how to plot labels TFRecords in histogram - tensorflow

Question

Hello i have many files of TFRecords. i use python tensorflow and want to plot in one histogram all labels.
TFRecords is pair of (image,label)
so how i can extract all the labels ?
i have try to extract labels and have success plot several batches
all_label = []
for image, label in ds_train.take(10):
all_label.append(label)
sns.distplot(all_label)

Answer 1

Maybe something like this.
import re
#import pdftotext
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = open(path, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0
caching = True
pagenos=set()
for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
fp.close()
device.close()
retstr.close()
return text
with open('C:\\Users\\Finance10K.txt') as f:
clean_cont = f.read().splitlines()
clean_cont
doc=[i.replace('\xe2\x80\x9c','') for i in clean_cont ]
doc=[i.replace('\xe2\x80\x9d','') for i in doc ]
doc=[i.replace('\xe2\x80\x99s','') for i in doc ]
docs = [x for x in doc if x != ' ']
docss = [x for x in docs if x != '']
doc
docs
docss
financedoc=[re.sub("[^a-zA-Z]+", " ", s) for s in docss]
financedoc
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
from sklearn.decomposition import LatentDirichletAllocation
import numpy as np
import pandas as pd
#%pylab
#%matplotlib inline
from sklearn.feature_extraction.stop_words import ENGLISH_STOP_WORDS
vect=CountVectorizer(ngram_range=(1,1),stop_words='english')
fin=vect.fit_transform(financedoc)
fin
pd.DataFrame(fin.toarray(),columns=vect.get_feature_names())
lda=LatentDirichletAllocation(n_components=5)
lda.fit_transform(fin)
lda_dtf=lda.fit_transform(fin)
sorting=np.argsort(lda.components_)[:,::-1]
features=np.array(vect.get_feature_names())
import mglearn
mglearn.tools.print_topics(topics=range(5), feature_names=features,
sorting=sorting, topics_per_chunk=5, n_words=10)
#from __future__ import print_function
import pyLDAvis
import pyLDAvis.sklearn
pyLDAvis.enable_notebook()
zit=pyLDAvis.sklearn.prepare(lda,fin,vect)
pyLDAvis.show(zit)