khushalps/api_utils_converse_v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Resetting utils subtree.

Browse Source
This commit is contained in:
khushal
2025-01-07 18:51:02 +05:30
parent b20d4850c2
commit 9a9be7d4dc
187 changed files with 140 additions and 141306 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils_v2/dataframe/__init__.py
View File
utils_v2/dataframe/splitter.py
-118
View File
@@ -1,118 +0,0 @@
"""
AUTHOR:
Khushal P Soonderji
DATE:
Tuesday, 22nd Oct., 2024
OBJECTIVE:
To provide an easy way to split dataframes into chunks and divide the workload nto more manageable batches.
REFERENCES:
N/A
DOWNLOADS:
N/A
USAGE EXAMPLE:
for sub_df in DataFrameSplitter(df, chunk_size = 50):
# Do your task here:
pass
"""
# *****************************************************************************************************************
# ***** ****
# *** IMPORT ***
# ***** ****
# *****************************************************************************************************************
# --- Nothing Yet
# *****************************************************************************************************************
# ***** ****
# *** MACROS / ONE-TIME INIT ***
# ***** ****
# *****************************************************************************************************************
# --- Nothing Yet
# *****************************************************************************************************************
# ***** ****
# *** VARIABLES ***
# ***** ****
# *****************************************************************************************************************
# --- Nothing Yet
# *****************************************************************************************************************
# ***** ****
# *** FUNCTIONS ***
# ***** ****
# *****************************************************************************************************************
# --- Nothing Yet
# *****************************************************************************************************************
# ***** ****
# *** CLASSES ***
# ***** ****
# *****************************************************************************************************************
class DataFrameSplitter:
def __init__(self, df, chunk_size):
"""
Use this to process your dataframe in batches. Useful for when you need to send out alerts at intervals or need
to maintain checkpoints.
:param df: The dataframe to iterate over.
:param chunk_size: The max. no. of rows to pick at once.
"""
self.df = df
self.row_count = df.shape[0]
self.chunk_size = chunk_size
self.offset = 0
def __iter__(self):
self.offset = 0
return self
def __next__(self):
if self.offset >= self.row_count:
raise StopIteration
end = self.offset + self.chunk_size
chunk = self.df.iloc[self.offset:end]
self.offset = end
return chunk
# *****************************************************************************************************************
# ***** ****
# *** MAIN PROGRAM ***
# ***** ****
# *****************************************************************************************************************
if __name__ == "__main__":
pass