def run(dataset, hyperparameters, metrics, fname=None):
# # Load Resources
word2vec = None
if hyperparameters['model'] != 'rand':
word2vec = load_word2vec()
# # Load Dataset
df = load_dataset(dataset[0], **dataset[1])
# # Preprocess
df['clean_tweets'] = df.tweet.apply(
TweetPreprocessor(normalize=['link', 'mention']).preprocess)
df['tokens'] = df.clean_tweets.apply(TweetTokenizer().tokenize)
X_train, X_dev, X_test, y_train, y_dev, y_test = train_dev_test_split(
df.tokens, df.label)
# # Train
clf = NeuralNetClassifier(module=TextCNN,
corpus=df.tokens,
word_vectors=word2vec,
metrics=metrics,
**hyperparameters)
clf.fit(X_train, y_train, validation_data=(X_dev, y_dev))
# # Predict
y_pred = clf.predict(X_test)
# # Evaluate
pprint(
dict(dataset=dataset,
hyperparameters=hyperparameters,
scores={
scorer: get_score_func(scorer)(y_test, y_pred)
for scorer in metrics
}))
# # Save to file
X_test['pred'] = y_pred
X_test.to_excel(scratch_path('predictions_%s.xlsx' % fname))
def run(dataset, features, word_embedding, metrics, fname):
if dataset.lower().startswith('f'):
df = load_fdcl18()
else:
df = load_dwmw17()
tqdm.pandas(desc='Preprocessing Progress: ')
df['clean_tweet'] = df.tweet.progress_apply(TweetPreprocessor(normalize=['link', 'mention']).preprocess, )
tqdm.pandas(desc='Tokenizing Progress: ')
df['tokens'] = df.clean_tweet.progress_apply(TweetTokenizer().tokenize)
# #
# Feature Extraction
# tfidf_pipeline
ff = []
if 'tfidf_vectorizer' in features:
tfidf_kwargs = dict(
tokenizer=TweetTokenizer().tokenize,
stop_words=stopwords,
min_df=.0025,
max_df=0.25,
ngram_range=(1, 3)
)
ff += [('tfidf_vectorizer', TfidfVectorizer(**tfidf_kwargs), 'clean_tweet')]
# framenet_pipeline
if 'framenet_pipeline' in features:
count_vectorizer = ('count_vectorizer', CountVectorizer())
truncated_svd = ('truncated_svd', TruncatedSVD(algorithm='randomized', n_components=10))
ff += [('framenet_pipeline', Pipeline([count_vectorizer, truncated_svd]), 'framenet')]
# mean_embedding
if 'mean_embedding' in features:
ff += [('mean_embedding', mean_embedding(word_embedding), 'tokens')]
# hatebase_vectorizer
if 'hatebase_vectorizer' in features:
ff += [('hatebase_vectorizer', HatebaseVectorizer(features=features['hatebase_vectorizer']), 'clean_tweet')]
# transfer_vectorizer
if 'transfer_vectorizer' in features:
hyper_params = features['transfer_vectorizer']
hyper_params['module'] = TextCNN
hyper_params['corpus'] = df.tokens
hyper_params['word_vectors'] = word_embedding
# """ # Cross-validate and save predictions
args = [NeuralNetClassifier, hyper_params, ['conv_%i' % i for i in range(3)], False]
ff += [('transfer_vectorizer', TransferVectorizer(*args), 'tokens')]
# # Estimator
pipeline = Pipeline([('column_transformer', ColumnTransformer(ff)), ('clf', LinearSVC())])
# # Evaluation (Cross Validation)
# """ # Cross-validate and save predictions
cv = CrossValidator(pipeline, n_splits=5, scoring=metrics)
df['predictions'], cv_results = cv.cross_val_predict(df, df.label, return_scores=True)
# """ Print Scores
pprint({'dataset': dataset, 'features': features})
pprint(cv_results)
scores = {}
for scorer in metrics:
scores[scorer] = ['%.2f' % (np.average(cv_results[scorer]) * 100) + ',']
pprint(scores, type='table')
# """ Save Predictions #
df.to_excel(scratch_path('predictions_%s_%s.xlsx' % (dataset, fname)))
from scripts.utils import scratch_path
from tklearn.datasets import load_fdcl18, load_dwmw17
from tklearn.model_selection import CrossValidator
from tklearn.neural_network import NeuralNetClassifier
from tklearn.neural_network.model import TextCNN
from tklearn.preprocessing.tweet import TweetPreprocessor
from tklearn.text.word_vec import load_word2vec
from tklearn.utils import pprint
DATASET = 'FDCL18'
if __name__ == '__main__':
# Load Dataset and Extract Features
if DATASET.lower().startswith('f'):
df = load_fdcl18(num_classes=2)
pprint({'dataset': 'FDCL18(num_classes=2)'})
else:
df = load_dwmw17(num_classes=2)
pprint({'dataset': 'DWMW17(num_classes=2)'})
df['clean_tweets'] = df.tweet.apply(TweetPreprocessor(normalize=['link', 'mention']).preprocess)
df['tokens'] = df.clean_tweets.apply(TweetTokenizer().tokenize)
# Load Resources
word2vec = load_word2vec()
# Hyperparameters
kwargs = {
'model': 'multichannel',
'epoch': 100,
'learning_rate': 0.01,
'max_sent_len': 50,
'batch_size': 50,
# 'word_dim': 300,
def run(dataset, features, word2vec, metrics, fname=None):
if dataset == 'fdcl18':
df1 = load_fdcl18(num_classes=2)
df2 = load_dwmw17(num_classes=2)
df2 = df2.drop(
['count', 'hate_speech', 'offensive_language', 'neither'], axis=1)
else:
df1 = load_dwmw17(num_classes=2)
df2 = load_fdcl18(num_classes=2)
df1 = df1.drop(
['count', 'hate_speech', 'offensive_language', 'neither'], axis=1)
# # Preprocessing
preprocess = TweetPreprocessor(normalize=['link', 'mention']).preprocess
tokenize = TweetTokenizer().tokenize
# # # DF 1 - Preprocessing
tqdm.pandas(desc='Preprocessing Progress: ')
df1['clean_tweet'] = df1.tweet.progress_apply(preprocess)
tqdm.pandas(desc='Tokenizing Progress: ')
df1['tokens'] = df1.clean_tweet.progress_apply(tokenize)
# # # DF 2 - Preprocessing
tqdm.pandas(desc='Preprocessing Progress: ')
df2['clean_tweet'] = df2.tweet.progress_apply(preprocess)
tqdm.pandas(desc='Tokenizing Progress: ')
df2['tokens'] = df2.clean_tweet.progress_apply(tokenize)
# #
# # Feature Extraction
# # # tfidf_pipeline
ff = []
if 'tfidf_vectorizer' in features:
tfidf_kwargs = dict(tokenizer=TweetTokenizer().tokenize,
stop_words=stopwords,
min_df=.0025,
max_df=0.25,
ngram_range=(1, 3))
ff += [('tfidf_vectorizer', TfidfVectorizer(**tfidf_kwargs),
'clean_tweet')]
# # # framenet_pipeline
if 'framenet_pipeline' in features:
count_vectorizer = ('count_vectorizer', CountVectorizer())
truncated_svd = ('truncated_svd',
TruncatedSVD(algorithm='randomized', n_components=10))
ff += [('framenet_pipeline',
Pipeline([count_vectorizer, truncated_svd]), 'framenet')]
# # # mean_embedding
if 'mean_embedding' in features:
ff += [('mean_embedding', mean_embedding(word2vec), 'tokens')]
# # # hatebase_vectorizer
if 'hatebase_vectorizer' in features:
ff += [('hatebase_vectorizer',
HatebaseVectorizer(features=features['hatebase_vectorizer']),
'clean_tweet')]
# # # transfer_vectorizer
if 'transfer_vectorizer' in features:
hyper_params = features['transfer_vectorizer']
hyper_params['module'] = TextCNN
hyper_params['corpus'] = df1.tokens
hyper_params['word_vectors'] = word2vec
# """ # Cross-validate and save predictions
args = [
NeuralNetClassifier, hyper_params,
['conv_%i' % i for i in range(3)], False
]
ff += [('transfer_vectorizer', TransferVectorizer(*args), 'tokens')]
# # # estimator
pipeline = Pipeline([('column_transformer', ColumnTransformer(ff)),
('clf', LinearSVC())])
# # Grid Search``
# param_grid = [
# {'clf__C': [0.1, 1, 10, 50], 'classifier': linear_svc},
# # {'classifier': sgd_classifier},
# ]
# gs = GridSearchCV(pipeline, param_grid, cv=5)
# result = gs.fit(df, df.label).predict(df)
# # Evaluation
pipeline.fit(df1, df1.label)
y_true, y_pred = df2.label, pipeline.predict(df2)
# df2['predictions'] = y_pred
# """ Print Scores
pprint({'dataset': dataset, 'features': features})
scores = {}
for scorer in metrics:
scores[scorer] = [get_score_func(scorer)(y_true, y_pred)]
pprint(scores, type='table')