dataman-git

for doc in new_texts_vector:
  print(doc)

dataman-git

new_corpus

dataman-git

#  predicting new text which is in text dataframe  
new_texts = [
    'The new Windows operating system will be released',
    'The system uses the most difficult technologies and techniques',
    'The U.S. consumer prices dropped for the first time in ten months'
 ]

from gensim.parsing.preprocessing import preprocess_string
new_texts_tokenized = []
for doc in new_texts:

dataman-git

# Print the Keyword in the 10 topics
import pprint as pp
pp.pprint(lda_bow.print_topics()[2])

dataman-git

#Creating Topic Distance Visualization 
pyLDAvis.enable_notebook()
p = gensimvis.prepare(lda_bow, bow_corpus, gensim_dictionary)
p

dataman-git

# Load the model trained before.
from gensim.models import LdaModel
from gensim.test.utils import datapath
from gensim.corpora import Dictionary

# Load the LDA model trained on BOW data
bow_file = datapath("/content/gdrive/My Drive/data/gensim/LDA_bow_151")
lda_bow = LdaModel.load(bow_file)

# Load the LDA model trained on TF-IDF data

dataman-git

#!pip install pyLDAvis
import pyLDAvis
import pyLDAvis.sklearn
import pyLDAvis.gensim_models as gensimvis
pyLDAvis.enable_notebook()

dataman-git

from matplotlib import pyplot as plt
plt.plot(numTopicsList, coherenceList_UMass)
plt.savefig("/content/gdrive/My Drive/data/gensim/LDA_bow_coherence")
plt.show()

dataman-git

coherenceList_UMass

dataman-git

from gensim.models import LdaModel
from gensim.models.coherencemodel import CoherenceModel
from gensim.test.utils import datapath
np.random.seed(42)
def coherence_UMass(corpus, name, k):
   # Load the model trained before.
   tempfile = datapath("/content/gdrive/My Drive/data/gensim/LDA_" + name + "_" + str(k))
   lda = LdaModel.load(tempfile)
   coherence = CoherenceModel(model=lda, 
                              texts=text_tokenized,