Fix linters

Author: bzaczynski

polars-vs-pandas/DataFrame_Plots.ipynb

@@ -146,10 +146,14 @@
     "orders_pandas = pd.DataFrame(sales_data)\n",
     "\n",
     "(\n",
-    "    orders_pandas.groupby([\"region\",])[\"sales_income\"]\n",
+    "    orders_pandas.groupby(\n",
+    "        [\n",
+    "            \"region\",\n",
+    "        ]\n",
+    "    )[\"sales_income\"]\n",
     "    .sum()\n",
     "    .plot(kind=\"bar\", title=\"Total Sales per Region ($)\", ylabel=\"total_sales\")\n",
-    ")\n"
+    ")"
    ],
    "id": "4199475a83ffc612",
    "outputs": [

polars-vs-pandas/data_generation.py

@@ -6,7 +6,9 @@ def generate_data(number_of_rows):
 
     return {
         "order_id": range(1, number_of_rows + 1),
-        "region": rng.choice(["North", "South", "East", "West"], size=number_of_rows),
+        "region": rng.choice(
+            ["North", "South", "East", "West"], size=number_of_rows
+        ),
         "sales_person": rng.choice(
             ["Armstrong", "Aldrin", "Collins"], size=number_of_rows
         ),

polars-vs-pandas/dataframe_and_lazyframe_time_tests.py

@@ -4,7 +4,6 @@
 
 import pandas as pd
 import polars as pl
-
 from data_generation import generate_data
 
 
@@ -56,13 +55,19 @@ def analyze_polars_lazyframe(polars_lf):
 
 print("\nAnalyzing Dataframes...")
 print(f"Pandas dataframe analysis time for {int(sys.argv[1])} rows:")
-print(Timer(functools.partial(analyze_pandas_dataframe, pandas_df)).timeit(100))
+print(
+    Timer(functools.partial(analyze_pandas_dataframe, pandas_df)).timeit(100)
+)
 
 print(f"\nPolars dataframe analysis time for {int(sys.argv[1])} rows:")
-print(Timer(functools.partial(analyze_polars_dataframe, polars_df)).timeit(100))
+print(
+    Timer(functools.partial(analyze_polars_dataframe, polars_df)).timeit(100)
+)
 
 print(f"\nPolars lazyframe analysis time for {int(sys.argv[1])} rows:")
-print(Timer(functools.partial(analyze_polars_lazyframe, polars_lf)).timeit(100))
+print(
+    Timer(functools.partial(analyze_polars_lazyframe, polars_lf)).timeit(100)
+)
 
 print("\nShow Boots sales in the East region for pandas DataFrame")
 print(analyze_pandas_dataframe(pandas_df)["East"]["Boots"])

polars-vs-pandas/sample_pandas_and_polars_code.py

@@ -14,7 +14,9 @@
 orders_pandas = pd.read_parquet("online_retail.parquet")
 
 (
-    orders_pandas.assign(Total=orders_pandas["Quantity"] * orders_pandas["UnitPrice"])
+    orders_pandas.assign(
+        Total=orders_pandas["Quantity"] * orders_pandas["UnitPrice"]
+    )
     .filter(["InvoiceNo", "Quantity", "UnitPrice", "Total"])
     .query("Total > 100")
 ).head(3)

polars-vs-pandas/streaming_test.py

@@ -3,7 +3,6 @@
 from timeit import Timer
 
 import polars as pl
-
 from data_generation import generate_data
 
 
@@ -28,7 +27,11 @@ def analyze_polars_streaming(polars_lf):
 polars_lf = create_polars_lazyframe(test_data)
 
 print(f"Polars lazyframe analysis time for {int(sys.argv[1])} rows:")
-print(Timer(functools.partial(analyze_polars_lazyframe, polars_lf)).timeit(100))
+print(
+    Timer(functools.partial(analyze_polars_lazyframe, polars_lf)).timeit(100)
+)
 
 print(f"\nPolars streaming analysis time for {int(sys.argv[1])} rows:")
-print(Timer(functools.partial(analyze_polars_streaming, polars_lf)).timeit(100))
+print(
+    Timer(functools.partial(analyze_polars_streaming, polars_lf)).timeit(100)
+)