TR suggestions

Author: gahjelle

pandas-iterate-over-rows/README.md

@@ -1,10 +1,10 @@
 # How to Iterate Over a pandas DataFrame's Rows
 
-In these supplementary materials you'll find the examples discussed in the tutorial, along with some bonus materials.
+In these supplementary materials you'll find the examples discussed in the tutorial [How to Iterate Over Rows in pandas, and Why You Shouldn't](https://realpython.com/pandas-iterate-over-rows/), along with some bonus materials.
 
-The main extra dependency for the bonus materials is [perfplot](https://github.com/nschloe/perfplot). To install all dependencies into your venv
+In addition to the third-party packages used in the tutorial, you should also install [perfplot](https://github.com/nschloe/perfplot) to play with the bonus examples. To install all dependencies into your virtual environment, you can run the following command:
 
-```shell
+```console
 $ python -m pip install pandas httpx codetiming perfplot
 ```
 

pandas-iterate-over-rows/cumulative_sum_perfplot.py

@@ -35,7 +35,7 @@ def get_products(n):
     kernels=[pandas_cumsum, loop_cumsum],
     labels=["pandas cumsum", "loop cumsum"],
     equality_check=None,
-    title="Loop vs Pandas Cumulative Sum",
+    title="Loop vs pandas Cumulative Sum",
     xlabel="Number of Rows",
 )
 

pandas-iterate-over-rows/how_to_loop.py

@@ -25,11 +25,14 @@ def check_connection(name, url):
 for website in websites.itertuples():
     check_connection(website.name, website.url)
 
-# %%
+# %% You may use .iterrows() if you have dynamic columnnames
+name_column = "name"
+url_column = "url"
 for _, website in websites.iterrows():
-    check_connection(website["name"], website["url"])
+    check_connection(website[name_column], website[url_column])
 
 # %% Use list comprehension to iterate through all rows
+#    Note that this creates a list that is thrown away again
 [
     check_connection(website.name, website.url)
     for website in websites.itertuples()
@@ -43,5 +46,8 @@ def check_connection(name, url):
 for website in websites.T.to_dict().values():
     print(website)
 
-# %%
-websites.aggregate(["sum"])
+# %% Use .agg() to aggregate over columns
+websites.agg(
+    total_views=("total_views", "sum"),
+    average_views=("total_views", "mean"),
+)

pandas-iterate-over-rows/products.py

@@ -13,7 +13,7 @@
     else:
         cumulative_sum.append(income)
 
-products.assign(cumulative_income=cumulative_sum)
+products = products.assign(cumulative_income=cumulative_sum)
 
 # %% To get cumulative sum, instead of looping, you can create intermediate
 # columns and use .cumsum()

pandas-iterate-over-rows/take_sum.py

@@ -2,24 +2,22 @@
 
 import pandas as pd
 
-# %%
+# %% Read demo data
 
 websites = pd.read_csv("resources/popular_websites.csv", index_col=0)
 
-# %% Best way: use the dedicated pandas method
+# %% Best way: use the dedicated pandas .sum() method
 
 websites["total_views"].sum()
 
-# %% List comprehension
+# %% List comprehension with .itertuples()
 
 sum(website.total_views for website in websites.itertuples())
 
-# %% itertuples()
+# %% Manual loop with .itertuples()
 
 total = 0
 for website in websites.itertuples():
     total += website.total_views
 
 total
-
-# %%

pandas-iterate-over-rows/take_sum_perfplot.py

@@ -2,10 +2,6 @@
 import perfplot
 
 
-def pandas_sum(websites):
-    return websites["total_views"].sum()
-
-
 def loop_sum(websites):
     total = 0
     for row in websites.itertuples():
@@ -17,6 +13,10 @@ def python_sum(websites):
     return sum(row.total_views for row in websites.itertuples())
 
 
+def pandas_sum(websites):
+    return websites["total_views"].sum()
+
+
 def get_websites(n):
     websites = pd.read_csv("resources/popular_websites.csv", index_col=0)
     if n < len(websites):
@@ -29,9 +29,9 @@ def get_websites(n):
 plot = perfplot.bench(
     n_range=[2**i for i in range(17)],
     setup=get_websites,
-    kernels=[pandas_sum, loop_sum, python_sum],
-    labels=["pandas sum", "loop sum", "python sum"],
-    title="Python vs Pandas sum",
+    kernels=[loop_sum, python_sum, pandas_sum],
+    labels=["loop sum", "python sum", "pandas sum"],
+    title="Python vs pandas sum",
     xlabel="Number of Rows",
 )