LDA (Latent Dirichlet Allocation) predicting with python scikit-learn

LDApredict.py

# derived from http://scikit-learn.org/stable/auto_examples/applications/topics_extraction_with_nmf_lda.html
# explanations are located there : https://www.linkedin.com/pulse/dissociating-training-predicting-latent-dirichlet-lucien-tardres

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.decomposition import LatentDirichletAllocation
import pickle

# create a blank model
lda = LatentDirichletAllocation()

# load parameters from file
with open ('outfile', 'rb') as fd:
    (features,lda.components_,lda.exp_dirichlet_component_,lda.doc_topic_prior_) = pickle.load(fd)

# the dataset to predict on (first two samples were also in the training set so one can compare)
data_samples = ["I like to eat broccoli and bananas.",
                "I ate a banana and spinach smoothie for breakfast.",
                "kittens and dogs are boring"
               ]
# Vectorize the training set using the model features as vocabulary
tf_vectorizer = CountVectorizer(vocabulary=features)
tf = tf_vectorizer.fit_transform(data_samples)

# transform method returns a matrix with one line per document, columns being topics weight
predict = lda.transform(tf)
print(predict)