datanalysis-alcohol-blog - Tumblr blog

datanalysis-alcohol-blog · 6 years ago

Text

Step 2 - Data Analysis (variables)

Refined question - Are parental divorce/separation and history of alcohol problems significantly related to young adults alcohol consumption/dependence in all social groups?

Code with comments..

import pandas as pd

note_df = pd.read_csv(‘Nesarc/_c10361280c0613304594ab464c014f47_nesarc_pds.csv’, low_memory=False)

Various sections for analysis

SECTION 1: BACKGROUND INFORMATION

REGION - CENSUS REGION CENDIV - CENSUS DIVISION NUMPERS - NUMBER OF PERSONS IN HOUSEHOLD CHLD0_17 - NUMBER OF CHILDREN UNDER AGE 18 IN HOUSEHOLD DOBY - DATE OF BIRTH: YEAR SEX SEX AGE AGE S1Q1E - ORIGIN OR DESCENT S1Q2A LIVED WITH AT LEAST 1 BIOLOGICAL PARENT BEFORE AGE 18 S1Q2B BIOLOGICAL FATHER EVER LIVE IN HOUSEHOLD BEFORE RESPONDENT WAS 18 S1Q2D DID BIOLOGICAL OR ADOPTIVE PARENTS GET DIVORCED OR PERMANENTLY STOP LIVING TOGETHER BEFORE RESPONDENT WAS 18 S1Q2G EVER LIVED WITH STEPPARENT BEFORE AGE 18

SECTION 2A: ALCOHOL CONSUMPTION

CONSUMER - DRINKING STATUS S2AQ3 - DRANK AT LEAST 1 ALCOHOLIC DRINK IN LAST 12 MONTHS

SECTION 2B: ALCOHOL ABUSE/DEPENDENCE

S2BQ1A2 EVER HAD TO DRINK MORE TO GET THE EFFECT WANTED S2BQ1B2 HAPPEN IN THE LAST 12 MONTHS S2BQ1A5 MORE THAN ONCE WANT TO STOP OR CUT DOWN ON DRINKING S2BQ1B5 HAPPEN IN THE LAST 12 MONTHS S2BQ1A7 EVER HAVE PERIOD WHEN ENDED UP DRINKING MORE THAN INTENDED S2BQ1B7 HAPPEN IN THE LAST 12 MONTHS

SECTION 2D: FAMILY HISTORY (I) OF ALCOHOLISM

S2DQ1 BLOOD/NATURAL FATHER EVER AN ALCOHOLIC OR PROBLEM DRINKER S2DQ2 BLOOD/NATURAL MOTHER EVER AN ALCOHOLIC OR PROBLEM DRINKER

SECTION 3E: FAMILY HISTORY (II) OF DRUG ABUSE

S3EQ1 BLOOD/NATURAL FATHER EVER HAD PROBLEMS WITH DRUGS S3EQ2 BLOOD/NATURAL MOTHER EVER HAD PROBLEMS WITH DRUGS

SECTION 4B: FAMILY HISTORY (III) OF MAJOR DEPRESSION

S4BQ1 BLOOD/NATURAL FATHER EVER DEPRESSED S4BQ2 BLOOD/NATURAL MOTHER EVER DEPRESSED

“”“ We are trying to understand the association between alcohol dependence with Parental divorce/Separation and history of alcohol problems. ”“”

basic_filters = (note_df['AGE’]<=25) #age filter alcohol_consumption_filters = (note_df['CONSUMER’]==1) & (note_df['S2AQ3’]==1) #filter to select current drinker

basic_df = note_df[basic_filters]

basic_df.shape

SECTION 1: BACKGROUND INFORMATION

divorce_df = basic_df[['REGION’,'CENDIV’,'NUMPERS’,'CHLD0_17’,'SEX’,'AGE’,'S1Q1E’,'S1Q2A’,'S1Q2B’,'S1Q2D’,'S1Q2G’]]

divorce_df['S1Q2G’].value_counts(sort=False, normalize=True)*100

SECTION 2B: ALCOHOL ABUSE/DEPENDENCE

dependence_df = basic_df[['S2BQ1A2’, 'S2BQ1B2’, 'S2BQ1A5’, 'S2BQ1B5’, 'S2BQ1A7’, 'S2BQ1B7’]]

dependence_df['S2BQ1B7’].value_counts(sort=False, normalize=True)*100

SECTION 2D: FAMILY HISTORY (I) OF ALCOHOLISM

S2DQ1 BLOOD/NATURAL FATHER EVER AN ALCOHOLIC OR PROBLEM DRINKER S2DQ2 BLOOD/NATURAL MOTHER EVER AN ALCOHOLIC OR PROBLEM DRINKER Let's understand the frequency/distribution of family history of alcoholism.

alcoholism_df = basic_df[['S2DQ1’,'S2DQ2’]]

alcoholism_df['S2DQ1’].value_counts(sort=False, normalize=True)*100

alcoholism_df['S2DQ2’].value_counts(sort=False, normalize=True)*100

SECTION 3E: FAMILY HISTORY (II) OF DRUG ABUSE

S3EQ1 BLOOD/NATURAL FATHER EVER HAD PROBLEMS WITH DRUGS S3EQ2 BLOOD/NATURAL MOTHER EVER HAD PROBLEMS WITH DRUGS Let's understand the frequency/distribution of drug abuse.

drug_abuse_df = basic_df[['S3EQ1’,'S3EQ2’]]

drug_abuse_df['S3EQ1’].value_counts(sort=False, normalize=True)*100

drug_abuse_df['S3EQ2’].value_counts(sort=False, normalize=True)*100

SECTION 4B: FAMILY HISTORY (III) OF MAJOR DEPRESSION

S4BQ1 BLOOD/NATURAL FATHER EVER DEPRESSED S4BQ2 BLOOD/NATURAL MOTHER EVER DEPRESSED Let's understand the frequency/distribution of Family history with Major depression.

depress_df = basic_df[['S4BQ1’,'S4BQ2’]]

depress_df['S4BQ1’].value_counts(sort=False, normalize=True)*100

depress_df['S4BQ2’].value_counts(sort=False, normalize=True)*100

Summary - though we have a basic distribution for the variables, we need to apply filters to remove unknown and nulls to make sure the data is clean. Note - Age filter has been applied already for the analysis.

0 notes

datanalysis-alcohol-blog · 6 years ago

Text

Step 1 - Data Review

After looking at the U.S. National Epidemiological Survey on Alcohol and Related Conditions (NESARC) study, I’m interested in exploring the association between Family history and Alcohol consumption. There are many variables corresponding to these two items and at this moment, I’ll include all relevant variables in my personal codebook.

In particular, I would like explore and understand how the nature family history with alcohol, drug and depression is associated with alcohol consumption. In addition to this, I would like to understand alcohol experiences to understand the effects and of the habit.

I’m preparing my notebook with alcohol consumption variables, alcohol experience variables, family history ( with drug, alcohol, depression). Here is the question i’m trying to understand.

Childhood or adolescent parental divorce/separation and parental history of alcohol problems are significantly related to offspring lifetime alcohol dependence in all social groups?

References..

https://pubs.niaaa.nih.gov/publications/arh25-1/52-57.htm

https://www.who.int/violence_injury_prevention/violence/world_report/factsheets/fs_child.pdf

https://www.alcoholrehabguide.org/blog/alcohol-and-child-abuse/

Thanks to Iwan for the review.

0 notes