changes to make dash app work

dash_app.py

@@ -1,47 +1,106 @@
+'''Module to create a Dash app that displays visualizations of YNAB data.'''
+
 import polars as pl
 import plotly.express as px
 from dash import Dash, html, dcc
 import dash_bootstrap_components as dbc
-from dash.dash_table import DataTable
+import pandas as pd
 
-# Incorporate data
-df = pl.read_parquet('data/warehouse/transactions.parquet')
-print("Data loaded from Parquet file:")
-print(df)
+# Load data
+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')
 
-relevant_data = df.sql('''
+# 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')\
+                    .join(dates, left_on='transaction_date', right_on='date_id', suffix='_date')\
+
+# Create aggregations
+spend_per_day = master_df.sql('''
     SELECT 
         date,
-        sum(transaction_amount) as total
+        year,
+        month,
+        day,
+        ABS(SUM(transaction_amount)) as total
     FROM self
-    GROUP BY date
+    WHERE category_name != 'Inflow: Ready to Assign'
+    GROUP BY date, year, month, day
     ORDER BY date DESC
     '''
 )
-print("Data after SQL query:")
-print(relevant_data)
+
+spend_per_category = master_df.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_df.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
+    '''
+)
 
 # Convert DataFrame to list of dictionaries
-data = relevant_data.to_dicts()
-print("Data converted to list of dictionaries:")
-print(data)
+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()
 
-# Initialize the app with a dark theme
-app = Dash(external_stylesheets=[dbc.themes.DARKLY])
+# 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)
 
-# Create the line graph with dark mode styling
-fig = px.line(relevant_data.to_pandas(), x="date", y="total", title='Spend Per Day')
-fig.update_layout(
+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'
+)
+
+# Initialize the app with a dark theme
+app = Dash(external_stylesheets=[dbc.themes.DARKLY])
+
 # App layout
 app.layout = dbc.Container(
     [
         dbc.Row(
-            dbc.Col(html.Div("My First App with My Data", className="text-center text-light"), width=12)
+            dbc.Col(
+                html.Div("Data Pipeline For YNAB, Preview Visualisations",
+                        className="text-center text-light"),
+                        width=12
+                )
         ),
         dbc.Row(
             [
@@ -49,14 +108,24 @@ app.layout = dbc.Container(
                     dbc.Card(
                         dbc.CardBody(
                             [
-                                html.H4("Data Table", className="card-title"),
-                                DataTable(
-                                    data=data, 
-                                    columns=[{"name": i, "id": i} for i in relevant_data.columns], 
-                                    page_size=5,
-                                    style_header={'backgroundColor': 'black', 'color': 'white'},
-                                    style_cell={'backgroundColor': 'black', 'color': 'white'}
-                                )
+                                html.H4("Spend Per Day", className="card-title"),
+                                dcc.Graph(figure=spend_per_day_line)
+                            ]
+                        ),
+                        className="mb-4"
+                    ),
+                    width=12
+                )
+            ]
+        ),
+        dbc.Row(
+            [
+                dbc.Col(
+                    dbc.Card(
+                        dbc.CardBody(
+                            [
+                                html.H4("Spend Per Category", className="card-title"),
+                                dcc.Graph(figure=spend_per_category_bar)
                             ]
                         ),
                         className="mb-4"
@@ -67,8 +136,8 @@ app.layout = dbc.Container(
                     dbc.Card(
                         dbc.CardBody(
                             [
-                                html.H4("Spend Per Day", className="card-title"),
-                                dcc.Graph(figure=fig)
+                                html.H4("Spend Per Payee", className="card-title"),
+                                dcc.Graph(figure=spend_per_payee_bar)
                             ]
                         ),
                         className="mb-4"

pipeline/dimensions.py

@@ -191,6 +191,18 @@ class DimDate(Dimensions):
         except Exception as e:
             logging.error(f"Failed to create a new column to indicate if the date is a weekday or weekend: {e}")
             return
+        
+        # Create a primary key by concatenating year, month, and day with no separators
+        try:
+            dates_df = dates_df.with_columns([
+                (pl.col('year').cast(pl.Utf8) + 
+                 pl.col('month').cast(pl.Utf8).str.zfill(2) +
+                 pl.col('day').cast(pl.Utf8).str.zfill(2)
+                ).alias('date_id')
+            ])
+        except Exception as e:
+            logging.error(f"Failed to create the primary key column: {e}")
+            return
         # Write the DataFrame to a new parquet file
         logging.info("Writing the transformed dates DataFrame to parquet file")
         try:

pipeline/facts.py

@@ -27,12 +27,23 @@ class FactTransactions(Facts):
         
         # Transform the DataFrame
         logging.info("Transforming the transactions DataFrame")
+        try:
+            # Ensure the date column is in datetime format
+            transactions_df = transactions_df.with_columns([
+                pl.col("date").str.strptime(pl.Date, format="%Y-%m-%d").alias("date")
+            ])
+        except Exception as e:
+            logging.error(f"Failed to covert the date to date format: {e}")
+            return
+        
         try:
             transactions_df = (
                 transactions_df
                 .with_columns([
                     pl.col("id").alias("transaction_id"),
-                    pl.col("date").alias("transaction_date"),
+                    (pl.col("date").dt.year().cast(pl.Utf8) +
+                        pl.col("date").dt.month().cast(pl.Utf8).str.zfill(2) +
+                        pl.col("date").dt.day().cast(pl.Utf8).str.zfill(2)).alias("transaction_date"),
                     pl.col("amount").alias("transaction_amount"),
                     pl.col("memo").alias("transaction_memo"),
                     pl.col("cleared").alias("transaction_cleared"),
@@ -45,7 +56,7 @@ class FactTransactions(Facts):
                 ])
                 .with_columns([
                     pl.col("memo").fill_null("unknown"),
-                    (pl.col("amount") / 100).alias("transaction_amount"),
+                    (pl.col("amount") / 1000).alias("transaction_amount"),
                 ])
                 .drop([
                     "transfer_transaction_id", "matched_transaction_id", "import_id",
@@ -98,7 +109,7 @@ class FactScheduledTransactions(Facts):
                 ])
                 .with_columns([
                     pl.col("memo").fill_null("unknown"),
-                    (pl.col("amount") / 100).alias("scheduled_transaction_amount"),
+                    (pl.col("amount") / 1000).alias("scheduled_transaction_amount"),
                 ])
                 .drop([
                     "subtransactions", "deleted","flag_name","account_name",

pipeline/raw_to_base.py

@@ -130,7 +130,7 @@ Then move the files back in one at a time oldest to newest and run again for eac
                 df = df.with_columns(
                     pl.when(pl.col(col).is_null())
                     .then(pl.lit("null"))
-                    .otherwise(pl.col(col).map_elements(lambda x: str(x) if x is not None else "null"))
+                    .otherwise(pl.col(col).map_elements(lambda x: str(x) if x is not None else "null", return_dtype=pl.Utf8))
                     .alias(col)
                 )
         return df