svm_predict.py

class SVMSentiment(Base):
    """Predict fine-grained sentiment scores using a sklearn 
    linear Support Vector Machine (SVM) pipeline."""
    def __init__(self, model_file: str=None) -> None:
        super().__init__()
        from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
        from sklearn.linear_model import SGDClassifier
        from sklearn.pipeline import Pipeline
        self.pipeline = Pipeline(
            [
                ('vect', CountVectorizer()),
                ('tfidf', TfidfTransformer()),
                ('clf', SGDClassifier(
                    loss='hinge',
                    penalty='l2',
                    alpha=1e-3,
                    random_state=42,
                    max_iter=100,
                    learning_rate='optimal',
                    tol=None,
                )),
            ]
        )

    def predict(self, train_file: str, test_file: str, lower_case: bool=False) -> pd.DataFrame:
        "Train model using sklearn pipeline"
        train_df = self.read_data(train_file, lower_case)
        learner = self.pipeline.fit(train_df['text'], train_df['truth'])
        # Predict class labels using the learner and output DataFrame
        test_df = self.read_data(test_file, lower_case)
        test_df['pred'] = learner.predict(test_df['text'])
        return test_df