mirror of
https://github.com/adulau/napkin-text-analysis.git
synced 2024-11-21 09:27:07 +00:00
chg: [cli] black the napkin binary
This commit is contained in:
parent
a2a074436e
commit
8541ae3192
GPG key ID:
09E2CD4944E6CBCD
1 changed files with 198 additions and 107 deletions
143
bin/napkin.py
143
bin/napkin.py
|
|
@ -15,21 +15,78 @@ version = "0.9"
|
|||
parser = argparse.ArgumentParser(description="Extract statistical analysis of text")
|
||||
parser.add_argument('-v', help="verbose output")
|
||||
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('-s', help="display the overall statistics (default is False)", default=False, action='store_true')
|
||||
parser.add_argument('-o', help="output format (default is csv), json, readable", default="csv")
|
||||
parser.add_argument('-l', help="language used for the analysis (default is en)", default="en")
|
||||
parser.add_argument('-i', help="Use stdin instead of a filename", default=False, action='store_true')
|
||||
parser.add_argument('--verbatim', help="Don't use the lemmatized form, use verbatim. (default is the lematized form)", default=False, action='store_true')
|
||||
parser.add_argument('--no-flushdb', help="Don't flush the redisdb, useful when you want to process multiple files and aggregate the results. (by default the redis database is flushed at each run)", default=False, action='store_true')
|
||||
parser.add_argument('--binary', help="set output in binary instead of UTF-8 (default)", default=False, action='store_true')
|
||||
parser.add_argument('--analysis', help="Limit output to a specific analysis (verb, noun, hashtag, mention, digit, url, oov, labels, punct). (Default is all analysis are displayed)", default='all')
|
||||
parser.add_argument('--disable-parser', help="disable parser component in Spacy", default=False, action='store_true')
|
||||
parser.add_argument('--disable-tagger', help="disable tagger component in Spacy", default=False, action='store_true')
|
||||
parser.add_argument('--token-span', default= None, help='Find the sentences where a specific token is located')
|
||||
parser.add_argument('--table-format', help="set tabulate format (default is fancy_grid)", default="fancy_grid")
|
||||
parser.add_argument('--full-labels', help="store each label value in a ranked set (default is False)", action='store_true', default=False)
|
||||
#parser.add_argument('--geolocation', help="export geolocation (default is False)", action='store_true', default=False)
|
||||
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(
|
||||
'-o', help="output format (default is csv), json, readable", default="csv"
|
||||
)
|
||||
parser.add_argument(
|
||||
'-l', help="language used for the analysis (default is en)", default="en"
|
||||
)
|
||||
parser.add_argument(
|
||||
'-i', help="Use stdin instead of a filename", default=False, action='store_true'
|
||||
)
|
||||
parser.add_argument(
|
||||
'--verbatim',
|
||||
help="Don't use the lemmatized form, use verbatim. (default is the lematized form)",
|
||||
default=False,
|
||||
action='store_true',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--no-flushdb',
|
||||
help="Don't flush the redisdb, useful when you want to process multiple files and aggregate the results. (by default the redis database is flushed at each run)",
|
||||
default=False,
|
||||
action='store_true',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--binary',
|
||||
help="set output in binary instead of UTF-8 (default)",
|
||||
default=False,
|
||||
action='store_true',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--analysis',
|
||||
help="Limit output to a specific analysis (verb, noun, hashtag, mention, digit, url, oov, labels, punct). (Default is all analysis are displayed)",
|
||||
default='all',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--disable-parser',
|
||||
help="disable parser component in Spacy",
|
||||
default=False,
|
||||
action='store_true',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--disable-tagger',
|
||||
help="disable tagger component in Spacy",
|
||||
default=False,
|
||||
action='store_true',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--token-span',
|
||||
default=None,
|
||||
help='Find the sentences where a specific token is located',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--table-format',
|
||||
help="set tabulate format (default is fancy_grid)",
|
||||
default="fancy_grid",
|
||||
)
|
||||
parser.add_argument(
|
||||
'--full-labels',
|
||||
help="store each label value in a ranked set (default is False)",
|
||||
action='store_true',
|
||||
default=False,
|
||||
)
|
||||
# parser.add_argument('--geolocation', help="export geolocation (default is False)", action='store_true', default=False)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
|
|
@ -37,11 +94,13 @@ if args.f is None and not args.i:
|
|||
parser.print_help()
|
||||
sys.exit()
|
||||
|
||||
#if args.geolocation:
|
||||
# if args.geolocation:
|
||||
# args.full_labels = True
|
||||
|
||||
if not args.binary:
|
||||
redisdb = redis.Redis(host="localhost", port=6379, db=5, encoding='utf-8', decode_responses=True)
|
||||
redisdb = redis.Redis(
|
||||
host="localhost", port=6379, db=5, encoding='utf-8', decode_responses=True
|
||||
)
|
||||
else:
|
||||
redisdb = redis.Redis(host="localhost", port=6379, db=5)
|
||||
|
||||
|
|
@ -61,7 +120,7 @@ if args.disable_tagger:
|
|||
disable.append("tagger")
|
||||
|
||||
if args.l == "fr":
|
||||
try :
|
||||
try:
|
||||
nlp = spacy.load("fr_core_news_md", disable=disable)
|
||||
except:
|
||||
print("Downloading missing model")
|
||||
|
|
@ -90,20 +149,52 @@ if args.i:
|
|||
|
||||
detect_lang = cld3.get_language(text)
|
||||
if detect_lang[0] != args.l:
|
||||
sys.exit("Language detected ({}) is different than the NLP used ({})".format(detect_lang[0], args.l))
|
||||
sys.exit(
|
||||
"Language detected ({}) is different than the NLP used ({})".format(
|
||||
detect_lang[0], args.l
|
||||
)
|
||||
)
|
||||
|
||||
doc = nlp(text)
|
||||
|
||||
analysis = ["verb", "noun", "hashtag", "mention",
|
||||
"digit", "url", "oov", "labels",
|
||||
"punct", "email"]
|
||||
analysis = [
|
||||
"verb",
|
||||
"noun",
|
||||
"hashtag",
|
||||
"mention",
|
||||
"digit",
|
||||
"url",
|
||||
"oov",
|
||||
"labels",
|
||||
"punct",
|
||||
"email",
|
||||
]
|
||||
|
||||
if args.token_span and not disable:
|
||||
analysis.append("span")
|
||||
|
||||
redisdb.hset("stats", "token", doc.__len__())
|
||||
|
||||
labels = [ "EVENT", "PERCENT", "MONEY", "FAC", "TIME", "QUANTITY", "WORK_OF_ART", "LANGUAGE", "PRODUCT", "LOC", "LAW", "DATE", "ORDINAL", "NORP", "ORG", "CARDINAL", "GPE", "PERSON"]
|
||||
labels = [
|
||||
"EVENT",
|
||||
"PERCENT",
|
||||
"MONEY",
|
||||
"FAC",
|
||||
"TIME",
|
||||
"QUANTITY",
|
||||
"WORK_OF_ART",
|
||||
"LANGUAGE",
|
||||
"PRODUCT",
|
||||
"LOC",
|
||||
"LAW",
|
||||
"DATE",
|
||||
"ORDINAL",
|
||||
"NORP",
|
||||
"ORG",
|
||||
"CARDINAL",
|
||||
"GPE",
|
||||
"PERSON",
|
||||
]
|
||||
|
||||
for entity in doc.ents:
|
||||
redisdb.zincrby("labels", 1, entity.label_)
|
||||
|
|
@ -165,7 +256,7 @@ for token in doc:
|
|||
|
||||
|
||||
if args.o == "json":
|
||||
output_json = {"format":"napkin", "version": version}
|
||||
output_json = {"format": "napkin", "version": version}
|
||||
for anal in analysis:
|
||||
more_info = ""
|
||||
if args.analysis == "all" or args.analysis == anal:
|
||||
|
|
@ -183,10 +274,10 @@ for anal in analysis:
|
|||
header = ["\033[1mTop {} of {} {}\033[0m".format(args.t, anal, more_info)]
|
||||
readable_table = []
|
||||
elif args.o == "json":
|
||||
output_json.update({anal:[]})
|
||||
output_json.update({anal: []})
|
||||
for a in x:
|
||||
if args.o == "csv":
|
||||
print("{},{},{}".format(anal,a[0],a[1]))
|
||||
print("{},{},{}".format(anal, a[0], a[1]))
|
||||
elif args.o == "readable":
|
||||
if previous_value == a[1]:
|
||||
readable_table.append(["{}".format(a[0])])
|
||||
|
|
|
|||
Loading…
Reference in a new issue