def plot_reference_summary_no_distribution():
import collections
C = {}
M = 0
for cid in ['Engineer', 'IE256', 'IE256_2016', 'CS0445']:
support_file = '../data/%s_supporters.txt'%cid
supports = fio.LoadDictJson(support_file)
M = max(M, max(supports))
C[cid] = collections.Counter(supports)
for cid in ['Engineer', 'IE256', 'IE256_2016', 'CS0445']:
del C[cid][0]
A = {}
for i in range(1, M+1):
for cid in ['Engineer', 'IE256', 'IE256_2016', 'CS0445']:
if cid not in A:
A[cid] = collections.defaultdict(float)
r = C[cid][i]*1.0/sum(C[cid].values()) if i in C[cid] else 0
A[cid][i] += r + A[cid][i-1]
for i in range(1, M+1):
for cid in ['Engineer', 'IE256', 'IE256_2016', 'CS0445']:
print A[cid][i], '\t',
print
def combine_files(lectures, features=None, prompts=['q1', 'q2']):
phrasedir1 = '../data/%s/oracle_annotator_1/phrase/' % course
phrasedir2 = '../data/%s/oracle_annotator_2/phrase/' % course
X = []
Y = []
if features == None:
sim_extractor = Similarity()
features = sorted(sim_extractor.features.keys())
for i, lec in enumerate(lectures):
for q in prompts:
for phrasedir in [phrasedir1, phrasedir2]:
path = phrasedir + str(lec) + '/'
filename = os.path.join(path, q + sim_exe)
data = fio.LoadDictJson(filename)
for fdict, score, _ in data:
row = []
for name in features:
x = fdict[name]
if str(x) == 'nan':
x = 0.0
row.append(x)
X.append(row)
Y.append(score)
return X, Y
def PrintClusterRankSummary(datadir):
sheets = range(0,maxWeek)
lectures = fio.LoadDictJson('../data/CourseMIRROR/lectures.json')
head = ['week', 'data', 'Point of Interest', "Muddiest Point"]
body = []
for i, sheet in enumerate(sheets):
row = []
week = i + 1
row.append(week)
row.append(getDate(lectures, course, week))
for type in ['q1', 'q2', 'q3', 'q4']:
path = datadir + str(i+1)+ '/'
summaryfile = path + type + '.summary'
if not fio.IsExist(summaryfile): continue
summaries = [line.strip() for line in fio.ReadFile(summaryfile)]
sourcefile = path + type + '.summary.source'
sources = [line.split(',') for line in fio.ReadFile(sourcefile)]
combinedSummary = []
for j, (summary, source) in enumerate(zip(summaries, sources)):
summary = summary.replace('"', '\'')
combinedSummary.append(str(j+1) + ") " + summary + " [" + str(len(source)) + "]")
row.append('"' + chr(10).join(combinedSummary)+ '"')
body.append(row)
fio.WriteMatrix(datadir + "summary.txt", body, head)
def correlation_analysis(course):
phrasedir1 = '../data/%s/oracle_annotator_1/phrase/' % course
phrasedir2 = '../data/%s/oracle_annotator_2/phrase/' % course
outdir = '../data/%s/simlearning/' % course
fio.NewPath(outdir)
sim_extractor = Similarity()
features = sorted(sim_extractor.features.keys())
head = features + ['score', 'predict']
body = []
lectures = annotation.Lectures
name = '_'.join(features)
for i, lec in enumerate(lectures):
model_file = os.path.join(model_dir, '%d_%s.model' % (lec, name))
with open(model_file, 'rb') as handle:
clf = pickle.load(handle)
for q in ['q1', 'q2']:
outfile = os.path.join(outdir, str(lec), '%s%s' % (q, sim_exe))
for phrasedir in [phrasedir1, phrasedir2]:
path = phrasedir + str(lec) + '/'
filename = os.path.join(path, q + sim_exe)
data = fio.LoadDictJson(filename)
for fdict, score, _ in data:
row = []
for fname in features:
x = fdict[fname]
if str(x) == 'nan':
x = 0.0
row.append(x)
predict_score = clf.predict([row])
row.append(score)
row.append(predict_score[0])
body.append(row)
out_correlation = os.path.join(outdir, 'data.txt')
print out_correlation
fio.WriteMatrix(out_correlation, body, head)
def check_stopword():
from CourseMirror_Survey import stopwords
vocab = fio.LoadDictJson(global_params.vocab)
for word, count in vocab.items():
if count < 5: continue
if word in stopwords:
print word, '\t', count
def correlation_analysis_noduplicate():
phrasedir1 = '../data/%s/oracle_annotator_1/phrase/' % course
phrasedir2 = '../data/%s/oracle_annotator_2/phrase/' % course
outdir = '../data/%s/simlearning/' % course
fio.NewPath(outdir)
sim_extractor = Similarity()
features = sorted(sim_extractor.features.keys())
head = features + ['score']
body = []
lectures = annotation.Lectures
for i, lec in enumerate(lectures):
for q in ['q1', 'q2']:
outfile = os.path.join(outdir, str(lec), '%s%s' % (q, sim_exe))
for phrasedir in [phrasedir1, phrasedir2]:
path = phrasedir + str(lec) + '/'
filename = os.path.join(path, q + sim_exe)
data = fio.LoadDictJson(filename)
for fdict, score, pd in data:
if pd['p1'] == pd['p2']:
print pd['p1']
continue
row = []
for name in features:
x = fdict[name]
if str(x) == 'nan':
x = 0.0
row.append(x)
row.append(score)
body.append(row)
out_correlation = os.path.join(outdir, 'data.txt')
fio.WriteMatrix(out_correlation, body, head)
def __init__(self, key_prefix, sum_prefix, N):
'''
N is number of annotators
'''
self.key_prefix = key_prefix
self.sum_prefix = sum_prefix
self.N = N
#load phrase color map
phrasefile = key_prefix + phrase_exe
phrases = fio.LoadList(phrasefile)
colorfile = key_prefix + color_exe
color_map = fio.LoadDictJson(colorfile)
phrase_color_map = self.combine_phrase_color(phrases, color_map)
#get phrase summary color map
sumfile = sum_prefix + sum_exe
summaries = fio.LoadList(sumfile)
self.summary_color = self.get_summary_color(summaries, phrase_color_map)
#get summary count
sumcountfile = sum_prefix + sum_count_exe
self.summary_no = [int(x) for x in fio.LoadList(sumcountfile)]
assert(len(self.summary_color) == len(self.summary_no))
#load human_summary color map
self.ref_color = []
for i in range(N):
d = {}
ref_sumcolor_file = '%s%s.%d.color'%(sum_prefix, ref_exe, i)
ref_sumno_file = '%s%s.%d.no'%(sum_prefix, ref_exe, i)
for color, no in zip(fio.LoadList(ref_sumcolor_file), fio.LoadList(ref_sumno_file)):
d[int(color)] = int(no)
self.ref_color.append(d)
def __init__(self, prefix=""):
self.features = {
'optimumComparerLSATasa': self.LSA,
'LexicalOverlap': self.LexicalOverlap,
'optimumComparerWNLin': self.LIN,
'BLEU': self.BLEU,
'ROUGE': self.ROUGE,
'Cosine': self.Cosine,
'WordEmbedding': self.WordEmbedding,
#'WMD': self.WMD,
}
self.prefix = prefix
self.Cache = {}
self.cachefile = os.path.join(prefix + 'cache.json')
print self.cachefile
if fio.IsExist(self.cachefile):
with open(self.cachefile, 'r') as fin:
self.Cache = json.load(fin)
if self.prefix != '':
self.matrixdict = {}
for sim in [
'optimumComparerLSATasa', 'LexicalOverlap',
'optimumComparerWNLin', 'BLEU'
]:
self.matrixdict[sim] = {}
filename = self.prefix + sim
phrases, matrix = fio.ReadMatrix(filename, hasHead=True)
index = {}
for i, p in enumerate(phrases):
index[p] = i
self.matrixdict[sim]['index'] = index
self.matrixdict[sim]['matrix'] = matrix
self.word2vec = fio.LoadDictJson(global_params.word2vec_model)
def loadmodel(modelbin, vocabjson, output):
vocab = fio.LoadDictJson(vocabjson)
word_vecs = load_bin_vec(modelbin, vocab)
fio.SaveDict2Json(word_vecs, output)
def run(self, cid, summarylastlecture=False):
max_lecture = 30
# max_lecture = self.get_max_lecture_num(cid)
# print "max_lecture", max_lecture
# #get reflections
# reflections = self.get_reflections(cid)
jsonfile = '../data/CourseMIRROR/reflections.json'
# with open(jsonfile, 'w') as outfile:
# json.dump(reflections, outfile, encoding='utf-8', indent=2)
#
reflections = fio.LoadDictJson(jsonfile)
#get lectures
lectures = self.get_lectures(cid)
jsonfile = '../data/CourseMIRROR/lectures.json'
with open(jsonfile, 'w') as outfile:
json.dump(lectures, outfile, encoding='utf-8', indent=2)
self.N = len(reflections['results'])
print "total number of reflections:", self.N
if self.N == self.old_N: #no need to summary
return
self.old_N = self.N
#run senna
# os.system('python CourseMirror_Survey.py ' + str(cid) + ' ' + str(max_lecture))
#
# cmd = 'cmd /C "runSennaCourseMirror.bat '+str(cid)+ ' ' + str(max_lecture) + '"'
# os.system(cmd)
#
#
# cmd = 'python QPS_extraction.py %s %d %s %s %s'%(cid, max_lecture, self.system, str(self.method), 'N')
# os.system(cmd)
# cmd = 'python QPS_prepare.py ' + str(cid) + ' ' + str(max_lecture) + ' ' + str(self.system) + ' ' + str(self.method)
# os.system(cmd)
#
# #. get PhraseMead input (CourseMirror_MeadPhrase.py)
# cmd = 'python CourseMirror_MeadPhrase.py ' + str(cid) + ' ' + str(max_lecture) + ' ' + str(self.system) + ' ' + str(self.method)
# print cmd
# os.system(cmd)
# #
# olddir = os.path.dirname(os.path.realpath(__file__))
#
# # . get PhraseMead output
# meaddir = global_params.meaddir
# cmd = './get_mead_summary_phrase_qps.sh ' + str(cid) + ' ' + str(max_lecture) + ' ' + str(self.system)
# os.chdir(meaddir)
# retcode = subprocess.call([cmd], shell=True)
# print retcode
# subprocess.call("exit 1", shell=True)
# os.chdir(olddir)
#
# # . get LSA results (CourseMirrorphrase2phraseSimilarity.java)
# #cmd = 'cmd /C "runLSA.bat '+str(cid)+ ' ' + str(max_lecture) + ' ' + str(self.system) + ' ' + str(self.method) + '"'
# cmd = 'cmd /C "runLSA_All.bat '+str(cid)+ ' ' + str(max_lecture) + ' ' + str(self.system) + ' ' + str(self.method) + '"'
# os.system(cmd)
#get community dection results
# get ClusterARank (CourseMirror_phraseClusteringbasedShallowSummaryKmedoid-New-Malformed-LexRank.py)
cmd = "python CourseMirror_ClusterARank.py %s %d %s %s %s" % (
cid, max_lecture, self.system, self.method, self.similarity)
print cmd
os.system(cmd)
cmd = "python get_summary.py %s %s" % (cid, self.system)
print cmd
os.system(cmd)
cmd = "python get_Rouge.py %s %d %s %s" % (
cid, max_lecture, self.system, self.method + '_' + self.similarity)
print cmd
os.system(cmd)
cmd = "python eval_student_number.py %s %d %s %s %s" % (
cid, max_lecture, self.system, self.method, self.similarity)
print cmd
os.system(cmd)