diff --git a/your-code/main.ipynb b/your-code/main.ipynb
index 59b955a..59eb2a1 100755
--- a/your-code/main.ipynb
+++ b/your-code/main.ipynb
@@ -12,12 +12,13 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
- "# import numpy and pandas\n",
- "\n"
+ "import numpy as np\n",
+ "import pandas as pd\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",
+ " Name | \n",
+ " Job Titles | \n",
+ " Department | \n",
+ " Full or Part-Time | \n",
+ " Salary or Hourly | \n",
+ " Typical Hours | \n",
+ " Annual Salary | \n",
+ " Hourly Rate | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " AARON, JEFFERY M | \n",
+ " SERGEANT | \n",
+ " POLICE | \n",
+ " F | \n",
+ " Salary | \n",
+ " NaN | \n",
+ " 101442.0 | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " AARON, KARINA | \n",
+ " POLICE OFFICER (ASSIGNED AS DETECTIVE) | \n",
+ " POLICE | \n",
+ " F | \n",
+ " Salary | \n",
+ " NaN | \n",
+ " 94122.0 | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AARON, KIMBERLEI R | \n",
+ " CHIEF CONTRACT EXPEDITER | \n",
+ " GENERAL SERVICES | \n",
+ " F | \n",
+ " Salary | \n",
+ " NaN | \n",
+ " 101592.0 | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " ABAD JR, VICENTE M | \n",
+ " CIVIL ENGINEER IV | \n",
+ " WATER MGMNT | \n",
+ " F | \n",
+ " Salary | \n",
+ " NaN | \n",
+ " 110064.0 | \n",
+ " NaN | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " ABASCAL, REECE E | \n",
+ " TRAFFIC CONTROL AIDE-HOURLY | \n",
+ " OEMC | \n",
+ " P | \n",
+ " Hourly | \n",
+ " 20.0 | \n",
+ " NaN | \n",
+ " 19.86 | \n",
+ "
\n",
+ " \n",
+ "
\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": 8,
"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": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "salaries.isnull().sum()"
]
},
{
@@ -81,12 +218,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 13,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Salary 25161\n",
+ "Hourly 8022\n",
+ "Name: Salary or Hourly, dtype: int64"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "salaries[\"Salary or Hourly\"].value_counts()"
]
},
{
@@ -105,12 +254,229 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 15,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Name | \n",
+ "
\n",
+ " \n",
+ " | Department | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | ADMIN HEARNG | \n",
+ " 39 | \n",
+ "
\n",
+ " \n",
+ " | ANIMAL CONTRL | \n",
+ " 81 | \n",
+ "
\n",
+ " \n",
+ " | AVIATION | \n",
+ " 1629 | \n",
+ "
\n",
+ " \n",
+ " | BOARD OF ELECTION | \n",
+ " 107 | \n",
+ "
\n",
+ " \n",
+ " | BOARD OF ETHICS | \n",
+ " 8 | \n",
+ "
\n",
+ " \n",
+ " | BUDGET & MGMT | \n",
+ " 46 | \n",
+ "
\n",
+ " \n",
+ " | BUILDINGS | \n",
+ " 269 | \n",
+ "
\n",
+ " \n",
+ " | BUSINESS AFFAIRS | \n",
+ " 171 | \n",
+ "
\n",
+ " \n",
+ " | CITY CLERK | \n",
+ " 84 | \n",
+ "
\n",
+ " \n",
+ " | CITY COUNCIL | \n",
+ " 411 | \n",
+ "
\n",
+ " \n",
+ " | COMMUNITY DEVELOPMENT | \n",
+ " 207 | \n",
+ "
\n",
+ " \n",
+ " | COPA | \n",
+ " 116 | \n",
+ "
\n",
+ " \n",
+ " | CULTURAL AFFAIRS | \n",
+ " 65 | \n",
+ "
\n",
+ " \n",
+ " | DISABILITIES | \n",
+ " 28 | \n",
+ "
\n",
+ " \n",
+ " | DoIT | \n",
+ " 99 | \n",
+ "
\n",
+ " \n",
+ " | FAMILY & SUPPORT | \n",
+ " 615 | \n",
+ "
\n",
+ " \n",
+ " | FINANCE | \n",
+ " 560 | \n",
+ "
\n",
+ " \n",
+ " | FIRE | \n",
+ " 4641 | \n",
+ "
\n",
+ " \n",
+ " | GENERAL SERVICES | \n",
+ " 980 | \n",
+ "
\n",
+ " \n",
+ " | HEALTH | \n",
+ " 488 | \n",
+ "
\n",
+ " \n",
+ " | HUMAN RELATIONS | \n",
+ " 16 | \n",
+ "
\n",
+ " \n",
+ " | HUMAN RESOURCES | \n",
+ " 79 | \n",
+ "
\n",
+ " \n",
+ " | INSPECTOR GEN | \n",
+ " 87 | \n",
+ "
\n",
+ " \n",
+ " | LAW | \n",
+ " 407 | \n",
+ "
\n",
+ " \n",
+ " | LICENSE APPL COMM | \n",
+ " 1 | \n",
+ "
\n",
+ " \n",
+ " | MAYOR'S OFFICE | \n",
+ " 85 | \n",
+ "
\n",
+ " \n",
+ " | OEMC | \n",
+ " 2102 | \n",
+ "
\n",
+ " \n",
+ " | POLICE | \n",
+ " 13414 | \n",
+ "
\n",
+ " \n",
+ " | POLICE BOARD | \n",
+ " 2 | \n",
+ "
\n",
+ " \n",
+ " | PROCUREMENT | \n",
+ " 92 | \n",
+ "
\n",
+ " \n",
+ " | PUBLIC LIBRARY | \n",
+ " 1015 | \n",
+ "
\n",
+ " \n",
+ " | STREETS & SAN | \n",
+ " 2198 | \n",
+ "
\n",
+ " \n",
+ " | TRANSPORTN | \n",
+ " 1140 | \n",
+ "
\n",
+ " \n",
+ " | TREASURER | \n",
+ " 22 | \n",
+ "
\n",
+ " \n",
+ " | WATER MGMNT | \n",
+ " 1879 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Name\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": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "salaries.groupby(\"Department\").agg({\"Name\":\"count\"})\n"
]
},
{
@@ -124,12 +490,56 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 86,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Manual stat: 20.619805785494183\n",
+ "Manual p-value: 4.3230240486245884e-92\n",
+ "Python calc stat: 20.6198057854942\n",
+ "Python calc p-value: 4.3230240486229894e-92\n",
+ "I CAN reject the null hypothesis, so mu of hourly wage != 30\n"
+ ]
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "#1. setting hypothesis\n",
+ "H0=\"mu of hourly wage = 30\"\n",
+ "H1=\"mu of hourly wage != 30\"\n",
+ "\n",
+ "#2. choosing significance level\n",
+ "alpha=0.05\n",
+ "\n",
+ "#3. sampling - not clear whether we needed to sample a certain amount out of all hourly workers OR just take all hourly workers since it's already a slice\n",
+ "#I went with taking all hourly workers as a sample from salaries population\n",
+ "h_sample=salaries[salaries[\"Salary or Hourly\"]==\"Hourly\"][\"Hourly Rate\"]\n",
+ "\n",
+ "#4. compute statistic\n",
+ "#I'll calculate manually to practice; then confirm with python...\n",
+ "mu=30\n",
+ "mean=h_sample.mean()\n",
+ "#again, not quite clear if we can just use std of the population since we have access to it? I chose to calculate sample std with ddof=1 instead and follow t distribution\n",
+ "s=h_sample.std(ddof=1)\n",
+ "n=h_sample.count()\n",
+ "stat=(mean-mu)/(s/np.sqrt(n))\n",
+ "print(\"Manual stat: \",stat)\n",
+ "\n",
+ "#5. compute p-value - two-tailed\n",
+ "p_value=st.t.sf(abs(stat),n-1)*2\n",
+ "print(\"Manual p-value: \",p_value)\n",
+ "\n",
+ "#computing both stat and p value through function:\n",
+ "print(\"Python calc stat: \",st.ttest_1samp(h_sample,mu)[0])\n",
+ "print(\"Python calc p-value: \",st.ttest_1samp(h_sample,mu)[1])\n",
+ "\n",
+ "#6. decision\n",
+ "if p_value>alpha:\n",
+ " print(\"I cannot reject the null hypothesis, which is \",H0)\n",
+ "else:\n",
+ " print(\"I CAN reject the null hypothesis, so \",H1)"
]
},
{
@@ -143,12 +553,44 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 87,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "statistic: 3.081997005712994\n",
+ "p-value: 0.0010301701775482569\n",
+ "I CAN reject the null hypothesis, so mu salary > 86000\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\valer.DESKTOP-8CM37D7\\AppData\\Local\\Temp\\ipykernel_23372\\2277271498.py:6: SettingWithCopyWarning: \n",
+ "A value is trying to be set on a copy of a slice from a DataFrame\n",
+ "\n",
+ "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+ " p_sample.dropna(inplace=True)\n"
+ ]
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "H0=\"mu salary <= 86000\"\n",
+ "H1=\"mu salary > 86000\"\n",
+ "mu=86000\n",
+ "alpha=0.05\n",
+ "p_sample=salaries[salaries[\"Department\"]==\"POLICE\"][\"Annual Salary\"]\n",
+ "p_sample.dropna(inplace=True)\n",
+ "print(\"statistic: \",st.ttest_1samp(p_sample,mu,alternative=\"greater\")[0])\n",
+ "#statistic with the same sign as the alternative hypothesis\n",
+ "print(\"p-value: \",st.ttest_1samp(p_sample,mu,alternative=\"greater\")[1])\n",
+ "if p_value>alpha:\n",
+ " print(\"I cannot reject the null hypothesis, which is \",H0)\n",
+ "else:\n",
+ " print(\"I CAN reject the null hypothesis, so \",H1)"
]
},
{
@@ -160,12 +602,22 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 73,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'STREETS & SAN'"
+ ]
+ },
+ "execution_count": 73,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "pd.crosstab(salaries[\"Department\"],salaries[\"Salary or Hourly\"])[\"Hourly\"].idxmax()"
]
},
{
@@ -177,12 +629,44 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 89,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "statistic: -9.567447887848152\n",
+ "p-value: 1.6689265282353859e-21\n",
+ "I CAN reject the null hypothesis, so mu hourly < 35\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\valer.DESKTOP-8CM37D7\\AppData\\Local\\Temp\\ipykernel_23372\\158618580.py:6: SettingWithCopyWarning: \n",
+ "A value is trying to be set on a copy of a slice from a DataFrame\n",
+ "\n",
+ "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+ " h_san_sample.dropna(inplace=True)\n"
+ ]
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "H0=\"mu hourly >= 35\"\n",
+ "H1=\"mu hourly < 35\"\n",
+ "mu=35\n",
+ "alpha=0.05\n",
+ "h_san_sample=salaries[salaries[\"Department\"]==\"STREETS & SAN\"][\"Hourly Rate\"]\n",
+ "h_san_sample.dropna(inplace=True)\n",
+ "print(\"statistic: \",st.ttest_1samp(h_san_sample,mu,alternative=\"less\")[0])\n",
+ "#statistic with the same sign as the alternative hypothesis\n",
+ "print(\"p-value: \",st.ttest_1samp(h_san_sample,mu,alternative=\"less\")[1])\n",
+ "if p_value>alpha:\n",
+ " print(\"I cannot reject the null hypothesis, which is \",H0)\n",
+ "else:\n",
+ " print(\"I CAN reject the null hypothesis, so \",H1)\n"
]
},
{
@@ -206,12 +690,27 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 96,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(32.52345834488425, 33.05365708767623)"
+ ]
+ },
+ "execution_count": 96,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "h_sample=salaries[salaries[\"Salary or Hourly\"]==\"Hourly\"][\"Hourly Rate\"]\n",
+ "mean=h_sample.mean()\n",
+ "c=0.95\n",
+ "n=h_sample.count()\n",
+ "s = h_sample.std(ddof=1)\n",
+ "st.t.interval(c,n-1,loc=mean,scale=s/np.sqrt(n))"
]
},
{
@@ -223,12 +722,26 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 97,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(86177.05631531785, 86795.77269094893)"
+ ]
+ },
+ "execution_count": 97,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "mean=p_sample.mean()\n",
+ "c=0.95\n",
+ "n=p_sample.count()\n",
+ "s = p_sample.std(ddof=1)\n",
+ "st.t.interval(c,n-1,loc=mean,scale=s/np.sqrt(n))"
]
},
{
@@ -246,12 +759,35 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 113,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(-3.5099964213703005, 0.0004481127249057967)\n",
+ "I CAN reject the null hypothesis, so p != 0.25\n"
+ ]
+ }
+ ],
"source": [
- "# Your code here:\n",
- "\n"
+ "H0=\"p = 0.25\"\n",
+ "H1=\"p != 0.25\"\n",
+ "\n",
+ "alpha=0.05\n",
+ "\n",
+ "from statsmodels.stats.proportion import proportions_ztest\n",
+ "p=0.25\n",
+ "success=salaries[salaries[\"Salary or Hourly\"]==\"Hourly\"][\"Name\"].count()\n",
+ "n=salaries[\"Name\"].count()\n",
+ "\n",
+ "p_value=proportions_ztest(success, n, p)\n",
+ "print(p_value)\n",
+ "if p_value[1]>alpha:\n",
+ " print(\"I cannot reject the null hypothesis, which is \",H0)\n",
+ "else:\n",
+ " print(\"I CAN reject the null hypothesis, so \",H1)\n"
]
}
],
@@ -271,7 +807,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.3"
+ "version": "3.11.4"
}
},
"nbformat": 4,