diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index c438d85b7..90e766b87 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -35,7 +35,7 @@ repos:
           - "--config=pyproject.toml"
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.5.6
+    rev: v0.6.1
     hooks:
       - id: ruff
         args: [--fix]
diff --git a/examples/notebooks/Pivot Data from Long to Wide Form.ipynb b/examples/notebooks/Pivot Data from Long to Wide Form.ipynb
index 4ec840901..d19d93189 100644
--- a/examples/notebooks/Pivot Data from Long to Wide Form.ipynb	
+++ b/examples/notebooks/Pivot Data from Long to Wide Form.ipynb	
@@ -13,8 +13,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd \n",
-    "import janitor as jn "
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/Pivoting Data from Wide to Long.ipynb b/examples/notebooks/Pivoting Data from Wide to Long.ipynb
index 7203100a8..1d202e078 100644
--- a/examples/notebooks/Pivoting Data from Wide to Long.ipynb	
+++ b/examples/notebooks/Pivoting Data from Wide to Long.ipynb	
@@ -13,10 +13,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import janitor\n",
-    "import pandas as pd\n",
+    "import re\n",
+    "\n",
     "import numpy as np\n",
-    "import re"
+    "import pandas as pd"
    ]
   },
   {
diff --git a/examples/notebooks/Row_to_Names.ipynb b/examples/notebooks/Row_to_Names.ipynb
index 2852ffdbd..9562fb2fa 100644
--- a/examples/notebooks/Row_to_Names.ipynb
+++ b/examples/notebooks/Row_to_Names.ipynb
@@ -27,9 +27,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "from io import StringIO"
+    "from io import StringIO\n",
+    "\n",
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/anime.ipynb b/examples/notebooks/anime.ipynb
index 7f4eaff6a..fae98321d 100644
--- a/examples/notebooks/anime.ipynb
+++ b/examples/notebooks/anime.ipynb
@@ -44,7 +44,6 @@
    "outputs": [],
    "source": [
     "# Import pyjanitor and pandas\n",
-    "import janitor\n",
     "import pandas as pd\n",
     "import pandas_flavor as pf"
    ]
@@ -57,6 +56,7 @@
    "source": [
     "# Suppress user warnings when we try overwriting our custom pandas flavor functions\n",
     "import warnings\n",
+    "\n",
     "warnings.filterwarnings('ignore')"
    ]
   },
diff --git a/examples/notebooks/bad_values.ipynb b/examples/notebooks/bad_values.ipynb
index 0018c1aa8..cfcb9820a 100644
--- a/examples/notebooks/bad_values.ipynb
+++ b/examples/notebooks/bad_values.ipynb
@@ -19,9 +19,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "import numpy as np"
+    "import numpy as np\n",
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/bird_call.ipynb b/examples/notebooks/bird_call.ipynb
index 06b32b128..ef3c765cb 100644
--- a/examples/notebooks/bird_call.ipynb
+++ b/examples/notebooks/bird_call.ipynb
@@ -38,8 +38,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor"
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/board_games.ipynb b/examples/notebooks/board_games.ipynb
index 43a0e65c2..7f44eaa0d 100644
--- a/examples/notebooks/board_games.ipynb
+++ b/examples/notebooks/board_games.ipynb
@@ -30,9 +30,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "import os"
+    "\n",
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/case_when.ipynb b/examples/notebooks/case_when.ipynb
index 0c729e808..b1ae20492 100644
--- a/examples/notebooks/case_when.ipynb
+++ b/examples/notebooks/case_when.ipynb
@@ -2,41 +2,27 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "# Multiple Conditions with case_when"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "source": [
-    "import pandas as pd\n",
-    "import janitor"
-   ],
+   "metadata": {},
    "outputs": [],
-   "metadata": {}
+   "source": [
+    "import pandas as pd\n"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "source": [
-    "# https://stackoverflow.com/q/19913659/7175713\n",
-    "df = pd.DataFrame({'col1': list('ABBC'), 'col2': list('ZZXY')})\n",
-    "\n",
-    "df"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "  col1 col2\n",
-       "0    A    Z\n",
-       "1    B    Z\n",
-       "2    B    X\n",
-       "3    C    Y"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -84,43 +70,41 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "  col1 col2\n",
+       "0    A    Z\n",
+       "1    B    Z\n",
+       "2    B    X\n",
+       "3    C    Y"
       ]
      },
+     "execution_count": 2,
      "metadata": {},
-     "execution_count": 2
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "# https://stackoverflow.com/q/19913659/7175713\n",
+    "df = pd.DataFrame({'col1': list('ABBC'), 'col2': list('ZZXY')})\n",
+    "\n",
+    "df"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "- Single Condition:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "source": [
-    "df.case_when(\n",
-    "    df.col1 == \"Z\",  # condition\n",
-    "    \"green\",         # value if True\n",
-    "    \"red\",           # value if False\n",
-    "    column_name = \"color\"\n",
-    "    )"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "  col1 col2 color\n",
-       "0    A    Z   red\n",
-       "1    B    Z   red\n",
-       "2    B    X   red\n",
-       "3    C    Y   red"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -173,44 +157,43 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "  col1 col2 color\n",
+       "0    A    Z   red\n",
+       "1    B    Z   red\n",
+       "2    B    X   red\n",
+       "3    C    Y   red"
       ]
      },
+     "execution_count": 3,
      "metadata": {},
-     "execution_count": 3
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df.case_when(\n",
+    "    df.col1 == \"Z\",  # condition\n",
+    "    \"green\",         # value if True\n",
+    "    \"red\",           # value if False\n",
+    "    column_name = \"color\"\n",
+    "    )"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "- Multiple Conditions:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "source": [
-    "df.case_when(\n",
-    "    df.col2.eq(\"Z\") & df.col1.eq(\"A\"), \"yellow\",  # first condition and value\n",
-    "    df.col2.eq(\"Z\") & df.col1.eq(\"B\"), \"blue\",    # second condition and value\n",
-    "    df.col1.eq(\"B\"), \"purple\",                    # third condition and value \n",
-    "    \"black\",                                      # default if no condition is True\n",
-    "    column_name = \"color\"\n",
-    "    )"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "  col1 col2   color\n",
-       "0    A    Z  yellow\n",
-       "1    B    Z    blue\n",
-       "2    B    X  purple\n",
-       "3    C    Y   black"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -263,40 +246,44 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "  col1 col2   color\n",
+       "0    A    Z  yellow\n",
+       "1    B    Z    blue\n",
+       "2    B    X  purple\n",
+       "3    C    Y   black"
       ]
      },
+     "execution_count": 4,
      "metadata": {},
-     "execution_count": 4
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df.case_when(\n",
+    "    df.col2.eq(\"Z\") & df.col1.eq(\"A\"), \"yellow\",  # first condition and value\n",
+    "    df.col2.eq(\"Z\") & df.col1.eq(\"B\"), \"blue\",    # second condition and value\n",
+    "    df.col1.eq(\"B\"), \"purple\",                    # third condition and value \n",
+    "    \"black\",                                      # default if no condition is True\n",
+    "    column_name = \"color\"\n",
+    "    )"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "Anonymous functions (lambda) are supported as well:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "source": [
-    "# https://stackoverflow.com/q/43391591/7175713\n",
-    "raw_data = {'age1': [23,45,21],'age2': [10,20,50]}\n",
-    "df = pd.DataFrame(raw_data, columns = ['age1','age2'])\n",
-    "df"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "   age1  age2\n",
-       "0    23    10\n",
-       "1    45    20\n",
-       "2    21    50"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -339,35 +326,33 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "   age1  age2\n",
+       "0    23    10\n",
+       "1    45    20\n",
+       "2    21    50"
       ]
      },
+     "execution_count": 5,
      "metadata": {},
-     "execution_count": 5
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "# https://stackoverflow.com/q/43391591/7175713\n",
+    "raw_data = {'age1': [23,45,21],'age2': [10,20,50]}\n",
+    "df = pd.DataFrame(raw_data, columns = ['age1','age2'])\n",
+    "df"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "source": [
-    "df.case_when(\n",
-    "    lambda df: (df.age1 - df.age2) > 0,   # condition\n",
-    "    lambda df: df.age1 - df.age2,         # value if True\n",
-    "    lambda df: df.age2 - df.age1,         # default if False\n",
-    "    column_name = \"diff\"\n",
-    ")"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "   age1  age2  diff\n",
-       "0    23    10    13\n",
-       "1    45    20    25\n",
-       "2    21    50    29"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -414,31 +399,41 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "   age1  age2  diff\n",
+       "0    23    10    13\n",
+       "1    45    20    25\n",
+       "2    21    50    29"
       ]
      },
+     "execution_count": 6,
      "metadata": {},
-     "execution_count": 6
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df.case_when(\n",
+    "    lambda df: (df.age1 - df.age2) > 0,   # condition\n",
+    "    lambda df: df.age1 - df.age2,         # value if True\n",
+    "    lambda df: df.age2 - df.age1,         # default if False\n",
+    "    column_name = \"diff\"\n",
+    ")"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "data types are preserved; under the hood it uses [pd.Series.mask](https://pandas.pydata.org/docs/reference/api/pandas.Series.mask.html):"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "source": [
-    "df = df.astype('Int64')\n",
-    "df.dtypes"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
       "text/plain": [
        "age1    Int64\n",
@@ -446,35 +441,23 @@
        "dtype: object"
       ]
      },
+     "execution_count": 7,
      "metadata": {},
-     "execution_count": 7
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df = df.astype('Int64')\n",
+    "df.dtypes"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
-   "source": [
-    "result = df.case_when(\n",
-    "            lambda df: (df.age1 - df.age2) > 0,   \n",
-    "            lambda df: df.age1 - df.age2,         \n",
-    "            lambda df: df.age2 - df.age1,         \n",
-    "            column_name = \"diff\"\n",
-    ")\n",
-    "\n",
-    "result"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "   age1  age2  diff\n",
-       "0    23    10    13\n",
-       "1    45    20    25\n",
-       "2    21    50    29"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -521,23 +504,36 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "   age1  age2  diff\n",
+       "0    23    10    13\n",
+       "1    45    20    25\n",
+       "2    21    50    29"
       ]
      },
+     "execution_count": 8,
      "metadata": {},
-     "execution_count": 8
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "result = df.case_when(\n",
+    "            lambda df: (df.age1 - df.age2) > 0,   \n",
+    "            lambda df: df.age1 - df.age2,         \n",
+    "            lambda df: df.age2 - df.age1,         \n",
+    "            column_name = \"diff\"\n",
+    ")\n",
+    "\n",
+    "result"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 9,
-   "source": [
-    "result.dtypes"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
       "text/plain": [
        "age1    Int64\n",
@@ -546,43 +542,29 @@
        "dtype: object"
       ]
      },
+     "execution_count": 9,
      "metadata": {},
-     "execution_count": 9
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "result.dtypes"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "The conditions can be a string, as long as they can be evaluated with `pd.eval` on the DataFrame, and return a boolean array:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 10,
-   "source": [
-    "# https://stackoverflow.com/q/54653356/7175713\n",
-    "data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], \n",
-    "        'age': [42, 52, 36, 24, 73], \n",
-    "        'preTestScore': [4, 24, 31, 2, 3],\n",
-    "        'postTestScore': [25, 94, 57, 62, 70]}\n",
-    "df = pd.DataFrame(data, columns = ['name', 'age', 'preTestScore', 'postTestScore'])\n",
-    "df"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "    name  age  preTestScore  postTestScore\n",
-       "0  Jason   42             4             25\n",
-       "1  Molly   52            24             94\n",
-       "2   Tina   36            31             57\n",
-       "3   Jake   24             2             62\n",
-       "4    Amy   73             3             70"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -647,39 +629,38 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "    name  age  preTestScore  postTestScore\n",
+       "0  Jason   42             4             25\n",
+       "1  Molly   52            24             94\n",
+       "2   Tina   36            31             57\n",
+       "3   Jake   24             2             62\n",
+       "4    Amy   73             3             70"
       ]
      },
+     "execution_count": 10,
      "metadata": {},
-     "execution_count": 10
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "# https://stackoverflow.com/q/54653356/7175713\n",
+    "data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], \n",
+    "        'age': [42, 52, 36, 24, 73], \n",
+    "        'preTestScore': [4, 24, 31, 2, 3],\n",
+    "        'postTestScore': [25, 94, 57, 62, 70]}\n",
+    "df = pd.DataFrame(data, columns = ['name', 'age', 'preTestScore', 'postTestScore'])\n",
+    "df"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 11,
-   "source": [
-    "df.case_when(\n",
-    "    \"age < 10\", \"baby\",\n",
-    "    \"10 <= age < 20\", \"kid\",\n",
-    "    \"20 <= age < 30\", \"young\", \n",
-    "    \"30 <= age < 50\", \"mature\",\n",
-    "    \"grandpa\",\n",
-    "    column_name = \"elderly\"\n",
-    ")"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "    name  age  preTestScore  postTestScore  elderly\n",
-       "0  Jason   42             4             25   mature\n",
-       "1  Molly   52            24             94  grandpa\n",
-       "2   Tina   36            31             57   mature\n",
-       "3   Jake   24             2             62    young\n",
-       "4    Amy   73             3             70  grandpa"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -750,45 +731,46 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "    name  age  preTestScore  postTestScore  elderly\n",
+       "0  Jason   42             4             25   mature\n",
+       "1  Molly   52            24             94  grandpa\n",
+       "2   Tina   36            31             57   mature\n",
+       "3   Jake   24             2             62    young\n",
+       "4    Amy   73             3             70  grandpa"
       ]
      },
+     "execution_count": 11,
      "metadata": {},
-     "execution_count": 11
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df.case_when(\n",
+    "    \"age < 10\", \"baby\",\n",
+    "    \"10 <= age < 20\", \"kid\",\n",
+    "    \"20 <= age < 30\", \"young\", \n",
+    "    \"30 <= age < 50\", \"mature\",\n",
+    "    \"grandpa\",\n",
+    "    column_name = \"elderly\"\n",
+    ")"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "When multiple conditions are satisfied, the first one is used:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 12,
-   "source": [
-    "df = range(3, 30, 3)\n",
-    "df = pd.DataFrame(df, columns = ['odd'])\n",
-    "df"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "   odd\n",
-       "0    3\n",
-       "1    6\n",
-       "2    9\n",
-       "3   12\n",
-       "4   15\n",
-       "5   18\n",
-       "6   21\n",
-       "7   24\n",
-       "8   27"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -851,41 +833,38 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "   odd\n",
+       "0    3\n",
+       "1    6\n",
+       "2    9\n",
+       "3   12\n",
+       "4   15\n",
+       "5   18\n",
+       "6   21\n",
+       "7   24\n",
+       "8   27"
       ]
      },
+     "execution_count": 12,
      "metadata": {},
-     "execution_count": 12
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df = range(3, 30, 3)\n",
+    "df = pd.DataFrame(df, columns = ['odd'])\n",
+    "df"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 13,
-   "source": [
-    "df.case_when(\n",
-    "    df.odd % 9 == 0, \n",
-    "    \"divisible by 9\",\n",
-    "    \"divisible by 3\",\n",
-    "    column_name = \"div_by_3_or_9\"\n",
-    ")"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "   odd   div_by_3_or_9\n",
-       "0    3  divisible by 3\n",
-       "1    6  divisible by 3\n",
-       "2    9  divisible by 9\n",
-       "3   12  divisible by 3\n",
-       "4   15  divisible by 3\n",
-       "5   18  divisible by 9\n",
-       "6   21  divisible by 3\n",
-       "7   24  divisible by 3\n",
-       "8   27  divisible by 9"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -958,55 +937,55 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "   odd   div_by_3_or_9\n",
+       "0    3  divisible by 3\n",
+       "1    6  divisible by 3\n",
+       "2    9  divisible by 9\n",
+       "3   12  divisible by 3\n",
+       "4   15  divisible by 3\n",
+       "5   18  divisible by 9\n",
+       "6   21  divisible by 3\n",
+       "7   24  divisible by 3\n",
+       "8   27  divisible by 9"
       ]
      },
+     "execution_count": 13,
      "metadata": {},
-     "execution_count": 13
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df.case_when(\n",
+    "    df.odd % 9 == 0, \n",
+    "    \"divisible by 9\",\n",
+    "    \"divisible by 3\",\n",
+    "    column_name = \"div_by_3_or_9\"\n",
+    ")"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "lines 2, 5 and 8 are divisible by 3; however, because the *first* condition tests if it is divisible by 9, that outcome is used instead."
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "If `column_name` exists in the DataFrame, then that column's values will be replaced with the outcome of `case_when`:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 14,
-   "source": [
-    "df.case_when(\n",
-    "    df.odd % 9 == 0, \n",
-    "    \"divisible by 9\",\n",
-    "    \"divisible by 3\",\n",
-    "    column_name = \"odd\"\n",
-    ")"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "              odd\n",
-       "0  divisible by 3\n",
-       "1  divisible by 3\n",
-       "2  divisible by 9\n",
-       "3  divisible by 3\n",
-       "4  divisible by 3\n",
-       "5  divisible by 9\n",
-       "6  divisible by 3\n",
-       "7  divisible by 3\n",
-       "8  divisible by 9"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1069,36 +1048,56 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "              odd\n",
+       "0  divisible by 3\n",
+       "1  divisible by 3\n",
+       "2  divisible by 9\n",
+       "3  divisible by 3\n",
+       "4  divisible by 3\n",
+       "5  divisible by 9\n",
+       "6  divisible by 3\n",
+       "7  divisible by 3\n",
+       "8  divisible by 9"
       ]
      },
+     "execution_count": 14,
      "metadata": {},
-     "execution_count": 14
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df.case_when(\n",
+    "    df.odd % 9 == 0, \n",
+    "    \"divisible by 9\",\n",
+    "    \"divisible by 3\",\n",
+    "    column_name = \"odd\"\n",
+    ")"
+   ]
   }
  ],
  "metadata": {
-  "orig_nbformat": 4,
+  "interpreter": {
+   "hash": "98b0a9b7b4eaaa670588a142fd0a9b87eaafe866f1db4228be72b4211d12040f"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.8.10 64-bit ('base': conda)",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python",
-   "version": "3.8.10",
-   "mimetype": "text/x-python",
    "codemirror_mode": {
     "name": "ipython",
     "version": 3
    },
-   "pygments_lexer": "ipython3",
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
    "nbconvert_exporter": "python",
-   "file_extension": ".py"
-  },
-  "kernelspec": {
-   "name": "python3",
-   "display_name": "Python 3.8.10 64-bit ('base': conda)"
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
   },
-  "interpreter": {
-   "hash": "98b0a9b7b4eaaa670588a142fd0a9b87eaafe866f1db4228be72b4211d12040f"
-  }
+  "orig_nbformat": 4
  },
  "nbformat": 4,
  "nbformat_minor": 2
diff --git a/examples/notebooks/coalesce.ipynb b/examples/notebooks/coalesce.ipynb
index f6ea32625..d20d4811f 100644
--- a/examples/notebooks/coalesce.ipynb
+++ b/examples/notebooks/coalesce.ipynb
@@ -13,9 +13,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
     "import numpy as np\n",
-    "import janitor "
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/complete.ipynb b/examples/notebooks/complete.ipynb
index 9785fe49a..027083b3d 100644
--- a/examples/notebooks/complete.ipynb
+++ b/examples/notebooks/complete.ipynb
@@ -14,8 +14,7 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "import numpy as np \n",
-    "import janitor\n"
+    "\n"
    ]
   },
   {
diff --git a/examples/notebooks/dirty_data.ipynb b/examples/notebooks/dirty_data.ipynb
index a91132132..ee58a4288 100644
--- a/examples/notebooks/dirty_data.ipynb
+++ b/examples/notebooks/dirty_data.ipynb
@@ -2,103 +2,52 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "# Processing Dirty Data"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "## Background \n",
     "\n",
     "This is fake data generated to demonstrate the capabilities of `pyjanitor`.  It contains a bunch of common problems that we regularly encounter when working with data.  Let's go fix it!"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "### Load Packages\n",
     "\n",
     "Importing `pyjanitor` is all that's needed to give Pandas Dataframes extra methods to work with your data."
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "source": [
-    "import pandas as pd\n",
-    "import janitor"
-   ],
+   "metadata": {},
    "outputs": [],
-   "metadata": {}
+   "source": [
+    "import pandas as pd\n"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "## Load Data"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "source": [
-    "df = pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
-    "df"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "      First Name Last Name Employee Status     Subject  Hire Date  \\\n",
-       "0          Jason    Bourne         Teacher          PE    39690.0   \n",
-       "1          Jason    Bourne         Teacher    Drafting    39690.0   \n",
-       "2         Alicia      Keys         Teacher       Music    37118.0   \n",
-       "3            Ada  Lovelace         Teacher         NaN    27515.0   \n",
-       "4          Desus      Nice  Administration        Dean    41431.0   \n",
-       "5   Chien-Shiung        Wu         Teacher     Physics    11037.0   \n",
-       "6   Chien-Shiung        Wu         Teacher   Chemistry    11037.0   \n",
-       "7            NaN       NaN             NaN         NaN        NaN   \n",
-       "8          James     Joyce         Teacher     English    32994.0   \n",
-       "9           Hedy    Lamarr         Teacher     Science    27919.0   \n",
-       "10        Carlos    Boozer           Coach  Basketball    42221.0   \n",
-       "11         Young    Boozer           Coach         NaN    34700.0   \n",
-       "12       Micheal    Larsen         Teacher     English    40071.0   \n",
-       "\n",
-       "    % Allocated Full time?  do not edit! ---> Certification Certification.1  \\\n",
-       "0          0.75        Yes                NaN   Physical ed         Theater   \n",
-       "1          0.25        Yes                NaN   Physical ed         Theater   \n",
-       "2          1.00        Yes                NaN  Instr. music     Vocal music   \n",
-       "3          1.00        Yes                NaN       PENDING       Computers   \n",
-       "4          1.00        Yes                NaN       PENDING             NaN   \n",
-       "5          0.50        Yes                NaN  Science 6-12         Physics   \n",
-       "6          0.50        Yes                NaN  Science 6-12         Physics   \n",
-       "7           NaN        NaN                NaN           NaN             NaN   \n",
-       "8          0.50         No                NaN           NaN    English 6-12   \n",
-       "9          0.50         No                NaN       PENDING             NaN   \n",
-       "10          NaN         No                NaN   Physical ed             NaN   \n",
-       "11          NaN         No                NaN           NaN  Political sci.   \n",
-       "12         0.80         No                NaN   Vocal music         English   \n",
-       "\n",
-       "    Certification.2  \n",
-       "0               NaN  \n",
-       "1               NaN  \n",
-       "2               NaN  \n",
-       "3               NaN  \n",
-       "4               NaN  \n",
-       "5               NaN  \n",
-       "6               NaN  \n",
-       "7               NaN  \n",
-       "8               NaN  \n",
-       "9               NaN  \n",
-       "10              NaN  \n",
-       "11              NaN  \n",
-       "12              NaN  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -317,43 +266,80 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "      First Name Last Name Employee Status     Subject  Hire Date  \\\n",
+       "0          Jason    Bourne         Teacher          PE    39690.0   \n",
+       "1          Jason    Bourne         Teacher    Drafting    39690.0   \n",
+       "2         Alicia      Keys         Teacher       Music    37118.0   \n",
+       "3            Ada  Lovelace         Teacher         NaN    27515.0   \n",
+       "4          Desus      Nice  Administration        Dean    41431.0   \n",
+       "5   Chien-Shiung        Wu         Teacher     Physics    11037.0   \n",
+       "6   Chien-Shiung        Wu         Teacher   Chemistry    11037.0   \n",
+       "7            NaN       NaN             NaN         NaN        NaN   \n",
+       "8          James     Joyce         Teacher     English    32994.0   \n",
+       "9           Hedy    Lamarr         Teacher     Science    27919.0   \n",
+       "10        Carlos    Boozer           Coach  Basketball    42221.0   \n",
+       "11         Young    Boozer           Coach         NaN    34700.0   \n",
+       "12       Micheal    Larsen         Teacher     English    40071.0   \n",
+       "\n",
+       "    % Allocated Full time?  do not edit! ---> Certification Certification.1  \\\n",
+       "0          0.75        Yes                NaN   Physical ed         Theater   \n",
+       "1          0.25        Yes                NaN   Physical ed         Theater   \n",
+       "2          1.00        Yes                NaN  Instr. music     Vocal music   \n",
+       "3          1.00        Yes                NaN       PENDING       Computers   \n",
+       "4          1.00        Yes                NaN       PENDING             NaN   \n",
+       "5          0.50        Yes                NaN  Science 6-12         Physics   \n",
+       "6          0.50        Yes                NaN  Science 6-12         Physics   \n",
+       "7           NaN        NaN                NaN           NaN             NaN   \n",
+       "8          0.50         No                NaN           NaN    English 6-12   \n",
+       "9          0.50         No                NaN       PENDING             NaN   \n",
+       "10          NaN         No                NaN   Physical ed             NaN   \n",
+       "11          NaN         No                NaN           NaN  Political sci.   \n",
+       "12         0.80         No                NaN   Vocal music         English   \n",
+       "\n",
+       "    Certification.2  \n",
+       "0               NaN  \n",
+       "1               NaN  \n",
+       "2               NaN  \n",
+       "3               NaN  \n",
+       "4               NaN  \n",
+       "5               NaN  \n",
+       "6               NaN  \n",
+       "7               NaN  \n",
+       "8               NaN  \n",
+       "9               NaN  \n",
+       "10              NaN  \n",
+       "11              NaN  \n",
+       "12              NaN  "
       ]
      },
+     "execution_count": 2,
      "metadata": {},
-     "execution_count": 2
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df = pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
+    "df"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "## Cleaning Column Names\n",
     "\n",
     "There are a bunch of problems with this data. Firstly, the column names are not lowercase, and they have spaces. This will make it cumbersome to use in a programmatic function. To solve this, we can use the `clean_names()` method."
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "source": [
-    "df_clean = df.clean_names()\n",
-    "df_clean.head(2)"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "  first_name last_name employee_status   subject  hire_date  %_allocated  \\\n",
-       "0      Jason    Bourne         Teacher        PE    39690.0         0.75   \n",
-       "1      Jason    Bourne         Teacher  Drafting    39690.0         0.25   \n",
-       "\n",
-       "  full_time_  do_not_edit!_> certification certification_1  certification_2  \n",
-       "0        Yes             NaN   Physical ed         Theater              NaN  \n",
-       "1        Yes             NaN   Physical ed         Theater              NaN  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -418,52 +404,48 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "  first_name last_name employee_status   subject  hire_date  %_allocated  \\\n",
+       "0      Jason    Bourne         Teacher        PE    39690.0         0.75   \n",
+       "1      Jason    Bourne         Teacher  Drafting    39690.0         0.25   \n",
+       "\n",
+       "  full_time_  do_not_edit!_> certification certification_1  certification_2  \n",
+       "0        Yes             NaN   Physical ed         Theater              NaN  \n",
+       "1        Yes             NaN   Physical ed         Theater              NaN  "
       ]
      },
+     "execution_count": 3,
      "metadata": {},
-     "execution_count": 3
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df_clean = df.clean_names()\n",
+    "df_clean.head(2)"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "Notice now how the column names have been made better."
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "If you squint at the unclean dataset, you'll notice one row and one column of data that are missing. We can also fix this! Building on top of the code block from above, let's now remove those empty columns using the `remove_empty()` method:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "source": [
-    "df_clean = df.clean_names().remove_empty()\n",
-    "df_clean.head(9).tail(4)"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "     first_name last_name employee_status    subject  hire_date  %_allocated  \\\n",
-       "5  Chien-Shiung        Wu         Teacher    Physics    11037.0          0.5   \n",
-       "6  Chien-Shiung        Wu         Teacher  Chemistry    11037.0          0.5   \n",
-       "7         James     Joyce         Teacher    English    32994.0          0.5   \n",
-       "8          Hedy    Lamarr         Teacher    Science    27919.0          0.5   \n",
-       "\n",
-       "  full_time_ certification certification_1  \n",
-       "5        Yes  Science 6-12         Physics  \n",
-       "6        Yes  Science 6-12         Physics  \n",
-       "7         No           NaN    English 6-12  \n",
-       "8         No       PENDING             NaN  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -546,63 +528,54 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "     first_name last_name employee_status    subject  hire_date  %_allocated  \\\n",
+       "5  Chien-Shiung        Wu         Teacher    Physics    11037.0          0.5   \n",
+       "6  Chien-Shiung        Wu         Teacher  Chemistry    11037.0          0.5   \n",
+       "7         James     Joyce         Teacher    English    32994.0          0.5   \n",
+       "8          Hedy    Lamarr         Teacher    Science    27919.0          0.5   \n",
+       "\n",
+       "  full_time_ certification certification_1  \n",
+       "5        Yes  Science 6-12         Physics  \n",
+       "6        Yes  Science 6-12         Physics  \n",
+       "7         No           NaN    English 6-12  \n",
+       "8         No       PENDING             NaN  "
       ]
      },
+     "execution_count": 4,
      "metadata": {},
-     "execution_count": 4
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df_clean = df.clean_names().remove_empty()\n",
+    "df_clean.head(9).tail(4)"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "Now this is starting to shape up well!"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "## Renaming Individual Columns\n",
     "\n",
     "Next, let's rename some of the columns. `%_allocated` and `full_time?` contain non-alphanumeric characters, so they make it a bit harder to use. We can rename them using the :py:meth:`rename_column()` method:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "source": [
-    "df_clean = (\n",
-    "    df\n",
-    "    .clean_names()\n",
-    "    .remove_empty()\n",
-    "    .rename_column(\"%_allocated\", \"percent_allocated\")\n",
-    "    .rename_column(\"full_time_\", \"full_time\")\n",
-    ")\n",
-    "\n",
-    "df_clean.head(5)"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "  first_name last_name employee_status   subject  hire_date  \\\n",
-       "0      Jason    Bourne         Teacher        PE    39690.0   \n",
-       "1      Jason    Bourne         Teacher  Drafting    39690.0   \n",
-       "2     Alicia      Keys         Teacher     Music    37118.0   \n",
-       "3        Ada  Lovelace         Teacher       NaN    27515.0   \n",
-       "4      Desus      Nice  Administration      Dean    41431.0   \n",
-       "\n",
-       "   percent_allocated full_time certification certification_1  \n",
-       "0               0.75       Yes   Physical ed         Theater  \n",
-       "1               0.25       Yes   Physical ed         Theater  \n",
-       "2               1.00       Yes  Instr. music     Vocal music  \n",
-       "3               1.00       Yes       PENDING       Computers  \n",
-       "4               1.00       Yes       PENDING             NaN  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -697,55 +670,63 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "  first_name last_name employee_status   subject  hire_date  \\\n",
+       "0      Jason    Bourne         Teacher        PE    39690.0   \n",
+       "1      Jason    Bourne         Teacher  Drafting    39690.0   \n",
+       "2     Alicia      Keys         Teacher     Music    37118.0   \n",
+       "3        Ada  Lovelace         Teacher       NaN    27515.0   \n",
+       "4      Desus      Nice  Administration      Dean    41431.0   \n",
+       "\n",
+       "   percent_allocated full_time certification certification_1  \n",
+       "0               0.75       Yes   Physical ed         Theater  \n",
+       "1               0.25       Yes   Physical ed         Theater  \n",
+       "2               1.00       Yes  Instr. music     Vocal music  \n",
+       "3               1.00       Yes       PENDING       Computers  \n",
+       "4               1.00       Yes       PENDING             NaN  "
       ]
      },
+     "execution_count": 5,
      "metadata": {},
-     "execution_count": 5
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df_clean = (\n",
+    "    df\n",
+    "    .clean_names()\n",
+    "    .remove_empty()\n",
+    "    .rename_column(\"%_allocated\", \"percent_allocated\")\n",
+    "    .rename_column(\"full_time_\", \"full_time\")\n",
+    ")\n",
+    "\n",
+    "df_clean.head(5)"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "Note how now we have really nice column names! You might be wondering why I'm not modifying the two certification columns -- that is the next thing we'll tackle."
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "## Coalescing Columns\n",
     "\n",
     "If we look more closely at the two `certification` columns, we'll see that they look like this:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "source": [
-    "df_clean[['certification', 'certification_1']]"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "   certification certification_1\n",
-       "0    Physical ed         Theater\n",
-       "1    Physical ed         Theater\n",
-       "2   Instr. music     Vocal music\n",
-       "3        PENDING       Computers\n",
-       "4        PENDING             NaN\n",
-       "5   Science 6-12         Physics\n",
-       "6   Science 6-12         Physics\n",
-       "7            NaN    English 6-12\n",
-       "8        PENDING             NaN\n",
-       "9    Physical ed             NaN\n",
-       "10           NaN  Political sci.\n",
-       "11   Vocal music         English"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -833,72 +814,46 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "   certification certification_1\n",
+       "0    Physical ed         Theater\n",
+       "1    Physical ed         Theater\n",
+       "2   Instr. music     Vocal music\n",
+       "3        PENDING       Computers\n",
+       "4        PENDING             NaN\n",
+       "5   Science 6-12         Physics\n",
+       "6   Science 6-12         Physics\n",
+       "7            NaN    English 6-12\n",
+       "8        PENDING             NaN\n",
+       "9    Physical ed             NaN\n",
+       "10           NaN  Political sci.\n",
+       "11   Vocal music         English"
       ]
      },
+     "execution_count": 6,
      "metadata": {},
-     "execution_count": 6
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df_clean[['certification', 'certification_1']]"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "Rows 8 and 11 have NaN in the left certification column, but have a value in the right certification column. Let's assume for a moment that the left certification column is intended to record the first certification that a teacher had obtained. In this case, the values in the right certification column on rows 8 and 11 should be moved to the first column. Let's do that with Janitor, using the `coalesce()` method, which does the following:"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "source": [
-    "df_clean = (\n",
-    "    df\n",
-    "    .clean_names()\n",
-    "    .remove_empty()\n",
-    "    .rename_column(\"%_allocated\", \"percent_allocated\")\n",
-    "    .rename_column(\"full_time_\", \"full_time\")\n",
-    "    .coalesce(\n",
-    "        'certification', 'certification_1',\n",
-    "        new_column_name='certification'\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "df_clean"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "      first_name last_name employee_status     subject  hire_date  \\\n",
-       "0          Jason    Bourne         Teacher          PE    39690.0   \n",
-       "1          Jason    Bourne         Teacher    Drafting    39690.0   \n",
-       "2         Alicia      Keys         Teacher       Music    37118.0   \n",
-       "3            Ada  Lovelace         Teacher         NaN    27515.0   \n",
-       "4          Desus      Nice  Administration        Dean    41431.0   \n",
-       "5   Chien-Shiung        Wu         Teacher     Physics    11037.0   \n",
-       "6   Chien-Shiung        Wu         Teacher   Chemistry    11037.0   \n",
-       "7          James     Joyce         Teacher     English    32994.0   \n",
-       "8           Hedy    Lamarr         Teacher     Science    27919.0   \n",
-       "9         Carlos    Boozer           Coach  Basketball    42221.0   \n",
-       "10         Young    Boozer           Coach         NaN    34700.0   \n",
-       "11       Micheal    Larsen         Teacher     English    40071.0   \n",
-       "\n",
-       "    percent_allocated full_time   certification certification_1  \n",
-       "0                0.75       Yes     Physical ed         Theater  \n",
-       "1                0.25       Yes     Physical ed         Theater  \n",
-       "2                1.00       Yes    Instr. music     Vocal music  \n",
-       "3                1.00       Yes         PENDING       Computers  \n",
-       "4                1.00       Yes         PENDING             NaN  \n",
-       "5                0.50       Yes    Science 6-12         Physics  \n",
-       "6                0.50       Yes    Science 6-12         Physics  \n",
-       "7                0.50        No    English 6-12    English 6-12  \n",
-       "8                0.50        No         PENDING             NaN  \n",
-       "9                 NaN        No     Physical ed             NaN  \n",
-       "10                NaN        No  Political sci.  Political sci.  \n",
-       "11               0.80        No     Vocal music         English  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1077,79 +1032,82 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "      first_name last_name employee_status     subject  hire_date  \\\n",
+       "0          Jason    Bourne         Teacher          PE    39690.0   \n",
+       "1          Jason    Bourne         Teacher    Drafting    39690.0   \n",
+       "2         Alicia      Keys         Teacher       Music    37118.0   \n",
+       "3            Ada  Lovelace         Teacher         NaN    27515.0   \n",
+       "4          Desus      Nice  Administration        Dean    41431.0   \n",
+       "5   Chien-Shiung        Wu         Teacher     Physics    11037.0   \n",
+       "6   Chien-Shiung        Wu         Teacher   Chemistry    11037.0   \n",
+       "7          James     Joyce         Teacher     English    32994.0   \n",
+       "8           Hedy    Lamarr         Teacher     Science    27919.0   \n",
+       "9         Carlos    Boozer           Coach  Basketball    42221.0   \n",
+       "10         Young    Boozer           Coach         NaN    34700.0   \n",
+       "11       Micheal    Larsen         Teacher     English    40071.0   \n",
+       "\n",
+       "    percent_allocated full_time   certification certification_1  \n",
+       "0                0.75       Yes     Physical ed         Theater  \n",
+       "1                0.25       Yes     Physical ed         Theater  \n",
+       "2                1.00       Yes    Instr. music     Vocal music  \n",
+       "3                1.00       Yes         PENDING       Computers  \n",
+       "4                1.00       Yes         PENDING             NaN  \n",
+       "5                0.50       Yes    Science 6-12         Physics  \n",
+       "6                0.50       Yes    Science 6-12         Physics  \n",
+       "7                0.50        No    English 6-12    English 6-12  \n",
+       "8                0.50        No         PENDING             NaN  \n",
+       "9                 NaN        No     Physical ed             NaN  \n",
+       "10                NaN        No  Political sci.  Political sci.  \n",
+       "11               0.80        No     Vocal music         English  "
       ]
      },
+     "execution_count": 7,
      "metadata": {},
-     "execution_count": 7
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df_clean = (\n",
+    "    df\n",
+    "    .clean_names()\n",
+    "    .remove_empty()\n",
+    "    .rename_column(\"%_allocated\", \"percent_allocated\")\n",
+    "    .rename_column(\"full_time_\", \"full_time\")\n",
+    "    .coalesce(\n",
+    "        'certification', 'certification_1',\n",
+    "        new_column_name='certification'\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "df_clean"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "Awesome stuff! Now we don't have two columns of scattered data, we have one column of densely populated data.`"
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "## Dealing with Excel Dates\n",
     "\n",
     "Finally, notice how the `hire_date` column isn't date formatted. It's got this weird Excel serialization.\n",
     "To clean up this data, we can use the :py:meth:`convert_excel_date` method."
-   ],
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
-   "source": [
-    "df_clean = (\n",
-    "    df\n",
-    "    .clean_names()\n",
-    "    .remove_empty()\n",
-    "    .rename_column('%_allocated', 'percent_allocated')\n",
-    "    .rename_column('full_time_', 'full_time')\n",
-    "    .coalesce('certification', 'certification_1', target_column_name = 'certification')\n",
-    "    .convert_excel_date('hire_date')\n",
-    ")\n",
-    "df_clean"
-   ],
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
-      "text/plain": [
-       "      first_name last_name employee_status     subject  hire_date  \\\n",
-       "0          Jason    Bourne         Teacher          PE 2008-08-30   \n",
-       "1          Jason    Bourne         Teacher    Drafting 2008-08-30   \n",
-       "2         Alicia      Keys         Teacher       Music 2001-08-15   \n",
-       "3            Ada  Lovelace         Teacher         NaN 1975-05-01   \n",
-       "4          Desus      Nice  Administration        Dean 2013-06-06   \n",
-       "5   Chien-Shiung        Wu         Teacher     Physics 1930-03-20   \n",
-       "6   Chien-Shiung        Wu         Teacher   Chemistry 1930-03-20   \n",
-       "7          James     Joyce         Teacher     English 1990-05-01   \n",
-       "8           Hedy    Lamarr         Teacher     Science 1976-06-08   \n",
-       "9         Carlos    Boozer           Coach  Basketball 2015-08-05   \n",
-       "10         Young    Boozer           Coach         NaN 1995-01-01   \n",
-       "11       Micheal    Larsen         Teacher     English 2009-09-15   \n",
-       "\n",
-       "    percent_allocated full_time   certification certification_1  \n",
-       "0                0.75       Yes     Physical ed         Theater  \n",
-       "1                0.25       Yes     Physical ed         Theater  \n",
-       "2                1.00       Yes    Instr. music     Vocal music  \n",
-       "3                1.00       Yes         PENDING       Computers  \n",
-       "4                1.00       Yes         PENDING             NaN  \n",
-       "5                0.50       Yes    Science 6-12         Physics  \n",
-       "6                0.50       Yes    Science 6-12         Physics  \n",
-       "7                0.50        No    English 6-12    English 6-12  \n",
-       "8                0.50        No         PENDING             NaN  \n",
-       "9                 NaN        No     Physical ed             NaN  \n",
-       "10                NaN        No  Political sci.  Political sci.  \n",
-       "11               0.80        No     Vocal music         English  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1328,26 +1286,70 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "      first_name last_name employee_status     subject  hire_date  \\\n",
+       "0          Jason    Bourne         Teacher          PE 2008-08-30   \n",
+       "1          Jason    Bourne         Teacher    Drafting 2008-08-30   \n",
+       "2         Alicia      Keys         Teacher       Music 2001-08-15   \n",
+       "3            Ada  Lovelace         Teacher         NaN 1975-05-01   \n",
+       "4          Desus      Nice  Administration        Dean 2013-06-06   \n",
+       "5   Chien-Shiung        Wu         Teacher     Physics 1930-03-20   \n",
+       "6   Chien-Shiung        Wu         Teacher   Chemistry 1930-03-20   \n",
+       "7          James     Joyce         Teacher     English 1990-05-01   \n",
+       "8           Hedy    Lamarr         Teacher     Science 1976-06-08   \n",
+       "9         Carlos    Boozer           Coach  Basketball 2015-08-05   \n",
+       "10         Young    Boozer           Coach         NaN 1995-01-01   \n",
+       "11       Micheal    Larsen         Teacher     English 2009-09-15   \n",
+       "\n",
+       "    percent_allocated full_time   certification certification_1  \n",
+       "0                0.75       Yes     Physical ed         Theater  \n",
+       "1                0.25       Yes     Physical ed         Theater  \n",
+       "2                1.00       Yes    Instr. music     Vocal music  \n",
+       "3                1.00       Yes         PENDING       Computers  \n",
+       "4                1.00       Yes         PENDING             NaN  \n",
+       "5                0.50       Yes    Science 6-12         Physics  \n",
+       "6                0.50       Yes    Science 6-12         Physics  \n",
+       "7                0.50        No    English 6-12    English 6-12  \n",
+       "8                0.50        No         PENDING             NaN  \n",
+       "9                 NaN        No     Physical ed             NaN  \n",
+       "10                NaN        No  Political sci.  Political sci.  \n",
+       "11               0.80        No     Vocal music         English  "
       ]
      },
+     "execution_count": 8,
      "metadata": {},
-     "execution_count": 8
+     "output_type": "execute_result"
     }
    ],
-   "metadata": {}
+   "source": [
+    "df_clean = (\n",
+    "    df\n",
+    "    .clean_names()\n",
+    "    .remove_empty()\n",
+    "    .rename_column('%_allocated', 'percent_allocated')\n",
+    "    .rename_column('full_time_', 'full_time')\n",
+    "    .coalesce('certification', 'certification_1', target_column_name = 'certification')\n",
+    "    .convert_excel_date('hire_date')\n",
+    ")\n",
+    "df_clean"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "We have a cleaned dataframe!"
-   ],
-   "metadata": {}
+   ]
   }
  ],
  "metadata": {
+  "interpreter": {
+   "hash": "98b0a9b7b4eaaa670588a142fd0a9b87eaafe866f1db4228be72b4211d12040f"
+  },
   "kernelspec": {
-   "name": "python3",
-   "display_name": "Python 3.8.10 64-bit ('base': conda)"
+   "display_name": "Python 3.8.10 64-bit ('base': conda)",
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -1360,9 +1362,6 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.8.10"
-  },
-  "interpreter": {
-   "hash": "98b0a9b7b4eaaa670588a142fd0a9b87eaafe866f1db4228be72b4211d12040f"
   }
  },
  "nbformat": 4,
diff --git a/examples/notebooks/encode_categorical.ipynb b/examples/notebooks/encode_categorical.ipynb
index 1c62efbdb..7e60adc3e 100644
--- a/examples/notebooks/encode_categorical.ipynb
+++ b/examples/notebooks/encode_categorical.ipynb
@@ -14,8 +14,7 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "import janitor\n",
-    "from numpy import nan"
+    "from numpy import nan\n"
    ]
   },
   {
diff --git a/examples/notebooks/expand_grid.ipynb b/examples/notebooks/expand_grid.ipynb
index 80dbaadf1..d44212796 100644
--- a/examples/notebooks/expand_grid.ipynb
+++ b/examples/notebooks/expand_grid.ipynb
@@ -25,8 +25,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
     "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
     "from janitor import expand_grid"
    ]
   },
diff --git a/examples/notebooks/fill_direction.ipynb b/examples/notebooks/fill_direction.ipynb
index 86fd78298..b8591b4ee 100644
--- a/examples/notebooks/fill_direction.ipynb
+++ b/examples/notebooks/fill_direction.ipynb
@@ -14,8 +14,7 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "import janitor\n",
-    "from numpy import nan"
+    "from numpy import nan\n"
    ]
   },
   {
diff --git a/examples/notebooks/french_trains.ipynb b/examples/notebooks/french_trains.ipynb
index 57750f0d5..f04d24db4 100644
--- a/examples/notebooks/french_trains.ipynb
+++ b/examples/notebooks/french_trains.ipynb
@@ -27,8 +27,7 @@
    "outputs": [],
    "source": [
     "from collections import Counter\n",
-    "import janitor\n",
-    "import os\n",
+    "\n",
     "import pandas as pd\n",
     "import seaborn as sns\n",
     "\n",
diff --git a/examples/notebooks/groupby_agg.ipynb b/examples/notebooks/groupby_agg.ipynb
index 2c943c032..14e9d73f8 100644
--- a/examples/notebooks/groupby_agg.ipynb
+++ b/examples/notebooks/groupby_agg.ipynb
@@ -44,9 +44,8 @@
    "outputs": [],
    "source": [
     "# load modules\n",
-    "import pandas as pd\n",
     "import numpy as np\n",
-    "import janitor"
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/inflating_converting_currency.ipynb b/examples/notebooks/inflating_converting_currency.ipynb
index 08c372b51..9a0e1f97b 100644
--- a/examples/notebooks/inflating_converting_currency.ipynb
+++ b/examples/notebooks/inflating_converting_currency.ipynb
@@ -62,9 +62,8 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "import os"
+    "\n",
+    "import pandas as pd\n"
    ]
   },
   {
@@ -118,7 +117,6 @@
    },
    "outputs": [],
    "source": [
-    "from janitor.finance import inflate_currency, convert_currency\n",
     "\n",
     "# Use split-apply-combine strategy to obtain 2018$ values\n",
     "# Group the data frame by year\n",
@@ -189,7 +187,6 @@
    },
    "outputs": [],
    "source": [
-    "from datetime import date\n",
     "\n",
     "# # Apply the convert_currency() method to the 'expenditure_2018' column\n",
     "# # Use the exchange rate from Dec. 31, 2018, since our data are in 2018$\n",
diff --git a/examples/notebooks/medium_franchise.ipynb b/examples/notebooks/medium_franchise.ipynb
index a063abe35..d187ca540 100644
--- a/examples/notebooks/medium_franchise.ipynb
+++ b/examples/notebooks/medium_franchise.ipynb
@@ -54,10 +54,10 @@
    "outputs": [],
    "source": [
     "# Import pyjanitor and pandas\n",
-    "import janitor\n",
+    "from typing import List\n",
+    "\n",
     "import pandas as pd\n",
-    "import pandas_flavor as pf\n",
-    "from typing import List"
+    "import pandas_flavor as pf"
    ]
   },
   {
@@ -68,6 +68,7 @@
    "source": [
     "# Suppress user warnings when we try overwriting our custom pandas flavor functions\n",
     "import warnings\n",
+    "\n",
     "warnings.filterwarnings('ignore')"
    ]
   },
@@ -973,7 +974,7 @@
     "    for col in df.columns:\n",
     "        try:\n",
     "            df[col] = pd.to_numeric(df[col])\n",
-    "        except ValueError as e:\n",
+    "        except ValueError:\n",
     "            continue\n",
     "    return df\n",
     "\n",
diff --git a/examples/notebooks/normalize.ipynb b/examples/notebooks/normalize.ipynb
index 8eebfb992..f653ebb56 100644
--- a/examples/notebooks/normalize.ipynb
+++ b/examples/notebooks/normalize.ipynb
@@ -21,10 +21,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import janitor\n",
     "import pandas as pd\n",
-    "import numpy as np\n",
     "import seaborn as sns\n",
+    "\n",
     "sns.set(style=\"whitegrid\")"
    ]
   },
diff --git a/examples/notebooks/process_text.ipynb b/examples/notebooks/process_text.ipynb
index c6f77978b..1b899193d 100644
--- a/examples/notebooks/process_text.ipynb
+++ b/examples/notebooks/process_text.ipynb
@@ -13,9 +13,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "import re"
+    "import re\n",
+    "\n",
+    "import pandas as pd\n"
    ]
   },
   {
diff --git a/examples/notebooks/pyjanitor_intro.ipynb b/examples/notebooks/pyjanitor_intro.ipynb
index 8fb2be6d4..1527edd29 100644
--- a/examples/notebooks/pyjanitor_intro.ipynb
+++ b/examples/notebooks/pyjanitor_intro.ipynb
@@ -137,16 +137,14 @@
    ]
   },
   {
-   "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "import pandas_flavor as pf\n",
-    "import numpy as np"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 1,
-   "outputs": []
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -156,17 +154,13 @@
    ]
   },
   {
-   "source": [
-    "df = pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 2,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>First Name</th>\n      <th>Last Name</th>\n      <th>Employee Status</th>\n      <th>Subject</th>\n      <th>Hire Date</th>\n      <th>% Allocated</th>\n      <th>Full time?</th>\n      <th>do not edit! ---&gt;</th>\n      <th>Certification</th>\n      <th>Certification.1</th>\n      <th>Certification.2</th>\n      <th>Unnamed: 11</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Vocal music</td>\n      <td>English</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      First Name Last Name Employee Status     Subject  Hire Date  \\\n",
        "0          Jason    Bourne         Teacher          PE    39690.0   \n",
@@ -224,12 +218,16 @@
        "14              NaN          NaN  \n",
        "15              NaN          NaN  \n",
        "16              NaN          NaN  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>First Name</th>\n      <th>Last Name</th>\n      <th>Employee Status</th>\n      <th>Subject</th>\n      <th>Hire Date</th>\n      <th>% Allocated</th>\n      <th>Full time?</th>\n      <th>do not edit! ---&gt;</th>\n      <th>Certification</th>\n      <th>Certification.1</th>\n      <th>Certification.2</th>\n      <th>Unnamed: 11</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Vocal music</td>\n      <td>English</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 2,
      "metadata": {},
-     "execution_count": 2
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df = pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
+    "df"
    ]
   },
   {
@@ -253,28 +251,13 @@
    ]
   },
   {
-   "source": [
-    "cleaned_df = (\n",
-    "    pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
-    "    .clean_names()\n",
-    "    .remove_empty()\n",
-    "    .rename_column(\"%_allocated\", \"percent_allocated\")\n",
-    "    .rename_column(\"full_time_\", \"full_time\")\n",
-    "    .coalesce([\"certification\", \"certification_1\"], \"certification\")\n",
-    "    .encode_categorical([\"subject\", \"employee_status\", \"full_time\"])\n",
-    "    .convert_excel_date(\"hire_date\")\n",
-    "    .reset_index(drop=True)\n",
-    ")\n",
-    "\n",
-    "cleaned_df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 3,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>2008-08-30</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>2008-08-30</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>2001-08-15</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>1975-05-01</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>2013-06-06</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>1990-05-01</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>1976-06-08</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>2015-08-05</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>1995-01-01</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>2009-09-15</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE 2008-08-30   \n",
@@ -303,12 +286,27 @@
        "9                 NaN        No     Physical ed  \n",
        "10                NaN        No  Political sci.  \n",
        "11               0.80        No     Vocal music  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>2008-08-30</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>2008-08-30</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>2001-08-15</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>1975-05-01</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>2013-06-06</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>1990-05-01</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>1976-06-08</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>2015-08-05</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>1995-01-01</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>2009-09-15</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 3,
      "metadata": {},
-     "execution_count": 3
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "cleaned_df = (\n",
+    "    pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
+    "    .clean_names()\n",
+    "    .remove_empty()\n",
+    "    .rename_column(\"%_allocated\", \"percent_allocated\")\n",
+    "    .rename_column(\"full_time_\", \"full_time\")\n",
+    "    .coalesce([\"certification\", \"certification_1\"], \"certification\")\n",
+    "    .encode_categorical([\"subject\", \"employee_status\", \"full_time\"])\n",
+    "    .convert_excel_date(\"hire_date\")\n",
+    "    .reset_index(drop=True)\n",
+    ")\n",
+    "\n",
+    "cleaned_df"
    ]
   },
   {
@@ -330,17 +328,13 @@
    ]
   },
   {
-   "source": [
-    "df = pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 4,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>First Name</th>\n      <th>Last Name</th>\n      <th>Employee Status</th>\n      <th>Subject</th>\n      <th>Hire Date</th>\n      <th>% Allocated</th>\n      <th>Full time?</th>\n      <th>do not edit! ---&gt;</th>\n      <th>Certification</th>\n      <th>Certification.1</th>\n      <th>Certification.2</th>\n      <th>Unnamed: 11</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Vocal music</td>\n      <td>English</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      First Name Last Name Employee Status     Subject  Hire Date  \\\n",
        "0          Jason    Bourne         Teacher          PE    39690.0   \n",
@@ -398,12 +392,16 @@
        "14              NaN          NaN  \n",
        "15              NaN          NaN  \n",
        "16              NaN          NaN  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>First Name</th>\n      <th>Last Name</th>\n      <th>Employee Status</th>\n      <th>Subject</th>\n      <th>Hire Date</th>\n      <th>% Allocated</th>\n      <th>Full time?</th>\n      <th>do not edit! ---&gt;</th>\n      <th>Certification</th>\n      <th>Certification.1</th>\n      <th>Certification.2</th>\n      <th>Unnamed: 11</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Vocal music</td>\n      <td>English</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 4,
      "metadata": {},
-     "execution_count": 4
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df = pd.read_excel('dirty_data.xlsx', engine='openpyxl')\n",
+    "df"
    ]
   },
   {
@@ -414,17 +412,13 @@
    ]
   },
   {
-   "source": [
-    "df = df.clean_names()\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 5,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>%_allocated</th>\n      <th>full_time_</th>\n      <th>do_not_edit!_&gt;</th>\n      <th>certification</th>\n      <th>certification_1</th>\n      <th>certification_2</th>\n      <th>unnamed_11</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Vocal music</td>\n      <td>English</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE    39690.0   \n",
@@ -482,12 +476,16 @@
        "14              NaN         NaN  \n",
        "15              NaN         NaN  \n",
        "16              NaN         NaN  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>%_allocated</th>\n      <th>full_time_</th>\n      <th>do_not_edit!_&gt;</th>\n      <th>certification</th>\n      <th>certification_1</th>\n      <th>certification_2</th>\n      <th>unnamed_11</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>NaN</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Vocal music</td>\n      <td>English</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 5,
      "metadata": {},
-     "execution_count": 5
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df = df.clean_names()\n",
+    "df"
    ]
   },
   {
@@ -498,17 +496,13 @@
    ]
   },
   {
-   "source": [
-    "df = df.remove_empty()\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 6,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>%_allocated</th>\n      <th>full_time_</th>\n      <th>certification</th>\n      <th>certification_1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n      <td>English</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE    39690.0   \n",
@@ -537,12 +531,16 @@
        "9           NaN         No   Physical ed             NaN  \n",
        "10          NaN         No           NaN  Political sci.  \n",
        "11         0.80         No   Vocal music         English  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>%_allocated</th>\n      <th>full_time_</th>\n      <th>certification</th>\n      <th>certification_1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n      <td>English</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 6,
      "metadata": {},
-     "execution_count": 6
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df = df.remove_empty()\n",
+    "df"
    ]
   },
   {
@@ -553,20 +551,13 @@
    ]
   },
   {
-   "source": [
-    "df = (\n",
-    "    df.rename_column(\"%_allocated\", \"percent_allocated\")\n",
-    "    .rename_column(\"full_time_\", \"full_time\")\n",
-    ")\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 7,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n      <th>certification_1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n      <td>English</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE    39690.0   \n",
@@ -595,12 +586,19 @@
        "9                 NaN        No   Physical ed             NaN  \n",
        "10                NaN        No           NaN  Political sci.  \n",
        "11               0.80        No   Vocal music         English  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n      <th>certification_1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>Theater</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n      <td>Vocal music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>Computers</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>Physics</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>NaN</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n      <td>English</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 7,
      "metadata": {},
-     "execution_count": 7
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df = (\n",
+    "    df.rename_column(\"%_allocated\", \"percent_allocated\")\n",
+    "    .rename_column(\"full_time_\", \"full_time\")\n",
+    ")\n",
+    "df"
    ]
   },
   {
@@ -611,17 +609,13 @@
    ]
   },
   {
-   "source": [
-    "df = df.coalesce([\"certification\", \"certification_1\"], \"certification\")\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 8,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE    39690.0   \n",
@@ -650,12 +644,16 @@
        "9                 NaN        No     Physical ed  \n",
        "10                NaN        No  Political sci.  \n",
        "11               0.80        No     Vocal music  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>39690.0</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>39690.0</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>37118.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>27515.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>41431.0</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>11037.0</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>32994.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>27919.0</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>42221.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>34700.0</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>40071.0</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 8,
      "metadata": {},
-     "execution_count": 8
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df = df.coalesce([\"certification\", \"certification_1\"], \"certification\")\n",
+    "df"
    ]
   },
   {
@@ -666,15 +664,11 @@
    ]
   },
   {
-   "source": [
-    "df.dtypes"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 9,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
       "text/plain": [
        "first_name            object\n",
@@ -688,22 +682,21 @@
        "dtype: object"
       ]
      },
+     "execution_count": 9,
      "metadata": {},
-     "execution_count": 9
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df.dtypes"
    ]
   },
   {
-   "source": [
-    "df.encode_categorical([\"subject\", \"employee_status\", \"full_time\"])\n",
-    "df.dtypes"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 10,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
       "text/plain": [
        "first_name             object\n",
@@ -717,9 +710,14 @@
        "dtype: object"
       ]
      },
+     "execution_count": 10,
      "metadata": {},
-     "execution_count": 10
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df.encode_categorical([\"subject\", \"employee_status\", \"full_time\"])\n",
+    "df.dtypes"
    ]
   },
   {
@@ -730,17 +728,13 @@
    ]
   },
   {
-   "source": [
-    "df.convert_excel_date(\"hire_date\")\n",
-    "df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 11,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>2008-08-30</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>2008-08-30</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>2001-08-15</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>1975-05-01</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>2013-06-06</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>1990-05-01</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>1976-06-08</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>2015-08-05</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>1995-01-01</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>2009-09-15</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE 2008-08-30   \n",
@@ -769,12 +763,16 @@
        "9                 NaN        No     Physical ed  \n",
        "10                NaN        No  Political sci.  \n",
        "11               0.80        No     Vocal music  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>2008-08-30</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>2008-08-30</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>2001-08-15</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>1975-05-01</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>2013-06-06</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>1990-05-01</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>1976-06-08</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>2015-08-05</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>1995-01-01</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>2009-09-15</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 11,
      "metadata": {},
-     "execution_count": 11
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "df.convert_excel_date(\"hire_date\")\n",
+    "df"
    ]
   },
   {
@@ -792,26 +790,13 @@
    ]
   },
   {
-   "source": [
-    "data_df = (\n",
-    "    cleaned_df\n",
-    "    .copy()\n",
-    "    .add_columns(\n",
-    "        lucky_number=np.random.randint(0, 10, len(cleaned_df)),\n",
-    "        age=np.random.randint(10, 100, len(cleaned_df)),\n",
-    "        employee_of_month_count=np.random.randint(0, 5, len(cleaned_df))\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "data_df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 12,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n      <th>lucky_number</th>\n      <th>age</th>\n      <th>employee_of_month_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>2008-08-30</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>6</td>\n      <td>74</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>2008-08-30</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>6</td>\n      <td>90</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>2001-08-15</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n      <td>2</td>\n      <td>47</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>1975-05-01</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>9</td>\n      <td>76</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>2013-06-06</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>4</td>\n      <td>69</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>7</td>\n      <td>61</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>4</td>\n      <td>47</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>1990-05-01</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n      <td>9</td>\n      <td>34</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>1976-06-08</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n      <td>6</td>\n      <td>23</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>2015-08-05</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n      <td>1</td>\n      <td>21</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>1995-01-01</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n      <td>1</td>\n      <td>83</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>2009-09-15</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n      <td>5</td>\n      <td>81</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "      first_name last_name employee_status     subject  hire_date  \\\n",
        "0          Jason    Bourne         Teacher          PE 2008-08-30   \n",
@@ -854,12 +839,25 @@
        "9                         3  \n",
        "10                        1  \n",
        "11                        2  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>first_name</th>\n      <th>last_name</th>\n      <th>employee_status</th>\n      <th>subject</th>\n      <th>hire_date</th>\n      <th>percent_allocated</th>\n      <th>full_time</th>\n      <th>certification</th>\n      <th>lucky_number</th>\n      <th>age</th>\n      <th>employee_of_month_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>PE</td>\n      <td>2008-08-30</td>\n      <td>0.75</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>6</td>\n      <td>74</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Jason</td>\n      <td>Bourne</td>\n      <td>Teacher</td>\n      <td>Drafting</td>\n      <td>2008-08-30</td>\n      <td>0.25</td>\n      <td>Yes</td>\n      <td>Physical ed</td>\n      <td>6</td>\n      <td>90</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Alicia</td>\n      <td>Keys</td>\n      <td>Teacher</td>\n      <td>Music</td>\n      <td>2001-08-15</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>Instr. music</td>\n      <td>2</td>\n      <td>47</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Ada</td>\n      <td>Lovelace</td>\n      <td>Teacher</td>\n      <td>NaN</td>\n      <td>1975-05-01</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>9</td>\n      <td>76</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Desus</td>\n      <td>Nice</td>\n      <td>Administration</td>\n      <td>Dean</td>\n      <td>2013-06-06</td>\n      <td>1.00</td>\n      <td>Yes</td>\n      <td>PENDING</td>\n      <td>4</td>\n      <td>69</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Physics</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>7</td>\n      <td>61</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Chien-Shiung</td>\n      <td>Wu</td>\n      <td>Teacher</td>\n      <td>Chemistry</td>\n      <td>1930-03-20</td>\n      <td>0.50</td>\n      <td>Yes</td>\n      <td>Science 6-12</td>\n      <td>4</td>\n      <td>47</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>James</td>\n      <td>Joyce</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>1990-05-01</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>English 6-12</td>\n      <td>9</td>\n      <td>34</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hedy</td>\n      <td>Lamarr</td>\n      <td>Teacher</td>\n      <td>Science</td>\n      <td>1976-06-08</td>\n      <td>0.50</td>\n      <td>No</td>\n      <td>PENDING</td>\n      <td>6</td>\n      <td>23</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Carlos</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>Basketball</td>\n      <td>2015-08-05</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Physical ed</td>\n      <td>1</td>\n      <td>21</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Young</td>\n      <td>Boozer</td>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>1995-01-01</td>\n      <td>NaN</td>\n      <td>No</td>\n      <td>Political sci.</td>\n      <td>1</td>\n      <td>83</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Micheal</td>\n      <td>Larsen</td>\n      <td>Teacher</td>\n      <td>English</td>\n      <td>2009-09-15</td>\n      <td>0.80</td>\n      <td>No</td>\n      <td>Vocal music</td>\n      <td>5</td>\n      <td>81</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 12,
      "metadata": {},
-     "execution_count": 12
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "data_df = (\n",
+    "    cleaned_df\n",
+    "    .copy()\n",
+    "    .add_columns(\n",
+    "        lucky_number=np.random.randint(0, 10, len(cleaned_df)),\n",
+    "        age=np.random.randint(10, 100, len(cleaned_df)),\n",
+    "        employee_of_month_count=np.random.randint(0, 5, len(cleaned_df))\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "data_df"
    ]
   },
   {
@@ -870,23 +868,13 @@
    ]
   },
   {
-   "source": [
-    "stats_df = (\n",
-    "    data_df.groupby('employee_status')\n",
-    "    .agg(['mean', 'median'])\n",
-    "    .collapse_levels()\n",
-    "    .reset_index()\n",
-    ")\n",
-    "\n",
-    "stats_df"
-   ],
    "cell_type": "code",
-   "metadata": {},
    "execution_count": 13,
+   "metadata": {},
    "outputs": [
     {
-     "output_type": "execute_result",
      "data": {
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>employee_status</th>\n      <th>percent_allocated_mean</th>\n      <th>percent_allocated_median</th>\n      <th>lucky_number_mean</th>\n      <th>lucky_number_median</th>\n      <th>age_mean</th>\n      <th>age_median</th>\n      <th>employee_of_month_count_mean</th>\n      <th>employee_of_month_count_median</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Administration</td>\n      <td>1.000000</td>\n      <td>1.0</td>\n      <td>4</td>\n      <td>4</td>\n      <td>69.000000</td>\n      <td>69</td>\n      <td>2.000000</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>1</td>\n      <td>1</td>\n      <td>52.000000</td>\n      <td>52</td>\n      <td>2.000000</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Teacher</td>\n      <td>0.644444</td>\n      <td>0.5</td>\n      <td>6</td>\n      <td>6</td>\n      <td>59.222222</td>\n      <td>61</td>\n      <td>1.333333</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
       "text/plain": [
        "  employee_status  percent_allocated_mean  percent_allocated_median  \\\n",
        "0  Administration                1.000000                       1.0   \n",
@@ -902,12 +890,22 @@
        "0                      2.000000                               2  \n",
        "1                      2.000000                               2  \n",
        "2                      1.333333                               0  "
-      ],
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>employee_status</th>\n      <th>percent_allocated_mean</th>\n      <th>percent_allocated_median</th>\n      <th>lucky_number_mean</th>\n      <th>lucky_number_median</th>\n      <th>age_mean</th>\n      <th>age_median</th>\n      <th>employee_of_month_count_mean</th>\n      <th>employee_of_month_count_median</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Administration</td>\n      <td>1.000000</td>\n      <td>1.0</td>\n      <td>4</td>\n      <td>4</td>\n      <td>69.000000</td>\n      <td>69</td>\n      <td>2.000000</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Coach</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>1</td>\n      <td>1</td>\n      <td>52.000000</td>\n      <td>52</td>\n      <td>2.000000</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Teacher</td>\n      <td>0.644444</td>\n      <td>0.5</td>\n      <td>6</td>\n      <td>6</td>\n      <td>59.222222</td>\n      <td>61</td>\n      <td>1.333333</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+      ]
      },
+     "execution_count": 13,
      "metadata": {},
-     "execution_count": 13
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "stats_df = (\n",
+    "    data_df.groupby('employee_status')\n",
+    "    .agg(['mean', 'median'])\n",
+    "    .collapse_levels()\n",
+    "    .reset_index()\n",
+    ")\n",
+    "\n",
+    "stats_df"
    ]
   }
  ],
diff --git a/examples/notebooks/select_columns.ipynb b/examples/notebooks/select_columns.ipynb
index 88a9e1a37..09d410833 100644
--- a/examples/notebooks/select_columns.ipynb
+++ b/examples/notebooks/select_columns.ipynb
@@ -13,13 +13,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import janitor\n",
-    "import numpy as np\n",
     "import datetime\n",
     "import re\n",
-    "from janitor import patterns\n",
-    "from pandas.api.types import is_datetime64_dtype"
+    "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from pandas.api.types import is_datetime64_dtype\n",
+    "\n",
+    "from janitor import patterns"
    ]
   },
   {
diff --git a/examples/notebooks/sort_columns.ipynb b/examples/notebooks/sort_columns.ipynb
index efbb2bc30..c143e2f24 100644
--- a/examples/notebooks/sort_columns.ipynb
+++ b/examples/notebooks/sort_columns.ipynb
@@ -13,9 +13,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd \n",
-    "import janitor\n",
-    "from numpy import nan"
+    "import pandas as pd\n",
+    "from numpy import nan\n"
    ]
   },
   {
diff --git a/examples/notebooks/sort_naturally.ipynb b/examples/notebooks/sort_naturally.ipynb
index 672683650..806392c6c 100644
--- a/examples/notebooks/sort_naturally.ipynb
+++ b/examples/notebooks/sort_naturally.ipynb
@@ -13,9 +13,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas_flavor as pf\n",
-    "import pandas as pd\n",
-    "import janitor"
+    "import pandas as pd"
    ]
   },
   {
diff --git a/examples/notebooks/teacher_pupil.ipynb b/examples/notebooks/teacher_pupil.ipynb
index f2a38206e..3c62df006 100644
--- a/examples/notebooks/teacher_pupil.ipynb
+++ b/examples/notebooks/teacher_pupil.ipynb
@@ -151,7 +151,6 @@
     }
    ],
    "source": [
-    "import janitor\n",
     "import pandas as pd\n",
     "import pandas_flavor as pf\n",
     "\n",
diff --git a/examples/notebooks/transform_column.ipynb b/examples/notebooks/transform_column.ipynb
index fe53a2550..5a2b112f0 100644
--- a/examples/notebooks/transform_column.ipynb
+++ b/examples/notebooks/transform_column.ipynb
@@ -36,9 +36,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import janitor\n",
-    "import pandas as pd\n",
-    "import numpy as np"
+    "import numpy as np\n",
+    "import pandas as pd"
    ]
   },
   {
@@ -148,6 +147,7 @@
    "source": [
     "from random import choice\n",
     "\n",
+    "\n",
     "def make_strings(length: int):\n",
     "    return \"\".join(choice(\"ABCDEFGHIJKLMNOPQRSTUVWXYZ\") for _ in range(length))\n",
     "\n",