Reputation: 4501
I have the following code that is reading from a CSV and writing to PyTables. However, pd.read_csv creates a dataframe and this is not handled in PyTables. How do I solve this problem? I can create numpy arrays but this seems like over kill and possibly time consuming? (Transaction Record is a class i created with the right data types - i have to replicate this if using numpy)
def get_transaction_report_in_chunks(transaction_file):
transaction_report_data = pd.read_csv(transaction_file, index_col=None, parse_dates=False, chunksize=500000)
return transaction_report_data
def write_to_hdf_from_multiple_csv(transaction_file_path):
hdf = tables.open_file(filename='MyDB.h5', mode='a')
transaction_report_table = hdf.create_table(hdf.root, 'Transaction_Report_Table_x', Transaction_Record, "Transaction Report Table")
all_files = glob.glob(os.path.join(transaction_file_path, "*.csv"))
for transaction_file in all_files:
for transaction_chunk in get_transaction_report_in_chunks(transaction_file):
transaction_report_table.append(transaction_chunk)
transaction_report_table.flush()
hdf.Close()
Upvotes: 2
Views: 1431
Reputation: 210822
I would use Pandas HDF Store, which is very convinient API for PyTables under the hood:
def write_to_hdf_from_multiple_csv(csv_file_path,
hdf_fn='/default_path/to/MyDB.h5',
hdf_key='Transaction_Report_Table_x',
df_cols_to_index=True): # you can specify here a list of columns that must be indexed, i.e.: ['name', 'department']
files = glob.glob(os.path.join(csv_file_path, '*.csv'))
# create HDF file (AKA '.h5' or PyTables)
store = pd.HDFStore(hdf_fn)
for f in files:
for chunk in pd.read_csv(f, chunksize=500000):
# don't index data columns in each iteration - we'll do it later ...
store.append(hdf_key, chunk, data_columns=df_cols_to_index, index=False)
# index data columns in HDFStore
store.create_table_index(hdf_key, columns=df_cols_to_index, optlevel=9, kind='full')
store.close()
Upvotes: 3