with open("awards.csv", "w") as out_file:
out_file.write("Org,# of Awards,Total Award Amount\n")
for rec in award_recs:
out_file.write(rec + "," + str(award_recs[rec][0]) + "," + str(award_recs[rec][1]) + "\n")
# Extract abstract ID from filename
abstractID = fileid.replace(".txt", "")
abstractID = re.split("[\/]", abstractID)
abstractID = abstractID[2]
# Reset counter for the number of sentences in the abstract
sent_num = 0
# Find abstract by looping through paragraphs, counting them, and applying the GetAbstract function
para_num = -1
for para in corpus.paras(fileid):
para_num += 1
GetAbstract()
# If the abstract is blank, add 1 to the distribution for 0 sentences
if abstract == []:
if 0 not in sent_dist:
sent_dist[0] = 1
else:
sent_dist[0] += 1
# Loop through each sentence in the abstract
for line in abstract:
# Iterate the sentence counter
sent_num += 1
from TreeTaggerWrapper import treetaggerwrapper
#1) build a TreeTagger wrapper:
tagger = treetaggerwrapper.TreeTagger(TAGLANG='en',TAGDIR='D:/Programme/TreeTagger')
#2) tag your text.
tags = tagger.TagText("This is a very short text to tag.")
#3) use the tags list... (list of string output from TreeTagger).
print tags
# Check, whether the format of the tagged postings is good for the tagged corpus reader
# p.51 NLTK Cookbook
input_directory = path
from nltk.corpus.reader import TaggedCorpusReader
reader = TaggedCorpusReader(input_directory, r'.*\.txt')
reader.words()
# ['The', 'expense', 'and', 'time', 'involved', 'are', ...]
reader.tagged_words()
reader.sents()
reader.tagged_sents()
reader.paras()
reader.tagged_paras()
# testing the import #
#import sys
import myMath
print myMath.add(4,5)
print myMath.division(4, 2)
print myMath.multiply(10, 5)
print myMath.fibonacci(8)
print myMath.squareroot(48)