def get_graph_data(df_with_fingerprints: pd.DataFrame, out_file: str, batchno: int, batchsize: int = 1000):
    # Calculate Tanimoto similarity for a given batch
    # Need to batch this to avoid OOMing. Each batch will get smaller
    sources, targets, similarities = [], [], []
    all_fingerprints = df_with_fingerprints['morgan_fingerprint'].values.tolist()
    for i in tqdm(range(batchsize)): # Use tqdm to estimate time
        batch_i = i + (batchsize * batchno)
        if batch_i <= (len(all_fingerprints) - 1):
            row = df_with_fingerprints.index[batch_i]
            fingerprint_1 = df_with_fingerprints.at[row, 'morgan_fingerprint']
            source_inchi_simp = df_with_fingerprints.at[row, COMPOUND_ID_COL]
            sims = DataStructs.BulkTanimotoSimilarity(fingerprint_1, all_fingerprints[batch_i + 1:])
            # collect the ids and values
            for m in range(len(sims)):
                target_row = df_with_fingerprints.index[batch_i + 1 + m]
                sources.append(source_inchi_simp)
                targets.append(df_with_fingerprints.at[target_row, COMPOUND_ID_COL])
                similarities.append(sims[m])
    if len(sources) > 0:
        simTable = pd.DataFrame(data={'SOURCE': sources, 'TARGET': targets, 'SIMILARITY': similarities})
        simTable = simTable.reset_index(drop=True)
        simTable.to_csv(out_file + str(batchno) + '.csv')
    else:
        print(f'No data for batch number: {batchno}')

PandasTools.AddMoleculeColumnToFrame(df, 'SMILES', 'Molecule', includeFingerprints=True)
# Produce a hashed Morgan fingerprint for each molecule
df['morgan_fingerprint'] = df['Molecule'].apply(lambda x: GetMorganFingerprintAsBitVect(x, 2)) #Use apply here for better readability
for i in range(number_of_batches):
    get_graph_data(df, os.path.join(graph_data_folder, 'all_graph_data'), i)