Reformat notebook

realpython · Nov 20, 2023 · 65af430 · 65af430
1 parent b0886f2
commit 65af430
Show file tree

Hide file tree

Showing 2 changed files with 30 additions and 18 deletions.
diff --git a/python-for-data-analysis/README.md b/python-for-data-analysis/README.md
@@ -6,7 +6,7 @@ The `james_bond_data.csv` file contains the original uncleansed data and is the
 
 A cleansed version of the original data is available in the `james_bond_data_cleansed.csv` file.
 
-The complete code is available in the `Solution-New.ipynb` Jupyter notebook.
+The complete code is available in the `james_bond_analysis.ipynb` Jupyter notebook.
 
 ## Setup
 

diff --git a/python-for-data-analysis/james_bond_analysis.ipynb b/python-for-data-analysis/james_bond_analysis.ipynb
@@ -406,22 +406,32 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data = james_bond_data.combine_first(\n",
-    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
-    ").assign(\n",
-    "    US_Gross=lambda data: (\n",
-    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
-    "    ),\n",
-    "    World_Gross=lambda data: (\n",
-    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
-    "    ),\n",
-    "    Budget=lambda data: (\n",
-    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
-    "    ),\n",
-    "    Film_Length=lambda data: (data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)),\n",
-    "    Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
-    "    Release_Year=lambda data: data[\"Release\"].dt.year\n",
-    ").drop_duplicates(ignore_index=True)\n",
+    "data = (\n",
+    "    james_bond_data.combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        US_Gross=lambda data: (\n",
+    "            data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        World_Gross=lambda data: (\n",
+    "            data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        Budget=lambda data: (\n",
+    "            data[\"Budget ($ 000s)\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        Film_Length=lambda data: (\n",
+    "            data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "        Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    "    )\n",
+    "    .drop_duplicates(ignore_index=True)\n",
+    ")\n",
     "\n",
     "duplicate_movies = [\"The Man with the Golden Gun\", \"The Living Daylights\"]\n",
     "data[data[\"Movie\"].isin(duplicate_movies)]"
@@ -721,7 +731,9 @@
    "source": [
     "length = data[\"Film_Length\"].value_counts(bins=7).sort_index()\n",
     "length.plot.bar(\n",
-    "    title=\"Film Length Distribution\", xlabel=\"Time Range (mins)\", ylabel=\"Count\"\n",
+    "    title=\"Film Length Distribution\",\n",
+    "    xlabel=\"Time Range (mins)\",\n",
+    "    ylabel=\"Count\",\n",
     ")"
    ]
   },