Add Python script to process CSV files and generate formatted output

README.md

@@ -1,2 +1,45 @@
-# Quantium starter repo
-This repo contains everything you need to get started on the program! Good luck!
+import pandas as pd
+import dash
+from dash import dcc, html
+from dash.dependencies import Input, Output
+import plotly.express as px
+
+# Read the CSV file containing sales data
+sales_data = pd.read_csv('https://gist.githubusercontent.com/chriddyp/c78bf172206ce24f77d6363a2d754b59/raw/c353e8ef842413cae56ae3920b8fd78468aa4cb2/usa-agricultural-exports-2011.csv')
+
+
+# Convert 'date' column to datetime
+sales_data['date'] = pd.to_datetime(sales_data['date'])
+
+# Sort data by date
+sales_data = sales_data.sort_values(by='date')
+
+# Initialize the Dash app
+app = dash.Dash(__name__)
+
+# Define the layout of the app
+app.layout = html.Div([
+    html.H1("Pink Morsel Sales Visualizer"),
+    dcc.Graph(id='sales-chart'),
+])
+
+# Define callback to update the chart based on user input
+@app.callback(
+    Output('sales-chart', 'figure'),
+    [Input('sales-chart', 'hoverData')]
+)
+def update_chart(hoverData):
+    # Filter data before and after the price increase
+    before_increase = sales_data[sales_data['date'] < '2021-01-15']
+    after_increase = sales_data[sales_data['date'] >= '2021-01-15']
+
+    # Create line chart
+    fig = px.line(sales_data, x='date', y='Sales', title="Sales Before and After Pink Morsel Price Increase")
+
+    # Highlight the price increase date
+    fig.add_vline(x='2021-01-15', line_dash="dash", annotation_text="Price Increase", annotation_position="top right")
+
+    return fig
+
+if __name__ == '__main__':
+    app.run_server(debug=True)

app.py

@@ -0,0 +1,35 @@
+# Run this app with `python app.py` and
+# visit http://127.0.0.1:8050/ in your web browser.
+
+
+from dash import Dash, html, dcc
+import plotly.express as px
+import pandas as pd
+
+app = Dash(__name__)
+
+# assume you have a "long-form" data frame
+# see https://plotly.com/python/px-arguments/ for more options
+df = pd.DataFrame({
+    "Fruit": ["Apples", "Oranges", "Bananas", "Apples", "Oranges", "Bananas"],
+    "Amount": [4, 1, 2, 2, 4, 5],
+    "City": ["SF", "SF", "SF", "Montreal", "Montreal", "Montreal"]
+})
+
+fig = px.bar(df, x="Fruit", y="Amount", color="City", barmode="group")
+
+app.layout = html.Div(children=[
+    html.H1(children='Hello Dash'),
+
+    html.Div(children='''
+        Dash: A web application framework for your data.
+    '''),
+
+    dcc.Graph(
+        id='example-graph',
+        figure=fig
+    )
+])
+
+if __name__ == '__main__':
+    app.run(debug=True)

script.py

@@ -0,0 +1,27 @@
+import pandas as pd
+
+# Read CSV files
+df1 = pd.read_csv('data/file1.csv')
+df2 = pd.read_csv('data/file2.csv')
+df3 = pd.read_csv('data/file3.csv')
+
+# Filter rows by product
+df1 = df1[df1['product'] == 'Pink Morsels']
+df2 = df2[df2['product'] == 'Pink Morsels']
+df3 = df3[df3['product'] == 'Pink Morsels']
+
+# Create 'Sales' column
+df1['Sales'] = df1['quantity'] * df1['price']
+df2['Sales'] = df2['quantity'] * df2['price']
+df3['Sales'] = df3['quantity'] * df3['price']
+
+# Keep only required columns
+df1 = df1[['Sales', 'date', 'region']]
+df2 = df2[['Sales', 'date', 'region']]
+df3 = df3[['Sales', 'date', 'region']]
+
+# Concatenate DataFrames
+result = pd.concat([df1, df2, df3])
+
+# Write to output CSV file
+result.to_csv('output.csv', index=False)