value = float(value) except ValueError: pass new[key] = value return new if __name__ == "__main__": import argparse import json import csv import sys from corpus import iter_corpus, iter_test_corpus from predictor import PhraseSentimentPredictor parser = argparse.ArgumentParser(description=__doc__) parser.add_argument("filename") config = parser.parse_args() config = json.load(open(config.filename)) start=time.time() predictor = PhraseSentimentPredictor(**config) predictor.fit(list(iter_corpus())) print "fitting takes "+str(time.time()-start) test = list(iter_test_corpus()) #prediction = predictor.predict(test) score = predictor.score(test,'test') print("test score {}%".format(score * 100)) print 'programme finished!'
import csv, os from transformations import ExtractText if not os.path.exists('./data/vocabulary'): datapoints = list(iter_corpus()) vocabulary = set() et = ExtractText() X = et.transform(datapoints) for datap in X: for w in datap.split(): vocabulary.add(w.lower()) vocabulary = list(vocabulary) vocabulary.sort() with open('./data/vocabulary', 'wb') as f: wr = csv.writer(f) for voc in vocabulary: wr.writerow([voc]) parser = argparse.ArgumentParser(description=__doc__) parser.add_argument("filename") config = parser.parse_args() config = json.load(open(config.filename)) factory = lambda: PhraseSentimentPredictor(**config) factory() # Run once to check config is ok report = PrintPartialCV() analyse(factory) print "Analysis finished!"