Data Processing

# Upload your data
lyceum python run analyze.py -m cpu

# analyze.py
import pandas as pd
import json

# Read from Lyceum storage
df = pd.read_csv('/lyceum/storage/sales_data.csv')
print(f"Loaded {len(df)} rows")

# Analysis
summary = df.groupby('region').agg({
    'revenue': ['sum', 'mean', 'count']
}).round(2)

print(summary)

# Save results back to storage
report = {
    'total_revenue': float(df['revenue'].sum()),
    'total_rows': len(df),
    'top_region': df.groupby('region')['revenue'].sum().idxmax()
}

with open('/lyceum/storage/report.json', 'w') as f:
    json.dump(report, f, indent=2)

print(f"Report saved. Total revenue: ${report['total_revenue']:,.2f}")

import os
import pandas as pd

storage = '/lyceum/storage/'
csv_files = [f for f in os.listdir(storage) if f.endswith('.csv')]
print(f"Found {len(csv_files)} CSV files")

all_data = []
for filename in csv_files:
    df = pd.read_csv(os.path.join(storage, filename))
    df['source'] = filename
    all_data.append(df)
    print(f"  {filename}: {len(df)} rows")

combined = pd.concat(all_data, ignore_index=True)
combined.to_csv(f'{storage}combined.csv', index=False)
print(f"Combined: {len(combined)} total rows")

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('/lyceum/storage/data.csv')

fig, ax = plt.subplots(figsize=(10, 6))
df.groupby('month')['revenue'].sum().plot(kind='bar', ax=ax)
ax.set_title('Monthly Revenue')
ax.set_ylabel('Revenue ($)')

plt.tight_layout()
plt.savefig('/lyceum/storage/chart.png', dpi=300)
print("Chart saved to storage")

lyceum docker run jupyter/scipy-notebook:latest \
  -c "python /lyceum/storage/pipeline.py" \
  -m cpu \
  -t 600