exploring options

This commit is contained in:
2025-12-09 15:33:28 +00:00
parent bd0a421bb9
commit c415b81bc8
4 changed files with 57 additions and 23 deletions
+50 -17
View File
@@ -1,6 +1,6 @@
import polars as pd
import os
import logging
class CombineTimeseries:
def __init__(self, config, locations):
@@ -15,23 +15,56 @@ class CombineTimeseries:
if group not in self.grouped_locations:
self.grouped_locations[group] = []
self.grouped_locations[group].append(location)
logging.info(f'Count of zones: {len(self.grouped_locations)}')
def combine_csv_files(self):
for group, loc_list in self.grouped_locations.items():
combined_df = None
for loc in loc_list:
csv_to_load = f"./csv_files/{loc[0]}_timeseries_data.csv"
df = pd.read_csv(csv_to_load)
if combined_df is None:
combined_df = df
else:
combined_df = combined_df.join(df, on='datetime')
# def combine_csv_files(self):
# to_delete = []
# for group, loc_list in self.grouped_locations.items():
# output_file =f"{self.config.COMBINED_FOLDER}/zone_{group}_timeseries_data.csv"
# combined_df = None
# for loc in loc_list:
# csv_to_load = f"{self.config.CSV_TOP_FOLDER}/{loc[0]}_timeseries_data.csv"
# df = pd.read_csv(csv_to_load, streaming=True)
# if combined_df is None:
# combined_df = df
# else:
# combined_df = combined_df.join(df, on='datetime')
# if self.config.delete_csv_after_combining:
# to_delete.append(csv_to_load)
# sorted_df = combined_df.sort('datetime')
# print(f'writing file to {output_file}')
# sorted_df.write_csv(output_file)
# if len(to_delete) > 0:
# for path in to_delete:
# print(f'deleting {path}')
# os.remove(path)
def combine_csv_files(self):
to_delete = []
for group, loc_list in self.grouped_locations.items():
output_file = f"{self.config.COMBINED_FOLDER}/zone_{group}_timeseries_data.csv"
# Use LazyFrame for memory-efficient processing
lazy_dfs = []
for loc in loc_list:
csv_to_load = f"{self.config.CSV_TOP_FOLDER}/{loc[0]}_timeseries_data.csv"
df = pd.scan_csv(csv_to_load) # Lazy read
lazy_dfs.append(df)
if self.config.delete_csv_after_combining:
os.remove(csv_to_load)
to_delete.append(csv_to_load)
output_file = (
f"{self.config.COMBINED_FOLDER}/zone_{group}_timeseries_data.csv"
)
sorted_df = combined_df.sort('datetime')
sorted_df.write_csv(output_file)
# Combine with LazyFrame operations
combined_lazy = pd.concat(lazy_dfs, how='align').collect(streaming=True) # Collect at the end
sorted_df = combined_lazy.sort('datetime')
print(f'writing file to {output_file}')
sorted_df.write_csv(output_file)
if len(to_delete) > 0:
for path in to_delete:
print(f'deleting {path}')
os.remove(path)
+2 -3
View File
@@ -5,6 +5,7 @@ import polars as pd
from datetime import datetime
import os
import concurrent.futures
import logging
@@ -169,7 +170,6 @@ class GenerateTimeseries:
executor.shutdown(wait=False, cancel_futures=True)
raise
# Write CSVs for each location
def write_results_to_csv(self, results, locations):
"""Write extracted data to CSV files for each location.
@@ -177,7 +177,6 @@ class GenerateTimeseries:
results (dict): Aggregated results {zone_id: {'dates': [], 'values': []}}
locations (list): List of location data
"""
print("Writing CSV files...")
for location in locations:
zone_id = location[0]
data = results[zone_id]
@@ -201,4 +200,4 @@ class GenerateTimeseries:
output_path,
float_precision=4
)
print("All CSV files written.")
logging.info("All CSV files written.")