ret.append(target_in_tweet)
return ret
if __name__ == '__main__':
useDev = True
if useDev == False:
tweets_train, targets_train, labels_train = readTweetsOfficial(tokenize_tweets.FILETRAIN, 'windows-1252', 2)
tweets_dev, targets_dev, labels_dev = readTweetsOfficial(tokenize_tweets.FILEDEV, 'windows-1252', 2)
else:
tweets_train, targets_train, labels_train = readTweetsOfficial(tokenize_tweets.FILETRAIN, 'windows-1252', 2)
tweets_origdev, targets_origdev, labels_origdev = readTweetsOfficial(tokenize_tweets.FILEDEV, 'windows-1252', 2)
tweets_train.extend(tweets_origdev)
targets_train.extend(targets_origdev)
labels_train.extend(labels_origdev)
tweets_dev, targets_dev, labels_dev = readTweetsOfficial(tokenize_tweets.FILETEST, 'windows-1252', 2)
# "model_phrase_100_samp500_it2000.ckpt"
features_train, labels_train, features_dev, labels_dev = extractFeaturesAutoencoder("model_trump_phrase_100_samp500_it2600.ckpt",
tweets_train, targets_train, labels_train, tweets_dev, targets_dev, labels_dev, "false", True)
#train_classifiers(features_train, labels_train, features_dev, labels_dev, "out_auto_added.txt") # train and predict two 2-way models
train_classifier_3way(features_train, labels_train, features_dev, labels_dev, "out_trump_postprocess.txt", [], "false", "false", useDev=useDev)
#train_classifiers_PosVNeg(features_train, labels_train, features_dev, labels_dev, "out_auto.txt")
eval(tokenize_tweets.FILETEST, "out_trump_postprocess.txt")
if line.startswith('ID\t'):
outfIn.write(line)
outfOut.write(line)
else:
if cntr in inlist:
outfIn.write(line)
else:
outfOut.write(line)
cntr += 1
outfIn.close()
outfOut.close()
if __name__ == '__main__':
tweets_gold, targets_gold, labels_gold = readTweetsOfficial(
tokenize_tweets.FILEDEV, 'windows-1252', 2)
tweets_res, targets_res, labels_res = readTweetsOfficial(
"out_hillary_auto_false_targetInTweet.txt", 'windows-1252', 2)
inlist = selectTrainData(tweets_gold, targets_gold)
printInOutFiles(inlist, "out_hillary_auto_false_targetInTweet.txt",
"out_hillary_inTwe.txt", "out_hillary_outTwe.txt")
printInOutFiles(inlist, tokenize_tweets.FILEDEV, "_gold_hillary_inTwe.txt",
"_gold_hillary_outTwe.txt")
print("Inlist")
eval("_gold_hillary_inTwe.txt", "out_hillary_inTwe.txt")
print("Outlist")
eval("_gold_hillary_outTwe.txt", "out_hillary_outTwe.txt")
tokenize_tweets.FILEDEV, 'windows-1252', 2)
else:
tweets_train, targets_train, labels_train = readTweetsOfficial(
tokenize_tweets.FILETRAIN, 'windows-1252', 2)
tweets_origdev, targets_origdev, labels_origdev = readTweetsOfficial(
tokenize_tweets.FILEDEV, 'windows-1252', 2)
tweets_train.extend(tweets_origdev)
targets_train.extend(targets_origdev)
labels_train.extend(labels_origdev)
tweets_dev, targets_dev, labels_dev = readTweetsOfficial(
tokenize_tweets.FILETEST, 'windows-1252', 2)
# "model_phrase_100_samp500_it2000.ckpt"
features_train, labels_train, features_dev, labels_dev = extractFeaturesAutoencoder(
"model_trump_phrase_100_samp500_it2600.ckpt", tweets_train,
targets_train, labels_train, tweets_dev, targets_dev, labels_dev,
"false", True)
#train_classifiers(features_train, labels_train, features_dev, labels_dev, "out_auto_added.txt") # train and predict two 2-way models
train_classifier_3way(features_train,
labels_train,
features_dev,
labels_dev,
"out_trump_postprocess.txt", [],
"false",
"false",
useDev=useDev)
#train_classifiers_PosVNeg(features_train, labels_train, features_dev, labels_dev, "out_auto.txt")
eval(tokenize_tweets.FILETEST, "out_trump_postprocess.txt")
outfIn.write(line)
outfOut.write(line)
else:
if cntr in inlist:
outfIn.write(line)
else:
outfOut.write(line)
cntr += 1
outfIn.close()
outfOut.close()
if __name__ == "__main__":
tweets_gold, targets_gold, labels_gold = readTweetsOfficial(tokenize_tweets.FILEDEV, "windows-1252", 2)
tweets_res, targets_res, labels_res = readTweetsOfficial(
"out_hillary_auto_false_targetInTweet.txt", "windows-1252", 2
)
inlist = selectTrainData(tweets_gold, targets_gold)
printInOutFiles(
inlist, "out_hillary_auto_false_targetInTweet.txt", "out_hillary_inTwe.txt", "out_hillary_outTwe.txt"
)
printInOutFiles(inlist, tokenize_tweets.FILEDEV, "_gold_hillary_inTwe.txt", "_gold_hillary_outTwe.txt")
print("Inlist")
eval("_gold_hillary_inTwe.txt", "out_hillary_inTwe.txt")
print("Outlist")
eval("_gold_hillary_outTwe.txt", "out_hillary_outTwe.txt")