7c960272c5ab4d25a022538f5849addec3e6bfee,loglizer/preprocessing.py,FeatureExtractor,transform,#FeatureExtractor#,71

Before Change

        for i in range(X_seq.shape[0]):
            X_df.loc[i, :] = [0] * len(self.events)
            event_counts = Counter(X_seq[i])
            for event, count in event_counts.items():
                if event in self.events:
                    X_df.loc[i, event] = count
        X = X_df.fillna(0).values
        
        num_instance, num_event = X.shape
        if self.term_weighting == "tf-idf":

After Change

            X_new: The transformed data matrix
        
        print("====== Transformed test data summary ======")
        X_counts = []
        for i in range(X_seq.shape[0]):
            event_counts = Counter(X_seq[i])
            X_counts.append(event_counts)
        X_df = pd.DataFrame(X_counts)
        X_df = X_df.fillna(0)
        empty_events = set(self.events) - set(X_df.columns)
        for event in empty_events:
            X_df[event] = [0] * len(X_df)
        X = X_df[self.events].values
        if self.oov:
            oov_vec = np.sum(X_df[X_df.columns.difference(self.events)].values > 0, axis=1)
            X = np.hstack([X, oov_vec.reshape(X.shape[0], 1)])
        

Instances