Hypothesis Testing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import statistics\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2728: DtypeWarning: Columns (4,24,28) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    }
   ],
   "source": [
    "payroll = pd.read_csv(\"/Users/vamseemuppavarapu/data.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Cleansing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "payroll = payroll[pd.notnull(payroll['Payroll Department'])]\n",
    "payroll.rename(columns={'Projected Annual Salary' : 'Annual_sal'}, inplace = True)\n",
    "payroll.rename(columns={'Job Class Title' : 'Job_title'}, inplace = True)\n",
    "payroll.rename(columns={'Base Pay' : 'Base_Pay'}, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in ['Annual_sal','Q1 Payments','Q2 Payments','Q3 Payments','Q4 Payments','Payments Over Base Pay',\n",
    "          'Total Payments','Base_Pay','Permanent Bonus Pay','Longevity Bonus Pay','Temporary Bonus Pay','Overtime Pay',\n",
    "          'Other Pay & Adjustments','Other Pay (Payroll Explorer)','Average Health Cost','Average Dental Cost',\n",
    "          'Average Basic Life','Average Benefit Cost']:\n",
    "    payroll[i] = payroll[i].str.replace('$','')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Outlier removal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "payroll = payroll[payroll.Annual_sal != 0]  \n",
    "payroll = payroll[payroll.Base_Pay != 0]\n",
    "payroll.Annual_sal = payroll.Annual_sal.astype(float)\n",
    "payroll.Base_Pay = payroll.Base_Pay.astype(float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.6/site-packages/scipy/stats/stats.py:1706: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
      "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a27775cc0>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1a27775cf8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (12,6))\n",
    "sns.distplot(payroll.Annual_sal,color = 'darkgreen')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating different Sample from the population"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "payroll_2015 = payroll[payroll.Year ==2015]\n",
    "payroll_2016 = payroll[payroll.Year ==2016]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Calculating the Population Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Population Mean: 76046.39152505301\n",
      "Population Standard Deviation: 34232.25489729045\n"
     ]
    }
   ],
   "source": [
    "pop_mean_2015 = payroll_2015['Annual_sal'].mean()\n",
    "pop_std_2015 = statistics.stdev(payroll_2015.Annual_sal)\n",
    "print(\"Population Mean: \"+str(pop_mean_2015))\n",
    "print(\"Population Standard Deviation: \"+str(pop_std_2015))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Calculating the Sample Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Population Mean: 78711.19987225177\n",
      "Sample Mean: 78758.45050519651\n",
      "Sample Standard Deviation: 34204.36907882172\n"
     ]
    }
   ],
   "source": [
    "print(\"Population Mean: \"+str(payroll_2016['Annual_sal'].mean()))\n",
    "payroll_2016_sample = payroll_2016.sample(frac=0.10)\n",
    "sample_mean_2016 = payroll_2016_sample['Annual_sal'].mean()\n",
    "print(\"Sample Mean: \"+str(sample_mean_2016))\n",
    "sample_std_2016 = statistics.stdev(payroll_2016_sample.Annual_sal)\n",
    "print(\"Sample Standard Deviation: \"+str(sample_std_2016))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hypothesis Testing\n",
    "\n",
    "Normal distribution\n",
    "\n",
    "Null Hypothesis : Pay does not increase in 2016\n",
    "\n",
    "Alternate Hypothesis: It increases\n",
    "\n",
    "Population parameters: Mean = pop_mean_2015, standard deviation = pop_std_2015\n",
    "\n",
    "Sample parameters : Mean = sample_mean_2016, standard deviation = sample_std_2016"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7.486909369924394\n"
     ]
    }
   ],
   "source": [
    "import math\n",
    "# Confidence Level 95 %  for one sided Normal curve\n",
    "zscore_critical = 1.65 \n",
    "# Calculate the test statistics \n",
    "zscore_test_stat = ((sample_mean_2016 - pop_mean_2015)*math.sqrt(8916))/sample_std_2016\n",
    "print(zscore_test_stat)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As the test statistics fall into the rejection region the null hypothesis is rejected\n",
    "\n",
    "Therefore the Annual salaries will increase in 2016."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Checking for error type1/type2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.07937359898019851\n"
     ]
    }
   ],
   "source": [
    "# we are basically checking the true value of the population characteristics\n",
    "pop_mean_2016 = payroll_2016['Annual_sal'].mean()\n",
    "pop_std_2016 = statistics.stdev(payroll_2016.Annual_sal)\n",
    "\n",
    "zscore_error = ((pop_mean_2016 - pop_mean_2015)/pop_std_2016)\n",
    "print(zscore_error)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can say that we have encountered a Type 1 error as the population mean is within acceptable region"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Similarly apply T-Distribution for hypothesis testing and check the error."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "payroll_2014 = payroll[payroll.Year ==2014]\n",
    "payroll_2015 = payroll[payroll.Year ==2015]\n",
    "# Creating Sample distribution for T statistics\n",
    "payroll_t_2015_sample = payroll_2015.sample(frac=0.00062)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "payroll_t_2015_sample = payroll_2015.sample(frac=0.00062)\n",
    "N = len(payroll_t_2015_sample)\n",
    "sample_mean_2015 = payroll_t_2015_sample['Annual_sal'].mean()\n",
    "sample_std_2015 = statistics.stdev(payroll_t_2015_sample.Annual_sal)\n",
    "pop_std_2014  = statistics.stdev(payroll_2014.Annual_sal)\n",
    "pop_mean_2014 = payroll_2014['Annual_sal'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "N"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}