def get_file():
global fname
# need to retrieve the uploaded file here for further processing
print(fname)
print(request.form)
dict = request.form.to_dict()
#filename = str(request)[ str(request).index('=')+1 : str(request).index('\' [GET]>') ]
text = simpleTokenize('uploads/' + fname)
"""text2 = cleanText( 'uploads/' + fname )
pos = ''.join(random.choices(string.ascii_uppercase + string.digits, k=10))
savePOSPiChart(text2, pos)
top = ''.join(random.choices(string.ascii_uppercase + string.digits, k=10))
saveTopWords(text2, top)
bw = ['yellow', 'fish', 'glass', 'foot', 'beach', 'suicide']
genGraph = ''.join(random.choices(string.ascii_uppercase + string.digits, k=10))
secgen = similarContext( text, bw)
saveChronoMap(text, bw, secgen, genGraph)
genReport = wpReport(text, bw, secgen, 10)
charReport = sampleCharacter(text, 'Caddy', 3, 100)
return render_template('results.html', pq = percentQuotes(text), sen = senlenStats(text), pos = pos, top = top, genGraph=genGraph,genReport=genReport, charReport=charReport)
"""
return render_template('hello.html')
def wpReport(filename, firstgen, secgen, ssName, numTop, writeTo):
sys.stdout = open(writeTo, 'w')
print("\n\n\nTitle: " + ssName)
print("FirstGen Words: " + str(firstgen))
print("SecondGen Words: " + str(secgen))
text = simpleTokenize(filename)
arr = wordProgression(text, firstgen, secgen)
for i in range(numTop):
topIndex = arr.index(max(arr))
topWords = text[topIndex * 100:topIndex * 100 + 100]
print("\n\nNumber " + str(i))
print("--> Score: " + str(arr[topIndex]) + "\n--> Z-Score: " +
str(stats.zscore(arr)[topIndex]))
print("--> Average Score " + str(statistics.mean(arr)))
fg = 0
sg = 0
for i in range(len(topWords)):
if topWords[i] in firstgen:
fg += 1
if topWords[i] in secgen:
sg += 1
print("Number of FirstGen Words: " + str(fg))
print("Number of SecondGen Words: " + str(sg))
print(TreebankWordDetokenizer().detokenize(topWords))
del arr[arr.index(max(arr))]
sys.stdout = sys.__stdout__
def wpReport(filename, firstgen, secgen, ssName, numTop): str = "" str = "\n\n\nTitle: " + ssName + "\n" str += "FirstGen Words: " + str(firstgen)+ "\n" str += "SecondGen Words: " + str(secgen) + "\n" text = simpleTokenize(filename) arr = wordProgression(text, firstgen, secgen) for i in range(numTop): topIndex = arr.index(max(arr)) topWords = text[topIndex*100:topIndex*100+100] str+="\n\nNumber " + str(i) + "\n" str+= "--> Score: " + str( arr[topIndex]) + "\n--> Z-Score: " + str(stats.zscore(arr)[topIndex]) + "\n" str+="--> Average Score " + str(statistics.mean(arr)) + "\n" fg=0 sg=0 for i in range(len(topWords)): if topWords[i] in firstgen: fg+=1 if topWords[i] in secgen: sg+=1 str+="Number of FirstGen Words: " + str(fg) + "\n" str+="Number of SecondGen Words: " + str(sg) + "\n" str+= TreebankWordDetokenizer().detokenize(topWords) + "\n" del arr[arr.index(max(arr))] return str
def vectorize(fileName, firstgen):
text = simpleTokenize(fileName)
vector = [
strength(text),
avgSentenceLength(text),
rebound(text, firstgen) * 1000.0
]
return vector
def plotChronoMap(textName, firstgen, secgen, title):
#fig, axs = plt.subplots(1)
#fig.suptitle('Short Story Readings on Salinger')
t = nltk.Text(word.lower() for word in simpleTokenize(textName))
y = wordProgression( t , firstgen, secgen)
x = list(range( int(len(t)/100) +1))
# If you want to make separate plots
plt.plot(x,y)
plt.savefig('/templates/static/graphs/' + title + '.png')
def generateSimilarWords(rootTextName, newDocName, words):
text = nltk.Text(word.lower() for word in simpleTokenize(rootTextName))
sys.stdout = open(newDocName, 'w')
stop_words = set(stopwords.words("english"))
for i in range(len(words)):
print(words[i])
text.similar(words[i], 1)
print()
sys.stdout = sys.__stdout__
m = simpleTokenize(newDocName)
n = m.copy()
for i in range(len(m)):
if m[i] == "No" and m[i + 1] == "matches":
n.remove("No")
n.remove("matches")
elif m[i] in words or m[i] in stop_words:
n.remove(m[i])
return n
def plotChronoMap(textName, firstgen, secgen, title, graphNum):
t = nltk.Text(word.lower() for word in simpleTokenize(textName))
y = wordProgression(t, firstgen, secgen)
x = list(range(int(len(t) / 100) + 1))
# If you want to make separate plots
#a, f = plt.subplots(1)
#a.suptitle(title)
#f.plot(x,y)
axs[graphNum].plot(x, y)
axs[graphNum].set_title(title)
def plotChronoMap(textName, firstgen, secgen, title, graphNum, writeTo):
#fig, axs = plt.subplots(1)
#fig.suptitle('Short Story Readings on Salinger')
t = nltk.Text(word.lower() for word in simpleTokenize(textName))
y = wordProgression(t, firstgen, secgen)
x = list(range(int(len(t) / 100) + 1))
# If you want to make separate plots
a, f = plt.subplots(1)
a.suptitle(title)
f.plot(x, y)
def nextGeneration(rootTextName, newDocName, words):
text = nltk.Text(word.lower() for word in simpleTokenize(rootTextName) )
sys.stdout = open(newDocName, 'w')
for i in range(len(words)):
# Original word
print(words[i])
# Context words within document
text.similar(words[i], 1)
# Context words from Wikipedia
w = wikipediaWords(words, 7)
for j in range(len(w[i])):
print(w[i][j])
sys.stdout = sys.__stdout__
m = simpleTokenize(newDocName)
n = m.copy()
for i in range(len(m)):
if m[i] == "No" and m[i+1] == "matches":
n.remove("No")
n.remove("matches")
return n
def firstgen(fileName): w = cleanText( simpleTokenize(fileName) ) w = set(w) lim = 5 + random.randint(0,3) w = [o for o in w if len(o) >= lim] ret = [] for i in range(30): rand = random.randint(0, len(w)-1) ret.append( w[rand] ) w.pop(rand) return ret
def master(baseText, metricText, firstgen, writeTo): #simpleTokenize(metricText) simpleTokenize(baseText) secgen = nextGeneration(baseText, writeTo, firstgen) wpReport(baseText, firstgen, secgen, metricText, 5) plotChronoMap(baseText, firstgen, secgen, metricText)
new.append(text[i + start])
master.append(new)
n = n - 1
indices.remove(x)
return master
# Given an array of character names, does comparative analysis on the surrounding
# text of the characters
def characterCompare(text, chars):
x = []
for i in range(len(chars)):
# 5 samples from each character
sample = sampleCharacter(text, chars[i], 5, 200)
temp = []
# Creating vectors for each sample
for j in range(len(sample)):
temp.append(
vectorize2(
sample[j],
['retard', 'female', 'greedy', 'suicidal', 'incestuous']))
# Averaging sampled vectors
x.append(np.mean(temp, axis=0).tolist())
#x.append(temp)
print(x)
characterCompare(simpleTokenize('SoundAndFury.txt'),
['Caddy', 'Benjy', 'Quentin', 'Jason', 'Dilsey'])
#print( np.mean([[3,5,7], [1,5,7], [3,6,7]], axis = 0).tolist() )
