Skip to content

SINAI / clef-pan2018

Go to a project
Commit 8f96e893 by Arturo Montejo Ráez
Options

classify_comp working on tira.io

parent 1df9d9e2
Inline Side-by-side
Showing with 295 additions and 136 deletions
.gitignore 0 → 100644
__pycache__
ComplexityEnglish.py
import sys
sys.path.append('/home/garciacumbreras18/dist/freeling/APIs/python')
from ComplexityLanguage import ComplexityLanguage
import re
import math
......@@ -179,4 +181,4 @@ class ComplexityEnglish(ComplexityLanguage):
return metrics
\ No newline at end of file
ComplexityFrench.py
import sys
sys.path.append('/home/garciacumbreras18/dist/freeling/APIs/python')
from ComplexityLanguage import ComplexityLanguage
import freeling
import os
......@@ -15,9 +17,9 @@ class ComplexityFrench(ComplexityLanguage):
ComplexityLanguage.__init__(self, lang)
## Modify this line to be your FreeLing installation directory
FREELINGDIR = "/usr/local"
DATA = FREELINGDIR+"/share/freeling/"
CLASSDIR = "/home/sinai/Experiments/CLEF-PAN/"
FREELINGDIR = "/home/garciacumbreras18/dist/freeling"
DATA = FREELINGDIR+"/data/"
CLASSDIR = ""
self.lang = lang
freeling.util_init_locale("default")
......@@ -50,12 +52,8 @@ class ComplexityFrench(ComplexityLanguage):
self.tg=freeling.hmm_tagger(DATA+lang+"/tagger.dat",True,2)
self.sen=freeling.senses(DATA+lang+"/senses.dat")
#Listas de palabras de Dale-Chall
CLASSDIR = "/home/sinai/Experiments/CLEF-PAN/"
f = open(CLASSDIR + 'DaleChall.txt')
f = open(CLASSDIR + '/home/garciacumbreras18/DaleChall.txt')
lines = f.readlines()
f.close()
......@@ -143,4 +141,4 @@ class ComplexityFrench(ComplexityLanguage):
return metrics
\ No newline at end of file
ComplexityItalian.py
# -*- coding: utf-8 -*-
import sys
sys.path.append('/home/garciacumbreras18/dist/freeling/APIs/python')
import freeling
import os
import re
......@@ -12,9 +14,9 @@ class ComplexityItalian():
def __init__(self, lang = 'it'):
## Modify this line to be your FreeLing installation directory
FREELINGDIR = "/usr/local"
DATA = FREELINGDIR+"/share/freeling/"
CLASSDIR = "/home/sinai/Experiments/CLEF-PAN/"
FREELINGDIR = "/home/garciacumbreras18/dist/freeling"
DATA = FREELINGDIR+"/data/"
self.DATA = DATA
self.lang = lang
freeling.util_init_locale("default")
......@@ -279,4 +281,4 @@ class ComplexityItalian():
\ No newline at end of file
ComplexityLanguage.py
# -*- coding: utf-8 -*-
import sys
sys.path.append('/home/garciacumbreras18/dist/freeling/APIs/python')
import freeling
import os
import re
......@@ -8,14 +12,14 @@ import scipy.stats
import math
class ComplexityLanguage():
def __init__(self, lang):
## Modify this line to be your FreeLing installation directory
FREELINGDIR = "/usr/local"
DATA = FREELINGDIR+"/share/freeling/"
FREELINGDIR = "/home/garciacumbreras18/dist/freeling"
DATA = FREELINGDIR+"/data/"
self.DATA = DATA
self.lang = lang
freeling.util_init_locale("default")
......@@ -24,49 +28,49 @@ class ComplexityLanguage():
# create options set for maco analyzer. Default values are Ok, except for data files.
op= freeling.maco_options(lang)
op.set_data_files( "",
op.set_data_files( "",
self.DATA + "common/punct.dat",
self.DATA + self.lang + "/dicc.src",
self.DATA + self.lang + "/afixos.dat",
"",
self.DATA + self.lang + "/locucions.dat",
self.DATA + self.lang + "/locucions.dat",
self.DATA + self.lang + "/np.dat",
self.DATA + self.lang + "/quantities.dat",
self.DATA + self.lang + "/probabilitats.dat")
# create analyzers
self.tk=freeling.tokenizer(self.DATA+self.lang+"/tokenizer.dat")
#self.sp=freeling.splitter("/home/sinai/Freeling/data/"+self.lang+"/splitter.dat")
self.sp=freeling.splitter(self.DATA+self.lang+"/splitter.dat")
#self.sp=freeling.splitter("/home/sinai/Freeling/data/"+self.lang+"/splitter.dat")
self.sp=freeling.splitter(self.DATA+self.lang+"/splitter.dat")
self.mf=freeling.maco(op)
# activate mmorpho modules to be used in next call
self.mf.set_active_options(False, True, True, True, # select which among created
True, True, False, True, # submodules are to be used.
True, True, True, True ) # default: all created submodules are used
self.mf.set_active_options(False, True, True, True, # select which among created
True, True, False, True, # submodules are to be used.
True, True, True, True ) # default: all created submodules are used
# create tagger, sense anotator, and parsers
self.tg=freeling.hmm_tagger(self.DATA+self.lang+"/tagger.dat",True,2)
self.sen=freeling.senses(self.DATA+self.lang+"/senses.dat")
#self.parser= freeling.chart_parser(DATA+lang+"/chunker/grammar-chunk.dat")
#self.dep=freeling.dep_txala(DATA+lang+"/dep_txala/dependences.dat", self.parser.get_start_symbol())
"""
"""
config es una lista de valores booleanos que activa o desactivan el cálculo de una medida
config = [
True|False, # PUNCTUATION MARKS
True|False, # SCI
True|False, # ARI
True|False, # ARI
True|False, # MU
]
Si config == None se calculan todas las métricas de complejidad soportadas
"""
self.config = [True, True, True, True]
self.metricsStr = ['AVERAGE PUNCTUATION MARKS', 'SCI', 'ARI', 'MU']
pass
def textProcessing(self, text):
text = text.replace(u'\xa0', u' ').replace('"', '')
# meter todas las funciones en una patron de los tokens válidos
......@@ -86,9 +90,9 @@ class ComplexityLanguage():
#ls = self.dep.analyze(ls)
#print("After dependencies", len(ls))
self.sentences = ls
self.N_sentences = len(ls)
self.N_sentences = len(ls)
self.sp.close_session(sid)
#print('Las oraciones: ', self.sentences)
'''
Filtra aquellos tokens que no sean adjetivos, verbos o sustantivos
......@@ -97,11 +101,11 @@ class ComplexityLanguage():
for sentence in self.sentences:
ws = sentence.get_words();
pos_content_sentences.append([w for w in ws if re.match('N.*|V.*|A.*', w.get_tag())])
self.pos_content_sentences = pos_content_sentences
return self.pos_content_sentences, self.sentences, self.N_sentences
self.pos_content_sentences = pos_content_sentences
return self.pos_content_sentences, self.sentences, self.N_sentences
def punctuationMarks(self):
#Solo nos interesa contar los tokens que sean signo de puntuación.
#Number of words.
......@@ -114,10 +118,10 @@ class ComplexityLanguage():
else:
lwords.append(w.get_form())
self.N_words = len(lwords)
#print('Number of words (N_w): ', self.N_words, '\n' )
self.N_punctuation = len(punctuation)
self.punctuation = punctuation
......@@ -125,14 +129,14 @@ class ComplexityLanguage():
punctuation_over_words = 0
else:
punctuation_over_words = self.N_punctuation / self.N_words
self.punctuation_over_words = punctuation_over_words
#print("PUNCTUATION MARKS = ", self.N_punctuation,'\n')
return self.punctuation_over_words, self.N_punctuation, self.punctuation, self.N_words
def sentenceComplexity(self):
#Number of complex sentences
N_cs = 0
for sentence in self.sentences:
......@@ -149,25 +153,25 @@ class ComplexityLanguage():
else:
previous_is_verb = False
if count>0:
N_cs += 1
N_cs += 1
self.N_cs = N_cs
#print("Number of complex sentences: ", self.N_cs, "\n")
ASL = self.N_words / self.N_sentences
self.ASL = ASL
#print("Average Sentence Length (ASL) = ", self.ASL, '\n')
CS = self.N_cs / self.N_sentences
self.CS = CS
#print("Complex Sentences (CS) = ", self.CS, '\n')
SCI = (ASL + CS)/ 2
self.SCI = SCI
#print("SENTENCE COMPLEXITY INDEX:(SCI) = ", self.SCI, "\n")
return self.SCI, self.CS, self.N_cs, self.ASL
return self.SCI, self.CS, self.N_cs, self.ASL
def autoReadability(self):
#Number of characters
count = 0
......@@ -178,24 +182,24 @@ class ComplexityLanguage():
count +=1
else:
listwords.append(w.get_form())
self.listwords = listwords
self.listwords = listwords
N_charac = 0
for characters in self.listwords:
N_charac += len(characters)
self.N_charac = N_charac
#print("Number of characters: ", self.N_charac, "\n")
ARI = 4.71 * self.N_charac / self.N_words + 0.5 * self.N_words / self.N_sentences - 21.43
self.ARI = ARI
#print("AUTOMATED READABILITY INDEX (ARI) = ", self.ARI, '\n')
return self.ARI, self.N_charac, self.listwords
return self.ARI, self.N_charac, self.listwords
def mureadability(self):
#Number of syllables and Number of words with 3 or more syllables:tagger
N_syllables = 0
N_syllables3 = 0
......@@ -207,10 +211,10 @@ class ComplexityLanguage():
count+=1
if count>=3:
N_syllables3 += 1
self.N_syllables = N_syllables
self.N_syllables3 = N_syllables3
#Number of letters
N_letters= 0
letters = []
......@@ -220,33 +224,33 @@ class ComplexityLanguage():
letters.append(word)
N_letters+=len(word)
vecletters.append(len(word))
self.letters = letters
self.N_letters = N_letters
self.vecletters = vecletters
x=self.N_letters / self.N_words
varianza=np.var(self.vecletters)
mu = (self.N_words /(self.N_words-1))*(x/varianza)*100
#print("READABILITY MU: ", mu, "\n")
self.mu = mu
return self.mu, self.N_syllables, self.N_syllables3, self.letters, self.N_letters, self.vecletters
def calcMetrics(self, text):
"""
Calcula la métricas de complejidad activadas en la configuración
"""
"""
Calcula la métricas de complejidad activadas en la configuración
"""
self.textProcessing(text)
metrics = {}
punctuationMarks = None
autoreadability = None
sentencecomplexity = None
for i in range(0, len(self.metricsStr)):
if self.config == None or self.config[i] and self.metricsStr[i] == 'AVERAGE PUNCTUATION MARKS':
punctuationmarks = self.punctuationMarks()
metrics['AVERAGE PUNCTUATION MARKS'] = punctuationmarks[0]
......@@ -259,9 +263,9 @@ class ComplexityLanguage():
if self.config == None or self.config[i] and self.metricsStr[i] == 'MU':
mureadability = self. mureadability()
metrics['MU'] = mureadability[0]
return metrics
return metrics
def getPOS(self, text):
self.textProcessing(text)
pos_sentences = []
......@@ -270,6 +274,5 @@ class ComplexityLanguage():
pos_sentences.append([w.get_tag() for w in ws])
#print('POS',pos_sentences)
self.pos_sentences = pos_sentences
return self.pos_sentences
\ No newline at end of file
ComplexitySpanish.py
......@@ -17,7 +17,7 @@ class ComplexitySpanish(ComplexityLanguage):
self.dep=freeling.dep_txala(self.DATA+self.lang+"/dep_txala/dependences.dat", self.parser.get_start_symbol())
# Para leer el texto que introducimos
CLASSDIR = "/home/sinai/Experiments/CLEF-PAN/"
CLASSDIR = "/home/garciacumbreras18/"
f = open(CLASSDIR + 'CREA_total.txt')
lines = f.readlines()
......@@ -300,4 +300,4 @@ class ComplexitySpanish(ComplexityLanguage):
metrics['CRAWFORD'] = self.yearsCrawford()
return metrics
\ No newline at end of file
classify_comp deleted 100755 → 0
#!/usr/bin/python3
#/usr/bin/env python
# -*- coding: utf-8 -*-
# Authors:
# Rocío López-Anguita (rlanguit@ujaen.es)
# Arturo Montejo-Ráez (amontejo@ujaen.es)
# Centro de Estudios Avanzados en TIC (CEATIC)
# Universidad de Jaén
# 2018
import json
import os
from ComplexityLanguage import ComplexityLanguage
from ComplexitySpanish import ComplexitySpanish
from ComplexityEnglish import ComplexityEnglish
from ComplexityFrench import ComplexityFrench
from ComplexityPolish import ComplexityPolish
from ComplexityItalian import ComplexityItalian
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn.decomposition import PCA
from sklearn import preprocessing
import argparse
parser = argparse.ArgumentParser(description='PAN2018 author identificator based on text complexity metrics')
parser.add_argument('-i', type=string, help='input directory')
parser.add_argument('-o', type=string, help='output directory')
args = parser.parse_args()
print(args.i, args.o)
exit()
print('Loading complexity analyzers for different languages...\n', flush=True)
mlComplexityText = {
'en': ComplexityEnglish(),
'sp': ComplexitySpanish(),
'fr': ComplexityFrench(),
'pl': ComplexityPolish(),
'it': ComplexityItalian()
}
INPUT_DIR = args.i
OUTPUT_DIR = args.o
with open(INPUT_DIR+'/collection-info.json', 'r') as f:
collectionInfo = json.load(f)
f.close()
print(type(collectionInfo))
\ No newline at end of file
classify_comp.py 0 → 100755
#!/home/garciacumbreras18/anaconda3/bin/python3
#/usr/bin/env python
# -*- coding: utf-8 -*-
###############################################################################
# Authors:
# Rocío López-Anguita (rlanguit@ujaen.es)
# Arturo Montejo-Ráez (amontejo@ujaen.es)
# Centro de Estudios Avanzados en TIC (CEATIC)
#
# Universidad de Jaén - 2018
###############################################################################
import json
import os
from ComplexityLanguage import ComplexityLanguage
from ComplexitySpanish import ComplexitySpanish
from ComplexityEnglish import ComplexityEnglish
from ComplexityFrench import ComplexityFrench
from ComplexityPolish import ComplexityPolish
from ComplexityItalian import ComplexityItalian
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn.decomposition import PCA
from sklearn import preprocessing
import argparse
## ----------------------------------------------------------------------------
##
## Read command lines arguments
##
parser = argparse.ArgumentParser(description='PAN2018 author identificator based on text complexity metrics')
parser.add_argument('-i', type=str, help='input directory')
parser.add_argument('-o', type=str, help='output directory')
args = parser.parse_args()
INPUT_DIR, OUTPUT_DIR = args.i, args.o
## ----------------------------------------------------------------------------
##
## Load of analyzers
##
print('Loading complexity analyzers for different languages...\n', flush=True)
mlComplexityText = {
'en': ComplexityEnglish(),
'sp': ComplexitySpanish(),
'fr': ComplexityFrench(),
'pl': ComplexityPolish(),
'it': ComplexityItalian()
}
## ----------------------------------------------------------------------------
##
## Corpus loading (both, train and test data sets)
##
complexity_known = pd.DataFrame()
complexity_unknown = pd.DataFrame()
labels = {}
labels_cand = []
#
# Recorremos todos los problemas
#
print('Loading collection-info.json file from', args.i, flush=True)
with open(INPUT_DIR+'/collection-info.json', 'r') as f:
collectionInfo = json.load(f)
f.close()
for problem in collectionInfo:
print('\n\nProblem: ', problem['problem-name'], flush=True)
print('Language: ', problem['language'], flush=True)
#
# Cargamos la clase para el cálculo de la complejidad del idioma correspondiente
#
complexityText = mlComplexityText[problem['language']]
#
# Recorremos todos los candidatos
#
print("Loading problem data...\n", flush=True)
with open(INPUT_DIR + '/' + problem['problem-name'] + '/problem-info.json', 'r') as problem_info_fhd:
problem_info= json.load(problem_info_fhd)
problem_info_fhd.close()
#
# Leemos los textos de autoría conocida (TEXTOS DE ENTRENAMIENTO)
#
print("Loading training data")
for candidate in problem_info['candidate-authors']:
print('Candidate: ', candidate['author-name'], flush=True)
files = os.listdir(os.path.join(INPUT_DIR, problem['problem-name'], candidate['author-name']))
probcand = problem['problem-name'] + candidate['author-name']
if not probcand in labels:
labels[probcand] = len(labels)
labels_cand += [probcand]
#
# Procesamos todo los textos de ese candidato
#
for i, nameFile in enumerate(files):
print('Reading text file: ', nameFile, flush=True)
with open(os.path.join(os.path.join(INPUT_DIR,problem['problem-name'], candidate['author-name']), nameFile),'r') as context:
calcmetrics = complexityText.calcMetrics(context.read())
dfi = pd.DataFrame(calcmetrics, index=[i])
dfi['problem'] = problem['problem-name']
dfi['language'] = problem['language']
dfi['candidate'] = candidate['author-name']
dfi['label'] = labels[probcand]
dfi['filename'] = nameFile
complexity_known = complexity_known.append([dfi])
#
# Si existe ground-truth, lo leemos para conocer los candidatos
#
unknown_candidates = False
if os.path.isfile(INPUT_DIR +'/'+ problem['problem-name'] + '/ground-truth.json'):
print("Reading ground truth...", flush=True)
with open(INPUT_DIR +'/'+ problem['problem-name'] + '/ground-truth.json', 'r') as ground_truth_fhd:
ground_truth = json.load(ground_truth_fhd)
ground_truth_fhd.close()
unknown_candidates = {}
for item in ground_truth['ground_truth']:
unknown_candidates[item['unknown-text']] = item['true-author']
#
# Recorremos archivos sin etiquetar (TEXTOS DE TEST)
#
print("Loading test data", flush=True)
for i, unknown_file in enumerate(os.listdir(os.path.join(INPUT_DIR, problem['problem-name'], problem_info['unknown-folder']))):
print("Analyzing file", unknown_file, flush=True)
with open(INPUT_DIR + '/' + problem['problem-name'] + '/' + problem_info['unknown-folder'] + '/' + unknown_file, 'r') as unknown_fhd:
calcmetrics = complexityText.calcMetrics(unknown_fhd.read())
unknown_fhd.close()
dfi = pd.DataFrame(calcmetrics, index=[i])
dfi['problem'] = problem['problem-name']
dfi['language'] = problem['language']
if unknown_candidates and unknown_candidates[unknown_file]:
probcand = problem['problem-name'] + unknown_candidates[unknown_file]
dfi['candidate'] = unknown_candidates[unknown_file]
dfi['label'] = labels[probcand]
else:
dfi['candidate'] = None
dfi['label'] = None
dfi['filename'] = unknown_file
complexity_unknown = complexity_unknown.append([dfi])
## ----------------------------------------------------------------------------
##
## Training and classification
##
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
from sklearn import svm
clf = svm.LinearSVC(C=1)
for problem in set(complexity_known['problem']):
answers = []
print('------- Training and classifying ', problem, flush=True)
#
# Para el train cogemos los textos conocidos
#
train = complexity_known.loc[complexity_known['problem'] == problem]
train = train.dropna(axis=1, how='any')
train_target = train['label']
train_data= train.drop(['problem', 'language', 'candidate', 'filename', 'label'], axis=1)
train_data = pd.DataFrame(preprocessing.normalize(train_data, norm='l2'))
#
# Para el test cogemos los textos desconocidos
#
test = complexity_unknown.loc[complexity_unknown['problem'] == problem]
test = test.dropna(axis=1, how='any')
test_target = test['label']
test_data = test.drop(['problem', 'language', 'candidate', 'filename', 'label'], axis=1)
test_data = pd.DataFrame(preprocessing.normalize(test_data, norm='l2'))
#Entrenamos con los textos con candidatos conocidos y predecimos con los datos desconocidos
y_pred = clf.fit(train_data, train_target).predict(test_data)
for index, row in test.iterrows():
probcand = labels_cand[y_pred[index]]
answers.append({
'unknown-text': row['filename'],
'predicted-author': probcand[probcand.find("candidate"):],
})
with open(OUTPUT_DIR + '/answers-' + problem +'.json', 'w') as file:
json.dump(answers, file, indent=4)
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 sign in to comment