From cfa2ac68a72457f67fb4d82ac8773e16f5edd8d1 Mon Sep 17 00:00:00 2001
From: Shrenik-Bhalgat <59737962+Shrenik-Bhalgat@users.noreply.github.com>
Date: Mon, 24 Aug 2020 14:49:59 +0530
Subject: [PATCH 1/5] Add files via upload

---
 ShrenikBhalgat-assignment1.ipynb | 426 +++++++++++++++++++++++++++++++
 1 file changed, 426 insertions(+)
 create mode 100644 ShrenikBhalgat-assignment1.ipynb

diff --git a/ShrenikBhalgat-assignment1.ipynb b/ShrenikBhalgat-assignment1.ipynb
new file mode 100644
index 0000000..ae2a14f
--- /dev/null
+++ b/ShrenikBhalgat-assignment1.ipynb
@@ -0,0 +1,426 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list1=[1,2,3,4,5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 2, 3, 4, 5])"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array1=np.array(list1)\n",
+    "array1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list2=[[1,2,3],[4,5,6],[7,8,9]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1, 2, 3],\n",
+       "       [4, 5, 6],\n",
+       "       [7, 8, 9]])"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array2=np.array(list2)\n",
+    "array2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 1,  3,  5,  7,  9, 11, 13, 15, 17])"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array3=np.arange(1,18,2)\n",
+    "array3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 1,  3,  5],\n",
+       "       [ 7,  9, 11],\n",
+       "       [13, 15, 17]])"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array3.reshape(3,3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 6, 7, 2, 9, 7, 7, 2, 1, 4])"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array4=np.random.randint(1,10,10)\n",
+    "array4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 2, 3, 4, 5])"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array5=np.arange(1,6,1)\n",
+    "array5"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1],\n",
+       "       [2],\n",
+       "       [3],\n",
+       "       [4],\n",
+       "       [5]])"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array5.reshape(5,1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5,)"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array5.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array6=np.arange(10)\n",
+    "array6"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array6[3]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array6[4]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array6[9]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0\n",
+      "2\n",
+      "4\n",
+      "6\n",
+      "8\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in array6:\n",
+    "    if i%2==0:\n",
+    "        print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(7,10):\n",
+    "    array6[i]=100"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([  0,   1,   2,   3,   4,   5,   6, 100, 100, 100])"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array6"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "array7=np.arange(25)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "array7=array7.reshape(5,5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5, 5)"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array7.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 6,  7,  8],\n",
+       "       [11, 12, 13],\n",
+       "       [16, 17, 18]])"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array7[1:4,1:4]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.8.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

From 75a0a755e66fe25aa40a7b773b3c26be7f494cde Mon Sep 17 00:00:00 2001
From: Shrenik-Bhalgat <59737962+Shrenik-Bhalgat@users.noreply.github.com>
Date: Sun, 6 Sep 2020 13:05:53 +0530
Subject: [PATCH 2/5] Shreniik Bhalgat Asssignment 2

---
 Assignment2 Shrenik Bhalgat.ipynb | 1270 +++++++++++++++++++++++++++++
 1 file changed, 1270 insertions(+)
 create mode 100644 Assignment2 Shrenik Bhalgat.ipynb

diff --git a/Assignment2 Shrenik Bhalgat.ipynb b/Assignment2 Shrenik Bhalgat.ipynb
new file mode 100644
index 0000000..20d821b
--- /dev/null
+++ b/Assignment2 Shrenik Bhalgat.ipynb	
@@ -0,0 +1,1270 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "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>Id</th>\n",
+       "      <th>EmployeeName</th>\n",
+       "      <th>JobTitle</th>\n",
+       "      <th>BasePay</th>\n",
+       "      <th>OvertimePay</th>\n",
+       "      <th>OtherPay</th>\n",
+       "      <th>Benefits</th>\n",
+       "      <th>TotalPay</th>\n",
+       "      <th>TotalPayBenefits</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Notes</th>\n",
+       "      <th>Agency</th>\n",
+       "      <th>Status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>NATHANIEL FORD</td>\n",
+       "      <td>GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY</td>\n",
+       "      <td>167411.18</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>400184.25</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>567595.43</td>\n",
+       "      <td>567595.43</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>GARY JIMENEZ</td>\n",
+       "      <td>CAPTAIN III (POLICE DEPARTMENT)</td>\n",
+       "      <td>155966.02</td>\n",
+       "      <td>245131.88</td>\n",
+       "      <td>137811.38</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>538909.28</td>\n",
+       "      <td>538909.28</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>ALBERT PARDINI</td>\n",
+       "      <td>CAPTAIN III (POLICE DEPARTMENT)</td>\n",
+       "      <td>212739.13</td>\n",
+       "      <td>106088.18</td>\n",
+       "      <td>16452.60</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>335279.91</td>\n",
+       "      <td>335279.91</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>CHRISTOPHER CHONG</td>\n",
+       "      <td>WIRE ROPE CABLE MAINTENANCE MECHANIC</td>\n",
+       "      <td>77916.00</td>\n",
+       "      <td>56120.71</td>\n",
+       "      <td>198306.90</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>332343.61</td>\n",
+       "      <td>332343.61</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>PATRICK GARDNER</td>\n",
+       "      <td>DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)</td>\n",
+       "      <td>134401.60</td>\n",
+       "      <td>9737.00</td>\n",
+       "      <td>182234.59</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>326373.19</td>\n",
+       "      <td>326373.19</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148649</th>\n",
+       "      <td>148650</td>\n",
+       "      <td>Roy I Tillery</td>\n",
+       "      <td>Custodian</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148650</th>\n",
+       "      <td>148651</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148651</th>\n",
+       "      <td>148652</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148652</th>\n",
+       "      <td>148653</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148653</th>\n",
+       "      <td>148654</td>\n",
+       "      <td>Joe Lopez</td>\n",
+       "      <td>Counselor, Log Cabin Ranch</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>-618.13</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>-618.13</td>\n",
+       "      <td>-618.13</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>San Francisco</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>148654 rows × 13 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            Id       EmployeeName  \\\n",
+       "0            1     NATHANIEL FORD   \n",
+       "1            2       GARY JIMENEZ   \n",
+       "2            3     ALBERT PARDINI   \n",
+       "3            4  CHRISTOPHER CHONG   \n",
+       "4            5    PATRICK GARDNER   \n",
+       "...        ...                ...   \n",
+       "148649  148650      Roy I Tillery   \n",
+       "148650  148651       Not provided   \n",
+       "148651  148652       Not provided   \n",
+       "148652  148653       Not provided   \n",
+       "148653  148654          Joe Lopez   \n",
+       "\n",
+       "                                              JobTitle    BasePay  \\\n",
+       "0       GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY  167411.18   \n",
+       "1                      CAPTAIN III (POLICE DEPARTMENT)  155966.02   \n",
+       "2                      CAPTAIN III (POLICE DEPARTMENT)  212739.13   \n",
+       "3                 WIRE ROPE CABLE MAINTENANCE MECHANIC   77916.00   \n",
+       "4         DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)  134401.60   \n",
+       "...                                                ...        ...   \n",
+       "148649                                       Custodian       0.00   \n",
+       "148650                                    Not provided        NaN   \n",
+       "148651                                    Not provided        NaN   \n",
+       "148652                                    Not provided        NaN   \n",
+       "148653                      Counselor, Log Cabin Ranch       0.00   \n",
+       "\n",
+       "        OvertimePay   OtherPay  Benefits   TotalPay  TotalPayBenefits  Year  \\\n",
+       "0              0.00  400184.25       NaN  567595.43         567595.43  2011   \n",
+       "1         245131.88  137811.38       NaN  538909.28         538909.28  2011   \n",
+       "2         106088.18   16452.60       NaN  335279.91         335279.91  2011   \n",
+       "3          56120.71  198306.90       NaN  332343.61         332343.61  2011   \n",
+       "4           9737.00  182234.59       NaN  326373.19         326373.19  2011   \n",
+       "...             ...        ...       ...        ...               ...   ...   \n",
+       "148649         0.00       0.00       0.0       0.00              0.00  2014   \n",
+       "148650          NaN        NaN       NaN       0.00              0.00  2014   \n",
+       "148651          NaN        NaN       NaN       0.00              0.00  2014   \n",
+       "148652          NaN        NaN       NaN       0.00              0.00  2014   \n",
+       "148653         0.00    -618.13       0.0    -618.13           -618.13  2014   \n",
+       "\n",
+       "        Notes         Agency  Status  \n",
+       "0         NaN  San Francisco     NaN  \n",
+       "1         NaN  San Francisco     NaN  \n",
+       "2         NaN  San Francisco     NaN  \n",
+       "3         NaN  San Francisco     NaN  \n",
+       "4         NaN  San Francisco     NaN  \n",
+       "...       ...            ...     ...  \n",
+       "148649    NaN  San Francisco     NaN  \n",
+       "148650    NaN  San Francisco     NaN  \n",
+       "148651    NaN  San Francisco     NaN  \n",
+       "148652    NaN  San Francisco     NaN  \n",
+       "148653    NaN  San Francisco     NaN  \n",
+       "\n",
+       "[148654 rows x 13 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df=pd.read_csv('Salaries.csv')\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Id', 'EmployeeName', 'JobTitle', 'BasePay', 'OvertimePay', 'OtherPay',\n",
+       "       'Benefits', 'TotalPay', 'TotalPayBenefits', 'Year', 'Notes', 'Agency',\n",
+       "       'Status'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Display colum names\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(148654, 13)"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Display the number of rows and columns\n",
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 148654 entries, 0 to 148653\n",
+      "Data columns (total 13 columns):\n",
+      " #   Column            Non-Null Count   Dtype  \n",
+      "---  ------            --------------   -----  \n",
+      " 0   Id                148654 non-null  int64  \n",
+      " 1   EmployeeName      148654 non-null  object \n",
+      " 2   JobTitle          148654 non-null  object \n",
+      " 3   BasePay           148045 non-null  float64\n",
+      " 4   OvertimePay       148650 non-null  float64\n",
+      " 5   OtherPay          148650 non-null  float64\n",
+      " 6   Benefits          112491 non-null  float64\n",
+      " 7   TotalPay          148654 non-null  float64\n",
+      " 8   TotalPayBenefits  148654 non-null  float64\n",
+      " 9   Year              148654 non-null  int64  \n",
+      " 10  Notes             0 non-null       float64\n",
+      " 11  Agency            148654 non-null  object \n",
+      " 12  Status            0 non-null       float64\n",
+      "dtypes: float64(8), int64(2), object(3)\n",
+      "memory usage: 14.7+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Display the dataframes info\n",
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "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>Id</th>\n",
+       "      <th>BasePay</th>\n",
+       "      <th>OvertimePay</th>\n",
+       "      <th>OtherPay</th>\n",
+       "      <th>Benefits</th>\n",
+       "      <th>TotalPay</th>\n",
+       "      <th>TotalPayBenefits</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Notes</th>\n",
+       "      <th>Status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>148654.000000</td>\n",
+       "      <td>148045.000000</td>\n",
+       "      <td>148650.000000</td>\n",
+       "      <td>148650.000000</td>\n",
+       "      <td>112491.000000</td>\n",
+       "      <td>148654.000000</td>\n",
+       "      <td>148654.000000</td>\n",
+       "      <td>148654.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>74327.500000</td>\n",
+       "      <td>66325.448840</td>\n",
+       "      <td>5066.059886</td>\n",
+       "      <td>3648.767297</td>\n",
+       "      <td>25007.893151</td>\n",
+       "      <td>74768.321972</td>\n",
+       "      <td>93692.554811</td>\n",
+       "      <td>2012.522643</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>42912.857795</td>\n",
+       "      <td>42764.635495</td>\n",
+       "      <td>11454.380559</td>\n",
+       "      <td>8056.601866</td>\n",
+       "      <td>15402.215858</td>\n",
+       "      <td>50517.005274</td>\n",
+       "      <td>62793.533483</td>\n",
+       "      <td>1.117538</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-166.010000</td>\n",
+       "      <td>-0.010000</td>\n",
+       "      <td>-7058.590000</td>\n",
+       "      <td>-33.890000</td>\n",
+       "      <td>-618.130000</td>\n",
+       "      <td>-618.130000</td>\n",
+       "      <td>2011.000000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>37164.250000</td>\n",
+       "      <td>33588.200000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>11535.395000</td>\n",
+       "      <td>36168.995000</td>\n",
+       "      <td>44065.650000</td>\n",
+       "      <td>2012.000000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>74327.500000</td>\n",
+       "      <td>65007.450000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>811.270000</td>\n",
+       "      <td>28628.620000</td>\n",
+       "      <td>71426.610000</td>\n",
+       "      <td>92404.090000</td>\n",
+       "      <td>2013.000000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>111490.750000</td>\n",
+       "      <td>94691.050000</td>\n",
+       "      <td>4658.175000</td>\n",
+       "      <td>4236.065000</td>\n",
+       "      <td>35566.855000</td>\n",
+       "      <td>105839.135000</td>\n",
+       "      <td>132876.450000</td>\n",
+       "      <td>2014.000000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>148654.000000</td>\n",
+       "      <td>319275.010000</td>\n",
+       "      <td>245131.880000</td>\n",
+       "      <td>400184.250000</td>\n",
+       "      <td>96570.660000</td>\n",
+       "      <td>567595.430000</td>\n",
+       "      <td>567595.430000</td>\n",
+       "      <td>2014.000000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  Id        BasePay    OvertimePay       OtherPay  \\\n",
+       "count  148654.000000  148045.000000  148650.000000  148650.000000   \n",
+       "mean    74327.500000   66325.448840    5066.059886    3648.767297   \n",
+       "std     42912.857795   42764.635495   11454.380559    8056.601866   \n",
+       "min         1.000000    -166.010000      -0.010000   -7058.590000   \n",
+       "25%     37164.250000   33588.200000       0.000000       0.000000   \n",
+       "50%     74327.500000   65007.450000       0.000000     811.270000   \n",
+       "75%    111490.750000   94691.050000    4658.175000    4236.065000   \n",
+       "max    148654.000000  319275.010000  245131.880000  400184.250000   \n",
+       "\n",
+       "            Benefits       TotalPay  TotalPayBenefits           Year  Notes  \\\n",
+       "count  112491.000000  148654.000000     148654.000000  148654.000000    0.0   \n",
+       "mean    25007.893151   74768.321972      93692.554811    2012.522643    NaN   \n",
+       "std     15402.215858   50517.005274      62793.533483       1.117538    NaN   \n",
+       "min       -33.890000    -618.130000       -618.130000    2011.000000    NaN   \n",
+       "25%     11535.395000   36168.995000      44065.650000    2012.000000    NaN   \n",
+       "50%     28628.620000   71426.610000      92404.090000    2013.000000    NaN   \n",
+       "75%     35566.855000  105839.135000     132876.450000    2014.000000    NaN   \n",
+       "max     96570.660000  567595.430000     567595.430000    2014.000000    NaN   \n",
+       "\n",
+       "       Status  \n",
+       "count     0.0  \n",
+       "mean      NaN  \n",
+       "std       NaN  \n",
+       "min       NaN  \n",
+       "25%       NaN  \n",
+       "50%       NaN  \n",
+       "75%       NaN  \n",
+       "max       NaN  "
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Display stats of the dataframe\n",
+    "df.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Id                       0\n",
+       "EmployeeName             0\n",
+       "JobTitle                 0\n",
+       "BasePay                609\n",
+       "OvertimePay              4\n",
+       "OtherPay                 4\n",
+       "Benefits             36163\n",
+       "TotalPay                 0\n",
+       "TotalPayBenefits         0\n",
+       "Year                     0\n",
+       "Notes               148654\n",
+       "Agency                   0\n",
+       "Status              148654\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#display null values per column\n",
+    "df.isnull().sum(axis=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "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>Id</th>\n",
+       "      <th>EmployeeName</th>\n",
+       "      <th>JobTitle</th>\n",
+       "      <th>BasePay</th>\n",
+       "      <th>OvertimePay</th>\n",
+       "      <th>OtherPay</th>\n",
+       "      <th>Benefits</th>\n",
+       "      <th>TotalPay</th>\n",
+       "      <th>TotalPayBenefits</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Agency</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>NATHANIEL FORD</td>\n",
+       "      <td>GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY</td>\n",
+       "      <td>167411.18</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>400184.25</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>567595.43</td>\n",
+       "      <td>567595.43</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>GARY JIMENEZ</td>\n",
+       "      <td>CAPTAIN III (POLICE DEPARTMENT)</td>\n",
+       "      <td>155966.02</td>\n",
+       "      <td>245131.88</td>\n",
+       "      <td>137811.38</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>538909.28</td>\n",
+       "      <td>538909.28</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>ALBERT PARDINI</td>\n",
+       "      <td>CAPTAIN III (POLICE DEPARTMENT)</td>\n",
+       "      <td>212739.13</td>\n",
+       "      <td>106088.18</td>\n",
+       "      <td>16452.60</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>335279.91</td>\n",
+       "      <td>335279.91</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>CHRISTOPHER CHONG</td>\n",
+       "      <td>WIRE ROPE CABLE MAINTENANCE MECHANIC</td>\n",
+       "      <td>77916.00</td>\n",
+       "      <td>56120.71</td>\n",
+       "      <td>198306.90</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>332343.61</td>\n",
+       "      <td>332343.61</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>PATRICK GARDNER</td>\n",
+       "      <td>DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)</td>\n",
+       "      <td>134401.60</td>\n",
+       "      <td>9737.00</td>\n",
+       "      <td>182234.59</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>326373.19</td>\n",
+       "      <td>326373.19</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148649</th>\n",
+       "      <td>148650</td>\n",
+       "      <td>Roy I Tillery</td>\n",
+       "      <td>Custodian</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148650</th>\n",
+       "      <td>148651</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148651</th>\n",
+       "      <td>148652</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148652</th>\n",
+       "      <td>148653</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>Not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148653</th>\n",
+       "      <td>148654</td>\n",
+       "      <td>Joe Lopez</td>\n",
+       "      <td>Counselor, Log Cabin Ranch</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>-618.13</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>-618.13</td>\n",
+       "      <td>-618.13</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>San Francisco</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>148654 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            Id       EmployeeName  \\\n",
+       "0            1     NATHANIEL FORD   \n",
+       "1            2       GARY JIMENEZ   \n",
+       "2            3     ALBERT PARDINI   \n",
+       "3            4  CHRISTOPHER CHONG   \n",
+       "4            5    PATRICK GARDNER   \n",
+       "...        ...                ...   \n",
+       "148649  148650      Roy I Tillery   \n",
+       "148650  148651       Not provided   \n",
+       "148651  148652       Not provided   \n",
+       "148652  148653       Not provided   \n",
+       "148653  148654          Joe Lopez   \n",
+       "\n",
+       "                                              JobTitle    BasePay  \\\n",
+       "0       GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY  167411.18   \n",
+       "1                      CAPTAIN III (POLICE DEPARTMENT)  155966.02   \n",
+       "2                      CAPTAIN III (POLICE DEPARTMENT)  212739.13   \n",
+       "3                 WIRE ROPE CABLE MAINTENANCE MECHANIC   77916.00   \n",
+       "4         DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)  134401.60   \n",
+       "...                                                ...        ...   \n",
+       "148649                                       Custodian       0.00   \n",
+       "148650                                    Not provided        NaN   \n",
+       "148651                                    Not provided        NaN   \n",
+       "148652                                    Not provided        NaN   \n",
+       "148653                      Counselor, Log Cabin Ranch       0.00   \n",
+       "\n",
+       "        OvertimePay   OtherPay  Benefits   TotalPay  TotalPayBenefits  Year  \\\n",
+       "0              0.00  400184.25       NaN  567595.43         567595.43  2011   \n",
+       "1         245131.88  137811.38       NaN  538909.28         538909.28  2011   \n",
+       "2         106088.18   16452.60       NaN  335279.91         335279.91  2011   \n",
+       "3          56120.71  198306.90       NaN  332343.61         332343.61  2011   \n",
+       "4           9737.00  182234.59       NaN  326373.19         326373.19  2011   \n",
+       "...             ...        ...       ...        ...               ...   ...   \n",
+       "148649         0.00       0.00       0.0       0.00              0.00  2014   \n",
+       "148650          NaN        NaN       NaN       0.00              0.00  2014   \n",
+       "148651          NaN        NaN       NaN       0.00              0.00  2014   \n",
+       "148652          NaN        NaN       NaN       0.00              0.00  2014   \n",
+       "148653         0.00    -618.13       0.0    -618.13           -618.13  2014   \n",
+       "\n",
+       "               Agency  \n",
+       "0       San Francisco  \n",
+       "1       San Francisco  \n",
+       "2       San Francisco  \n",
+       "3       San Francisco  \n",
+       "4       San Francisco  \n",
+       "...               ...  \n",
+       "148649  San Francisco  \n",
+       "148650  San Francisco  \n",
+       "148651  San Francisco  \n",
+       "148652  San Francisco  \n",
+       "148653  San Francisco  \n",
+       "\n",
+       "[148654 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#remove columns with all values as nan\n",
+    "df.dropna(axis=1,how='all',inplace=True)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Id                  148654\n",
+       "EmployeeName        110811\n",
+       "JobTitle              2159\n",
+       "BasePay             109489\n",
+       "OvertimePay          65998\n",
+       "OtherPay             83225\n",
+       "Benefits             98465\n",
+       "TotalPay            138486\n",
+       "TotalPayBenefits    142098\n",
+       "Year                     4\n",
+       "Agency                   1\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#display number of unique values in each column\n",
+    "df.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Id                  148654\n",
+       "EmployeeName        110811\n",
+       "JobTitle              2159\n",
+       "BasePay             109489\n",
+       "OvertimePay          65998\n",
+       "OtherPay             83225\n",
+       "Benefits             98465\n",
+       "TotalPay            138486\n",
+       "TotalPayBenefits    142098\n",
+       "Year                     4\n",
+       "Agency                   1\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#display number of unique values in each column\n",
+    "df.apply(lambda x: x.nunique(), axis=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Id                  148654\n",
+       "EmployeeName        110811\n",
+       "JobTitle              2159\n",
+       "BasePay             109489\n",
+       "OvertimePay          65998\n",
+       "OtherPay             83225\n",
+       "Benefits             98465\n",
+       "TotalPay            138486\n",
+       "TotalPayBenefits    142098\n",
+       "Year                     4\n",
+       "Agency                   1\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#display number of unique values in each column\n",
+    "df.apply(pd.Series.nunique)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "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>Year</th>\n",
+       "      <th>TotalPay</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2011</td>\n",
+       "      <td>71744.103871</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2012</td>\n",
+       "      <td>74113.262265</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2013</td>\n",
+       "      <td>77611.443142</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2014</td>\n",
+       "      <td>75463.918140</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Year      TotalPay\n",
+       "0  2011  71744.103871\n",
+       "1  2012  74113.262265\n",
+       "2  2013  77611.443142\n",
+       "3  2014  75463.918140"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#mean of total pay based on year\n",
+    "df.groupby('Year', as_index=False)['TotalPay'].mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "77321"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#how many people have 0 overtime pay\n",
+    "(df['OvertimePay']==0).sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count  0     71333.000000\n",
+       "       1     77321.000000\n",
+       "mean   0     90527.759214\n",
+       "       1     60229.348901\n",
+       "std    0     46961.054390\n",
+       "       1     49307.912350\n",
+       "min    0         0.000000\n",
+       "       1      -618.130000\n",
+       "25%    0     59104.230000\n",
+       "       1     13290.450000\n",
+       "50%    0     82984.830000\n",
+       "       1     58158.590000\n",
+       "75%    0    121560.910000\n",
+       "       1     91115.090000\n",
+       "max    0    538909.280000\n",
+       "       1    567595.430000\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#stats of total pay of people having 0 overtime pay\n",
+    "df.groupby(df['OvertimePay']==0, as_index=False)['TotalPay'].describe()\n",
+    "# 0 represents people with non 0 overtime pay\n",
+    "# 1 represents people with 0 overtime pay"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "count     77321.000000\n",
+       "mean      60229.348901\n",
+       "std       49307.912350\n",
+       "min        -618.130000\n",
+       "25%       13290.450000\n",
+       "50%       58158.590000\n",
+       "75%       91115.090000\n",
+       "max      567595.430000\n",
+       "Name: TotalPay, dtype: float64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#stats of total pay of people having 0 overtime pay\n",
+    "df[df.OvertimePay==0].describe()['TotalPay']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    1\n",
+       "Name: Id, dtype: int64"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#find Id of that person with max TotalPay you got in previous question\n",
+    "df[df.TotalPay==df[df.OvertimePay==0].max()['TotalPay']]['Id']\n",
+    "#we can also use .Id instead of ['Id']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "12345    REBECCA CHIU\n",
+       "Name: EmployeeName, dtype: object"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#name of employee with total pay benefits = 87619.78\n",
+    "df[df.TotalPayBenefits==87619.78]['EmployeeName'] # or .EmployeeName "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "132"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#how many people have BasePay > 150000 and OvertimePay > 100000\n",
+    "df[(df['BasePay']> 150000) & (df['OvertimePay']> 100000)].size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "JobTitle            ZOO CURATOR\n",
+       "TotalPayBenefits         436224\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# which job title generally has highest average TotalPayBenefits\n",
+    "df.groupby('JobTitle', as_index=False)['TotalPayBenefits'].mean().max()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2512"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#How many employees are POLICE\n",
+    "df[df['JobTitle'].str.contains('POLICE')] ['JobTitle'].size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.8.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

From e446bf76dbdf877e11cb4da6080db3ed809c8acf Mon Sep 17 00:00:00 2001
From: Shrenik-Bhalgat <59737962+Shrenik-Bhalgat@users.noreply.github.com>
Date: Sun, 6 Sep 2020 13:22:07 +0530
Subject: [PATCH 3/5] Add files via upload


From c99e7368e00abad4bdd8d2b78f4fa0febccb0887 Mon Sep 17 00:00:00 2001
From: Shrenik-Bhalgat <59737962+Shrenik-Bhalgat@users.noreply.github.com>
Date: Sun, 6 Sep 2020 13:27:58 +0530
Subject: [PATCH 4/5] Add files via upload


From 4a5e0a463f401a59d3c64d1e8e3dffa5eb321e7e Mon Sep 17 00:00:00 2001
From: Shrenik-Bhalgat <59737962+Shrenik-Bhalgat@users.noreply.github.com>
Date: Sun, 6 Sep 2020 13:40:56 +0530
Subject: [PATCH 5/5] Add files via upload