Load pandas dataframe with chunksize determined by column variable
If you iterate through the csv file line by line, you can yield
chunks with a generator dependent on any column.
Working example:
import pandas as pd
def iter_chunk_by_id(file):
csv_reader = pd.read_csv(file, iterator=True, chunksize=1, header=None)
first_chunk = csv_reader.get_chunk()
id = first_chunk.iloc[0,0]
chunk = pd.DataFrame(first_chunk)
for l in csv_reader:
if id == l.iloc[0,0]:
id = l.iloc[0,0]
chunk = chunk.append(l)
continue
id = l.iloc[0,0]
yield chunk
chunk = pd.DataFrame(l)
yield chunk
## data.csv ##
# 1, foo, bla
# 1, off, aff
# 2, roo, laa
# 3, asd, fds
# 3, qwe, tre
# 3, tre, yxc
chunk_iter = iter_chunk_by_id("data.csv")
for chunk in chunk_iter:
print(chunk)
print("_____")
Output:
0 1 2
0 1 foo bla
1 1 off aff
_____
0 1 2
2 2 roo laa
3 2 jkl xds
_____
0 1 2
4 3 asd fds
5 3 qwe tre
6 3 tre yxc
_____
I built on the answer provided by @elcombato to take any chunk size. I actually had a similar use case and processing each line one by one made my program unbearably slow
def iter_chunk_by_id(file_name, chunk_size=10000):
"""generator to read the csv in chunks of user_id records. Each next call of generator will give a df for a user"""
csv_reader = pd.read_csv(file_name, compression='gzip', iterator=True, chunksize=chunk_size, header=0, error_bad_lines=False)
chunk = pd.DataFrame()
for l in csv_reader:
l[['id', 'everything_else']] = l[
'col_name'].str.split('|', 1, expand=True)
hits = l['id'].astype(float).diff().dropna().nonzero()[0]
if not len(hits):
# if all ids are same
chunk = chunk.append(l[['col_name']])
else:
start = 0
for i in range(len(hits)):
new_id = hits[i]+1
chunk = chunk.append(l[['col_name']].iloc[start:new_id, :])
yield chunk
chunk = pd.DataFrame()
start = new_id
chunk = l[['col_name']].iloc[start:, :]
yield chunk