From 6dececc1a8b5e3942727d8baf47e76a609e0a31b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20H=C3=BClsken?=
 <150256186+huelsth@users.noreply.github.com>
Date: Sun, 21 Apr 2024 21:51:02 +0200
Subject: [PATCH] Create analyze.py

---
 data/analyze.py | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 data/analyze.py

diff --git a/data/analyze.py b/data/analyze.py
new file mode 100644
index 0000000000..3c7af13493
--- /dev/null
+++ b/data/analyze.py
@@ -0,0 +1,21 @@
+import pandas as pd
+
+# Load the three CSV files
+sales_data_0 = pd.read_csv('data/daily_sales_data_0.csv')
+sales_data_1 = pd.read_csv('data/daily_sales_data_1.csv')
+sales_data_2 = pd.read_csv('data/daily_sales_data_2.csv')
+
+# Combine the data from the three files
+combined_sales_data = pd.concat([sales_data_0, sales_data_1, sales_data_2])
+
+# Filter rows where the product is Pink Morsels
+pink_morsels_data = combined_sales_data[combined_sales_data['product'] == 'Pink Morsels']
+
+# Calculate total sales by multiplying quantity and price
+pink_morsels_data['sales'] = pink_morsels_data['quantity'] * pink_morsels_data['price']
+
+# Select and rearrange 
+formatted_data = pink_morsels_data[['sales', 'date', 'region']]
+
+# Save the formatted data into a single output file
+formatted_data.to_csv('formatted_sales_data.csv', index=False)