0,
"metadata": {
"colab": {
   "name": "hw3.ipynb",
   "version": "0.3.2",
   "provenance": [],
   "collapsed_sections": []
},
"kernelspec": {
   "name": "python3",
   "display_name": "Python 3"
}
},
"cells": [
{
   "cell_type": "code",
   "metadata": {
   "id": "XHBbNEMVnJKS",
   "colab_type": "code",
   "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 238
   },
   "outputId": "c75af25b-15cd-4263-80b3-0083a227f736"
   },
   "source": [
   "## a.\n",
   "import pandas as pd\n",
   "import statsmodels.formula.api as smf\n",
   "import numpy as np\n",
   "\n",
   "# Reading data using pandas\n",
   "raw_df=pd.read_csv(\"https://raw.githubusercontent.com/lordflaron/ARE106data/master/lawsch85.csv\")\n",
   "\n",
   "# Printing first 10 rows\n",
   "print(raw_df.head(n=10))"
   ],
   "execution_count": 45,
   "outputs": [
   {
      "output_type": "stream",
      "text": [
         " Unnamed: 0 rank salary cost ... top10 r11_25 r26_40 r41_60\n",
         "0       0 128 31400.0 8340.0 ...    0    0    0    0\n",
         "1       1 104 33098.0 6980.0 ...    0    0    0    0\n",
         "2       2 34 32870.0 16370.0 ...    0    0    1    0\n",
         "3       3 49 35000.0 17566.0 ...    0    0    0    1\n",
         "4       4 95 33606.0 8350.0 ...    0    0    0    0\n",
         "5       5 98 31700.0 8350.0 ...    0    0    0    0\n",
         "6       6 124 30410.0 6020.0 ...    0    0    0    0\n",
         "7       7 157 30150.0 5986.0 ...    0    0    0    0\n",
         "8       8 145 31300.0 4785.0 ...    0    0    0    0\n",
         "9       9 91 33200.0 7680.0 ...    0    0    0    0\n",
         "\n",
         "[10 rows x 19 columns]\n"
      ],
      "name": "stdout"
   }
   ]
},
{
   "cell_type": "code",
   "metadata": {
   "id": "M83N08wioMcf",
   "colab_type": "code",
   "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 221
   },
   "outputId": "1c0a7c6a-eebb-4292-8f5d-8cbd053963a8"
   },
   "source": [
   "## b. Put your answer in this cell.\n",
   "\n",
   "# Printing the summary of the data frame\n",
   "print(raw_df.describe())\n",
   "# Printing count of salary\n",
   "print(raw_df.describe().salary['count'])"
   ],
   "execution_count": 7,
   "outputs": [
   {
      "output_type": "stream",
      "text": [
         "    Unnamed: 0    rank    salary ...    r11_25    r26_40    r41_60\n",
         "count 156.000000 156.000000 148.000000 ... 156.000000 156.000000 156.000000\n",
         "mean 77.500000 83.750000 38946.716216 ... 0.102564 0.083333 0.115385\n",
         "std 45.177428 50.064169 12188.840435 ... 0.304366 0.277276 0.320514\n",
         "min    0.000000 1.000000 24900.000000 ... 0.000000 0.000000 0.000000\n",
         "25% 38.750000 40.750000 29950.000000 ... 0.000000 0.000000 0.000000\n",
         "50% 77.500000 83.500000 34725.000000 ... 0.000000 0.000000 0.000000\n",
         "75% 116.250000 125.500000 41350.000000 ... 0.000000 0.000000 0.000000\n",
         "max 155.000000 175.000000 78325.000000 ... 1.000000 1.000000 1.000000\n",
         "\n",
         "[8 rows x 19 columns]\n",
         "148.0\n"
      ],
      "name": "stdout"
   }
   ]
},
{
   "cell_type": "code",
   "metadata": {
   "id": "8ZC6ymaRpH0q",
   "colab_type": "code",
   "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 238
   },
   "outputId": "d7383bfa-89d0-4a3b-ad6e-5dd46c2525cd"
   },
   "source": [
   "## c. Put your answer in this cell.\n",
   "# Assigning new column ie. log_salary which is log of salary and dropping na's\n",
   "df = raw_df.assign(log_salary= np.log(raw_df.salary)).dropna()"
   ],
   "execution_count": 10,
   "outputs": [
   {
      "output_type": "stream",
      "text": [
         " Unnamed: 0 rank salary cost ... r11_25 r26_40 r41_60 log_salary\n",
         "0       0 128 31400.0 8340.0 ...    0    0    0 10.354563\n",
         "1       1 104 33098.0 6980.0 ...    0    0    0 10.407228\n",
         "2       2 34 32870.0 16370.0 ...    0    1    0 10.400316\

Problem 1. The dataset GPA-GRE contains 16 years of GPA, Verbal and...