Downsample large data file

downsample.py

import pandas as pd

# 1. Read raw CSV
df = pd.read_csv("raw_data.csv")

# 2. Convert the timestamp column to datetime (adjust column name/format as necessary)
df["timestamp"] = pd.to_datetime(df["timestamp"])

# 3. Make the timestamp the index
df.set_index("timestamp", inplace=True)

# 4. Resample to 10-second intervals, and compute mean, min, max on each numeric column
df_agg = df.resample("10S").agg(["mean", "min", "max"])

# 5. Optional: Flatten the multi-level column names produced by agg()
df_agg.columns = ["_".join(col).strip() for col in df_agg.columns.values]

# 6. Save the aggregated data to a new CSV
df_agg.to_csv("aggregated_data_10s.csv")

print("Done! Aggregated file saved as aggregated_data_10s.csv")