Jake/data_pipeline_for_YNAB
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

starting to implement callbacks

Browse Source
This commit is contained in:
Jake
2025-04-05 11:49:15 +01:00
parent b573b3b9bc
commit c9c287aa8a
4 changed files with 190 additions and 175 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main.py
+1 -1
View File
@@ -60,7 +60,7 @@ if __name__ == '__main__':
# Check if the data was successfully created # Check if the data was successfully created
data_exists = os.path.exists('data/processed') and os.listdir('data/processed') data_exists = os.path.exists('data/processed') and os.listdir('data/processed')
if data_exists: if data_exists:
app.run() # debug=True app.run(debug=True)
else: else:
logging.error('Data pipeline did not produce any data. Dash app will not run.') logging.error('Data pipeline did not produce any data. Dash app will not run.')
sys.exit(ec.NO_DATA_PRODUCED) sys.exit(ec.NO_DATA_PRODUCED)
visuals/components.py
+86 -69
View File
@@ -4,8 +4,7 @@ import pandas as pd
import logging import logging
import sys import sys
import config.exit_codes as ec import config.exit_codes as ec
import datetime
try: try:
accounts = pl.read_parquet('data/warehouse/accounts.parquet') accounts = pl.read_parquet('data/warehouse/accounts.parquet')
@@ -31,80 +30,98 @@ except Exception as e:
logging.error(f'Error joining DataFrames: {e}') logging.error(f'Error joining DataFrames: {e}')
sys.exit(ec.BAD_JOIN) sys.exit(ec.BAD_JOIN)
# Create aggregations def update_dates(start_date, end_date):
spend_per_day = master_transactions.sql(''' start_year = int(start_date[:4])
SELECT start_month = int(start_date[5:7])
date, start_day = int(start_date[8:10])
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(''' end_year = int(end_date[:4])
SELECT end_month = int(end_date[5:7])
category_name, end_day = int(end_date[8:10])
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(''' master_data = master_transactions.filter(
SELECT (pl.col('year_date') >= start_year ) & (pl.col('year_date') <= end_year) &
payee_name, (pl.col('month_date') >= start_month ) & (pl.col('month_date') <= end_month) &
ABS(SUM(transaction_amount)) as total (pl.col('day_date') >= start_day ) & (pl.col('day_date') <= end_day)
FROM self )
WHERE payee_name != 'Starting Balance' return master_data
AND transaction_amount < 0
GROUP BY payee_name def update_data(master_data):
ORDER BY total DESC # Create aggregations
''' spend_per_day = master_data.sql('''
) SELECT
total_spend = master_transactions.sql(''' date,
SELECT ABS(SUM(transaction_amount)) AS total year,
FROM self month,
WHERE payee_name != 'Starting Balance' day,
AND transaction_amount < 0 ABS(SUM(transaction_amount)) as total
''').item() FROM self
WHERE category_name != 'Inflow: Ready to Assign'
GROUP BY date, year, month, day
ORDER BY date DESC
'''
)
spend_per_category = master_data.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_data.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_data.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 # Convert DataFrame to list of dictionaries
spend_per_day_data = spend_per_day.to_dicts() spend_per_day_data = spend_per_day.to_dicts()
spend_per_category_data = spend_per_category.to_dicts() spend_per_category_data = spend_per_category.to_dicts()
spend_per_payee_data = spend_per_payee.to_dicts() spend_per_payee_data = spend_per_payee.to_dicts()
# Convert list of dictionaries to Pandas DataFrame # Convert list of dictionaries to Pandas DataFrame
spend_per_day_df = pd.DataFrame(spend_per_day_data) spend_per_day_df = pd.DataFrame(spend_per_day_data)
spend_per_category_df = pd.DataFrame(spend_per_category_data) spend_per_category_df = pd.DataFrame(spend_per_category_data)
spend_per_payee_df = pd.DataFrame(spend_per_payee_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 = px.line(spend_per_day_df, x="date", y="total")
spend_per_day_line.update_layout( spend_per_day_line.update_layout(
plot_bgcolor='black', plot_bgcolor='black',
paper_bgcolor='black', paper_bgcolor='black',
font_color='white' font_color='white'
) )
spend_per_category_bar = px.bar(spend_per_category_df, x="category_name", y="total") spend_per_category_bar = px.bar(spend_per_category_df, x="category_name", y="total")
spend_per_category_bar.update_layout( spend_per_category_bar.update_layout(
plot_bgcolor='black', plot_bgcolor='black',
paper_bgcolor='black', paper_bgcolor='black',
font_color='white' font_color='white'
) )
spend_per_payee_bar = px.bar(spend_per_payee_df, x="payee_name", y="total") spend_per_payee_bar = px.bar(spend_per_payee_df, x="payee_name", y="total")
spend_per_payee_bar.update_layout( spend_per_payee_bar.update_layout(
plot_bgcolor='black', plot_bgcolor='black',
paper_bgcolor='black', paper_bgcolor='black',
font_color='white' font_color='white'
) )
return spend_per_day_line, spend_per_category_bar, spend_per_payee_bar, total_spend
visuals/dash_app.py
+11 -23
View File
@@ -4,35 +4,23 @@ import dash_bootstrap_components as dbc
from dash.dependencies import Input, Output from dash.dependencies import Input, Output
import visuals.layout as layout import visuals.layout as layout
import visuals.components as charts
def update_visuals(start_date, end_date):
# Update the data based on the selected date range
master = charts.update_dates(start_date, end_date)
data = charts.update_data(master)
return layout.create_layout(data)
# Initialize the app with a dark theme # Initialize the app with a dark theme
app = dash.Dash(external_stylesheets=[dbc.themes.DARKLY]) app = dash.Dash(external_stylesheets=[dbc.themes.DARKLY])
# App layout # App layout
app.layout = layout.create_layout() app.layout = update_visuals()
# Update toggle visibility of off-canvas section
@app.callback( @app.callback(
Output('off-canvas-section', 'style'), [
[Input('toggle-button', 'n_clicks')] Input('date-picker-range', 'start_date'),
Input('date-picker-range', 'end_date')
]
) )
def update_off_canvas_section(n_clicks):
if n_clicks is not None:
return {'display': 'block'}
else:
return {'display': 'none'}
# Update off-canvas section with date range picker
@app.callback(
Output('off-canvas-section', 'children'),
[Input('toggle-button', 'n_clicks')]
)
def update_off_canvas_content(n_clicks):
if n_clicks is not None:
# Include a date range picker library (e.g., Dash Bootstrap components) for the off-canvas section
return [
dbc.Input(id='date-picker-start', type='date'),
dbc.Input(id='date-picker-end', type='date')
]
visuals/layout.py
+90 -80
View File
@@ -2,104 +2,114 @@ from dash import html, dcc
from datetime import date from datetime import date
import dash_bootstrap_components as dbc import dash_bootstrap_components as dbc
import visuals.components as charts
def create_layout(): def create_layout(data):
main_body = create_main_body() main_body = create_main_body(data)
sidebar = create_sidebar() topbar = create_topbar()
return [html.Div(main_body + sidebar)] return [html.Div(topbar + main_body)]
def create_sidebar():
def create_topbar():
return [ return [
html.Div(id='off-canvas-section', style={'display': 'none'}), dbc.Container(
dbc.Row( dbc.Row(
dbc.Col( [
dcc.DatePickerRange( dbc.Col(
id='date-picker-range', dcc.DatePickerRange(
start_date=date(2024, 1, 1), id="date-picker-range",
end_date=date(2026, 1, 1) start_date=date(2024, 1, 1),
), end_date=date(2026, 1, 1),
width=4 ),
), width=4,
align='center' ),
dbc.Col(
html.Button("Change Date Range", id="date-range-confirm-button"),
width=2,
),
]
)
) )
] ]
def create_main_body(): def create_main_body(data):
return [html.Button('Toggle Off-Canvas', id='toggle-button'), return [
dbc.Container( dbc.Container(
[ [
dbc.Row( dbc.Row(
dbc.Col(
html.Div(
"Data Pipeline For YNAB, Preview Visualisations",
className="text-center text-light",
),
width=12,
)
),
dbc.Row(
[
dbc.Col( dbc.Col(
dbc.Card( html.Div(
dbc.CardBody( "Data Pipeline For YNAB, Preview Visualisations",
[ className="text-center text-light",
html.H4("Spend Per Day", className="card-title"),
dcc.Graph(figure=charts.spend_per_day_line),
]
),
className="mb-4",
), ),
width=12, width=12,
) )
] ),
), dbc.Row(
dbc.Row( [
[ dbc.Col(
dbc.Col( dbc.Card(
dbc.Card( dbc.CardBody(
dbc.CardBody( [
[ html.H4(
html.H4( "Spend Per Day", className="card-title"
"Spend Per Category", className="card-title" ),
), dcc.Graph(figure=data.spend_per_day_line),
dcc.Graph(figure=charts.spend_per_category_bar), ]
] ),
className="mb-4",
), ),
className="mb-4", width=12,
)
]
),
dbc.Row(
[
dbc.Col(
dbc.Card(
dbc.CardBody(
[
html.H4(
"Spend Per Category", className="card-title"
),
dcc.Graph(figure=data.spend_per_category_bar),
]
),
className="mb-4",
),
width=5,
), ),
width=5, dbc.Col(
), dbc.Card(
dbc.Col( dbc.CardBody(
dbc.Card( [
dbc.CardBody( dcc.Markdown(f"""
[
dcc.Markdown(f"""
## Total Spend: ## Total Spend:
### £{charts.total_spend:,} ### £{data.total_spend:,}
"""), """),
] ]
),
className="mb-4",
), ),
className="mb-4", width=2,
), ),
width=2, dbc.Col(
), dbc.Card(
dbc.Col( dbc.CardBody(
dbc.Card( [
dbc.CardBody( html.H4(
[ "Spend Per Payee", className="card-title"
html.H4("Spend Per Payee", className="card-title"), ),
dcc.Graph(figure=charts.spend_per_payee_bar), dcc.Graph(figure=data.spend_per_payee_bar),
] ]
),
className="mb-4",
), ),
className="mb-4", width=5,
), ),
width=5, ]
), ),
] ],
), fluid=True,
], ),
fluid=True,
)
] ]