How to set up a training set in a supervised method? about pke HOT 3 CLOSED

#test file, wait for the keywords to be extracted.
extractor = pke.supervised.Kea(input_file='./dataset/4046.txt')
#test` set format
extractor.read_document(format='preprocessed')
#test set df count
df_counts = pke.load_document_frequency_file(input_file='./dataset/df.txt') #
extractor.feature_extraction(df=df_counts)
#kea model that have been trained
extractor.classify_candidates(model='./dataset/kea_model/kea_kdd_model') .
#I don't know how to get keywords
print extractor.get_n_best(n=2)

with gzip.open(output_file, 'w') as f:
    f.write('--NB_DOC--' + delimiter + str(nb_documents) + '\n')
    for ngram in frequencies:
        f.write((ngram).encode('utf-8') + delimiter + str(len(frequencies[ngram])) + '\n')

import pke
extractor = pke.supervised.Kea(input_file='/path/to/input')

# here the input document should be in preprocessed format, i.e. 
# whitespace-separated POS-tagged tokens, one sentence per line.
extractor.read_document(format='preprocessed')

# load the df counts
# here the Df counts file is normally a gzip compressed file, this is why you have the issue in the
# second part of your comment
df_counts = pke.load_document_frequency_file(input_file='/path/to/dfcounts')

# Extract the candidates, I think you miss that
extractor.candidate_selection()

# Compute the features for the candidates
extractor.feature_extraction(df=df_counts)

# Classify the candidates using your trained model
extractor.classify_candidates(model='./dataset/kea_model/kea_kdd_model') .

# Get the best 2 candidates
print extractor.get_n_best(n=2)