GitHub - julius-jsr/text

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
.gitattributes		.gitattributes
.gitignore		.gitignore
Chunker.py		Chunker.py
README.txt		README.txt
Tagger.py		Tagger.py
ch.py		ch.py
chum.p		chum.p
chunk.pkl		chunk.pkl
chunking.p		chunking.p
cl		cl
class_tag		class_tag
class_tag.py		class_tag.py
doc_clas.p		doc_clas.p
docs.py		docs.py
noise.py		noise.py
pos.p		pos.p
postagger.py		postagger.py
ppp.p		ppp.p
printNP.py		printNP.py
process.py		process.py
ptag.pkl		ptag.pkl
requirments.txt		requirments.txt
rev.py		rev.py
t2.pkl		t2.pkl
tagger.pkl		tagger.pkl
trainChunker.py		trainChunker.py

Repository files navigation

Requirements:
----------------------
python 2.7
nltk 2.0.4
Numpy 1.6.2
pyYAML 3.11

you also need to download nltk data to run the program
---------------------------------------------------------


the program will take a text document as an input and genrates a ER graph.

it identifies the entity and the relation between them.
----------------------------------------------------------




process.py is the main file.

you need to run process.py.

then

invoke :
ie_preprocess(document)

here document is the piece of code.

last list shows the list of nodes of the ER graph.

eg:
process.py

document="""The iPhone is a line of smartphones designed and marketed by Apple Inc. It runs Apple's iOS mobile operating system. The first generation iPhone was released on June 29, 2007. The most recent iPhones, the seventh-generation iPhone 5C and iPhone 5S, were introduced on September 10, 2013."""

ie_preprocess(document)