Last active
February 28, 2024 20:20
-
-
Save recalde/2ecccf076b5d01ce840cf1801695dc47 to your computer and use it in GitHub Desktop.
s3-stats
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
import pandas as pd | |
import matplotlib.pyplot as plt | |
import pyarrow.parquet as pq | |
import os | |
# Reading data using Apache Arrow | |
data_dir = '/path/to/your/data/directory' | |
file_paths = [os.path.join(data_dir, file) for file in os.listdir(data_dir) if file.endswith('.parquet')] | |
dfs = [pq.read_table(file).to_pandas() for file in file_paths] | |
df = pd.concat(dfs, ignore_index=True) | |
# Splitting the key column into separate columns | |
df[['date', 'app', 'environment']] = df['key'].str.split('/', expand=True) | |
# Convert 'modified' column to datetime | |
df['modified'] = pd.to_datetime(df['modified']) | |
# Summarizing the data | |
summary = df.groupby(['date', 'app']).agg(total_size=('size', 'sum')).reset_index() | |
# Summarizing to month | |
summary['month'] = summary['date'].str[:7] | |
# Stacked bar chart visualization | |
pivot_table = summary.pivot_table(index='month', columns='app', values='total_size', aggfunc='sum', fill_value=0) | |
pivot_table.plot(kind='bar', stacked=True, figsize=(10, 6)) | |
plt.xlabel('Month') | |
plt.ylabel('Sum of Size') | |
plt.title('Sum of Size per Month by App') | |
plt.xticks(rotation=45) | |
plt.tight_layout() | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment