| import datasets | |
| import pandas as pd | |
| dfs = [] | |
| for i in range(10): | |
| dfs.append( | |
| datasets.ArrowReader.read_table(f'segment_{i}/dataset.arrow').to_pandas() | |
| ) | |
| full_df = pd.concat(dfs, ignore_index=True) | |
| full_df.to_csv('dataset.csv') | |
| import datasets | |
| import pandas as pd | |
| dfs = [] | |
| for i in range(10): | |
| dfs.append( | |
| datasets.ArrowReader.read_table(f'segment_{i}/dataset.arrow').to_pandas() | |
| ) | |
| full_df = pd.concat(dfs, ignore_index=True) | |
| full_df.to_csv('dataset.csv') | |