expanding dash

2025-04-05 11:04:40 +01:00
parent 5af82e5753
commit b573b3b9bc
6 changed files with 206 additions and 77 deletions
@@ -0,0 +1,110 @@
+import polars as pl
+import plotly.express as px
+import pandas as pd
+import logging
+import sys
+import config.exit_codes as ec
+
+
+
+try:
+    accounts = pl.read_parquet('data/warehouse/accounts.parquet')
+    categories = pl.read_parquet('data/warehouse/categories.parquet')
+    dates = pl.read_parquet('data/warehouse/dates.parquet')
+    payees = pl.read_parquet('data/warehouse/payees.parquet')
+    scheduled_transactions = pl.read_parquet('data/warehouse/scheduled_transactions.parquet')
+    transactions = pl.read_parquet('data/warehouse/transactions.parquet')
+except FileNotFoundError:
+    logging.error('Data warehouse files not found. Run the data pipeline to create them.')
+    sys.exit(ec.MISSING_DATA_FILES)
+
+try:
+    # Join transactions with accounts, categories, and payees to create a master DataFrame
+    master_transactions = 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')\
+                        # date filter for callback date range
+                        #.filter(pl.col('transaction_date'))
+    
+except Exception as e:
+    logging.error(f'Error joining DataFrames: {e}')
+    sys.exit(ec.BAD_JOIN)
+
+# Create aggregations
+spend_per_day = master_transactions.sql('''
+    SELECT 
+        date,
+        year,
+        month,
+        day,
+        ABS(SUM(transaction_amount)) as total
+    FROM self
+    WHERE category_name != 'Inflow: Ready to Assign'
+    GROUP BY date, year, month, day
+    ORDER BY date DESC
+    '''
+)
+
+spend_per_category = master_transactions.sql('''
+    SELECT
+        category_name,
+        ABS(SUM(transaction_amount)) as total
+    FROM self
+    WHERE category_name != 'Inflow: Ready to Assign'
+    GROUP BY category_name
+    ORDER BY total DESC
+    '''
+)
+
+spend_per_payee = master_transactions.sql('''
+    SELECT
+        payee_name,
+        ABS(SUM(transaction_amount)) as total
+    FROM self
+    WHERE payee_name != 'Starting Balance'
+        AND transaction_amount < 0
+    GROUP BY payee_name
+    ORDER BY total DESC
+    '''
+)
+total_spend = master_transactions.sql('''
+    SELECT ABS(SUM(transaction_amount)) AS total
+    FROM self
+    WHERE payee_name != 'Starting Balance'
+        AND transaction_amount < 0
+''').item()
+
+
+# Convert DataFrame to list of dictionaries
+spend_per_day_data = spend_per_day.to_dicts()
+spend_per_category_data = spend_per_category.to_dicts()
+spend_per_payee_data = spend_per_payee.to_dicts()
+
+
+# Convert list of dictionaries to Pandas DataFrame
+spend_per_day_df = pd.DataFrame(spend_per_day_data)
+spend_per_category_df = pd.DataFrame(spend_per_category_data)
+spend_per_payee_df = pd.DataFrame(spend_per_payee_data)
+
+
+spend_per_day_line = px.line(spend_per_day_df, x="date", y="total")
+spend_per_day_line.update_layout(
+    plot_bgcolor='black',
+    paper_bgcolor='black',
+    font_color='white'
+)
+
+spend_per_category_bar = px.bar(spend_per_category_df, x="category_name", y="total")
+spend_per_category_bar.update_layout(
+    plot_bgcolor='black',
+    paper_bgcolor='black',
+    font_color='white'
+)
+
+spend_per_payee_bar = px.bar(spend_per_payee_df, x="payee_name", y="total")
+spend_per_payee_bar.update_layout(
+    plot_bgcolor='black',
+    paper_bgcolor='black',
+    font_color='white'
+)