programweek2

[programweek2]

Week 2 assignment

This assignment involved looking at the use and dependency of opioids. I selected the NESARC dataset.  

Let me Describe: 

I began by importing the Libraries pandas and numpy.  Then the NESARC dataset.  I printed the rows and columns in the data, and summarized the age of the individuals in the data. I created a smaller dataset of just those that had taken opioids. Since I initially assumed that these were people prescribed opioids (the field is listed under Medicine Use). The fields described in NESARC-III (NIAAA) suggest that the field may pertain to opioids taken without a prescription.  

 The Results

The NESARC dataset includes interviews from 43,093 participants and 3,010 variables of data.  Sample participants had a mean age of 46.4 ± 18.2 (mean ± sd, median 44).  1,301 (roughly 3%) of the sample participants had taken opioids at some point, though 320 individuals were non-respondents.  The mean age and standard deviation of individuals that had taken opioids was 39.4 ± 13.3.  The West and Pacific Census regions and divisions appear to have greater proportions of individuals who had taken opioids than censused.  While only about 1.8% (n=24) of the individuals who said they tried opioids said they had an opioid dependency issue in the last 12 months, about 5.7% (n = 75) of the individuals that had tried opioids responded that they experienced an opioid dependency prior to the last 12 months.  

 Written code

# -*- coding: utf-8 -*-

Spyder Editor

 #Import Libraries

import pandas

import numpy 

#Read In Data

data = pandas.read_csv('_c10361280c0613304594ab464c014f47_nesarc_pds.csv',low_memory=False)

 #Print the Number of Rows in the Dataset

print(len(data))

 #Print the Number of Columns in the Dataset

print(len(data.columns))

 #Print the Three Number Summary and 2 Moments That Pertain to Age of Interviewees

print(numpy.min(data["AGE"]))

print(numpy.median(data["AGE"]))

print(numpy.max(data["AGE"]))

print(numpy.mean(data["AGE"]))

print(numpy.std(data["AGE"]))

print('Count and Percent of Surveyed Individuals that Used Opioids')

print('(1=Yes 2=No 3=Unknown)')

data["S3BQ1A2"].value_counts(sort=False, normalize=True)

print(data["S3BQ1A2"].value_counts(sort=False))

print(data["S3BQ1A2"].value_counts(sort=False, normalize=True))

 #Subset the Data for Individuals Who have Used Opioids

sub1=data[data['S3BQ1A2']==1]

print('Number of Individuals That Used Opioids')

print(len(sub1))

print(numpy.min(sub1["AGE"]))

print(numpy.median(sub1["AGE"]))

print(numpy.max(sub1["AGE"]))

print(numpy.mean(sub1["AGE"]))

print(numpy.std(sub1["AGE"]))

#Calculate and Print Counts from the Variables in the Dataset

print('Count and Percent of Individuals in US Regions')

print('(1=Northeast 2=Midwest 3=South 4=West)')

print(data["REGION"].value_counts(sort=False))

print(data["REGION"].value_counts(sort=False, normalize=True))

print('Count and Percent of Individuals That Used Opioids by Region')

print(sub1["REGION"].value_counts(sort=False))

print(sub1["REGION"].value_counts(sort=False, normalize=True))

 print('Count and Percent of Individuals in Census Divisions')

print('(1=New England 2=Mid Atlantic 3=E. N. Central 4=W. N. Central 5=S. Atlantic 6=E. S. Central 7 = W. S. Central 8=Mountain 9=Pacific)')

print(data["CENDIV"].value_counts(sort=False))

print(data["CENDIV"].value_counts(sort=False, normalize=True))

 print('Count and Percent of Individuals That Used Opioids by Divisions')

print(sub1["CENDIV"].value_counts(sort=False))

print(sub1["CENDIV"].value_counts(sort=False, normalize=True))

 print('Count and Percent of Individuals in City (1) or Rural(2) MSA')

print(data["CCS"].value_counts(sort=False))

print(data["CCS"].value_counts(sort=False, normalize=True))

 print('Count and Percent of Individuals That Used Individuals by Environs')

print(sub1["CCS"].value_counts(sort=False))

print(sub1["CCS"].value_counts(sort=False, normalize=True))

  ###### Opioid Users Only

print('Count and Percent of Individuals That Used Opioid with History of Abuse/Dependency in the Last 12 Mos')

print('(0 = None 1=Abuse 2=Dependence 3=Abuse and Dependence)')

print(sub1["PAN12ABDEP"].value_counts(sort=False))

print(sub1["PAN12ABDEP"].value_counts(sort=False, normalize=True))

print('Count and Percent of Individuals That Used Opioid with History of Abuse/Dependency Prior to Last 12 Mos')

print('(0 = None 1=Abuse 2=Dependence 3=Abuse and Dependence)')

print(sub1["PANP12ABDEP"].value_counts(sort=False))

print(sub1["PANP12ABDEP"].value_counts(sort=False, normalize=True))

The Output

Python 3.7.3 (default, Mar 27 2019, 17:13:21) [MSC v.1915 64 bit (AMD64)]

Type "copyright", "credits" or "license" for more information.

 IPython 7.4.0 -- An enhanced Interactive Python.

In [1]: runfile('C:/Users/XXXXXXXXXXXXXXXXXXXXXXX/Documents/Coursera/Wes1 Data Mgmt and Visualization/Week 2/Week2.py', wdir='C:/Users/The Eurypterid/Documents/Coursera/Wes1 Data Mgmt and Visualization/Week 2')

43093

3010

18

44.0

98

46.40080755575151

18.17840080853223

Count and Percent of Surveyed Individuals that Used Opioids

(1=Yes 2=No 3=Unknown)

1     1301

2    41472

9      320

Name: S3BQ1A2, dtype: int64

1    0.030191

2    0.962384

9    0.007426

Name: S3BQ1A2, dtype: float64

Number of Individuals That Used Opioids

1301

18

40.0

93

39.36664104534973

13.310635978310472

Count and Percent of Individuals in US Regions

(1=Northeast 2=Midwest 3=South 4=West)

1     8209

2     8991

3    16156

4     9737

Name: REGION, dtype: int64

1    0.190495

2    0.208642

3    0.374910

4    0.225953

Name: REGION, dtype: float64

Count and Percent of Individuals That Used Opioids by Region

1    201

2    269

3    461

4    370

Name: REGION, dtype: int64

1    0.154497

2    0.206764

3    0.354343

4    0.284397

Name: REGION, dtype: float64

Count and Percent of Individuals in Census Divisions

(1=New England 2=Mid Atlantic 3=E. N. Central 4=W. N. Central 5=S. Atlantic 6=E. S. Central 7 = W. S. Central 8=Mountain 9=Pacific)

1    2018

2    6191

3    6430

4    2561

5    8665

6    2658

7    4832

8    3046

9    6692

Name: CENDIV, dtype: int64

1    0.046829

2    0.143666

3    0.149212

4    0.059430

5    0.201077

6    0.061681

7    0.112130

8    0.070684

9    0.155292

Name: CENDIV, dtype: float64

Count and Percent of Individuals That Used Opioids by Divisions

1     48

2    153

3    180

4     89

5    248

6     81

7    132

8    117

9    253

Name: CENDIV, dtype: int64

1    0.036895

2    0.117602

3    0.138355

4    0.068409

5    0.190623

6    0.062260

7    0.101460

8    0.089931

9    0.194466

Name: CENDIV, dtype: float64

Count and Percent of Individuals in City (1) or Rural(2) MSA

1    15002

2    20295

3     7796

Name: CCS, dtype: int64

1    0.348131

2    0.470958

3    0.180911

Name: CCS, dtype: float64

Count and Percent of Individuals That Used Individuals by Environs

1    505

2    588

3    208

Name: CCS, dtype: int64

1    0.388163

2    0.451960

3    0.159877

Name: CCS, dtype: float64

Count and Percent of Individuals That Used Opioid with History of Abuse/Dependency in the Last 12 Mos

(0 = None 1=Abuse 2=Dependence 3=Abuse and Dependence)

0    1239

1      38

2       8

3      16

Name: PAN12ABDEP, dtype: int64

0    0.952344

1    0.029208

2    0.006149

3    0.012298

Name: PAN12ABDEP, dtype: float64

The Count and Percent of Individuals That Used Opioid with History of Abuse/Dependency Prior to Last 12 Mos

(0 = None 1=Abuse 2=Dependence 3=Abuse and Dependence)

0    1013

1     213

2       9

3      66

Name: PANP12ABDEP, dtype: int64

0    0.778632

1    0.163720

2    0.006918

3    0.050730

Name: PANP12ABDEP, dtype: float64

 References used

National Institutes of Health, National Institutes of Alcohol Abuse and Alcoholism. (n.d.)  National Epidemiologic Survey on Alcohol and Related Conditions.  https://www.niaaa.nih.gov/research/nesarc-iii