes(as.factor(year), percent)) +
    geom_boxplot()

Instruction :

negative_by_year <- lyric_sentiment %>%
    # Filter for negative words
    filter(sentiment == "negative") %>%
    count(song, year, total_words) %>%
    ungroup() %>%
    # Define a new column: percent
    mutate(percent = n / total_words)

# Specify the model with percent as the response and year as the predictor
model_negative <- lm(percent ~ year, data = negative_by_year)

# Use summary to see the results of the model fitting
summary(model_negative)

Instruction :

positive_by_year <- lyric_sentiment %>%
    filter(sentiment == "positive") %>%
    # Count by song, year, and total number of words
    count(song, year, total_words) %>%
    ungroup() %>%
    # Define a new column: percent
    mutate(percent = n / total_words)

# Fit a linear model with percent as the response and year as the predictor
model_positive <- lm(percent ~ year, data = positive_by_year)

# Use summary to see the results of the model fitting
summary(model_positive)

Instruction :

在这里插入代码片