adulau/napkin-text-analysis
1
0
Fork 0
mirror of https://github.com/adulau/napkin-text-analysis.git synced 2024-11-22 01:47:06 +00:00
Code Issues Projects Releases Packages Wiki Activity

new: [output] JSON export added

Browse source
This commit is contained in:
Alexandre Dulaunoy 2020-09-21 07:50:57 +02:00
parent 3c3760019e
commit 3a09abc80c
Signed by: adulau
GPG key ID: 09E2CD4944E6CBCD
1 changed files with 14 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
bin/napkin.py
View file

@ -6,13 +6,14 @@ import spacy
from spacy_langdetect import LanguageDetector from spacy_langdetect import LanguageDetector
import argparse import argparse
import sys import sys
import simplejson as json
parser = argparse.ArgumentParser(description="Extract statistical analysis of text") parser = argparse.ArgumentParser(description="Extract statistical analysis of text")
parser.add_argument('-v', help="verbose output") parser.add_argument('-v', help="verbose output")
parser.add_argument('-f', help="file to analyse") parser.add_argument('-f', help="file to analyse")
parser.add_argument('-t', help="maximum value for the top list (default is 100) -1 is no limit", default=100) parser.add_argument('-t', help="maximum value for the top list (default is 100) -1 is no limit", default=100)
parser.add_argument('-s', help="display the overall statistics (default is False)", default=False, action='store_true') parser.add_argument('-s', help="display the overall statistics (default is False)", default=False, action='store_true')
parser.add_argument('-o', help="output format (default is csv)", default="csv") parser.add_argument('-o', help="output format (default is csv), json", default="csv")
args = parser.parse_args() args = parser.parse_args()
if args.f is None: if args.f is None:
parser.print_help() parser.print_help()
@ -89,13 +90,23 @@ for token in doc:
for entity in doc.ents: for entity in doc.ents:
redisdb.zincrby("labels:napkin", 1, entity.label_) redisdb.zincrby("labels:napkin", 1, entity.label_)
if args.o == "json":
output_json = {"format":"napkin"}
for anal in analysis: for anal in analysis:
x = redisdb.zrevrange(anal, 1, args.t, withscores=True) x = redisdb.zrevrange(anal, 1, args.t, withscores=True)
if args.o == "csv":
print ("# Top {} of {}".format(args.t, anal)) print ("# Top {} of {}".format(args.t, anal))
elif args.o == "json":
output_json.update({anal:[]})
for a in x: for a in x:
if args.o == "csv": if args.o == "csv":
print ("{},{}".format(a[0],a[1])) print ("{},{}".format(a[0],a[1]))
elif args.o == "json":
output_json[anal].append(a)
if args.o == "csv":
print ("#") print ("#")
if args.s: if args.s:
print (redisdb.hgetall('stats')) print (redisdb.hgetall('stats'))
if args.o == "json":
print(json.dumps(output_json))