Commit a82631c7 authored by Mateusz Pawlik's avatar Mateusz Pawlik

Tidied up sentiment script.

parent c2220f05
#!/bin/bash
# file: prepare_data.sh
#
# Program: Downloads and prepares data containing the sentiment dataset.
#
# Author: Thomas Huetter
# create target folder and change into it
mkdir sentiment
cd sentiment
# The MIT License (MIT)
# Copyright (c) 2017 Thomas Hütter, Mateusz Pawlik.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
# download the data files
# Download the data files.
wget https://nlp.stanford.edu/sentiment/trainDevTestTrees_PTB.zip
# unzip the data into folder original_data
unzip trainDevTestTrees_PTB.zip
# Extract the data into subdirectory.
unzip trainDevTestTrees_PTB.zip -d original_data
# remove zip file
rm -rf trainDevTestTrees_PTB.zip
# Prepare output from 'dev.txt' and 'train.txt':
# - convert dev.txt and train.txt into UTF-8 format
# - replace ( by {
# - replace ) by }
# - remove whitespace before '{'
# - sort by number of nodes (equivalent to number of "{")
iconv -f ISO-8859-1 -t "UTF-8" original_data/trees/dev.txt original_data/trees/train.txt | \
sed -e 's/(/{/g' | sed -e 's/)/}/g' | sed -E 's/[[:space:]]([{])/\1/g' | \
awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > sentiment_sorted.bracket
# change to unzipped folder
cd trees
# prepare data for file L.trees
# convert dev.txt and train.txt into UTF-8 format | replace ( by { | replace ) by } | remove whitespace before '{' | sort by number of nodes (equivalent to number of "{")
iconv -f ISO-8859-1 -t "UTF-8" dev.txt train.txt | sed -e 's/(/{/g' | sed -e 's/)/}/g' | sed -E 's/[[:space:]]([{])/\1/g' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../sentiment_sorted.bracket
# go back to the folder
cd ..
# Tidy up.
rm trainDevTestTrees_PTB.zip
rm -rf original_data
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment