Update notebooks for pandas 2.0.0, close wesm#170

ch06.ipynb

@@ -584,7 +584,7 @@
    "source": [
     "writer = pd.ExcelWriter(\"examples/ex2.xlsx\")\n",
     "frame.to_excel(writer, \"Sheet1\")\n",
-    "writer.save()"
+    "writer.close()"
    ]
   },
   {

ch07.ipynb

@@ -556,7 +556,7 @@
     "df = pd.DataFrame({\"key\": [\"b\", \"b\", \"a\", \"c\", \"a\", \"b\"],\n",
     "                   \"data1\": range(6)})\n",
     "df\n",
-    "pd.get_dummies(df[\"key\"])"
+    "pd.get_dummies(df[\"key\"], dtype=float)"
    ]
   },
   {
@@ -565,7 +565,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dummies = pd.get_dummies(df[\"key\"], prefix=\"key\")\n",
+    "dummies = pd.get_dummies(df[\"key\"], prefix=\"key\", dtype=float)\n",
     "df_with_dummy = df[[\"data1\"]].join(dummies)\n",
     "df_with_dummy"
    ]
@@ -1268,7 +1268,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pd.get_dummies(cat_s)"
+    "pd.get_dummies(cat_s, dtype=float)"
    ]
   },
   {

ch08.ipynb

@@ -737,14 +737,23 @@
    "execution_count": 66,
    "metadata": {},
    "outputs": [],
+   "source": [
+    "long_data.index.name = None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "long_data[\"value2\"] = np.random.standard_normal(len(long_data))\n",
     "long_data[:10]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 68,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -755,7 +764,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -765,14 +774,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 70,
    "metadata": {},
    "outputs": [],
    "source": []
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 71,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -785,7 +794,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 72,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -795,7 +804,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -806,7 +815,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 74,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -815,7 +824,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 75,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -824,7 +833,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 76,
    "metadata": {},
    "outputs": [],
    "source": [

ch09.ipynb

@@ -250,7 +250,7 @@
     "ax.set_xlim([\"1/1/2007\", \"1/1/2011\"])\n",
     "ax.set_ylim([600, 1800])\n",
     "\n",
-    "ax.set_title(\"Important dates in the 2008-2009 financial crisis\")"
+    "ax.set_title(\"Important dates in the 2008\u20132009 financial crisis\")"
    ]
   },
   {
@@ -550,7 +550,7 @@
    "outputs": [],
    "source": [
     "ax = sns.regplot(x=\"m1\", y=\"unemp\", data=trans_data)\n",
-    "ax.title(\"Changes in log(m1) versus log(unemp)\")"
+    "ax.set_title(\"Changes in log(m1) versus log(unemp)\")"
    ]
   },
   {

ch10.ipynb

@@ -35,7 +35,8 @@
    "outputs": [],
    "source": [
     "df = pd.DataFrame({\"key1\" : [\"a\", \"a\", None, \"b\", \"b\", \"a\", None],\n",
-    "                   \"key2\" : pd.Series([1, 2, 1, 2, 1, None, 1], dtype=\"Int64\"),\n",
+    "                   \"key2\" : pd.Series([1, 2, 1, 2, 1, None, 1],\n",
+    "                                      dtype=\"Int64\"),\n",
     "                   \"data1\" : np.random.standard_normal(7),\n",
     "                   \"data2\" : np.random.standard_normal(7)})\n",
     "df"
@@ -97,7 +98,7 @@
    "outputs": [],
    "source": [
     "df.groupby(\"key1\").mean()\n",
-    "df.groupby(\"key2\").mean()\n",
+    "df.groupby(\"key2\").mean(numeric_only=True)\n",
     "df.groupby([\"key1\", \"key2\"]).mean()"
    ]
   },
@@ -422,7 +423,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "tips.groupby([\"day\", \"smoker\"], as_index=False).mean()"
+    "grouped = tips.groupby([\"day\", \"smoker\"], as_index=False)\n",
+    "grouped.mean(numeric_only=True)"
    ]
   },
   {
@@ -852,7 +854,8 @@
    "outputs": [],
    "source": [
     "tips.head()\n",
-    "tips.pivot_table(index=[\"day\", \"smoker\"])"
+    "tips.pivot_table(index=[\"day\", \"smoker\"],\n",
+    "                 values=[\"size\", \"tip\", \"tip_pct\", \"total_bill\"])"
    ]
   },
   {

ch12.ipynb

@@ -82,7 +82,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dummies = pd.get_dummies(data.category, prefix='category')\n",
+    "dummies = pd.get_dummies(data.category, prefix='category',\n",
+    "                         dtype=float)\n",
     "data_with_dummies = data.drop('category', axis=1).join(dummies)\n",
     "data_with_dummies"
    ]
@@ -137,7 +138,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "coef, resid, _, _ = np.linalg.lstsq(X, y)"
+    "coef, resid, _, _ = np.linalg.lstsq(X, y, rcond=None)"
    ]
   },
   {

ch13.ipynb

@@ -604,7 +604,7 @@
     "def add_prop(group):\n",
     "    group[\"prop\"] = group[\"births\"] / group[\"births\"].sum()\n",
     "    return group\n",
-    "names = names.groupby([\"year\", \"sex\"]).apply(add_prop)"
+    "names = names.groupby([\"year\", \"sex\"], group_keys=False).apply(add_prop)"
    ]
   },
   {
@@ -1213,7 +1213,7 @@
     "    # If no mapping provided, return x\n",
     "    return emp_mapping.get(x, x)\n",
     "\n",
-    "fec[\"contbr_employer\"] = fec[\"contbr_employer\"].map(f)"
+    "fec[\"contbr_employer\"] = fec[\"contbr_employer\"].map(get_emp)"
    ]
   },
   {