try:
review_limit = int(args.review_limit)
except ValueError:
raise Exception("Review limit must be a number")
if review_limit < 100:
raise Exception("Review limit must be over 100")
# step 1 - pre processing the training data
# convert to combined pandas dataframe
# remving stopwords and stemming the review text
pre_processing = PreProcessing(limit_reviews=review_limit)
df_reviews = pre_processing.get_df_reviews()
df_meta = pre_processing.get_df_meta()
combined = pre_processing.filter_and_combine(df_reviews, df_meta)
reviews_clean = pre_processing.preprocess_reviews(
combined['reviewTextProcessed'].tolist())
no_stop_words = pre_processing.remove_stop_words(reviews_clean)
stemmed_reviews = pre_processing.get_stemmed_text(no_stop_words)
combined['reviewTextProcessed'] = stemmed_reviews
combined = pre_processing.change_categories_column(combined)
combined.to_csv(args.output_file, sep='\t', encoding='utf-8')
#pickle the list of preprocessed reviews to file
# with open(args.output_file, 'wb') as fp:
# pickle.dump(stemmed_reviews, fp)
except ValueError:
raise Exception("Review limit must be a number")
if review_limit < 100:
raise Exception("Review limit must be over 100")
# step 1 - pre processing the training data
# convert to combined pandas dataframe
# remving stopwords and stemming the review text
pre_processing = PreProcessing(limit_reviews=review_limit)
df_reviews = pre_processing.get_df_reviews()
df_meta = pre_processing.get_df_meta()
combined = pre_processing.filter_and_combine(df_reviews, df_meta)
combined['reviewTextProcessed'] = pre_processing.preprocess_reviews(
combined['reviewTextProcessed'])
combined['reviewTextProcessed'] = pre_processing.remove_stop_words(
combined['reviewTextProcessed'])
combined['reviewTextProcessed'] = pre_processing.get_stemmed_text(
combined['reviewTextProcessed'])
reviews_and_sentiment = combined[['reviewTextProcessed', 'overall']]
# convert string rating values to numerical values
reviews_and_sentiment['overall'] = pd.to_numeric(
reviews_and_sentiment['overall'])
# convert the rating value to 1 or 0 (sentiment value)
# if the average rating is 1, 2, 3 then 0 (negative sentiment)
# if the average rating is 4 or 5 then 1 (positive sentiment)
reviews_and_sentiment['sentiment'] = reviews_and_sentiment[