Power BI: Initial commit

Author: bzaczynski

power-bi-python/01_ingest.py

@@ -0,0 +1,21 @@
+import sqlite3
+
+import pandas as pd
+
+with sqlite3.connect(r"C:\Users\User\Desktop\car_sales.db") as connection:
+    df = pd.read_sql_query("SELECT * FROM sales", connection)
+
+cars = df[
+    [
+        "vin",
+        "car",
+        "mileage",
+        "license",
+        "color",
+        "purchase_date",
+        "purchase_price",
+        "investment",
+    ]
+]
+customers = df[["vin", "customer"]]
+sales = df[["vin", "sale_price", "sale_date"]]

power-bi-python/02_extract_email.py

@@ -0,0 +1,5 @@
+# 'dataset' holds the input data for this script
+dataset = dataset.assign(
+    full_name=dataset["customer"].str.extract(r"([^<]+)"),
+    email=dataset["customer"].str.extract(r"<([^>]+)>"),
+).drop(columns=["customer"])

power-bi-python/03_split_fullname.py

@@ -0,0 +1,5 @@
+# 'dataset' holds the input data for this script
+dataset[["first_name", "last_name"]] = dataset["full_name"].str.split(
+    n=1, expand=True
+)
+dataset.drop(columns=["full_name"], inplace=True)

power-bi-python/04_python_visual.py

@@ -0,0 +1,14 @@
+# The following code to create a dataframe and remove duplicated rows is always executed and acts as a preamble for your script:
+
+# dataset = pandas.DataFrame(color, vin)
+# dataset = dataset.drop_duplicates()
+
+# Paste or type your script code here:
+import matplotlib.pyplot as plt
+
+plt.style.use("seaborn")
+
+series = dataset[dataset["color"] != ""]["color"].value_counts()
+series.plot(kind="bar", color=series.index, edgecolor="black")
+
+plt.show()

power-bi-python/README.md

@@ -0,0 +1,7 @@
+# Microsoft Power BI and Python: Two Superpowers Combined
+
+These are supplementing materials for the Real Python [tutorial](https://realpython.com/power-bi-python/) on using Python in Microsoft Power BI Desktop, which include:
+
+- SQLite database with a single `sales` table (fake used car sales dataset)
+- Python scripts used in the tutorial
+- The resulting Power BI Desktop report