Joseph Kato jdkato

Spelling

Observed	Expected	File
softwares	software	big-data-in-the-linode-cloud-streaming-data-processing-with-apache-storm.md
strucure	structure	[how-to-scrape-a-website-with-beautiful-soup.md](https://github.com/linode/docs/blame/master/docs/applications/big-data/how-to-scrape-a-website-with-beautiful-soup.

	#!/bin/sed -f

	# Sed script to produce Penn Treebank tokenization on arbitrary raw text.
	# Yeah, sure.

	# expected input: raw text with ONE SENTENCE TOKEN PER LINE

	# by Robert MacIntyre, University of Pennsylvania, late 1995.

	# If this wasn't such a trivial program, I'd include all that stuff about

	#include "HMyClass.h"
	#include <stdio.h>

	void my_eh( const char * error_message, void * unused)
	{
	printf("my_eh: %s\n", error_message);
	}

	int main()
	{

	package main

	import (
	"gopkg.in/jdkato/prose.v2"
	)

	func main() {
	// You can pass "functional options" to control the document-creation
	// pipeline -- e.g., `prose.WithExtraction(false)` disables named-entity
	// extraction.

	package main

	import (
	"gopkg.in/jdkato/prose.v2"
	)

	func main() {
	doc, _ := prose.NewDocument("This is a sentence.")
	for _, token := range doc.Tokens() {
	fmt.Println(token.Text)

	package main

	import (
	"gopkg.in/jdkato/prose.v2"
	)

	func main() {
	doc, _ := prose.NewDocument("Lebron James plays basketball in Los Angeles.")
	for _, ent := range doc.Entities() {
	fmt.Println(ent.Text, ent.Label)

	package main

	import (
	"gopkg.in/jdkato/prose.v2"
	)

	func main() {
	// Where `ents` is `[]prose.LabeledEntity` from some external source.
	//
	// "iOS" is what we've named this model, but it can be anything.