From 8eda066bb63a2816d34fd770f5fb1589212a7947 Mon Sep 17 00:00:00 2001
From: Rachitha <47741826+Rachithaa@users.noreply.github.com>
Date: Mon, 24 Aug 2020 03:43:31 +0530
Subject: [PATCH 1/6] Assignment:1-Rachitha

First assignment completed
---
 Assignment1 Numpy.ipynb | 357 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 357 insertions(+)
 create mode 100644 Assignment1 Numpy.ipynb

diff --git a/Assignment1 Numpy.ipynb b/Assignment1 Numpy.ipynb
new file mode 100644
index 0000000..a087d87
--- /dev/null
+++ b/Assignment1 Numpy.ipynb	
@@ -0,0 +1,357 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Assignment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make a python list => \\[1,2,3,4,5\\]\n",
+    "\n",
+    "Convert it into numpy array and print it"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1 2 3 4 5]\n"
+     ]
+    }
+   ],
+   "source": [
+    "l1=[1,2,3,4,5]\n",
+    "n1=np.array(l1)\n",
+    "print(n1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make a python matrix (3 x 3) => \\[[1,2,3],[4,5,6],[7,8,9]\\]\n",
+    "\n",
+    "Convert it into numpy array and print it"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[1 2 3]\n",
+      " [4 5 6]\n",
+      " [7 8 9]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "matrix1=[[1,2,3],[4,5,6],[7,8,9]]\n",
+    "n2=np.array(matrix1)\n",
+    "print(n2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make a matrix (3 x 3) using built-in methods (like arange(), reshape() etc.):\n",
+    "\n",
+    "\\[ [1,3,5],\n",
+    "\n",
+    " [7,9,11],\n",
+    " \n",
+    " [13,15,17] \\]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 1,  3,  5],\n",
+       "       [ 7,  9, 11],\n",
+       "       [13, 15, 17]])"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "n3=np.arange(1,19,2)\n",
+    "n3.reshape(3,3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a numpy array with 10 random numbers from 0 to 10 (there should be few numbers greater than 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([9, 1, 0, 1, 0, 7, 3, 3, 3, 9])"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np.random.randint(0,10,10)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create numpy array => \\[1,2,3,4,5\\] and convert it to 2D array with 5 rows"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1],\n",
+       "       [2],\n",
+       "       [3],\n",
+       "       [4],\n",
+       "       [5]])"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r=np.arange(1,6)\n",
+    "a1=r.reshape(5,1)\n",
+    "a1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Print the shape of the above created array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5, 1)"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a1.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a numpy array with 10 elements in it. Access and print its 3rd, 4th and 9th element."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ 1  2  3  4  5  6  7  8  9 10]\n",
+      "3\n",
+      "4\n",
+      "9\n"
+     ]
+    }
+   ],
+   "source": [
+    "a1=np.arange(1,11)\n",
+    "print(a1)\n",
+    "print(a1[2])\n",
+    "print(a1[3])\n",
+    "print(a1[8])\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Print alternate elements of that array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1 3 5 7 9]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(a1[0:10:2])\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Change last 3 elements into 100 using broadcasting and print"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([  1,   2,   3,   4,   5,   6,   7, 100, 100, 100])"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a1[7:10]=100\n",
+    "a1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a 5 x 5 matrix (fill it with any element you like), print it.\n",
+    "\n",
+    "Then print the middle (3 x 3) matrix."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[ 1  2  3  4  5]\n",
+      " [ 6  7  8  9 10]\n",
+      " [11 12 13 14 15]\n",
+      " [16 17 18 19 20]\n",
+      " [21 22 23 24 25]]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 7,  8,  9],\n",
+       "       [12, 13, 14],\n",
+       "       [17, 18, 19]])"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r1=np.arange(1,26)\n",
+    "r2=r1.reshape(5,5)\n",
+    "print(r2)\n",
+    "r2[1:4,1:4]"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

From c0ffac793e70d42510d266387a10f00c0aaaf681 Mon Sep 17 00:00:00 2001
From: Rachitha <47741826+Rachithaa@users.noreply.github.com>
Date: Mon, 24 Aug 2020 13:19:12 +0530
Subject: [PATCH 2/6] Delete Assignment1 Numpy.ipynb

---
 Assignment1 Numpy.ipynb | 357 ----------------------------------------
 1 file changed, 357 deletions(-)
 delete mode 100644 Assignment1 Numpy.ipynb

diff --git a/Assignment1 Numpy.ipynb b/Assignment1 Numpy.ipynb
deleted file mode 100644
index a087d87..0000000
--- a/Assignment1 Numpy.ipynb	
+++ /dev/null
@@ -1,357 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Assignment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Import numpy as np"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Make a python list => \\[1,2,3,4,5\\]\n",
-    "\n",
-    "Convert it into numpy array and print it"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[1 2 3 4 5]\n"
-     ]
-    }
-   ],
-   "source": [
-    "l1=[1,2,3,4,5]\n",
-    "n1=np.array(l1)\n",
-    "print(n1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Make a python matrix (3 x 3) => \\[[1,2,3],[4,5,6],[7,8,9]\\]\n",
-    "\n",
-    "Convert it into numpy array and print it"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[[1 2 3]\n",
-      " [4 5 6]\n",
-      " [7 8 9]]\n"
-     ]
-    }
-   ],
-   "source": [
-    "matrix1=[[1,2,3],[4,5,6],[7,8,9]]\n",
-    "n2=np.array(matrix1)\n",
-    "print(n2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Make a matrix (3 x 3) using built-in methods (like arange(), reshape() etc.):\n",
-    "\n",
-    "\\[ [1,3,5],\n",
-    "\n",
-    " [7,9,11],\n",
-    " \n",
-    " [13,15,17] \\]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([[ 1,  3,  5],\n",
-       "       [ 7,  9, 11],\n",
-       "       [13, 15, 17]])"
-      ]
-     },
-     "execution_count": 38,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "n3=np.arange(1,19,2)\n",
-    "n3.reshape(3,3)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create a numpy array with 10 random numbers from 0 to 10 (there should be few numbers greater than 1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([9, 1, 0, 1, 0, 7, 3, 3, 3, 9])"
-      ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "np.random.randint(0,10,10)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create numpy array => \\[1,2,3,4,5\\] and convert it to 2D array with 5 rows"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([[1],\n",
-       "       [2],\n",
-       "       [3],\n",
-       "       [4],\n",
-       "       [5]])"
-      ]
-     },
-     "execution_count": 40,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "r=np.arange(1,6)\n",
-    "a1=r.reshape(5,1)\n",
-    "a1"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Print the shape of the above created array"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 41,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(5, 1)"
-      ]
-     },
-     "execution_count": 41,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "a1.shape"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create a numpy array with 10 elements in it. Access and print its 3rd, 4th and 9th element."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[ 1  2  3  4  5  6  7  8  9 10]\n",
-      "3\n",
-      "4\n",
-      "9\n"
-     ]
-    }
-   ],
-   "source": [
-    "a1=np.arange(1,11)\n",
-    "print(a1)\n",
-    "print(a1[2])\n",
-    "print(a1[3])\n",
-    "print(a1[8])\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Print alternate elements of that array"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 43,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[1 3 5 7 9]\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(a1[0:10:2])\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Change last 3 elements into 100 using broadcasting and print"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 44,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([  1,   2,   3,   4,   5,   6,   7, 100, 100, 100])"
-      ]
-     },
-     "execution_count": 44,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "a1[7:10]=100\n",
-    "a1"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create a 5 x 5 matrix (fill it with any element you like), print it.\n",
-    "\n",
-    "Then print the middle (3 x 3) matrix."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[[ 1  2  3  4  5]\n",
-      " [ 6  7  8  9 10]\n",
-      " [11 12 13 14 15]\n",
-      " [16 17 18 19 20]\n",
-      " [21 22 23 24 25]]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "array([[ 7,  8,  9],\n",
-       "       [12, 13, 14],\n",
-       "       [17, 18, 19]])"
-      ]
-     },
-     "execution_count": 45,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "r1=np.arange(1,26)\n",
-    "r2=r1.reshape(5,5)\n",
-    "print(r2)\n",
-    "r2[1:4,1:4]"
-   ]
-  }
- ],
- "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": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

From cd8060858a81e41792aa17e9d66883005f8e38a1 Mon Sep 17 00:00:00 2001
From: Rachitha <47741826+Rachithaa@users.noreply.github.com>
Date: Mon, 24 Aug 2020 14:10:16 +0530
Subject: [PATCH 3/6] Assignment 1-Rachitha

---
 Assignment1 Numpy.ipynb | 357 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 357 insertions(+)
 create mode 100644 Assignment1 Numpy.ipynb

diff --git a/Assignment1 Numpy.ipynb b/Assignment1 Numpy.ipynb
new file mode 100644
index 0000000..a087d87
--- /dev/null
+++ b/Assignment1 Numpy.ipynb	
@@ -0,0 +1,357 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Assignment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make a python list => \\[1,2,3,4,5\\]\n",
+    "\n",
+    "Convert it into numpy array and print it"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1 2 3 4 5]\n"
+     ]
+    }
+   ],
+   "source": [
+    "l1=[1,2,3,4,5]\n",
+    "n1=np.array(l1)\n",
+    "print(n1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make a python matrix (3 x 3) => \\[[1,2,3],[4,5,6],[7,8,9]\\]\n",
+    "\n",
+    "Convert it into numpy array and print it"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[1 2 3]\n",
+      " [4 5 6]\n",
+      " [7 8 9]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "matrix1=[[1,2,3],[4,5,6],[7,8,9]]\n",
+    "n2=np.array(matrix1)\n",
+    "print(n2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make a matrix (3 x 3) using built-in methods (like arange(), reshape() etc.):\n",
+    "\n",
+    "\\[ [1,3,5],\n",
+    "\n",
+    " [7,9,11],\n",
+    " \n",
+    " [13,15,17] \\]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 1,  3,  5],\n",
+       "       [ 7,  9, 11],\n",
+       "       [13, 15, 17]])"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "n3=np.arange(1,19,2)\n",
+    "n3.reshape(3,3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a numpy array with 10 random numbers from 0 to 10 (there should be few numbers greater than 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([9, 1, 0, 1, 0, 7, 3, 3, 3, 9])"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np.random.randint(0,10,10)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create numpy array => \\[1,2,3,4,5\\] and convert it to 2D array with 5 rows"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1],\n",
+       "       [2],\n",
+       "       [3],\n",
+       "       [4],\n",
+       "       [5]])"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r=np.arange(1,6)\n",
+    "a1=r.reshape(5,1)\n",
+    "a1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Print the shape of the above created array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5, 1)"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a1.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a numpy array with 10 elements in it. Access and print its 3rd, 4th and 9th element."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ 1  2  3  4  5  6  7  8  9 10]\n",
+      "3\n",
+      "4\n",
+      "9\n"
+     ]
+    }
+   ],
+   "source": [
+    "a1=np.arange(1,11)\n",
+    "print(a1)\n",
+    "print(a1[2])\n",
+    "print(a1[3])\n",
+    "print(a1[8])\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Print alternate elements of that array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1 3 5 7 9]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(a1[0:10:2])\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Change last 3 elements into 100 using broadcasting and print"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([  1,   2,   3,   4,   5,   6,   7, 100, 100, 100])"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a1[7:10]=100\n",
+    "a1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a 5 x 5 matrix (fill it with any element you like), print it.\n",
+    "\n",
+    "Then print the middle (3 x 3) matrix."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[ 1  2  3  4  5]\n",
+      " [ 6  7  8  9 10]\n",
+      " [11 12 13 14 15]\n",
+      " [16 17 18 19 20]\n",
+      " [21 22 23 24 25]]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 7,  8,  9],\n",
+       "       [12, 13, 14],\n",
+       "       [17, 18, 19]])"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r1=np.arange(1,26)\n",
+    "r2=r1.reshape(5,5)\n",
+    "print(r2)\n",
+    "r2[1:4,1:4]"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

From aaf8e37f2e2d63176a2bda2a382155ba4d6771d1 Mon Sep 17 00:00:00 2001
From: Rachitha <47741826+Rachithaa@users.noreply.github.com>
Date: Sun, 6 Sep 2020 21:51:21 +0530
Subject: [PATCH 4/6] Add files via upload

RACHITHA-SECOND ASSIGNMENT
---
 Assignment2 pandas-RACHITHA.ipynb | 1384 +++++++++++++++++++++++++++++
 1 file changed, 1384 insertions(+)
 create mode 100644 Assignment2 pandas-RACHITHA.ipynb

diff --git a/Assignment2 pandas-RACHITHA.ipynb b/Assignment2 pandas-RACHITHA.ipynb
new file mode 100644
index 0000000..3b934bf
--- /dev/null
+++ b/Assignment2 pandas-RACHITHA.ipynb	
@@ -0,0 +1,1384 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "#%matplotlib notebook\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "import the dataset into a dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "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>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",
+       "    <tr>\n",
+       "      <th>Id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148650</th>\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>148651</th>\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>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>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>148654</th>\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 × 12 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             EmployeeName                                        JobTitle  \\\n",
+       "Id                                                                          \n",
+       "1          NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
+       "2            GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "3          ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "4       CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
+       "5         PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
+       "...                   ...                                             ...   \n",
+       "148650      Roy I Tillery                                       Custodian   \n",
+       "148651       Not provided                                    Not provided   \n",
+       "148652       Not provided                                    Not provided   \n",
+       "148653       Not provided                                    Not provided   \n",
+       "148654          Joe Lopez                      Counselor, Log Cabin Ranch   \n",
+       "\n",
+       "          BasePay  OvertimePay   OtherPay  Benefits   TotalPay  \\\n",
+       "Id                                                               \n",
+       "1       167411.18         0.00  400184.25       NaN  567595.43   \n",
+       "2       155966.02    245131.88  137811.38       NaN  538909.28   \n",
+       "3       212739.13    106088.18   16452.60       NaN  335279.91   \n",
+       "4        77916.00     56120.71  198306.90       NaN  332343.61   \n",
+       "5       134401.60      9737.00  182234.59       NaN  326373.19   \n",
+       "...           ...          ...        ...       ...        ...   \n",
+       "148650       0.00         0.00       0.00       0.0       0.00   \n",
+       "148651        NaN          NaN        NaN       NaN       0.00   \n",
+       "148652        NaN          NaN        NaN       NaN       0.00   \n",
+       "148653        NaN          NaN        NaN       NaN       0.00   \n",
+       "148654       0.00         0.00    -618.13       0.0    -618.13   \n",
+       "\n",
+       "        TotalPayBenefits  Year  Notes         Agency  Status  \n",
+       "Id                                                            \n",
+       "1              567595.43  2011    NaN  San Francisco     NaN  \n",
+       "2              538909.28  2011    NaN  San Francisco     NaN  \n",
+       "3              335279.91  2011    NaN  San Francisco     NaN  \n",
+       "4              332343.61  2011    NaN  San Francisco     NaN  \n",
+       "5              326373.19  2011    NaN  San Francisco     NaN  \n",
+       "...                  ...   ...    ...            ...     ...  \n",
+       "148650              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148651              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148652              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148653              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148654           -618.13  2014    NaN  San Francisco     NaN  \n",
+       "\n",
+       "[148654 rows x 12 columns]"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1=pd.read_csv('Salaries.csv',index_col='Id')\n",
+    "d1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "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>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",
+       "    <tr>\n",
+       "      <th>Id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         EmployeeName                                        JobTitle  \\\n",
+       "Id                                                                      \n",
+       "1      NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
+       "2        GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "3      ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "4   CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
+       "5     PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
+       "\n",
+       "      BasePay  OvertimePay   OtherPay  Benefits   TotalPay  TotalPayBenefits  \\\n",
+       "Id                                                                             \n",
+       "1   167411.18         0.00  400184.25       NaN  567595.43         567595.43   \n",
+       "2   155966.02    245131.88  137811.38       NaN  538909.28         538909.28   \n",
+       "3   212739.13    106088.18   16452.60       NaN  335279.91         335279.91   \n",
+       "4    77916.00     56120.71  198306.90       NaN  332343.61         332343.61   \n",
+       "5   134401.60      9737.00  182234.59       NaN  326373.19         326373.19   \n",
+       "\n",
+       "    Year  Notes         Agency  Status  \n",
+       "Id                                      \n",
+       "1   2011    NaN  San Francisco     NaN  \n",
+       "2   2011    NaN  San Francisco     NaN  \n",
+       "3   2011    NaN  San Francisco     NaN  \n",
+       "4   2011    NaN  San Francisco     NaN  \n",
+       "5   2011    NaN  San Francisco     NaN  "
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display the column names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['EmployeeName', 'JobTitle', 'BasePay', 'OvertimePay', 'OtherPay',\n",
+       "       'Benefits', 'TotalPay', 'TotalPayBenefits', 'Year', 'Notes', 'Agency',\n",
+       "       'Status'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display the number of rows and cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "rows: 148654\n",
+      "columns: 12\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"rows: \"+str(len(d1.axes[0])))\n",
+    "print(\"columns: \"+str(len(d1.axes[1])))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(148654, 12)"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display the dataframe info (types of data in columns and not null values etc.)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 148654 entries, 1 to 148654\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column            Non-Null Count   Dtype  \n",
+      "---  ------            --------------   -----  \n",
+      " 0   EmployeeName      148654 non-null  object \n",
+      " 1   JobTitle          148654 non-null  object \n",
+      " 2   BasePay           148045 non-null  float64\n",
+      " 3   OvertimePay       148650 non-null  float64\n",
+      " 4   OtherPay          148650 non-null  float64\n",
+      " 5   Benefits          112491 non-null  float64\n",
+      " 6   TotalPay          148654 non-null  float64\n",
+      " 7   TotalPayBenefits  148654 non-null  float64\n",
+      " 8   Year              148654 non-null  int64  \n",
+      " 9   Notes             0 non-null       float64\n",
+      " 10  Agency            148654 non-null  object \n",
+      " 11  Status            0 non-null       float64\n",
+      "dtypes: float64(8), int64(1), object(3)\n",
+      "memory usage: 14.7+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "d1.info()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display stats of the dataframe like count, mean, std, max, 25% etc....."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "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>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>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>66325.448841</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>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>-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>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>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>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>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": [
+       "             BasePay    OvertimePay       OtherPay       Benefits  \\\n",
+       "count  148045.000000  148650.000000  148650.000000  112491.000000   \n",
+       "mean    66325.448841    5066.059886    3648.767297   25007.893151   \n",
+       "std     42764.635495   11454.380559    8056.601866   15402.215858   \n",
+       "min      -166.010000      -0.010000   -7058.590000     -33.890000   \n",
+       "25%     33588.200000       0.000000       0.000000   11535.395000   \n",
+       "50%     65007.450000       0.000000     811.270000   28628.620000   \n",
+       "75%     94691.050000    4658.175000    4236.065000   35566.855000   \n",
+       "max    319275.010000  245131.880000  400184.250000   96570.660000   \n",
+       "\n",
+       "            TotalPay  TotalPayBenefits           Year  Notes  Status  \n",
+       "count  148654.000000     148654.000000  148654.000000    0.0     0.0  \n",
+       "mean    74768.321972      93692.554811    2012.522643    NaN     NaN  \n",
+       "std     50517.005274      62793.533483       1.117538    NaN     NaN  \n",
+       "min      -618.130000       -618.130000    2011.000000    NaN     NaN  \n",
+       "25%     36168.995000      44065.650000    2012.000000    NaN     NaN  \n",
+       "50%     71426.610000      92404.090000    2013.000000    NaN     NaN  \n",
+       "75%    105839.135000     132876.450000    2014.000000    NaN     NaN  \n",
+       "max    567595.430000     567595.430000    2014.000000    NaN     NaN  "
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display null values per column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "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": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "remove columns will all values as NaN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "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>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",
+       "    <tr>\n",
+       "      <th>Id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148650</th>\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>148651</th>\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>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>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>148654</th>\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 × 10 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             EmployeeName                                        JobTitle  \\\n",
+       "Id                                                                          \n",
+       "1          NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
+       "2            GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "3          ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "4       CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
+       "5         PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
+       "...                   ...                                             ...   \n",
+       "148650      Roy I Tillery                                       Custodian   \n",
+       "148651       Not provided                                    Not provided   \n",
+       "148652       Not provided                                    Not provided   \n",
+       "148653       Not provided                                    Not provided   \n",
+       "148654          Joe Lopez                      Counselor, Log Cabin Ranch   \n",
+       "\n",
+       "          BasePay  OvertimePay   OtherPay  Benefits   TotalPay  \\\n",
+       "Id                                                               \n",
+       "1       167411.18         0.00  400184.25       NaN  567595.43   \n",
+       "2       155966.02    245131.88  137811.38       NaN  538909.28   \n",
+       "3       212739.13    106088.18   16452.60       NaN  335279.91   \n",
+       "4        77916.00     56120.71  198306.90       NaN  332343.61   \n",
+       "5       134401.60      9737.00  182234.59       NaN  326373.19   \n",
+       "...           ...          ...        ...       ...        ...   \n",
+       "148650       0.00         0.00       0.00       0.0       0.00   \n",
+       "148651        NaN          NaN        NaN       NaN       0.00   \n",
+       "148652        NaN          NaN        NaN       NaN       0.00   \n",
+       "148653        NaN          NaN        NaN       NaN       0.00   \n",
+       "148654       0.00         0.00    -618.13       0.0    -618.13   \n",
+       "\n",
+       "        TotalPayBenefits  Year         Agency  \n",
+       "Id                                             \n",
+       "1              567595.43  2011  San Francisco  \n",
+       "2              538909.28  2011  San Francisco  \n",
+       "3              335279.91  2011  San Francisco  \n",
+       "4              332343.61  2011  San Francisco  \n",
+       "5              326373.19  2011  San Francisco  \n",
+       "...                  ...   ...            ...  \n",
+       "148650              0.00  2014  San Francisco  \n",
+       "148651              0.00  2014  San Francisco  \n",
+       "148652              0.00  2014  San Francisco  \n",
+       "148653              0.00  2014  San Francisco  \n",
+       "148654           -618.13  2014  San Francisco  \n",
+       "\n",
+       "[148654 rows x 10 columns]"
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.dropna(how='all',axis=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display number of unique values in each column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "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",
+       "Notes                    0\n",
+       "Agency                   1\n",
+       "Status                   0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 68,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.nunique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "mean of total pay of all people based on year"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Year\n",
+       "2011    71744.103871\n",
+       "2012    74113.262265\n",
+       "2013    77611.443142\n",
+       "2014    75463.918140\n",
+       "Name: TotalPay, dtype: float64"
+      ]
+     },
+     "execution_count": 69,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.groupby('Year').mean()['TotalPay']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "how many people have 0 overtime pay"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "77321"
+      ]
+     },
+     "execution_count": 70,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(d1[d1['OvertimePay']==0]['OvertimePay'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "max, min, mean, median and other stats of TotalPay of people having 0 OvertimePay"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "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": 71,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[d1['OvertimePay']==0]['TotalPay'].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "find Id of that person with max TotalPay you got in previous question"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Int64Index([1], dtype='int64', name='Id')"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1=d1[d1['OvertimePay']==0]['TotalPay'].max()\n",
+    "d1[d1['TotalPay']==f1].index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Int64Index([1], dtype='int64', name='Id')"
+      ]
+     },
+     "execution_count": 73,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[d1['TotalPay']==567595.430000].index\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "name of employee with total pay benefits = 87619.78"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Id\n",
+       "12346    REBECCA CHIU\n",
+       "Name: EmployeeName, dtype: object"
+      ]
+     },
+     "execution_count": 74,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[d1['TotalPayBenefits']==87619.78]['EmployeeName']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "how many people have BasePay > 150000 and OvertimePay > 100000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "12"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[(d1['BasePay']> 150000) & (d1['OvertimePay'] > 100000)].count()['EmployeeName']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "which job title generally has highest average TotalPayBenefits"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY'"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1=d1.loc[d1['TotalPayBenefits'].idxmax()]\n",
+    "f1['JobTitle']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "How many employees are POLICE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2512"
+      ]
+     },
+     "execution_count": 77,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# .str.contains()\n",
+    "len(d1[d1['JobTitle'].str.contains('POLICE')])\n"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

From aac7cbe524dae4717e1abd1dc66b9e4b540f495e Mon Sep 17 00:00:00 2001
From: Rachitha <47741826+Rachithaa@users.noreply.github.com>
Date: Sun, 6 Sep 2020 21:52:41 +0530
Subject: [PATCH 5/6] Delete Assignment2 pandas-RACHITHA.ipynb

---
 Assignment2 pandas-RACHITHA.ipynb | 1384 -----------------------------
 1 file changed, 1384 deletions(-)
 delete mode 100644 Assignment2 pandas-RACHITHA.ipynb

diff --git a/Assignment2 pandas-RACHITHA.ipynb b/Assignment2 pandas-RACHITHA.ipynb
deleted file mode 100644
index 3b934bf..0000000
--- a/Assignment2 pandas-RACHITHA.ipynb	
+++ /dev/null
@@ -1,1384 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "#%matplotlib notebook\n",
-    "%matplotlib inline"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "import the dataset into a dataframe"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "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>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",
-       "    <tr>\n",
-       "      <th>Id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>148650</th>\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>148651</th>\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>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>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>148654</th>\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 × 12 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "             EmployeeName                                        JobTitle  \\\n",
-       "Id                                                                          \n",
-       "1          NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
-       "2            GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
-       "3          ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
-       "4       CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
-       "5         PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
-       "...                   ...                                             ...   \n",
-       "148650      Roy I Tillery                                       Custodian   \n",
-       "148651       Not provided                                    Not provided   \n",
-       "148652       Not provided                                    Not provided   \n",
-       "148653       Not provided                                    Not provided   \n",
-       "148654          Joe Lopez                      Counselor, Log Cabin Ranch   \n",
-       "\n",
-       "          BasePay  OvertimePay   OtherPay  Benefits   TotalPay  \\\n",
-       "Id                                                               \n",
-       "1       167411.18         0.00  400184.25       NaN  567595.43   \n",
-       "2       155966.02    245131.88  137811.38       NaN  538909.28   \n",
-       "3       212739.13    106088.18   16452.60       NaN  335279.91   \n",
-       "4        77916.00     56120.71  198306.90       NaN  332343.61   \n",
-       "5       134401.60      9737.00  182234.59       NaN  326373.19   \n",
-       "...           ...          ...        ...       ...        ...   \n",
-       "148650       0.00         0.00       0.00       0.0       0.00   \n",
-       "148651        NaN          NaN        NaN       NaN       0.00   \n",
-       "148652        NaN          NaN        NaN       NaN       0.00   \n",
-       "148653        NaN          NaN        NaN       NaN       0.00   \n",
-       "148654       0.00         0.00    -618.13       0.0    -618.13   \n",
-       "\n",
-       "        TotalPayBenefits  Year  Notes         Agency  Status  \n",
-       "Id                                                            \n",
-       "1              567595.43  2011    NaN  San Francisco     NaN  \n",
-       "2              538909.28  2011    NaN  San Francisco     NaN  \n",
-       "3              335279.91  2011    NaN  San Francisco     NaN  \n",
-       "4              332343.61  2011    NaN  San Francisco     NaN  \n",
-       "5              326373.19  2011    NaN  San Francisco     NaN  \n",
-       "...                  ...   ...    ...            ...     ...  \n",
-       "148650              0.00  2014    NaN  San Francisco     NaN  \n",
-       "148651              0.00  2014    NaN  San Francisco     NaN  \n",
-       "148652              0.00  2014    NaN  San Francisco     NaN  \n",
-       "148653              0.00  2014    NaN  San Francisco     NaN  \n",
-       "148654           -618.13  2014    NaN  San Francisco     NaN  \n",
-       "\n",
-       "[148654 rows x 12 columns]"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1=pd.read_csv('Salaries.csv',index_col='Id')\n",
-    "d1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "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>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",
-       "    <tr>\n",
-       "      <th>Id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         EmployeeName                                        JobTitle  \\\n",
-       "Id                                                                      \n",
-       "1      NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
-       "2        GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
-       "3      ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
-       "4   CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
-       "5     PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
-       "\n",
-       "      BasePay  OvertimePay   OtherPay  Benefits   TotalPay  TotalPayBenefits  \\\n",
-       "Id                                                                             \n",
-       "1   167411.18         0.00  400184.25       NaN  567595.43         567595.43   \n",
-       "2   155966.02    245131.88  137811.38       NaN  538909.28         538909.28   \n",
-       "3   212739.13    106088.18   16452.60       NaN  335279.91         335279.91   \n",
-       "4    77916.00     56120.71  198306.90       NaN  332343.61         332343.61   \n",
-       "5   134401.60      9737.00  182234.59       NaN  326373.19         326373.19   \n",
-       "\n",
-       "    Year  Notes         Agency  Status  \n",
-       "Id                                      \n",
-       "1   2011    NaN  San Francisco     NaN  \n",
-       "2   2011    NaN  San Francisco     NaN  \n",
-       "3   2011    NaN  San Francisco     NaN  \n",
-       "4   2011    NaN  San Francisco     NaN  \n",
-       "5   2011    NaN  San Francisco     NaN  "
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "display the column names"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Index(['EmployeeName', 'JobTitle', 'BasePay', 'OvertimePay', 'OtherPay',\n",
-       "       'Benefits', 'TotalPay', 'TotalPayBenefits', 'Year', 'Notes', 'Agency',\n",
-       "       'Status'],\n",
-       "      dtype='object')"
-      ]
-     },
-     "execution_count": 61,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.columns"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "display the number of rows and cols"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "rows: 148654\n",
-      "columns: 12\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\"rows: \"+str(len(d1.axes[0])))\n",
-    "print(\"columns: \"+str(len(d1.axes[1])))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(148654, 12)"
-      ]
-     },
-     "execution_count": 63,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.shape"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "display the dataframe info (types of data in columns and not null values etc.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'pandas.core.frame.DataFrame'>\n",
-      "Int64Index: 148654 entries, 1 to 148654\n",
-      "Data columns (total 12 columns):\n",
-      " #   Column            Non-Null Count   Dtype  \n",
-      "---  ------            --------------   -----  \n",
-      " 0   EmployeeName      148654 non-null  object \n",
-      " 1   JobTitle          148654 non-null  object \n",
-      " 2   BasePay           148045 non-null  float64\n",
-      " 3   OvertimePay       148650 non-null  float64\n",
-      " 4   OtherPay          148650 non-null  float64\n",
-      " 5   Benefits          112491 non-null  float64\n",
-      " 6   TotalPay          148654 non-null  float64\n",
-      " 7   TotalPayBenefits  148654 non-null  float64\n",
-      " 8   Year              148654 non-null  int64  \n",
-      " 9   Notes             0 non-null       float64\n",
-      " 10  Agency            148654 non-null  object \n",
-      " 11  Status            0 non-null       float64\n",
-      "dtypes: float64(8), int64(1), object(3)\n",
-      "memory usage: 14.7+ MB\n"
-     ]
-    }
-   ],
-   "source": [
-    "d1.info()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "display stats of the dataframe like count, mean, std, max, 25% etc....."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 65,
-   "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>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>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>66325.448841</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>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>-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>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>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>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>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": [
-       "             BasePay    OvertimePay       OtherPay       Benefits  \\\n",
-       "count  148045.000000  148650.000000  148650.000000  112491.000000   \n",
-       "mean    66325.448841    5066.059886    3648.767297   25007.893151   \n",
-       "std     42764.635495   11454.380559    8056.601866   15402.215858   \n",
-       "min      -166.010000      -0.010000   -7058.590000     -33.890000   \n",
-       "25%     33588.200000       0.000000       0.000000   11535.395000   \n",
-       "50%     65007.450000       0.000000     811.270000   28628.620000   \n",
-       "75%     94691.050000    4658.175000    4236.065000   35566.855000   \n",
-       "max    319275.010000  245131.880000  400184.250000   96570.660000   \n",
-       "\n",
-       "            TotalPay  TotalPayBenefits           Year  Notes  Status  \n",
-       "count  148654.000000     148654.000000  148654.000000    0.0     0.0  \n",
-       "mean    74768.321972      93692.554811    2012.522643    NaN     NaN  \n",
-       "std     50517.005274      62793.533483       1.117538    NaN     NaN  \n",
-       "min      -618.130000       -618.130000    2011.000000    NaN     NaN  \n",
-       "25%     36168.995000      44065.650000    2012.000000    NaN     NaN  \n",
-       "50%     71426.610000      92404.090000    2013.000000    NaN     NaN  \n",
-       "75%    105839.135000     132876.450000    2014.000000    NaN     NaN  \n",
-       "max    567595.430000     567595.430000    2014.000000    NaN     NaN  "
-      ]
-     },
-     "execution_count": 65,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.describe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "display null values per column"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "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": 66,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.isna().sum()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "remove columns will all values as NaN"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 67,
-   "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>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",
-       "    <tr>\n",
-       "      <th>Id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>148650</th>\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>148651</th>\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>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>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>148654</th>\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 × 10 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "             EmployeeName                                        JobTitle  \\\n",
-       "Id                                                                          \n",
-       "1          NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
-       "2            GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
-       "3          ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
-       "4       CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
-       "5         PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
-       "...                   ...                                             ...   \n",
-       "148650      Roy I Tillery                                       Custodian   \n",
-       "148651       Not provided                                    Not provided   \n",
-       "148652       Not provided                                    Not provided   \n",
-       "148653       Not provided                                    Not provided   \n",
-       "148654          Joe Lopez                      Counselor, Log Cabin Ranch   \n",
-       "\n",
-       "          BasePay  OvertimePay   OtherPay  Benefits   TotalPay  \\\n",
-       "Id                                                               \n",
-       "1       167411.18         0.00  400184.25       NaN  567595.43   \n",
-       "2       155966.02    245131.88  137811.38       NaN  538909.28   \n",
-       "3       212739.13    106088.18   16452.60       NaN  335279.91   \n",
-       "4        77916.00     56120.71  198306.90       NaN  332343.61   \n",
-       "5       134401.60      9737.00  182234.59       NaN  326373.19   \n",
-       "...           ...          ...        ...       ...        ...   \n",
-       "148650       0.00         0.00       0.00       0.0       0.00   \n",
-       "148651        NaN          NaN        NaN       NaN       0.00   \n",
-       "148652        NaN          NaN        NaN       NaN       0.00   \n",
-       "148653        NaN          NaN        NaN       NaN       0.00   \n",
-       "148654       0.00         0.00    -618.13       0.0    -618.13   \n",
-       "\n",
-       "        TotalPayBenefits  Year         Agency  \n",
-       "Id                                             \n",
-       "1              567595.43  2011  San Francisco  \n",
-       "2              538909.28  2011  San Francisco  \n",
-       "3              335279.91  2011  San Francisco  \n",
-       "4              332343.61  2011  San Francisco  \n",
-       "5              326373.19  2011  San Francisco  \n",
-       "...                  ...   ...            ...  \n",
-       "148650              0.00  2014  San Francisco  \n",
-       "148651              0.00  2014  San Francisco  \n",
-       "148652              0.00  2014  San Francisco  \n",
-       "148653              0.00  2014  San Francisco  \n",
-       "148654           -618.13  2014  San Francisco  \n",
-       "\n",
-       "[148654 rows x 10 columns]"
-      ]
-     },
-     "execution_count": 67,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.dropna(how='all',axis=1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "display number of unique values in each column"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 68,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "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",
-       "Notes                    0\n",
-       "Agency                   1\n",
-       "Status                   0\n",
-       "dtype: int64"
-      ]
-     },
-     "execution_count": 68,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.nunique()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "mean of total pay of all people based on year"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 69,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Year\n",
-       "2011    71744.103871\n",
-       "2012    74113.262265\n",
-       "2013    77611.443142\n",
-       "2014    75463.918140\n",
-       "Name: TotalPay, dtype: float64"
-      ]
-     },
-     "execution_count": 69,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1.groupby('Year').mean()['TotalPay']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "how many people have 0 overtime pay"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 70,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "77321"
-      ]
-     },
-     "execution_count": 70,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "len(d1[d1['OvertimePay']==0]['OvertimePay'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "max, min, mean, median and other stats of TotalPay of people having 0 OvertimePay"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 71,
-   "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": 71,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1[d1['OvertimePay']==0]['TotalPay'].describe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "find Id of that person with max TotalPay you got in previous question"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 72,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Int64Index([1], dtype='int64', name='Id')"
-      ]
-     },
-     "execution_count": 72,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "f1=d1[d1['OvertimePay']==0]['TotalPay'].max()\n",
-    "d1[d1['TotalPay']==f1].index"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 73,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Int64Index([1], dtype='int64', name='Id')"
-      ]
-     },
-     "execution_count": 73,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1[d1['TotalPay']==567595.430000].index\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "name of employee with total pay benefits = 87619.78"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 74,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Id\n",
-       "12346    REBECCA CHIU\n",
-       "Name: EmployeeName, dtype: object"
-      ]
-     },
-     "execution_count": 74,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1[d1['TotalPayBenefits']==87619.78]['EmployeeName']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "how many people have BasePay > 150000 and OvertimePay > 100000"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 75,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "12"
-      ]
-     },
-     "execution_count": 75,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "d1[(d1['BasePay']> 150000) & (d1['OvertimePay'] > 100000)].count()['EmployeeName']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "which job title generally has highest average TotalPayBenefits"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 76,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY'"
-      ]
-     },
-     "execution_count": 76,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "f1=d1.loc[d1['TotalPayBenefits'].idxmax()]\n",
-    "f1['JobTitle']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "How many employees are POLICE"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "2512"
-      ]
-     },
-     "execution_count": 77,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# .str.contains()\n",
-    "len(d1[d1['JobTitle'].str.contains('POLICE')])\n"
-   ]
-  }
- ],
- "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": "3.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

From 6adcb577f4c672b94fcc34974a9ea0c8778d143c Mon Sep 17 00:00:00 2001
From: Rachitha <47741826+Rachithaa@users.noreply.github.com>
Date: Sun, 6 Sep 2020 21:53:26 +0530
Subject: [PATCH 6/6] RACHITHA-SECOND ASSIGNMENT

---
 Assignment2 pandas-RACHITHA.ipynb | 1384 +++++++++++++++++++++++++++++
 1 file changed, 1384 insertions(+)
 create mode 100644 Assignment2 pandas-RACHITHA.ipynb

diff --git a/Assignment2 pandas-RACHITHA.ipynb b/Assignment2 pandas-RACHITHA.ipynb
new file mode 100644
index 0000000..3b934bf
--- /dev/null
+++ b/Assignment2 pandas-RACHITHA.ipynb	
@@ -0,0 +1,1384 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "#%matplotlib notebook\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "import the dataset into a dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "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>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",
+       "    <tr>\n",
+       "      <th>Id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148650</th>\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>148651</th>\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>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>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>148654</th>\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 × 12 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             EmployeeName                                        JobTitle  \\\n",
+       "Id                                                                          \n",
+       "1          NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
+       "2            GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "3          ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "4       CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
+       "5         PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
+       "...                   ...                                             ...   \n",
+       "148650      Roy I Tillery                                       Custodian   \n",
+       "148651       Not provided                                    Not provided   \n",
+       "148652       Not provided                                    Not provided   \n",
+       "148653       Not provided                                    Not provided   \n",
+       "148654          Joe Lopez                      Counselor, Log Cabin Ranch   \n",
+       "\n",
+       "          BasePay  OvertimePay   OtherPay  Benefits   TotalPay  \\\n",
+       "Id                                                               \n",
+       "1       167411.18         0.00  400184.25       NaN  567595.43   \n",
+       "2       155966.02    245131.88  137811.38       NaN  538909.28   \n",
+       "3       212739.13    106088.18   16452.60       NaN  335279.91   \n",
+       "4        77916.00     56120.71  198306.90       NaN  332343.61   \n",
+       "5       134401.60      9737.00  182234.59       NaN  326373.19   \n",
+       "...           ...          ...        ...       ...        ...   \n",
+       "148650       0.00         0.00       0.00       0.0       0.00   \n",
+       "148651        NaN          NaN        NaN       NaN       0.00   \n",
+       "148652        NaN          NaN        NaN       NaN       0.00   \n",
+       "148653        NaN          NaN        NaN       NaN       0.00   \n",
+       "148654       0.00         0.00    -618.13       0.0    -618.13   \n",
+       "\n",
+       "        TotalPayBenefits  Year  Notes         Agency  Status  \n",
+       "Id                                                            \n",
+       "1              567595.43  2011    NaN  San Francisco     NaN  \n",
+       "2              538909.28  2011    NaN  San Francisco     NaN  \n",
+       "3              335279.91  2011    NaN  San Francisco     NaN  \n",
+       "4              332343.61  2011    NaN  San Francisco     NaN  \n",
+       "5              326373.19  2011    NaN  San Francisco     NaN  \n",
+       "...                  ...   ...    ...            ...     ...  \n",
+       "148650              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148651              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148652              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148653              0.00  2014    NaN  San Francisco     NaN  \n",
+       "148654           -618.13  2014    NaN  San Francisco     NaN  \n",
+       "\n",
+       "[148654 rows x 12 columns]"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1=pd.read_csv('Salaries.csv',index_col='Id')\n",
+    "d1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "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>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",
+       "    <tr>\n",
+       "      <th>Id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         EmployeeName                                        JobTitle  \\\n",
+       "Id                                                                      \n",
+       "1      NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
+       "2        GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "3      ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "4   CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
+       "5     PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
+       "\n",
+       "      BasePay  OvertimePay   OtherPay  Benefits   TotalPay  TotalPayBenefits  \\\n",
+       "Id                                                                             \n",
+       "1   167411.18         0.00  400184.25       NaN  567595.43         567595.43   \n",
+       "2   155966.02    245131.88  137811.38       NaN  538909.28         538909.28   \n",
+       "3   212739.13    106088.18   16452.60       NaN  335279.91         335279.91   \n",
+       "4    77916.00     56120.71  198306.90       NaN  332343.61         332343.61   \n",
+       "5   134401.60      9737.00  182234.59       NaN  326373.19         326373.19   \n",
+       "\n",
+       "    Year  Notes         Agency  Status  \n",
+       "Id                                      \n",
+       "1   2011    NaN  San Francisco     NaN  \n",
+       "2   2011    NaN  San Francisco     NaN  \n",
+       "3   2011    NaN  San Francisco     NaN  \n",
+       "4   2011    NaN  San Francisco     NaN  \n",
+       "5   2011    NaN  San Francisco     NaN  "
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display the column names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['EmployeeName', 'JobTitle', 'BasePay', 'OvertimePay', 'OtherPay',\n",
+       "       'Benefits', 'TotalPay', 'TotalPayBenefits', 'Year', 'Notes', 'Agency',\n",
+       "       'Status'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display the number of rows and cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "rows: 148654\n",
+      "columns: 12\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"rows: \"+str(len(d1.axes[0])))\n",
+    "print(\"columns: \"+str(len(d1.axes[1])))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(148654, 12)"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display the dataframe info (types of data in columns and not null values etc.)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 148654 entries, 1 to 148654\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column            Non-Null Count   Dtype  \n",
+      "---  ------            --------------   -----  \n",
+      " 0   EmployeeName      148654 non-null  object \n",
+      " 1   JobTitle          148654 non-null  object \n",
+      " 2   BasePay           148045 non-null  float64\n",
+      " 3   OvertimePay       148650 non-null  float64\n",
+      " 4   OtherPay          148650 non-null  float64\n",
+      " 5   Benefits          112491 non-null  float64\n",
+      " 6   TotalPay          148654 non-null  float64\n",
+      " 7   TotalPayBenefits  148654 non-null  float64\n",
+      " 8   Year              148654 non-null  int64  \n",
+      " 9   Notes             0 non-null       float64\n",
+      " 10  Agency            148654 non-null  object \n",
+      " 11  Status            0 non-null       float64\n",
+      "dtypes: float64(8), int64(1), object(3)\n",
+      "memory usage: 14.7+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "d1.info()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display stats of the dataframe like count, mean, std, max, 25% etc....."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "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>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>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>66325.448841</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>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>-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>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>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>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>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": [
+       "             BasePay    OvertimePay       OtherPay       Benefits  \\\n",
+       "count  148045.000000  148650.000000  148650.000000  112491.000000   \n",
+       "mean    66325.448841    5066.059886    3648.767297   25007.893151   \n",
+       "std     42764.635495   11454.380559    8056.601866   15402.215858   \n",
+       "min      -166.010000      -0.010000   -7058.590000     -33.890000   \n",
+       "25%     33588.200000       0.000000       0.000000   11535.395000   \n",
+       "50%     65007.450000       0.000000     811.270000   28628.620000   \n",
+       "75%     94691.050000    4658.175000    4236.065000   35566.855000   \n",
+       "max    319275.010000  245131.880000  400184.250000   96570.660000   \n",
+       "\n",
+       "            TotalPay  TotalPayBenefits           Year  Notes  Status  \n",
+       "count  148654.000000     148654.000000  148654.000000    0.0     0.0  \n",
+       "mean    74768.321972      93692.554811    2012.522643    NaN     NaN  \n",
+       "std     50517.005274      62793.533483       1.117538    NaN     NaN  \n",
+       "min      -618.130000       -618.130000    2011.000000    NaN     NaN  \n",
+       "25%     36168.995000      44065.650000    2012.000000    NaN     NaN  \n",
+       "50%     71426.610000      92404.090000    2013.000000    NaN     NaN  \n",
+       "75%    105839.135000     132876.450000    2014.000000    NaN     NaN  \n",
+       "max    567595.430000     567595.430000    2014.000000    NaN     NaN  "
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display null values per column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "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": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "remove columns will all values as NaN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "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>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",
+       "    <tr>\n",
+       "      <th>Id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>148650</th>\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>148651</th>\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>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>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>148654</th>\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 × 10 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             EmployeeName                                        JobTitle  \\\n",
+       "Id                                                                          \n",
+       "1          NATHANIEL FORD  GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY   \n",
+       "2            GARY JIMENEZ                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "3          ALBERT PARDINI                 CAPTAIN III (POLICE DEPARTMENT)   \n",
+       "4       CHRISTOPHER CHONG            WIRE ROPE CABLE MAINTENANCE MECHANIC   \n",
+       "5         PATRICK GARDNER    DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)   \n",
+       "...                   ...                                             ...   \n",
+       "148650      Roy I Tillery                                       Custodian   \n",
+       "148651       Not provided                                    Not provided   \n",
+       "148652       Not provided                                    Not provided   \n",
+       "148653       Not provided                                    Not provided   \n",
+       "148654          Joe Lopez                      Counselor, Log Cabin Ranch   \n",
+       "\n",
+       "          BasePay  OvertimePay   OtherPay  Benefits   TotalPay  \\\n",
+       "Id                                                               \n",
+       "1       167411.18         0.00  400184.25       NaN  567595.43   \n",
+       "2       155966.02    245131.88  137811.38       NaN  538909.28   \n",
+       "3       212739.13    106088.18   16452.60       NaN  335279.91   \n",
+       "4        77916.00     56120.71  198306.90       NaN  332343.61   \n",
+       "5       134401.60      9737.00  182234.59       NaN  326373.19   \n",
+       "...           ...          ...        ...       ...        ...   \n",
+       "148650       0.00         0.00       0.00       0.0       0.00   \n",
+       "148651        NaN          NaN        NaN       NaN       0.00   \n",
+       "148652        NaN          NaN        NaN       NaN       0.00   \n",
+       "148653        NaN          NaN        NaN       NaN       0.00   \n",
+       "148654       0.00         0.00    -618.13       0.0    -618.13   \n",
+       "\n",
+       "        TotalPayBenefits  Year         Agency  \n",
+       "Id                                             \n",
+       "1              567595.43  2011  San Francisco  \n",
+       "2              538909.28  2011  San Francisco  \n",
+       "3              335279.91  2011  San Francisco  \n",
+       "4              332343.61  2011  San Francisco  \n",
+       "5              326373.19  2011  San Francisco  \n",
+       "...                  ...   ...            ...  \n",
+       "148650              0.00  2014  San Francisco  \n",
+       "148651              0.00  2014  San Francisco  \n",
+       "148652              0.00  2014  San Francisco  \n",
+       "148653              0.00  2014  San Francisco  \n",
+       "148654           -618.13  2014  San Francisco  \n",
+       "\n",
+       "[148654 rows x 10 columns]"
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.dropna(how='all',axis=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "display number of unique values in each column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "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",
+       "Notes                    0\n",
+       "Agency                   1\n",
+       "Status                   0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 68,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.nunique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "mean of total pay of all people based on year"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Year\n",
+       "2011    71744.103871\n",
+       "2012    74113.262265\n",
+       "2013    77611.443142\n",
+       "2014    75463.918140\n",
+       "Name: TotalPay, dtype: float64"
+      ]
+     },
+     "execution_count": 69,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1.groupby('Year').mean()['TotalPay']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "how many people have 0 overtime pay"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "77321"
+      ]
+     },
+     "execution_count": 70,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(d1[d1['OvertimePay']==0]['OvertimePay'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "max, min, mean, median and other stats of TotalPay of people having 0 OvertimePay"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "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": 71,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[d1['OvertimePay']==0]['TotalPay'].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "find Id of that person with max TotalPay you got in previous question"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Int64Index([1], dtype='int64', name='Id')"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1=d1[d1['OvertimePay']==0]['TotalPay'].max()\n",
+    "d1[d1['TotalPay']==f1].index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Int64Index([1], dtype='int64', name='Id')"
+      ]
+     },
+     "execution_count": 73,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[d1['TotalPay']==567595.430000].index\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "name of employee with total pay benefits = 87619.78"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Id\n",
+       "12346    REBECCA CHIU\n",
+       "Name: EmployeeName, dtype: object"
+      ]
+     },
+     "execution_count": 74,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[d1['TotalPayBenefits']==87619.78]['EmployeeName']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "how many people have BasePay > 150000 and OvertimePay > 100000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "12"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d1[(d1['BasePay']> 150000) & (d1['OvertimePay'] > 100000)].count()['EmployeeName']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "which job title generally has highest average TotalPayBenefits"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY'"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "f1=d1.loc[d1['TotalPayBenefits'].idxmax()]\n",
+    "f1['JobTitle']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "How many employees are POLICE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2512"
+      ]
+     },
+     "execution_count": 77,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# .str.contains()\n",
+    "len(d1[d1['JobTitle'].str.contains('POLICE')])\n"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}