Enron Correspondence EDA
Email corpus analysis —
Lucius-Morningstar/docclass-merged
correspondence feed
517,390
Messages
150
Custodians
100%
Parseable
83.1%
Internal
756
Median Body (chars)
4
Attorney Demands
Interactive Charts
Static Figures
Reports
Data
Corpus EDA
Claims EDA
Interactive Charts
Subclass Distribution (pie)
Messages by Hour of Day
Messages by Day of Week
Volume Over Time (quarterly)
Internal vs External Senders
Top 10 Senders by Volume
Email Body Length Distribution
Custodian Activity Distribution
Message Fan-Out (recipients)
Thread Size Distribution
Unique vs Duplicate Rate
Recipient Role Distribution
Static Figures (12)
01 — Subclass Distribution
02 — Hour of Day
03 — Day of Week
04 — Monthly Volume
05 — Internal vs External
06 — Top Senders
07 — Body Length
08 — Custodian Activity
09 — Fan-Out
10 — Thread Sizes
11 — Duplicates
12 — Recipient Roles
Reports
Final Report
raw markdown
Loading...
Findings
raw markdown
Loading...
Subclasses Discovery
raw markdown
Loading...
Full Report
raw markdown
Loading...
Data Files
📊
spot_check.csv
Random sample for verification
📄
pipeline/README.md
Pipeline integration notes
×
↑