From 91d67896d13fe39a9f9f6cf2e35492af59d31097 Mon Sep 17 00:00:00 2001
From: Jake Pullen <jpullen@aiimi.com>
Date: Thu, 29 Aug 2024 11:02:15 +0100
Subject: [PATCH] Refactor join conditions in dash_app fix is weekday issue,
 making fridays a weekend update ERD

---
 config/exit_codes.py   |  3 ++-
 dash_app.py            |  6 +++---
 docs/ERD.md            | 21 +++++++++++++++------
 main.py                | 11 +++++++++--
 pipeline/dimensions.py |  2 +-
 5 files changed, 30 insertions(+), 13 deletions(-)

diff --git a/config/exit_codes.py b/config/exit_codes.py
index 5c508c0..d1e9521 100644
--- a/config/exit_codes.py
+++ b/config/exit_codes.py
@@ -10,4 +10,5 @@ NOT_FOUND = 8
 CONFLICT = 9
 MOVE_FILE_ERROR = 10
 DUPLICATE_RESOLUTION_ERROR = 11
-UNIQUE_ID_NOT_FOUND = 12
\ No newline at end of file
+UNIQUE_ID_NOT_FOUND = 12
+NO_DATA_PRODUCED = 13
\ No newline at end of file
diff --git a/dash_app.py b/dash_app.py
index 9533285..d83f408 100644
--- a/dash_app.py
+++ b/dash_app.py
@@ -14,9 +14,9 @@ scheduled_transactions = pl.read_parquet('data/warehouse/scheduled_transactions.
 transactions = pl.read_parquet('data/warehouse/transactions.parquet')
 
 # Join transactions with accounts, categories, and payees to create a master DataFrame
-master_df = transactions.join(categories, left_on='category_id', right_on='id', suffix='_category')\
-                    .join(accounts, left_on='account_id', right_on='id', suffix='_account')\
-                    .join(payees, left_on='payee_id', right_on='id', suffix='_payee')\
+master_df = transactions.join(categories, left_on='category_id', right_on='category_id', suffix='_category')\
+                    .join(accounts, left_on='account_id', right_on='account_id', suffix='_account')\
+                    .join(payees, left_on='payee_id', right_on='payee_id', suffix='_payee')\
                     .join(dates, left_on='transaction_date', right_on='date_id', suffix='_date')\
 
 # Create aggregations
diff --git a/docs/ERD.md b/docs/ERD.md
index 23cc120..b0e2ea1 100644
--- a/docs/ERD.md
+++ b/docs/ERD.md
@@ -34,23 +34,29 @@ erDiagram
     }
     
     DATES {
-        int date_id
-        string date
+        string date_id
+        date date
         int year
         int month
         int day
+        boolean is_weekday
+        int weekday
     }
     
     TRANSACTIONS {
-        int transaction_id
+        str transaction_id
         int account_id
         int category_id
         int payee_id
-        int date_id
+        int transaction_date
         decimal amount
         boolean cleared
         boolean approved
         boolean deleted
+        string memo
+        string flag_color
+        str transfer_account_id
+
     }
     
     SCHEDULED_TRANSACTIONS {
@@ -58,10 +64,14 @@ erDiagram
         int account_id
         int category_id
         int payee_id
-        int date_id
+        str date_first
+        str date_next
         decimal amount
         string frequency
         boolean deleted
+        text memo
+        string flag_color
+        str transfer_account_id
     }
     
     TRANSACTIONS ||--o{ ACCOUNTS : "belongs to"
@@ -73,4 +83,3 @@ erDiagram
     SCHEDULED_TRANSACTIONS ||--o{ PAYEES : "belongs to"
     SCHEDULED_TRANSACTIONS ||--o{ DATES : "scheduled on"
 ```
-
diff --git a/main.py b/main.py
index e06bcec..41f079a 100644
--- a/main.py
+++ b/main.py
@@ -8,7 +8,6 @@ import logging.config
 import logging.handlers
 
 import config.exit_codes as ec
-#from dash_app import app
 from pipeline.pipeline_main import pipeline_main
 
 def set_up_logging():
@@ -58,7 +57,15 @@ config['BUDGET_ID'] = BUDGET_ID
 if __name__ == '__main__':
     try:
         pipeline_main(config)
-      #  app.run() #debug=True)
+        
+        # Check if the data was successfully created
+        data_exists = os.path.exists('data/processed') and os.listdir('data/processed')
+        if data_exists:
+            from dash_app import app
+            app.run() # debug=True
+        else:
+            logging.error('Data pipeline did not produce any data. Dash app will not run.')
+            sys.exit(ec.NO_DATA_PRODUCED)
     except SystemExit as e:
         exit_code = e.code
         if exit_code == ec.SUCCESS:
diff --git a/pipeline/dimensions.py b/pipeline/dimensions.py
index efa1390..146e303 100644
--- a/pipeline/dimensions.py
+++ b/pipeline/dimensions.py
@@ -200,7 +200,7 @@ class DimDate(Dimensions):
         try:
             # Create a new column to indicate if the date is a weekday or weekend
             dates_df = dates_df.with_columns([
-                (pl.col('weekday') < 5).alias('is_weekday')  # True for weekdays (Monday to Friday), False for weekends (Saturday and Sunday)
+                (pl.col('weekday') < 6).alias('is_weekday')  # True for weekdays (Monday to Friday), False for weekends (Saturday and Sunday)
             ])
         except Exception as e:
             logging.error(f"Failed to create a new column to indicate if the date is a weekday or weekend: {e}")