diff --git a/config.yaml b/config.yaml
new file mode 100644
index 0000000..680c808
--- /dev/null
+++ b/config.yaml
@@ -0,0 +1,4 @@
+crm_file: "sample_data/crm.csv"
+clickstream_file: "sample_data/clickstream.csv"
+output_dir: "output"
+log_dir: "logs"
diff --git a/logs/pipeline.log b/logs/pipeline.log
new file mode 100644
index 0000000..1cb4cb9
--- /dev/null
+++ b/logs/pipeline.log
@@ -0,0 +1,64 @@
+INFO:root:=== WEEK 2 PIPELINE START ===
+INFO:root:Loading CRM and clickstream data...
+INFO:root:=== WEEK 2 PIPELINE START ===
+INFO:root:Loading CRM and clickstream data...
+INFO:root:=== WEEK 2 PIPELINE START ===
+INFO:root:Loading CRM and clickstream data...
+INFO:root:=== WEEK 2 PIPELINE START ===
+INFO:root:Loading CRM and clickstream data...
+INFO:root:=== WEEK 2 PIPELINE START ===
+INFO:root:Loading CRM and clickstream data...
+INFO:root:=== WEEK 2 PIPELINE START ===
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
+INFO:root:Loading CRM and clickstream data...
+INFO:root:Hashing user IDs for pseudonymization...
+INFO:root:Merging datasets...
+INFO:root:Unified dataset saved to output\unified_dataset.csv
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..c4f3696
--- /dev/null
+++ b/main.py
@@ -0,0 +1,19 @@
+# main.py
+from src.pipeline.unified_stream import load_and_merge
+from src.pipeline.relative_date_trigger import apply_birthday_recursion
+from src.pipeline.rf_scoring import calculate_rf_score
+from src.pipeline.list_hygiene import apply_list_hygiene
+from src.pipeline.ethics_flags import apply_ethics_checks
+from src.pipeline.deliverability_check import run_deliverability_check
+
+print("=== WEEK 2 PIPELINE START ===")
+
+load_and_merge()
+apply_birthday_recursion()
+calculate_rf_score()
+apply_list_hygiene()
+
+apply_ethics_checks()
+run_deliverability_check()
+
+print("=== WEEK 2 PIPELINE COMPLETE ===")
diff --git a/output/rf_scored_dataset.csv b/output/rf_scored_dataset.csv
new file mode 100644
index 0000000..154cba3
--- /dev/null
+++ b/output/rf_scored_dataset.csv
@@ -0,0 +1,10 @@
+user_id_x,email,birth_date,gender,consent_flag,user_id_hashed,user_id_y,timestamp,page_depth,dwell_time,session_id,birthday_trigger,recency_index,rf_score
+4,dana@outlook.com,1992-05-30,F,True,4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a,4,2026-01-25 16:45:00+00:00,3,60,401,1992-04-30,28,0.034482758620689655
+3,charlie@tempmail.com,2000-11-21,M,False,4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce,3,2026-01-05 12:30:00+00:00,2,30,301,2000-10-21,48,0.02040816326530612
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-01-15 09:15:00+00:00,5,120,101,1990-01-17,38,0.02564102564102564
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-02-01 10:20:00+00:00,3,90,102,1990-01-17,21,0.045454545454545456
+7,grace@no-reply.com,1993-03-15,F,True,7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451,7,2025-09-15 17:10:00+00:00,2,45,701,1993-02-15,160,0.006211180124223602
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2025-12-20 14:10:00+00:00,4,60,201,1985-06-05,64,0.015384615384615385
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2026-02-10 08:50:00+00:00,6,180,202,1985-06-05,13,0.07142857142857142
+6,frank@gmail.com,1995-12-01,M,True,e7f6c011776e8db7cd330b54174fd76f7d0216b612387a5ffcfb81e6f0919683,6,2026-01-30 09:00:00+00:00,4,120,601,1995-11-01,24,0.04
+5,eric@mailinator.com,1988-09-10,M,True,ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d,5,2025-08-01 11:00:00+00:00,5,150,501,1988-08-10,205,0.0048543689320388345
diff --git a/output/unified_dataset.csv b/output/unified_dataset.csv
new file mode 100644
index 0000000..3241e63
--- /dev/null
+++ b/output/unified_dataset.csv
@@ -0,0 +1,10 @@
+user_id_x,email,birth_date,gender,consent_flag,user_id_hashed,user_id_y,timestamp,page_depth,dwell_time,session_id
+4,dana@outlook.com,1992-05-30,F,True,4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a,4,2026-01-25 16:45:00+00:00,3,60,401
+3,charlie@tempmail.com,2000-11-21,M,False,4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce,3,2026-01-05 12:30:00+00:00,2,30,301
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-01-15 09:15:00+00:00,5,120,101
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-02-01 10:20:00+00:00,3,90,102
+7,grace@no-reply.com,1993-03-15,F,True,7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451,7,2025-09-15 17:10:00+00:00,2,45,701
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2025-12-20 14:10:00+00:00,4,60,201
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2026-02-10 08:50:00+00:00,6,180,202
+6,frank@gmail.com,1995-12-01,M,True,e7f6c011776e8db7cd330b54174fd76f7d0216b612387a5ffcfb81e6f0919683,6,2026-01-30 09:00:00+00:00,4,120,601
+5,eric@mailinator.com,1988-09-10,M,True,ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d,5,2025-08-01 11:00:00+00:00,5,150,501
diff --git a/output/unified_dataset_cleaned.csv b/output/unified_dataset_cleaned.csv
new file mode 100644
index 0000000..42d281b
--- /dev/null
+++ b/output/unified_dataset_cleaned.csv
@@ -0,0 +1,10 @@
+user_id_x,email,birth_date,gender,consent_flag,user_id_hashed,user_id_y,timestamp,page_depth,dwell_time,session_id,birthday_trigger,recency_index,rf_score
+4,dana@outlook.com,1992-05-30,F,True,4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a,4,2026-01-25 16:45:00+00:00,3,60,401,1992-04-30,28,0.0344827586206896
+3,charlie@tempmail.com,2000-11-21,M,False,4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce,3,2026-01-05 12:30:00+00:00,2,30,301,2000-10-21,48,0.0204081632653061
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-01-15 09:15:00+00:00,5,120,101,1990-01-17,38,0.0256410256410256
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-02-01 10:20:00+00:00,3,90,102,1990-01-17,21,0.0454545454545454
+7,grace@no-reply.com,1993-03-15,F,True,7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451,7,2025-09-15 17:10:00+00:00,2,45,701,1993-02-15,160,0.0062111801242236
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2025-12-20 14:10:00+00:00,4,60,201,1985-06-05,64,0.0153846153846153
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2026-02-10 08:50:00+00:00,6,180,202,1985-06-05,13,0.0714285714285714
+6,frank@gmail.com,1995-12-01,M,True,e7f6c011776e8db7cd330b54174fd76f7d0216b612387a5ffcfb81e6f0919683,6,2026-01-30 09:00:00+00:00,4,120,601,1995-11-01,24,0.04
+5,eric@mailinator.com,1988-09-10,M,True,ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d,5,2025-08-01 11:00:00+00:00,5,150,501,1988-08-10,205,0.0048543689320388
diff --git a/output/unified_dataset_deliverable.csv b/output/unified_dataset_deliverable.csv
new file mode 100644
index 0000000..90771ec
--- /dev/null
+++ b/output/unified_dataset_deliverable.csv
@@ -0,0 +1,10 @@
+user_id_x,email,birth_date,gender,consent_flag,user_id_hashed,user_id_y,timestamp,page_depth,dwell_time,session_id,birthday_trigger,recency_index,rf_score,deliverable
+4,dana@outlook.com,1992-05-30,F,True,4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a,4,2026-01-25 16:45:00+00:00,3,60,401,1992-04-30,28,0.0344827586206896,True
+3,charlie@tempmail.com,2000-11-21,M,False,4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce,3,2026-01-05 12:30:00+00:00,2,30,301,2000-10-21,48,0.0204081632653061,True
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-01-15 09:15:00+00:00,5,120,101,1990-01-17,38,0.0256410256410256,True
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-02-01 10:20:00+00:00,3,90,102,1990-01-17,21,0.0454545454545454,True
+7,grace@no-reply.com,1993-03-15,F,True,7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451,7,2025-09-15 17:10:00+00:00,2,45,701,1993-02-15,160,0.0062111801242236,True
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2025-12-20 14:10:00+00:00,4,60,201,1985-06-05,64,0.0153846153846153,True
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2026-02-10 08:50:00+00:00,6,180,202,1985-06-05,13,0.0714285714285714,True
+6,frank@gmail.com,1995-12-01,M,True,e7f6c011776e8db7cd330b54174fd76f7d0216b612387a5ffcfb81e6f0919683,6,2026-01-30 09:00:00+00:00,4,120,601,1995-11-01,24,0.04,True
+5,eric@mailinator.com,1988-09-10,M,True,ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d,5,2025-08-01 11:00:00+00:00,5,150,501,1988-08-10,205,0.0048543689320388,True
diff --git a/output/unified_dataset_ethics.csv b/output/unified_dataset_ethics.csv
new file mode 100644
index 0000000..abbfeac
--- /dev/null
+++ b/output/unified_dataset_ethics.csv
@@ -0,0 +1,10 @@
+user_id_x,email,birth_date,gender,consent_flag,user_id_hashed,user_id_y,timestamp,page_depth,dwell_time,session_id,birthday_trigger,recency_index,rf_score,sensitive_flag
+4,dana@outlook.com,1992-05-30,F,True,4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a,4,2026-01-25 16:45:00+00:00,3,60,401,1992-04-30,28,0.0344827586206896,False
+3,charlie@tempmail.com,2000-11-21,M,False,4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce,3,2026-01-05 12:30:00+00:00,2,30,301,2000-10-21,48,0.0204081632653061,False
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-01-15 09:15:00+00:00,5,120,101,1990-01-17,38,0.0256410256410256,False
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-02-01 10:20:00+00:00,3,90,102,1990-01-17,21,0.0454545454545454,False
+7,grace@no-reply.com,1993-03-15,F,True,7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451,7,2025-09-15 17:10:00+00:00,2,45,701,1993-02-15,160,0.0062111801242236,False
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2025-12-20 14:10:00+00:00,4,60,201,1985-06-05,64,0.0153846153846153,False
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2026-02-10 08:50:00+00:00,6,180,202,1985-06-05,13,0.0714285714285714,False
+6,frank@gmail.com,1995-12-01,M,True,e7f6c011776e8db7cd330b54174fd76f7d0216b612387a5ffcfb81e6f0919683,6,2026-01-30 09:00:00+00:00,4,120,601,1995-11-01,24,0.04,False
+5,eric@mailinator.com,1988-09-10,M,True,ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d,5,2025-08-01 11:00:00+00:00,5,150,501,1988-08-10,205,0.0048543689320388,False
diff --git a/output/unified_dataset_with_triggers.csv b/output/unified_dataset_with_triggers.csv
new file mode 100644
index 0000000..265c897
--- /dev/null
+++ b/output/unified_dataset_with_triggers.csv
@@ -0,0 +1,10 @@
+user_id_x,email,birth_date,gender,consent_flag,user_id_hashed,user_id_y,timestamp,page_depth,dwell_time,session_id,birthday_trigger
+4,dana@outlook.com,1992-05-30,F,True,4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a,4,2026-01-25 16:45:00+00:00,3,60,401,1992-04-30
+3,charlie@tempmail.com,2000-11-21,M,False,4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce,3,2026-01-05 12:30:00+00:00,2,30,301,2000-10-21
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-01-15 09:15:00+00:00,5,120,101,1990-01-17
+1,alice@gmail.com,1990-02-17,F,True,6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b,1,2026-02-01 10:20:00+00:00,3,90,102,1990-01-17
+7,grace@no-reply.com,1993-03-15,F,True,7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451,7,2025-09-15 17:10:00+00:00,2,45,701,1993-02-15
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2025-12-20 14:10:00+00:00,4,60,201,1985-06-05
+2,bob@yahoo.com,1985-07-05,M,True,d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35,2,2026-02-10 08:50:00+00:00,6,180,202,1985-06-05
+6,frank@gmail.com,1995-12-01,M,True,e7f6c011776e8db7cd330b54174fd76f7d0216b612387a5ffcfb81e6f0919683,6,2026-01-30 09:00:00+00:00,4,120,601,1995-11-01
+5,eric@mailinator.com,1988-09-10,M,True,ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d,5,2025-08-01 11:00:00+00:00,5,150,501,1988-08-10
diff --git a/requirement.txt b/requirement.txt
new file mode 100644
index 0000000..e69de29
diff --git a/sample_data/clickstream.csv b/sample_data/clickstream.csv
new file mode 100644
index 0000000..473f134
--- /dev/null
+++ b/sample_data/clickstream.csv
@@ -0,0 +1,10 @@
+user_id,timestamp,page_depth,dwell_time,session_id
+1,2026-01-15 09:15:00,5,120,101
+1,2026-02-01 10:20:00,3,90,102
+2,2025-12-20 14:10:00,4,60,201
+2,2026-02-10 08:50:00,6,180,202
+3,2026-01-05 12:30:00,2,30,301
+4,2026-01-25 16:45:00,3,60,401
+5,2025-08-01 11:00:00,5,150,501
+6,2026-01-30 09:00:00,4,120,601
+7,2025-09-15 17:10:00,2,45,701
diff --git a/sample_data/crm.csv b/sample_data/crm.csv
new file mode 100644
index 0000000..6c6031c
--- /dev/null
+++ b/sample_data/crm.csv
@@ -0,0 +1,8 @@
+user_id,email,birth_date,gender,consent_flag
+1,alice@gmail.com,1990-02-17,F,True
+2,bob@yahoo.com,1985-07-05,M,True
+3,charlie@tempmail.com,2000-11-21,M,False
+4,dana@outlook.com,1992-05-30,F,True
+5,eric@mailinator.com,1988-09-10,M,True
+6,frank@gmail.com,1995-12-01,M,True
+7,grace@no-reply.com,1993-03-15,F,True
diff --git a/src/__init__.py b/src/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/__pycache__/__init__.cpython-312.pyc b/src/__pycache__/__init__.cpython-312.pyc
new file mode 100644
index 0000000..1e388c6
Binary files /dev/null and b/src/__pycache__/__init__.cpython-312.pyc differ
diff --git a/src/automation/__init__.py b/src/automation/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/pipeline/__init__.py b/src/pipeline/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/pipeline/__pycache__/__init__.cpython-312.pyc b/src/pipeline/__pycache__/__init__.cpython-312.pyc
new file mode 100644
index 0000000..9f12bf5
Binary files /dev/null and b/src/pipeline/__pycache__/__init__.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/config_loader.cpython-312.pyc b/src/pipeline/__pycache__/config_loader.cpython-312.pyc
new file mode 100644
index 0000000..62173ca
Binary files /dev/null and b/src/pipeline/__pycache__/config_loader.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/deliverability_check.cpython-312.pyc b/src/pipeline/__pycache__/deliverability_check.cpython-312.pyc
new file mode 100644
index 0000000..6f0ab3a
Binary files /dev/null and b/src/pipeline/__pycache__/deliverability_check.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/ethics_flags.cpython-312.pyc b/src/pipeline/__pycache__/ethics_flags.cpython-312.pyc
new file mode 100644
index 0000000..6f93269
Binary files /dev/null and b/src/pipeline/__pycache__/ethics_flags.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/list_hygiene.cpython-312.pyc b/src/pipeline/__pycache__/list_hygiene.cpython-312.pyc
new file mode 100644
index 0000000..9119a49
Binary files /dev/null and b/src/pipeline/__pycache__/list_hygiene.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/relative_date_trigger.cpython-312.pyc b/src/pipeline/__pycache__/relative_date_trigger.cpython-312.pyc
new file mode 100644
index 0000000..f048b2f
Binary files /dev/null and b/src/pipeline/__pycache__/relative_date_trigger.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/rf_scoring.cpython-312.pyc b/src/pipeline/__pycache__/rf_scoring.cpython-312.pyc
new file mode 100644
index 0000000..9741292
Binary files /dev/null and b/src/pipeline/__pycache__/rf_scoring.cpython-312.pyc differ
diff --git a/src/pipeline/__pycache__/unified_stream.cpython-312.pyc b/src/pipeline/__pycache__/unified_stream.cpython-312.pyc
new file mode 100644
index 0000000..f97b20a
Binary files /dev/null and b/src/pipeline/__pycache__/unified_stream.cpython-312.pyc differ
diff --git a/src/pipeline/config_loader.py b/src/pipeline/config_loader.py
new file mode 100644
index 0000000..df6bac7
--- /dev/null
+++ b/src/pipeline/config_loader.py
@@ -0,0 +1,9 @@
+import os
+import yaml
+
+# Project root
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+config_path = os.path.join(BASE_DIR, "config.yaml")
+
+with open(config_path, "r") as f:
+    config = yaml.safe_load(f)
diff --git a/src/pipeline/deliverability_check.py b/src/pipeline/deliverability_check.py
new file mode 100644
index 0000000..6585405
--- /dev/null
+++ b/src/pipeline/deliverability_check.py
@@ -0,0 +1,15 @@
+# src/pipeline/deliverability_check.py
+import pandas as pd
+import os
+from .config_loader import config
+
+def run_deliverability_check():
+    input_file = os.path.join(config["output_dir"], "unified_dataset_cleaned.csv")
+    df = pd.read_csv(input_file)
+    
+    # Basic simulation of SPF/DKIM validation
+    df["deliverable"] = df["email"].str.contains("@")
+    
+    output_file = os.path.join(config["output_dir"], "unified_dataset_deliverable.csv")
+    df.to_csv(output_file, index=False)
+    return df
diff --git a/src/pipeline/ethics_flags.py b/src/pipeline/ethics_flags.py
new file mode 100644
index 0000000..688e41d
--- /dev/null
+++ b/src/pipeline/ethics_flags.py
@@ -0,0 +1,27 @@
+# src/pipeline/ethics_flags.py
+import pandas as pd
+import os
+from .config_loader import config
+
+def apply_ethics_checks():
+    input_file = os.path.join(config["output_dir"], "unified_dataset_cleaned.csv")
+    df = pd.read_csv(input_file)
+    
+    # List of sensitive columns to check
+    sensitive_cols = ["medical_condition", "political_opinion", "dietary_restriction"]
+    
+    # Only include columns that exist in the dataset
+    existing_cols = [col for col in sensitive_cols if col in df.columns]
+    
+    # Apply sensitive flag if any sensitive info is present
+    if existing_cols:
+        df["sensitive_flag"] = df[existing_cols].notna().any(axis=1)
+    else:
+        # If none exist, create the flag with False
+        df["sensitive_flag"] = False
+    
+    # Save output
+    output_file = os.path.join(config["output_dir"], "unified_dataset_ethics.csv")
+    df.to_csv(output_file, index=False)
+    
+    return df
diff --git a/src/pipeline/list_hygiene.py b/src/pipeline/list_hygiene.py
new file mode 100644
index 0000000..fdf6af1
--- /dev/null
+++ b/src/pipeline/list_hygiene.py
@@ -0,0 +1,15 @@
+# src/pipeline/list_hygiene.py
+import pandas as pd
+import os
+from .config_loader import config
+
+def apply_list_hygiene():
+    input_file = os.path.join(config["output_dir"], "rf_scored_dataset.csv")
+    df = pd.read_csv(input_file)
+    
+    # Remove invalid domains, disposable emails
+    df = df[~df["email"].str.contains("example.com|test.com", na=False)]
+    
+    output_file = os.path.join(config["output_dir"], "unified_dataset_cleaned.csv")
+    df.to_csv(output_file, index=False)
+    return df
diff --git a/src/pipeline/relative_date_trigger.py b/src/pipeline/relative_date_trigger.py
new file mode 100644
index 0000000..b55995b
--- /dev/null
+++ b/src/pipeline/relative_date_trigger.py
@@ -0,0 +1,15 @@
+# src/pipeline/relative_date_trigger.py
+import pandas as pd
+import os
+from .config_loader import config
+
+def apply_birthday_recursion():
+    input_file = os.path.join(config["output_dir"], "unified_dataset.csv")
+    df = pd.read_csv(input_file)
+    
+    # Example: 11-month pre-birthday trigger
+    df["birthday_trigger"] = pd.to_datetime(df["birth_date"]) - pd.DateOffset(months=1)
+    
+    output_file = os.path.join(config["output_dir"], "unified_dataset_with_triggers.csv")
+    df.to_csv(output_file, index=False)
+    return df
diff --git a/src/pipeline/rf_scoring.py b/src/pipeline/rf_scoring.py
new file mode 100644
index 0000000..ae80bcd
--- /dev/null
+++ b/src/pipeline/rf_scoring.py
@@ -0,0 +1,18 @@
+# src/pipeline/rf_scoring.py
+import pandas as pd
+import os
+from .config_loader import config
+
+def calculate_rf_score():
+    input_file = os.path.join(config["output_dir"], "unified_dataset_with_triggers.csv")
+    df = pd.read_csv(input_file)
+    
+    # Simple RF scoring (Recency-Frequency)
+    now = pd.Timestamp.now(tz="UTC")
+    df["recency_index"] = (now - pd.to_datetime(df["timestamp"])).dt.days
+
+    df["rf_score"] = 1 / (df["recency_index"] + 1) + df.get("session_count", 0)
+    
+    output_file = os.path.join(config["output_dir"], "rf_scored_dataset.csv")
+    df.to_csv(output_file, index=False)
+    return df
diff --git a/src/pipeline/unified_stream.py b/src/pipeline/unified_stream.py
new file mode 100644
index 0000000..d27f90d
--- /dev/null
+++ b/src/pipeline/unified_stream.py
@@ -0,0 +1,32 @@
+# src/pipeline/unified_stream.py
+import os
+import pandas as pd
+import hashlib
+import logging
+from .config_loader import config
+
+os.makedirs(config["output_dir"], exist_ok=True)
+os.makedirs(config["log_dir"], exist_ok=True)
+logging.basicConfig(filename=os.path.join(config["log_dir"], "pipeline.log"),
+                    level=logging.INFO)
+
+def hash_user_id(user_id):
+    return hashlib.sha256(str(user_id).encode()).hexdigest()
+
+def load_and_merge():
+    logging.info("Loading CRM and clickstream data...")
+    crm = pd.read_csv(config["crm_file"])
+    click = pd.read_csv(config["clickstream_file"])
+    
+    logging.info("Hashing user IDs for pseudonymization...")
+    crm["user_id_hashed"] = crm["user_id"].apply(hash_user_id)
+    click["user_id_hashed"] = click["user_id"].apply(hash_user_id)
+    
+    logging.info("Merging datasets...")
+    merged = pd.merge(crm, click, on="user_id_hashed", how="outer")
+    merged["timestamp"] = pd.to_datetime(merged["timestamp"], utc=True)
+    
+    output_file = os.path.join(config["output_dir"], "unified_dataset.csv")
+    merged.to_csv(output_file, index=False)
+    logging.info(f"Unified dataset saved to {output_file}")
+    return merged
diff --git a/wiki/gdpr-audit.md b/wiki/gdpr-audit.md
new file mode 100644
index 0000000..3ccea82
--- /dev/null
+++ b/wiki/gdpr-audit.md
@@ -0,0 +1,54 @@
+# \# GDPR Adequacy Checklist
+
+# 
+
+# \## Governance \& Breach Protocols
+
+# \- DPO appointed and documented
+
+# \- 72-hour breach notification process defined
+
+# 
+
+# \## Consent \& Data Collection
+
+# \- No pre-ticked marketing consent boxes
+
+# \- Explicit consent required for birthday listings
+
+# 
+
+# \## Sensitive Data Handling
+
+# \- Medical data restricted to "unwell" status
+
+# \- Dietary data shared only with explicit consent
+
+# 
+
+# \## International Data Transfers
+
+# \- Photo/video sharing audited for adequacy mechanisms
+
+# 
+
+
+## Data Protection Officer (DPO)
+Name: [Your Name Here]
+Role: [Your Role Here]
+Contact: [email@example.com]
+Date Appointed: [YYYY-MM-DD]
+
+## Data Protection Officer (DPO)
+Name:
+Role:
+Contact:
+Date Appointed:
+
+## Regulatory Feature Specifications
+
+### Right of Access (Article 15)
+Users can request a downloadable summary of stored personal data.
+
+### Right of Erasure (Article 17)
+Users can trigger full deletion across all systems and subprocessors.