public class DB
extends java.lang.Object
Modifier and Type | Field and Description |
---|---|
static java.util.HashSet<java.lang.String> |
amenityTerms |
static java.util.HashMap<java.lang.String,java.util.HashMap<java.lang.String,java.lang.String>> |
sentiment |
static java.util.HashSet<java.lang.String> |
stopConcepts |
Constructor and Description |
---|
DB() |
Modifier and Type | Method and Description |
---|---|
static java.util.HashMap<java.lang.String,java.lang.Integer> |
addConceptSentimentScores(java.util.HashMap<java.lang.String,java.lang.Integer> scores,
java.lang.String SUMOs,
int total)
Add new scores to existing scores.
|
static java.util.HashMap<java.lang.String,java.lang.Integer> |
computeConceptSentiment(java.lang.String input)
Associate individual concepts with a sentiment score
|
static java.util.HashMap<java.lang.String,java.lang.Integer> |
computeConceptSentimentFromFile(java.lang.String filename)
Associate individual concepts with a sentiment score
|
static int |
computeSentiment(java.lang.String input)
Calculate an integer sentiment value for a string of words.
|
static int |
computeSentimentForWord(java.lang.String word)
Find the sentiment value for a given word, after finding the root
form of the word.
|
static void |
DiningDBImport() |
static void |
disambigReviews(java.util.ArrayList<Hotel> hotels) |
static boolean |
emptyString(java.lang.String input) |
void |
exportTable(KB kb)
Export a comma-delimited table of all the ground binary
statements in the knowledge base.
|
static java.util.ArrayList<java.lang.String> |
fill(java.lang.String value,
int count) |
void |
generateDB(KB kb)
Generate an SQL database from the knowledge base
Tables must be defined as instances of &%DatabaseTable and
must have &%localDocumentation and &%HasDatabaseColumn
relations.
|
static java.util.ArrayList<java.lang.String> |
geocode(java.lang.String address)
Call Google's geocode API to convert an address string into a
lat/lon, which is returned as an ArrayList of two String elements
containing a real-number format latitude and longitude.
|
static java.util.HashSet<java.lang.String> |
getAllRest() |
static java.util.ArrayList<java.lang.String> |
getFoodWordSenses(java.util.ArrayList<java.lang.String> al) |
static java.util.ArrayList<java.lang.String> |
getWordSenses(java.util.ArrayList<java.lang.String> al) |
static void |
guessGender(java.lang.String fname) |
static void |
main(java.lang.String[] args)
A test method
|
static java.lang.String |
parseCuisines(java.lang.String cuisine,
java.lang.String RST_RESTAURANTNAME,
java.lang.String RST_RESTAURANTID) |
static java.util.HashSet<java.lang.String> |
parseOneRestFile(java.lang.String fname)
A test method.
|
static java.util.HashSet<java.lang.String> |
parseRest(java.lang.String menu,
java.lang.String placename,
java.lang.String price,
java.lang.String address,
java.lang.String latitude,
java.lang.String longitude,
java.lang.String phone) |
void |
printSpreadsheet(java.util.TreeMap rows,
java.util.ArrayList relations)
Print a comma-delimited matrix.
|
static java.lang.String |
printTopSUMOInReviews(java.util.ArrayList<AVPair> topSUMO) |
java.util.HashMap |
printTPTPDataInCSV(java.util.HashMap byProver)
Print statistics in a summary form for TPTP test run
data
|
static java.lang.String |
processTimeDate(java.lang.String timeDate) |
java.util.HashMap |
processTPTPData()
Read statistics for TPTP test run data
|
static void |
readAmenities() |
static java.util.ArrayList<java.util.ArrayList> |
readDataInterchangeFormatFile(java.io.Reader inReader)
Parse an input stream Reader from a Data Interchange Format
(.dif) file into an ArrayList of ArrayLists.
|
static java.util.ArrayList<java.util.ArrayList> |
readDataInterchangeFormatFile(java.lang.String fname)
Parse and load a Data Interchange Format (.dif) file into an
ArrayList of ArrayLists.
|
static void |
readSentimentArray()
Fill out from a CSV file a map of word keys, and values broken down by POS,
listing whether it's a positive or negative word interior hash map keys are
type, POS, stemmed, polarity
|
static java.util.ArrayList<java.util.ArrayList<java.lang.String>> |
readSpreadsheet(java.io.Reader inReader,
java.util.List<java.lang.String> lineStartTokens,
boolean quote,
char delimiter)
Parse the input from a Reader for a CSV file into an ArrayList
of ArrayLists.
|
static java.util.ArrayList<java.util.ArrayList<java.lang.String>> |
readSpreadsheet(java.lang.String fname,
java.util.List lineStartTokens,
boolean quote) |
static java.util.ArrayList<java.util.ArrayList<java.lang.String>> |
readSpreadsheet(java.lang.String fname,
java.util.List lineStartTokens,
boolean quote,
char delimiter)
Parse a CSV file into an ArrayList of ArrayLists.
|
static java.util.HashMap<java.lang.String,java.lang.String> |
readStateAbbrevs() |
static void |
readStopConceptArray()
Fill out from a CSV file a set of concepts that should be ignored
during content extraction
|
static void |
RearDBtoKIF() |
java.util.HashMap |
resortTPTPData(java.util.HashMap stats)
Reorganize statistics in a summary form for TPTP test run
data
|
static void |
SUMOReviews(java.util.ArrayList<Hotel> reviews) |
static void |
testSentiment() |
static void |
testSentimentCorpus() |
static void |
textFileSentiment(java.lang.String fname,
boolean neg)
Compute sentiment for each line of a text file and output as CSV.
|
static void |
textSentiment() |
static void |
textSentimentByPeriod() |
static java.util.ArrayList<AVPair> |
topSUMOInReviews(java.util.ArrayList<Hotel> reviews)
Excludes cases of where the mapping is to multiple SUMO terms
|
static java.util.HashMap<java.lang.String,java.lang.Integer> |
wordSensesInReviews(java.util.ArrayList<Hotel> reviews) |
static java.lang.String |
wordWrap(java.lang.String input,
int length) |
static java.lang.String |
writeSpreadsheet(java.util.ArrayList<java.util.ArrayList<java.lang.String>> values,
boolean quote) |
static java.lang.String |
writeSpreadsheetLine(java.util.ArrayList<java.lang.String> al,
boolean quote) |
static int |
writeSuoKifStatements(KB kb,
java.lang.String sourceFilePath)
Writes to sourceFilePath all Formulae in kb that have
sourceFilePath as source file.
|
static int |
writeSuoKifStatements(java.util.Set statements,
java.io.PrintWriter pw) |
public static java.util.HashMap<java.lang.String,java.util.HashMap<java.lang.String,java.lang.String>> sentiment
public static java.util.HashSet<java.lang.String> amenityTerms
public static java.util.HashSet<java.lang.String> stopConcepts
public java.util.HashMap printTPTPDataInCSV(java.util.HashMap byProver) throws java.io.IOException
java.io.IOException
public java.util.HashMap resortTPTPData(java.util.HashMap stats) throws java.io.IOException
java.io.IOException
public java.util.HashMap processTPTPData() throws java.io.IOException
java.io.IOException
public void generateDB(KB kb)
public static java.util.ArrayList<java.util.ArrayList<java.lang.String>> readSpreadsheet(java.io.Reader inReader, java.util.List<java.lang.String> lineStartTokens, boolean quote, char delimiter)
inReader
- A reader for the file to be processedlineStartTokens
- If a List containing String tokens, all
lines not starting with one of the tokens will be concatenatedquote
- signifies whether to retain quotes in elementspublic static java.util.ArrayList<java.util.ArrayList<java.lang.String>> readSpreadsheet(java.lang.String fname, java.util.List lineStartTokens, boolean quote, char delimiter)
fname
- The pathname of the CSV file to be processedlineStartTokens
- If a List containing String tokens, all
lines not starting with one of the tokens will be concatenatedquote
- signifies whether to retain quotes in elementspublic static java.util.ArrayList<java.util.ArrayList<java.lang.String>> readSpreadsheet(java.lang.String fname, java.util.List lineStartTokens, boolean quote)
public static java.lang.String writeSpreadsheetLine(java.util.ArrayList<java.lang.String> al, boolean quote)
quote
- signifies whether to quote entries from the spreadsheetpublic static java.lang.String writeSpreadsheet(java.util.ArrayList<java.util.ArrayList<java.lang.String>> values, boolean quote)
quote
- signifies whether to quote entries from the spreadsheetpublic static java.util.ArrayList<java.util.ArrayList> readDataInterchangeFormatFile(java.io.Reader inReader)
inReader
- A reader created from the .dif file to be processedpublic static java.util.ArrayList<java.util.ArrayList> readDataInterchangeFormatFile(java.lang.String fname)
fname
- The pathname of the file to be processedpublic static int writeSuoKifStatements(java.util.Set statements, java.io.PrintWriter pw)
public static int writeSuoKifStatements(KB kb, java.lang.String sourceFilePath)
kb
- The KB from which Formulae will be writtensourceFilePath
- The canonical pathname of the file to
which Formulae will be writtenpublic void printSpreadsheet(java.util.TreeMap rows, java.util.ArrayList relations)
rows
- - the matrixrelations
- - the relations that form the column headerpublic void exportTable(KB kb)
The
- knowledge base.public static java.lang.String wordWrap(java.lang.String input, int length)
public static boolean emptyString(java.lang.String input)
public static void RearDBtoKIF()
public static java.lang.String parseCuisines(java.lang.String cuisine, java.lang.String RST_RESTAURANTNAME, java.lang.String RST_RESTAURANTID)
public static java.util.ArrayList<AVPair> topSUMOInReviews(java.util.ArrayList<Hotel> reviews)
public static java.util.HashMap<java.lang.String,java.lang.Integer> wordSensesInReviews(java.util.ArrayList<Hotel> reviews)
public static void SUMOReviews(java.util.ArrayList<Hotel> reviews)
public static void disambigReviews(java.util.ArrayList<Hotel> hotels)
an
- ArrayList of Hotel with reviews as textpublic static java.lang.String processTimeDate(java.lang.String timeDate)
public static java.util.HashMap<java.lang.String,java.lang.String> readStateAbbrevs()
w
- states whether to write SUMO statementspublic static java.util.ArrayList<java.lang.String> fill(java.lang.String value, int count)
public static void DiningDBImport()
public static java.util.ArrayList<java.lang.String> getWordSenses(java.util.ArrayList<java.lang.String> al)
public static java.util.ArrayList<java.lang.String> getFoodWordSenses(java.util.ArrayList<java.lang.String> al)
public static java.util.HashSet<java.lang.String> parseRest(java.lang.String menu, java.lang.String placename, java.lang.String price, java.lang.String address, java.lang.String latitude, java.lang.String longitude, java.lang.String phone)
public static java.util.HashSet<java.lang.String> getAllRest()
public static java.util.ArrayList<java.lang.String> geocode(java.lang.String address)
public static java.lang.String printTopSUMOInReviews(java.util.ArrayList<AVPair> topSUMO)
public static java.util.HashSet<java.lang.String> parseOneRestFile(java.lang.String fname)
fname
- has no file extension or directorypublic static void readStopConceptArray()
public static void readSentimentArray()
public static int computeSentiment(java.lang.String input)
public static int computeSentimentForWord(java.lang.String word)
public static java.util.HashMap<java.lang.String,java.lang.Integer> addConceptSentimentScores(java.util.HashMap<java.lang.String,java.lang.Integer> scores, java.lang.String SUMOs, int total)
public static java.util.HashMap<java.lang.String,java.lang.Integer> computeConceptSentimentFromFile(java.lang.String filename)
public static java.util.HashMap<java.lang.String,java.lang.Integer> computeConceptSentiment(java.lang.String input)
public static void readAmenities()
public static void textSentimentByPeriod()
public static void textSentiment()
public static void textFileSentiment(java.lang.String fname, boolean neg)
public static void testSentiment()
public static void testSentimentCorpus()
public static void guessGender(java.lang.String fname)
public static void main(java.lang.String[] args)