TR updates

Author: iansedano

pandas-iterate-over-rows/cumulative_sum_codetiming.py

@@ -1,16 +1,16 @@
-import codetiming
 import pandas as pd
+from codetiming import Timer
 
 
 def loop_cumsum(products):
     cumulative_sum = []
-    for row in products.itertuples():
+    for product in products.itertuples():
         if cumulative_sum:
             cumulative_sum.append(
-                cumulative_sum[-1] + (row.sales * row.unit_price)
+                cumulative_sum[-1] + (product.sales * product.unit_price)
             )
         else:
-            cumulative_sum.append(row.sales * row.unit_price)
+            cumulative_sum.append(product.sales * product.unit_price)
     return products.assign(cumulative_income=cumulative_sum)
 
 
@@ -21,10 +21,8 @@ def pandas_cumsum(products):
     ).drop(columns="income")
 
 
-for f in [pandas_cumsum, loop_cumsum]:
+for func in [loop_cumsum, pandas_cumsum]:
     products = pd.read_csv("resources/products.csv")
     products = pd.concat(products for _ in range(1000))
-    with codetiming.Timer(
-        name=f.__name__, text="{name:20}: {milliseconds:.2f} ms"
-    ):
-        f(products)
+    with Timer(name=func.__name__, text="{name:20}: {milliseconds:.2f} ms"):
+        func(products)

pandas-iterate-over-rows/cumulative_sum_perfplot.py

@@ -4,13 +4,13 @@
 
 def loop_cumsum(products):
     cumulative_sum = []
-    for row in products.itertuples():
+    for product in products.itertuples():
         if cumulative_sum:
             cumulative_sum.append(
-                cumulative_sum[-1] + (row.sales * row.unit_price)
+                cumulative_sum[-1] + (product.sales * product.unit_price)
             )
         else:
-            cumulative_sum.append(row.sales * row.unit_price)
+            cumulative_sum.append(product.sales * product.unit_price)
     return products.assign(cumulative_income=cumulative_sum)
 
 

pandas-iterate-over-rows/how_to_loop.py

@@ -3,38 +3,45 @@
 import pandas as pd
 
 # %% Read CSV and rename headers
-webs = pd.read_csv("resources/popular_websites.csv", index_col=0)
-
+websites = pd.read_csv("resources/popular_websites.csv", index_col=0)
+print(websites)
 
 # %% Define function to check connection
 def check_connection(name, url):
     try:
-        httpx.get(url)
+        response = httpx.get(url)
+        location = response.headers.get("location")
+        if location is None or location.startswith(url):
+            print(f"{name} is online!")
+        else:
+            print(f"{name} is online! But redirects to {location}")
+        return True
     except httpx.ConnectError:
-        print("Failed to establish a connection")
+        print(f"Failed to establish a connection with {url}")
         return False
-    print(f"{name} is online!")
-    return True
 
 
 # %% Use .itertuples() to iterate through all rows
-for web in webs.itertuples():
-    check_connection(web.website, web.url)
+for website in websites.itertuples():
+    check_connection(website.name, website.url)
 
 # %%
-for _, web in webs.iterrows():
-    check_connection(web["website"], web["url"])
+for _, website in websites.iterrows():
+    check_connection(website["name"], website["url"])
 
 # %% Use list comprehension to iterate through all rows
-[check_connection(web.website, web.url) for web in webs.itertuples()]
+[
+    check_connection(website.name, website.url)
+    for website in websites.itertuples()
+]
 
 # %% Use the index to iterate through rows
-for i in webs.index:
-    print({**webs.iloc[i]})
+for i in websites.index:
+    print({**websites.iloc[i]})
 
 # %% Transpose and cast to dictionary to iterate through rows
-for row in webs.T.to_dict().values():
-    print(row)
+for website in websites.T.to_dict().values():
+    print(website)
 
 # %%
-webs.aggregate(["sum"])
+websites.aggregate(["sum"])

pandas-iterate-over-rows/products.py

@@ -18,13 +18,13 @@
 
 cumulative_sum = []
 
-for row in products.itertuples():
+for product in products.itertuples():
     if cumulative_sum:
         cumulative_sum.append(
-            cumulative_sum[-1] + (row.sales * row.unit_price)
+            cumulative_sum[-1] + (product.sales * product.unit_price)
         )
     else:
-        cumulative_sum.append(row.sales * row.unit_price)
+        cumulative_sum.append(product.sales * product.unit_price)
 
 products.assign(cumulative_income=cumulative_sum)
 # %%

pandas-iterate-over-rows/resources/popular_websites.csv

@@ -1,11 +1,13 @@
-,website,url,total_views
+,name,url,total_views
 0,Google,https://www.google.com,520726795305.0
 1,YouTube,https://www.youtube.com,235813192004.0
 2,Facebook,https://www.facebook.com,223015726428.0
 3,Yahoo,https://www.yahoo.com,125654442849.0
-4,Wikipedia,https://www.wikipedia.com,44673637102.0
+4,Wikipedia,https://www.wikipedia.org,44673637102.0
 5,Baidu,"https://www.baidu.com",44097593606.0
-6,Twitter,https://www.twitter.com,30986763501.0
-7,Yandex,https://www.yandex.com,28579800000.0
+6,Twitter,https://twitter.com,30986763501.0
+7,Yandex,https://yandex.com,28579800000.0
 8,Instagram,https://www.instagram.com,26215196370.0
 9,AOL,https://www.aol.com,23212320843.0
+10,Netscape,https://www.netscape.com,5750000.0
+11,Nope,https://alwaysfails.example.com,0

pandas-iterate-over-rows/take_sum.py

@@ -4,21 +4,21 @@
 
 # %%
 
-webs = pd.read_csv("resources/popular_websites.csv", index_col=0)
+websites = pd.read_csv("resources/popular_websites.csv", index_col=0)
 
 # %% Best way: use the dedicated pandas method
 
-webs["total_views"].sum()
+websites["total_views"].sum()
 
 # %% List comprehension
 
-sum(row.total_views for row in webs.itertuples())
+sum(website.total_views for website in websites.itertuples())
 
 # %% itertuples()
 
 total = 0
-for row in webs.itertuples():
-    total += row.total_views
+for website in websites.itertuples():
+    total += website.total_views
 
 total
 

pandas-iterate-over-rows/take_sum_codetiming.py

@@ -1,26 +1,24 @@
-import codetiming
 import pandas as pd
+from codetiming import Timer
 
 
-def pandas_sum(webs):
-    return webs["total_views"].sum()
-
-
-def loop_sum(webs):
+def loop_sum(websites):
     total = 0
-    for row in webs.itertuples():
-        total += row.total_views
+    for website in websites.itertuples():
+        total += website.total_views
     return total
 
 
-def python_sum(webs):
-    return sum(row.total_views for row in webs.itertuples())
+def python_sum(websites):
+    return sum(website.total_views for website in websites.itertuples())
+
+
+def pandas_sum(websites):
+    return websites["total_views"].sum()
 
 
-for f in [pandas_sum, loop_sum, python_sum]:
-    webs = pd.read_csv("resources/popular_websites.csv", index_col=0)
-    webs = pd.concat([webs for _ in range(1000)])
-    with codetiming.Timer(
-        name=f.__name__, text="{name:20}: {milliseconds:.2f} ms"
-    ):
-        f(webs)
+for func in [loop_sum, python_sum, pandas_sum]:
+    websites = pd.read_csv("resources/popular_websites.csv", index_col=0)
+    websites = pd.concat([websites for _ in range(1000)])
+    with Timer(name=func.__name__, text="{name:20}: {milliseconds:.2f} ms"):
+        func(websites)

pandas-iterate-over-rows/take_sum_perfplot.py

@@ -2,26 +2,26 @@
 import perfplot
 
 
-def pandas_sum(df):
-    return df["total_views"].sum()
+def pandas_sum(websites):
+    return websites["total_views"].sum()
 
 
-def loop_sum(df):
+def loop_sum(websites):
     total = 0
-    for row in df.itertuples():
+    for row in websites.itertuples():
         total += row.total_views
     return total
 
 
-def python_sum(webs):
-    return sum(row.total_views for row in webs.itertuples())
+def python_sum(websites):
+    return sum(row.total_views for row in websites.itertuples())
 
 
-webs = pd.read_csv("resources/popular_websites.csv", index_col=0)
+websites = pd.read_csv("resources/popular_websites.csv", index_col=0)
 
 plot = perfplot.bench(
     n_range=[i**2 for i in range(1, 1000, 100)],
-    setup=lambda n: pd.concat([webs for _ in range(n)]),
+    setup=lambda n: pd.concat([websites for _ in range(n)]),
     kernels=[pandas_sum, loop_sum, python_sum],
     labels=["pandas sum", "loop sum", "python sum"],
 )