diff --git a/ML52/.ipynb_checkpoints/ML52-checkpoint.ipynb b/ML52/.ipynb_checkpoints/ML52-checkpoint.ipynb
new file mode 100644
index 0000000..28f89f0
--- /dev/null
+++ b/ML52/.ipynb_checkpoints/ML52-checkpoint.ipynb
@@ -0,0 +1,530 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "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>Gender</th>\n",
+       "      <th>Start Date</th>\n",
+       "      <th>Last Login Time</th>\n",
+       "      <th>Salary</th>\n",
+       "      <th>Bonus %</th>\n",
+       "      <th>Senior Management</th>\n",
+       "      <th>Team</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>Douglas</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>8/6/1993</td>\n",
+       "      <td>12:42 PM</td>\n",
+       "      <td>97308</td>\n",
+       "      <td>6.945</td>\n",
+       "      <td>True</td>\n",
+       "      <td>Marketing</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>Thomas</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>3/31/1996</td>\n",
+       "      <td>6:53 AM</td>\n",
+       "      <td>61933</td>\n",
+       "      <td>4.170</td>\n",
+       "      <td>True</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>Maria</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>4/23/1993</td>\n",
+       "      <td>11:17 AM</td>\n",
+       "      <td>130590</td>\n",
+       "      <td>11.858</td>\n",
+       "      <td>False</td>\n",
+       "      <td>Finance</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3</td>\n",
+       "      <td>Jerry</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>3/4/2005</td>\n",
+       "      <td>1:00 PM</td>\n",
+       "      <td>138705</td>\n",
+       "      <td>9.340</td>\n",
+       "      <td>True</td>\n",
+       "      <td>Finance</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4</td>\n",
+       "      <td>Larry</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>1/24/1998</td>\n",
+       "      <td>4:47 PM</td>\n",
+       "      <td>101004</td>\n",
+       "      <td>1.389</td>\n",
+       "      <td>True</td>\n",
+       "      <td>Client Services</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  First Name  Gender Start Date Last Login Time  Salary  Bonus %  \\\n",
+       "0    Douglas    Male   8/6/1993        12:42 PM   97308    6.945   \n",
+       "1     Thomas    Male  3/31/1996         6:53 AM   61933    4.170   \n",
+       "2      Maria  Female  4/23/1993        11:17 AM  130590   11.858   \n",
+       "3      Jerry    Male   3/4/2005         1:00 PM  138705    9.340   \n",
+       "4      Larry    Male  1/24/1998         4:47 PM  101004    1.389   \n",
+       "\n",
+       "  Senior Management             Team  \n",
+       "0              True        Marketing  \n",
+       "1              True              NaN  \n",
+       "2             False          Finance  \n",
+       "3              True          Finance  \n",
+       "4              True  Client Services  "
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df = pd.read_csv(\"employees.csv\")\n",
+    "\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 1000 entries, 0 to 999\n",
+      "Data columns (total 8 columns):\n",
+      "First Name           933 non-null object\n",
+      "Gender               855 non-null object\n",
+      "Start Date           1000 non-null object\n",
+      "Last Login Time      1000 non-null object\n",
+      "Salary               1000 non-null int64\n",
+      "Bonus %              1000 non-null float64\n",
+      "Senior Management    933 non-null object\n",
+      "Team                 957 non-null object\n",
+      "dtypes: float64(1), int64(1), object(6)\n",
+      "memory usage: 62.6+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "First Name            67\n",
+       "Gender               145\n",
+       "Start Date             0\n",
+       "Last Login Time        0\n",
+       "Salary                 0\n",
+       "Bonus %                0\n",
+       "Senior Management     67\n",
+       "Team                  43\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df[df['First Name'].notna()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Female    400\n",
+       "Male      395\n",
+       "Name: Gender, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['Gender'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Gender']=df['Gender'].fillna(method='ffill')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Team']=df['Team'].fillna(method='ffill')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0     8/6/1993\n",
+       "1    3/31/1996\n",
+       "2    4/23/1993\n",
+       "3     3/4/2005\n",
+       "4    1/24/1998\n",
+       "Name: Start Date, dtype: object"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"Start Date\"].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.to_datetime(df[\"Start Date\"])\n",
+    "\n",
+    "df[\"Start Date\"] = pd.to_datetime(df[\"Start Date\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    12:42 PM\n",
+       "1     6:53 AM\n",
+       "2    11:17 AM\n",
+       "3     1:00 PM\n",
+       "4     4:47 PM\n",
+       "Name: Last Login Time, dtype: object"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"Last Login Time\"].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.to_datetime(df[\"Last Login Time\"])\n",
+    "df[\"Last Login Time\"]= pd.to_datetime(df[\"Last Login Time\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0     True\n",
+       "1     True\n",
+       "2    False\n",
+       "3     True\n",
+       "4     True\n",
+       "Name: Senior Management, dtype: object"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"Senior Management\"].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[\"Senior Management\"].astype(\"bool\")\n",
+    "\n",
+    "df[\"Senior Management\"] = df[\"Senior Management\"].astype(\"bool\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[\"Gender\"].astype(\"category\")\n",
+    "\n",
+    "df[\"Gender\"] = df[\"Gender\"].astype(\"category\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "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>Gender</th>\n",
+       "      <th>Start Date</th>\n",
+       "      <th>Last Login Time</th>\n",
+       "      <th>Salary</th>\n",
+       "      <th>Bonus %</th>\n",
+       "      <th>Senior Management</th>\n",
+       "      <th>Team</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Douglas</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>1993-08-06</td>\n",
+       "      <td>2018-12-23 12:42:00</td>\n",
+       "      <td>97308</td>\n",
+       "      <td>6.945</td>\n",
+       "      <td>True</td>\n",
+       "      <td>Marketing</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Thomas</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>1996-03-31</td>\n",
+       "      <td>2018-12-23 06:53:00</td>\n",
+       "      <td>61933</td>\n",
+       "      <td>4.170</td>\n",
+       "      <td>True</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Maria</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>1993-04-23</td>\n",
+       "      <td>2018-12-23 11:17:00</td>\n",
+       "      <td>130590</td>\n",
+       "      <td>11.858</td>\n",
+       "      <td>False</td>\n",
+       "      <td>Finance</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Jerry</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>2005-03-04</td>\n",
+       "      <td>2018-12-23 13:00:00</td>\n",
+       "      <td>138705</td>\n",
+       "      <td>9.340</td>\n",
+       "      <td>True</td>\n",
+       "      <td>Finance</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Larry</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>1998-01-24</td>\n",
+       "      <td>2018-12-23 16:47:00</td>\n",
+       "      <td>101004</td>\n",
+       "      <td>1.389</td>\n",
+       "      <td>True</td>\n",
+       "      <td>Client Services</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  First Name  Gender Start Date     Last Login Time  Salary  Bonus %  \\\n",
+       "0    Douglas    Male 1993-08-06 2018-12-23 12:42:00   97308    6.945   \n",
+       "1     Thomas    Male 1996-03-31 2018-12-23 06:53:00   61933    4.170   \n",
+       "2      Maria  Female 1993-04-23 2018-12-23 11:17:00  130590   11.858   \n",
+       "3      Jerry    Male 2005-03-04 2018-12-23 13:00:00  138705    9.340   \n",
+       "4      Larry    Male 1998-01-24 2018-12-23 16:47:00  101004    1.389   \n",
+       "\n",
+       "   Senior Management             Team  \n",
+       "0               True        Marketing  \n",
+       "1               True              NaN  \n",
+       "2              False          Finance  \n",
+       "3               True          Finance  \n",
+       "4               True  Client Services  "
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df = pd.read_csv(\"employees.csv\", parse_dates=[\"Start Date\",\"Last Login Time\"])\n",
+    "df[\"Senior Management\"] = df[\"Senior Management\"].astype(\"bool\")\n",
+    "df[\"Gender\"] = df[\"Gender\"].astype(\"category\")\n",
+    "\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 1000 entries, 0 to 999\n",
+      "Data columns (total 8 columns):\n",
+      "First Name           933 non-null object\n",
+      "Gender               855 non-null category\n",
+      "Start Date           1000 non-null datetime64[ns]\n",
+      "Last Login Time      1000 non-null datetime64[ns]\n",
+      "Salary               1000 non-null int64\n",
+      "Bonus %              1000 non-null float64\n",
+      "Senior Management    1000 non-null bool\n",
+      "Team                 957 non-null object\n",
+      "dtypes: bool(1), category(1), datetime64[ns](2), float64(1), int64(1), object(2)\n",
+      "memory usage: 49.0+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/ML52/ML52.ipynb b/ML52/ML52.ipynb
index 6e9cecb..28f89f0 100644
--- a/ML52/ML52.ipynb
+++ b/ML52/ML52.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -38,7 +38,7 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>0</th>\n",
+       "      <td>0</td>\n",
        "      <td>Douglas</td>\n",
        "      <td>Male</td>\n",
        "      <td>8/6/1993</td>\n",
@@ -49,7 +49,7 @@
        "      <td>Marketing</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
+       "      <td>1</td>\n",
        "      <td>Thomas</td>\n",
        "      <td>Male</td>\n",
        "      <td>3/31/1996</td>\n",
@@ -60,7 +60,7 @@
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2</th>\n",
+       "      <td>2</td>\n",
        "      <td>Maria</td>\n",
        "      <td>Female</td>\n",
        "      <td>4/23/1993</td>\n",
@@ -71,7 +71,7 @@
        "      <td>Finance</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>3</th>\n",
+       "      <td>3</td>\n",
        "      <td>Jerry</td>\n",
        "      <td>Male</td>\n",
        "      <td>3/4/2005</td>\n",
@@ -82,7 +82,7 @@
        "      <td>Finance</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4</th>\n",
+       "      <td>4</td>\n",
        "      <td>Larry</td>\n",
        "      <td>Male</td>\n",
        "      <td>1/24/1998</td>\n",
@@ -112,7 +112,7 @@
        "4              True  Client Services  "
       ]
      },
-     "execution_count": 4,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -138,15 +138,15 @@
       "RangeIndex: 1000 entries, 0 to 999\n",
       "Data columns (total 8 columns):\n",
       "First Name           933 non-null object\n",
-      "Gender               855 non-null category\n",
-      "Start Date           1000 non-null datetime64[ns]\n",
-      "Last Login Time      1000 non-null datetime64[ns]\n",
+      "Gender               855 non-null object\n",
+      "Start Date           1000 non-null object\n",
+      "Last Login Time      1000 non-null object\n",
       "Salary               1000 non-null int64\n",
       "Bonus %              1000 non-null float64\n",
-      "Senior Management    1000 non-null bool\n",
+      "Senior Management    933 non-null object\n",
       "Team                 957 non-null object\n",
-      "dtypes: bool(1), category(1), datetime64[ns](2), float64(1), int64(1), object(2)\n",
-      "memory usage: 49.0+ KB\n"
+      "dtypes: float64(1), int64(1), object(6)\n",
+      "memory usage: 62.6+ KB\n"
      ]
     }
    ],
@@ -156,30 +156,80 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "0.7877813504823151"
+       "First Name            67\n",
+       "Gender               145\n",
+       "Start Date             0\n",
+       "Last Login Time        0\n",
+       "Salary                 0\n",
+       "Bonus %                0\n",
+       "Senior Management     67\n",
+       "Team                  43\n",
+       "dtype: int64"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "49.0/62.2"
+    "df.isnull().sum()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df = df[df['First Name'].notna()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Female    400\n",
+       "Male      395\n",
+       "Name: Gender, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['Gender'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Gender']=df['Gender'].fillna(method='ffill')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Team']=df['Team'].fillna(method='ffill')"
+   ]
   },
   {
    "cell_type": "code",
@@ -472,7 +522,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.1"
+   "version": "3.7.4"
   }
  },
  "nbformat": 4,