Created
April 13, 2020 20:05
-
-
Save rjurney/5cb1fe12cab88ad16fb99c13aed8af72 to your computer and use it in GitHub Desktop.
How to run a method on a field of a pandas DataFrame and set the result to another field
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def process_split(df: pd.DataFrame, f: types.FunctionType, in_key: str, out_key: str): | |
"""Process each chunk of a DataFrame, apply a funtion on an in_key and store it in an out_key""" | |
rows = [] | |
for index, row in df.iterrows(): | |
result = f(row[in_key]) | |
row[out_key] = result | |
rows.append(row) | |
df_out = pd.DataFrame(rows) | |
df_out = df_out.reindex().sort_index() | |
return df_out | |
def parallel_apply( | |
df: pd.DataFrame, | |
f: types.FunctionType, | |
in_key: str, | |
out_key: str, | |
n_cores: int=cpu_count | |
): | |
"""Apply a function to a DataFrame on an in_key and store it in an out_key with n_cores proceses""" | |
n_cores = int(cpu_count() / 2) if callable(cpu_count) else cpu_count | |
df_split = np.array_split(df, n_cores) | |
pool = Pool(n_cores) | |
df_out = pd.concat( | |
pool.starmap( | |
process_split, | |
repeat( | |
[df_split, f, in_key, out_key], | |
times=n_cores | |
), | |
) | |
) | |
df_out = df_out.reindex().sort_index() | |
pool.close() | |
pool.join() | |
return df_out |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment