data_measurements/npmi/npmi.py [381:398]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            sent_batch_df = pd.DataFrame(batch_sentence_row)
            # Subgroup counts per-sentence for the given batch
            subgroup_df = sent_batch_df[subgroup_idx]
            subgroup_df.columns = [subgroup]
            # Remove the sentences where the count of the subgroup is 0.
            # This way we have less computation & resources needs.
            subgroup_df = subgroup_df[subgroup_df > 0]
            mlb_subgroup_only = sent_batch_df[sent_batch_df[subgroup_idx] > 0]
            # Create cooccurrence matrix for the given subgroup and all words.
            batch_coo_df = pd.DataFrame(mlb_subgroup_only.T.dot(subgroup_df))

            # Creates a batch-sized dataframe of co-occurrence counts.
            # Note these could just be summed rather than be batch size.
            if initialize:
                coo_df = batch_coo_df
            else:
                coo_df = coo_df.add(batch_coo_df, fill_value=0)
            initialize = False
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



npmi/npmi.py [146:163]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            sent_batch_df = pd.DataFrame(batch_sentence_row)
            # Subgroup counts per-sentence for the given batch
            subgroup_df = sent_batch_df[subgroup_idx]
            subgroup_df.columns = [subgroup]
            # Remove the sentences where the count of the subgroup is 0.
            # This way we have less computation & resources needs.
            subgroup_df = subgroup_df[subgroup_df > 0]
            mlb_subgroup_only = sent_batch_df[sent_batch_df[subgroup_idx] > 0]
            # Create cooccurrence matrix for the given subgroup and all words.
            batch_coo_df = pd.DataFrame(mlb_subgroup_only.T.dot(subgroup_df))

            # Creates a batch-sized dataframe of co-occurrence counts.
            # Note these could just be summed rather than be batch size.
            if initialize:
                coo_df = batch_coo_df
            else:
                coo_df = coo_df.add(batch_coo_df, fill_value=0)
            initialize = False
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -