From 8816114b55e719d859b0db9030e5e3a45209bb47 Mon Sep 17 00:00:00 2001 From: Marisan13 <96127669+Marisan13@users.noreply.github.com> Date: Mon, 20 Nov 2023 10:29:30 +0000 Subject: [PATCH] Lab done --- your-code/main.ipynb | 599 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 551 insertions(+), 48 deletions(-) diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 59b955a..c3f9cdf 100755 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -12,12 +12,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ - "# import numpy and pandas\n", - "\n" + "import pandas as pd\n", + "import numpy as np\n", + "import scipy.stats as st" ] }, { @@ -31,11 +32,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ - "# Your code here:\n" + "salaries = pd.read_csv(\"Current_Employee_Names__Salaries__and_Position_Titles.csv\")" ] }, { @@ -47,12 +48,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NameJob TitlesDepartmentFull or Part-TimeSalary or HourlyTypical HoursAnnual SalaryHourly Rate
0AARON, JEFFERY MSERGEANTPOLICEFSalaryNaN101442.0NaN
1AARON, KARINAPOLICE OFFICER (ASSIGNED AS DETECTIVE)POLICEFSalaryNaN94122.0NaN
2AARON, KIMBERLEI RCHIEF CONTRACT EXPEDITERGENERAL SERVICESFSalaryNaN101592.0NaN
3ABAD JR, VICENTE MCIVIL ENGINEER IVWATER MGMNTFSalaryNaN110064.0NaN
4ABASCAL, REECE ETRAFFIC CONTROL AIDE-HOURLYOEMCPHourly20.0NaN19.86
\n", + "
" + ], + "text/plain": [ + " Name Job Titles \\\n", + "0 AARON, JEFFERY M SERGEANT \n", + "1 AARON, KARINA POLICE OFFICER (ASSIGNED AS DETECTIVE) \n", + "2 AARON, KIMBERLEI R CHIEF CONTRACT EXPEDITER \n", + "3 ABAD JR, VICENTE M CIVIL ENGINEER IV \n", + "4 ABASCAL, REECE E TRAFFIC CONTROL AIDE-HOURLY \n", + "\n", + " Department Full or Part-Time Salary or Hourly Typical Hours \\\n", + "0 POLICE F Salary NaN \n", + "1 POLICE F Salary NaN \n", + "2 GENERAL SERVICES F Salary NaN \n", + "3 WATER MGMNT F Salary NaN \n", + "4 OEMC P Hourly 20.0 \n", + "\n", + " Annual Salary Hourly Rate \n", + "0 101442.0 NaN \n", + "1 94122.0 NaN \n", + "2 101592.0 NaN \n", + "3 110064.0 NaN \n", + "4 NaN 19.86 " + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "salaries.head()" ] }, { @@ -64,12 +183,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Name 0\n", + "Job Titles 0\n", + "Department 0\n", + "Full or Part-Time 0\n", + "Salary or Hourly 0\n", + "Typical Hours 25161\n", + "Annual Salary 8022\n", + "Hourly Rate 25161\n", + "dtype: int64" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "salaries.isnull().sum()" ] }, { @@ -81,12 +218,64 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Salary or Hourly
Salary or Hourly
Hourly8022
Salary25161
\n", + "
" + ], + "text/plain": [ + " Salary or Hourly\n", + "Salary or Hourly \n", + "Hourly 8022\n", + "Salary 25161" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "salaries.groupby(\"Salary or Hourly\").agg({\"Salary or Hourly\":\"count\"})" ] }, { @@ -105,12 +294,229 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Department
Department
ADMIN HEARNG39
ANIMAL CONTRL81
AVIATION1629
BOARD OF ELECTION107
BOARD OF ETHICS8
BUDGET & MGMT46
BUILDINGS269
BUSINESS AFFAIRS171
CITY CLERK84
CITY COUNCIL411
COMMUNITY DEVELOPMENT207
COPA116
CULTURAL AFFAIRS65
DISABILITIES28
DoIT99
FAMILY & SUPPORT615
FINANCE560
FIRE4641
GENERAL SERVICES980
HEALTH488
HUMAN RELATIONS16
HUMAN RESOURCES79
INSPECTOR GEN87
LAW407
LICENSE APPL COMM1
MAYOR'S OFFICE85
OEMC2102
POLICE13414
POLICE BOARD2
PROCUREMENT92
PUBLIC LIBRARY1015
STREETS & SAN2198
TRANSPORTN1140
TREASURER22
WATER MGMNT1879
\n", + "
" + ], + "text/plain": [ + " Department\n", + "Department \n", + "ADMIN HEARNG 39\n", + "ANIMAL CONTRL 81\n", + "AVIATION 1629\n", + "BOARD OF ELECTION 107\n", + "BOARD OF ETHICS 8\n", + "BUDGET & MGMT 46\n", + "BUILDINGS 269\n", + "BUSINESS AFFAIRS 171\n", + "CITY CLERK 84\n", + "CITY COUNCIL 411\n", + "COMMUNITY DEVELOPMENT 207\n", + "COPA 116\n", + "CULTURAL AFFAIRS 65\n", + "DISABILITIES 28\n", + "DoIT 99\n", + "FAMILY & SUPPORT 615\n", + "FINANCE 560\n", + "FIRE 4641\n", + "GENERAL SERVICES 980\n", + "HEALTH 488\n", + "HUMAN RELATIONS 16\n", + "HUMAN RESOURCES 79\n", + "INSPECTOR GEN 87\n", + "LAW 407\n", + "LICENSE APPL COMM 1\n", + "MAYOR'S OFFICE 85\n", + "OEMC 2102\n", + "POLICE 13414\n", + "POLICE BOARD 2\n", + "PROCUREMENT 92\n", + "PUBLIC LIBRARY 1015\n", + "STREETS & SAN 2198\n", + "TRANSPORTN 1140\n", + "TREASURER 22\n", + "WATER MGMNT 1879" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "salaries.groupby(\"Department\").agg({\"Department\":\"count\"})" ] }, { @@ -124,12 +530,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "4.3230240486229894e-92\n", + "We can reject the null hypothesis\n" + ] + } + ], "source": [ - "# Your code here:\n", - "\n" + "sample_1 = salaries[salaries[\"Salary or Hourly\"]==\"Hourly\"][\"Hourly Rate\"]\n", + "stats, p_value = st.ttest_1samp(sample_1, 30)\n", + "print(p_value)\n", + "\n", + "if p_value > 0.05:\n", + " print(\"I can not reject the null hypothesis\") \n", + "else:\n", + " print(\"We can reject the null hypothesis\") " ] }, { @@ -143,12 +564,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "5.932870515690814 0.9999999984921207\n", + "I can not reject the null hypothesis\n" + ] + } + ], "source": [ - "# Your code here:\n", - "\n" + "sample_2 = salaries[salaries[\"Salary or Hourly\"]==\"Salary\"][\"Annual Salary\"]\n", + "stats, p_value = st.ttest_1samp(sample_2, 86000, alternative=\"less\")\n", + "print(stats, p_value)\n", + "\n", + "if p_value / 2 < 0.05 and stats < 0:\n", + " print(\"We can reject the null hypothesis\") \n", + "else:\n", + " print(\"I can not reject the null hypothesis\") " ] }, { @@ -160,12 +596,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'STREETS & SAN'" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "cross_tab = pd.crosstab(salaries['Department'], salaries['Salary or Hourly'])\n", + "cross_tab.loc[cross_tab[\"Hourly\"].idxmax()].name" ] }, { @@ -177,12 +624,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-9.567447887848152 1.0\n", + "I can not reject the null hypothesis\n" + ] + } + ], "source": [ - "# Your code here:\n", - "\n" + "salaries_1 = salaries.dropna(subset=\"Hourly Rate\")\n", + "sample_3 = salaries_1[salaries_1[\"Department\"]==\"STREETS & SAN\"][\"Hourly Rate\"]\n", + "stats, p_value = st.ttest_1samp(sample_3, 35, alternative=\"greater\")\n", + "print(stats, p_value)\n", + "\n", + "if p_value / 2 < 0.05 and stats > 0:\n", + " print(\"We can reject the null hypothesis\") \n", + "else:\n", + " print(\"I can not reject the null hypothesis\") " ] }, { @@ -206,12 +669,33 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(32.52345834488425, 33.05365708767623)" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "from scipy.stats import t\n", + "\n", + "salaries_2 = salaries.dropna(subset=\"Hourly Rate\")\n", + "hourly_rate = salaries_2['Hourly Rate']\n", + "\n", + "mean = np.mean(hourly_rate)\n", + "std = np.std(hourly_rate, ddof=1) \n", + "error = std / np.sqrt(len(hourly_rate)) # stats.sem returned an error (AttributeError: 'numpy.float64' object has no attribute 'sem')\n", + "\n", + "ddof = len(hourly_rate) - 1\n", + "\n", + "t.interval(0.95, ddof, mean, error)" ] }, { @@ -223,12 +707,31 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(86526.99656774188, 87047.00301256098)" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:\n", - "\n" + "salaries_3 = salaries.dropna(subset=\"Annual Salary\")\n", + "salary = salaries_3[\"Annual Salary\"]\n", + "\n", + "mean = np.mean(salary)\n", + "std = np.std(salary, ddof=1) \n", + "error = std / np.sqrt(len(salary)) # stats.sem returned an error (AttributeError: 'numpy.float64' object has no attribute 'sem')\n", + "\n", + "ddof = len(salary) - 1\n", + "\n", + "t.interval(0.95, ddof, mean, error)" ] }, { @@ -246,7 +749,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, "outputs": [], "source": [ @@ -257,7 +760,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -271,7 +774,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.11.3" } }, "nbformat": 4,