Python for Alteryx users

Overview of tools

We will recreate this Alteryx workflow using Python

Text input

import pandas as pd

text_input = pd.DataFrame(
   {"Person": ["You", "Me", "Everyone else"], "Number": [1, 1, 99]}
)
text_input

Input data

import pandas as pd

input_data = pd.read_csv("https://query.data.world/s/whbjtalht4sigazly6hdnnb5ynqald")
input_data.head()

Select tool

selected_data = (
   input_data.drop(columns=["Ship Date", "Ship Mode"])  # Example of deselecting
   .loc[
       :, ["Order ID", "Category", "Sub-Category", "Product Name", "Sales", "Quantity"]
   ]  # Example of selecting
   .rename(columns={"Sub-Category": "Sub-Cat", "Product Name": "Product"})
   .astype({"Quantity": "int64", "Category": "str"})
)
selected_data.head()

Formula tool

selected_data["Total Sales"] = selected_data["Sales"] * selected_data["Quantity"]
selected_data.head()

Filter tool

filtered_data = selected_data[selected_data["Sales"] > 1000]


# To get the false
sales_under_1000 = selected_data[selected_data["Sales"] < 1000]

filtered_data.head()

sales_under_1000.head()

Sort tool

sorted_data = filtered_data.sort_values(by="Sales", ascending=False)
sorted_data.head()

Summarize tool

summarized_data = (
   sorted_data.groupby(["Category", "Sub-Cat"])
   .agg({"Sales": "sum"})
   .rename(columns={"Sales": "Sales by Sub-Cat"})
).reset_index()
summarized_data.head()

summarized_data_alternative = sorted_data.groupby(["Category", "Sub-Cat"]).agg(
   Sales_by_Sub_Cat=pd.NamedAgg(column="Sales", aggfunc=sum)
).reset_index()
summarized_data_alternative.head()

Join tool

joined_data = pd.merge(
   sorted_data, summarized_data, on=["Category", "Sub-Cat"], how="inner"
)
joined_data.head()

left_join = pd.merge(
   sorted_data, summarized_data, on=["Category", "Sub-Cat"], how="left", indicator=True
)
left_join = left_join[left_join["_merge"] == "left_only"]
left_join.drop(columns="_merge", inplace=True)
left_join.head()

Union tool

unioned_data = joined_data.append(sales_under_1000)
unioned_data.head()

Output tool

unioned_data.to_csv("Sales summary.csv", index=False)