update lecture

gboeing · Feb 1, 2023 · 3cbaca1 · 3cbaca1
1 parent a3024c2
commit 3cbaca1
Showing 1 changed file with 6 additions and 5 deletions.
diff --git a/modules/04-data-cleaning-exploration/lecture.ipynb b/modules/04-data-cleaning-exploration/lecture.ipynb
@@ -99,7 +99,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_covid = df"
+    "df_covid = df.copy()"
    ]
   },
   {
@@ -235,7 +235,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_earnings = df"
+    "df_earnings = df.copy()"
    ]
   },
   {
@@ -298,6 +298,7 @@
    "source": [
     "# you have to make a decision: NAICS should be int, but it contains nulls\n",
     "# you could drop nulls then convert to int, or just leave it as float\n",
+    "# OR in recent versions of pandas, you could cast to type pd.Int64Dtype() which allows nulls\n",
     "pd.isnull(df['NAICS']).sum()"
    ]
   },
@@ -400,7 +401,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_business = df"
+    "df_business = df.copy()"
    ]
   },
   {
@@ -858,7 +859,7 @@
     "ax = sns.barplot(x=df_earnings['Total Compensation 1000s'],\n",
     "                 y=df_earnings['Department'],\n",
     "                 estimator=np.mean,\n",
-    "                 ci=95,\n",
+    "                 errorbar=('ci', 95),\n",
     "                 order=order,\n",
     "                 alpha=0.9)\n",
     "\n",
@@ -964,7 +965,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.10.8"
   }
  },
  "nbformat": 4,