MTBF and MTTR Python Script Generator for a Failure Log CSV

import pandas as pd

CSV_FILE = 'failure_log.csv'
ASSET = 'asset_id'
START = 'breakdown_start'
END = 'repair_end'
PERIOD_START = pd.Timestamp('2026-01-01')
PERIOD_END = pd.Timestamp('2026-09-30') + pd.Timedelta(days=1)

df = pd.read_csv(CSV_FILE, parse_dates=[START, END])

# Keep failures that started inside the analysis period and have valid times
df = df.dropna(subset=[ASSET, START, END])
df = df[(df[START] >= PERIOD_START) & (df[START] < PERIOD_END)]
df = df[df[END] >= df[START]].copy()

# Repair duration in hours
df['repair_hours'] = (df[END] - df[START]).dt.total_seconds() / 3600.0

total_hours = (PERIOD_END - PERIOD_START).total_seconds() / 3600.0

g = df.groupby(ASSET).agg(
    failures=(START, 'count'),
    downtime_hours=('repair_hours', 'sum'),
    mttr_hours=('repair_hours', 'mean'),
)

# Assumes the asset is scheduled to run for the whole period; replace total_hours
# with real scheduled run hours per asset if you have them.
g['uptime_hours'] = total_hours - g['downtime_hours']
g['mtbf_hours'] = g['uptime_hours'] / g['failures']
g['availability_pct'] = 100.0 * g['uptime_hours'] / total_hours

g = g.sort_values('downtime_hours', ascending=False).round(2)
print(g.to_string())
g.to_csv('mtbf_mttr_by_asset.csv')

MTTR = total repair hours / number of failures
MTBF = (scheduled run hours - total downtime hours) / number of failures
Availability = (scheduled run hours - downtime hours) / scheduled run hours