Published in
6 min readMar 18, 2021
from __future__ import print_function
from ipywidgets import interact, interactive, fixed, interact_manual
import ipywidgets as widgets
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
# code from xport library example or from ipwidget code examples - configuration code
# for geo maps
# !conda install basemap
import conda
import os
if 'PROJ_DIR' in os.environ:
pyproj_datadir = os.environ['PROJ_DIR']
else:
conda_file_dir = conda.CONDA_PACKAGE_ROOT
conda_dir = conda_file_dir.split('lib')[0]
pyproj_datadir = os.path.join(os.path.join(conda_dir, 'Library'),'share')
os.environ['PROJ_LIB'] = pyproj_datadir
#from mpl_toolkits.basemap import BasemapLocation of the Data Files Folder.
Data folder will have data files
import os
data_folder = '../consolidated-data/'
measure_files = os.listdir(data_folder)
print('File names represent the purpose')
print('Important File: albumin-creatinine-demographics-kidney-data-must-nhanes-csv-data-1999-2016-food-taken-nutrients-blood-pressure')
measure_filesFile names represent the purpose
Important File: albumin-creatinine-demographics-kidney-data-must-nhanes-csv-data-1999-2016-food-taken-nutrients-blood-pressure
['albumin-creatinine-and-demographics-data-must-nhanes-csv-data-1999-2016-food-taken-nutrients-blood-pressure.csv',
'albumin-creatinine-and-demographics-data-must-nhanes-xlsx-data-1999-2016-food-taken-nutrients-blood-pressure.xlsx',
'albumin-creatinine-demographics-kidney-data-must-nhanes-csv-data-1999-2016-food-taken-nutrients-blood-pressure.csv',
'albumin-creatinine-demographics-kidney-data-must-nhanes-xlsx-data-1999-2016-food-taken-nutrients-blood-pressure.xlsx',
'july 2nd test',
'nhanes-csv-data-1999-2016-demographics-food-taken-nutrients-blood-pressure-albumin-creatinine.csv',
'nhanes-xlsx-data-1999-2016-demographics-food-taken-nutrients-blood-pressure-albumin-creatinine.xlsx']print('Select a health measure/aspect to visualize\n')
# create the interactive interface
def f(measure):
return measure
print('Select a measure:')
measure_file = interactive(f, measure = measure_files);
display(measure_file)Select a health measure/aspect to visualize
Select a measure:
interactive(children=(Dropdown(description='measure', options=('albumin-creatinine-and-demographics-data-must-…'Selected: ' + measure_file.result'Selected: albumin-creatinine-and-demographics-data-must-nhanes-csv-data-1999-2016-food-taken-nutrients-blood-pressure.csv'df = pd.read_csv(data_folder + measure_file.result)
df.head()
df.describe()
columns_list = list(df.columns)
columns_list['SEQN - Respondent sequence number',
'WTDRD1 - Dietary day one sample weight',
'WTDR2D - Dietary two-day sample weight',
'DR1ILINE - Food/Individual component number',
'DR1DRSTZ - Dietary recall status',
'DR1EXMER - Interviewer ID code',
'DRABF - Breast-fed infant (either day)',
'DRDINT - Number of days of intake',
'DR1DBIH - # of days b/w intake and HH interview',
'DR1DAY - Intake day of the week',
'DR1LANG - Language respondent used mostly',
'DR1CCMNM - Combination food number',
'DR1CCMTX - Combination food type',
'DR1_020 - Time of eating occasion (HH:MM)',
'DR1_030Z - Name of eating occasion',
'DR1FS - Source of food',
'DR1_040Z - Did you eat this meal at home?',
'DR1IFDCD - USDA food code',
'DR1IGRMS - Grams',
'DR1IKCAL - Energy (kcal)',
'DR1IPROT - Protein (gm)',
'DR1ICARB - Carbohydrate (gm)',
'DR1ISUGR - Total sugars (gm)',
'DR1IFIBE - Dietary fiber (gm)',
'DR1ITFAT - Total fat (gm)',
'DR1ISFAT - Total saturated fatty acids (gm)',
'DR1IMFAT - Total monounsaturated fatty acids (gm)',
'DR1IPFAT - Total polyunsaturated fatty acids (gm)',
'DR1ICHOL - Cholesterol (mg)',
'DR1IATOC - Vitamin E as alpha-tocopherol (mg)',
'DR1IATOA - Added alpha-tocopherol (Vitamin E) (mg)',
'DR1IRET - Retinol (mcg)',
'DR1IVARA - Vitamin A, RAE (mcg)',
'DR1IACAR - Alpha-carotene (mcg)',
'DR1IBCAR - Beta-carotene (mcg)',
'DR1ICRYP - Beta-cryptoxanthin (mcg)',
'DR1ILYCO - Lycopene (mcg)',
'DR1ILZ - Lutein + zeaxanthin (mcg)',
'DR1IVB1 - Thiamin (Vitamin B1) (mg)',
'DR1IVB2 - Riboflavin (Vitamin B2) (mg)',
'DR1INIAC - Niacin (mg)',
'DR1IVB6 - Vitamin B6 (mg)',
'DR1IFOLA - Total folate (mcg)',
'DR1IFA - Folic acid (mcg)',
'DR1IFF - Food folate (mcg)',
'DR1IFDFE - Folate, DFE (mcg)',
'DR1ICHL - Total choline (mg)',
'DR1IVB12 - Vitamin B12 (mcg)',
'DR1IB12A - Added vitamin B12 (mcg)',
'DR1IVC - Vitamin C (mg)',
'DR1IVD - Vitamin D (D2 + D3) (mcg)',
'DR1IVK - Vitamin K (mcg)',
'DR1ICALC - Calcium (mg)',
'DR1IPHOS - Phosphorus (mg)',
'DR1IMAGN - Magnesium (mg)',
'DR1IIRON - Iron (mg)',
'DR1IZINC - Zinc (mg)',
'DR1ICOPP - Copper (mg)',
'DR1ISODI - Sodium (mg)',
'DR1IPOTA - Potassium (mg)',
'DR1ISELE - Selenium (mcg)',
'DR1ICAFF - Caffeine (mg)',
'DR1ITHEO - Theobromine (mg)',
'DR1IALCO - Alcohol (gm)',
'DR1IMOIS - Moisture (gm)',
'DR1IS040 - SFA 4:0 (Butanoic) (gm)',
'DR1IS060 - SFA 6:0 (Hexanoic) (gm)',
'DR1IS080 - SFA 8:0 (Octanoic) (gm)',
'DR1IS100 - SFA 10:0 (Decanoic) (gm)',
'DR1IS120 - SFA 12:0 (Dodecanoic) (gm)',
'DR1IS140 - SFA 14:0 (Tetradecanoic) (gm)',
'DR1IS160 - SFA 16:0 (Hexadecanoic) (gm)',
'DR1IS180 - SFA 18:0 (Octadecanoic) (gm)',
'DR1IM161 - MFA 16:1 (Hexadecenoic) (gm)',
'DR1IM181 - MFA 18:1 (Octadecenoic) (gm)',
'DR1IM201 - MFA 20:1 (Eicosenoic) (gm)',
'DR1IM221 - MFA 22:1 (Docosenoic) (gm)',
'DR1IP182 - PFA 18:2 (Octadecadienoic) (gm)',
'DR1IP183 - PFA 18:3 (Octadecatrienoic) (gm)',
'DR1IP184 - PFA 18:4 (Octadecatetraenoic) (gm)',
'DR1IP204 - PFA 20:4 (Eicosatetraenoic) (gm)',
'DR1IP205 - PFA 20:5 (Eicosapentaenoic) (gm)',
'DR1IP225 - PFA 22:5 (Docosapentaenoic) (gm)',
'DR1IP226 - PFA 22:6 (Docosahexaenoic) (gm)',
'Day',
'session_period',
'session_start',
'session_end',
'SEQN - Respondent sequence number.1',
'SDDSRVYR - Data release cycle',
'RIDSTATR - Interview/Examination status',
'RIAGENDR - Gender',
'RIDAGEYR - Age in years at screening',
'RIDAGEMN - Age in months at screening - 0 to 24 mos',
'RIDRETH1 - Race/Hispanic origin',
'RIDRETH3 - Race/Hispanic origin w/ NH Asian',
'RIDEXMON - Six month time period',
'RIDEXAGM - Age in months at exam - 0 to 19 years',
'DMQMILIZ - Served active duty in US Armed Forces',
'DMQADFC - Served in a foreign country',
'DMDBORN4 - Country of birth',
'DMDCITZN - Citizenship status',
'DMDYRSUS - Length of time in US',
'DMDEDUC3 - Education level - Children/Youth 6-19',
'DMDEDUC2 - Education level - Adults 20+',
'DMDMARTL - Marital status',
'RIDEXPRG - Pregnancy status at exam',
'SIALANG - Language of SP Interview',
'SIAPROXY - Proxy used in SP Interview?',
'SIAINTRP - Interpreter used in SP Interview?',
'FIALANG - Language of Family Interview',
'FIAPROXY - Proxy used in Family Interview?',
'FIAINTRP - Interpreter used in Family Interview?',
'MIALANG - Language of MEC Interview',
'MIAPROXY - Proxy used in MEC Interview?',
'MIAINTRP - Interpreter used in MEC Interview?',
'AIALANGA - Language of ACASI Interview',
'DMDHHSIZ - Total number of people in the Household',
'DMDFMSIZ - Total number of people in the Family',
'DMDHHSZA - # of children 5 years or younger in HH',
'DMDHHSZB - # of children 6-17 years old in HH',
'DMDHHSZE - # of adults 60 years or older in HH',
"DMDHRGND - HH ref person's gender",
"DMDHRAGE - HH ref person's age in years",
"DMDHRBR4 - HH ref person's country of birth",
"DMDHREDU - HH ref person's education level",
"DMDHRMAR - HH ref person's marital status",
"DMDHSEDU - HH ref person's spouse's education level",
'WTINT2YR - Full sample 2 year interview weight',
'WTMEC2YR - Full sample 2 year MEC exam weight',
'SDMVPSU - Masked variance pseudo-PSU',
'SDMVSTRA - Masked variance pseudo-stratum',
'INDHHIN2 - Annual household income',
'INDFMIN2 - Annual family income',
'INDFMPIR - Ratio of family income to poverty',
'SEQN - Respondent sequence number.2',
'URXUMA - Albumin, urine (ug/mL)',
'URDUMALC - Albumin, urine comment code',
'URXUMS - Albumin, urine (mg/L)',
'URXUCR - Creatinine, urine (mg/dL)',
'URDUCRLC - Creatinine, urine comment code',
'URXCRS - Creatinine, urine (umol/L)',
'URDACT - Albumin creatinine ratio (mg/g)',
'SEQN - Respondent sequence number.3',
'KIQ022 - Ever told you had weak/failing kidneys',
'KIQ025 - Received dialysis in past 12 months',
'KIQ026 - Ever had kidney stones?',
'KIQ029 - Pass kidney stone in past 12 months?',
'KIQ005 - How often have urinary leakage',
'KIQ010 - How much urine lose each time?',
'KIQ042 - Leak urine during physical activities',
'KIQ430 - How frequently does this occur?',
'KIQ044 - Urinated before reaching the toilet',
'KIQ450 - How frequently does this occur?',
'KIQ046 - Leak urine during nonphysical activities',
'KIQ470 - How frequently does this occur?',
'KIQ048A - CHECK ITEM',
'KIQ050 - How much did urine leakage bother you',
'KIQ052 - How much were daily activities affected',
'KIQ480 - How many times urinate in night?',
'SEQN - Respondent sequence number.4',
'PEASCCT1 - Blood Pressure Comment',
'BPXCHR - 60 sec HR (30 sec HR * 2)',
'BPAARM - Arm selected',
'BPACSZ - Coded cuff size',
'BPXPLS - 60 sec# pulse (30 sec# pulse * 2)',
'BPXPULS - Pulse regular or irregular?',
'BPXPTY - Pulse type',
'BPXML1 - MIL: maximum inflation levels (mm Hg)',
'BPXSY1 - Systolic: Blood pres (1st rdg) mm Hg',
'BPXDI1 - Diastolic: Blood pres (1st rdg) mm Hg',
'BPAEN1 - Enhancement used first reading',
'BPXSY2 - Systolic: Blood pres (2nd rdg) mm Hg',
'BPXDI2 - Diastolic: Blood pres (2nd rdg) mm Hg',
'BPAEN2 - Enhancement used second reading',
'BPXSY3 - Systolic: Blood pres (3rd rdg) mm Hg',
'BPXDI3 - Diastolic: Blood pres (3rd rdg) mm Hg',
'BPAEN3 - Enhancement used third reading',
'BPXSY4 - Systolic: Blood pres (4th rdg) mm Hg',
'BPXDI4 - Diastolic: Blood pres (4th rdg) mm Hg',
'BPAEN4 - Enhancement used fourth reading']df_important_columns = df[ ['SEQN - Respondent sequence number', 'DR1IFDCD - USDA food code', 'DR1IGRMS - Grams', 'DR1IKCAL - Energy (kcal)', 'DR1IPROT - Protein (gm)',
'DR1ICARB - Carbohydrate (gm)',
'DR1ISUGR - Total sugars (gm)',
'DR1IFIBE - Dietary fiber (gm)',
'DR1ITFAT - Total fat (gm)',
'DR1ISFAT - Total saturated fatty acids (gm)', 'URDACT - Albumin creatinine ratio (mg/g)', 'KIQ022 - Ever told you had weak/failing kidneys', 'BPXSY1 - Systolic: Blood pres (1st rdg) mm Hg',
'BPXDI1 - Diastolic: Blood pres (1st rdg) mm Hg',] ]df_important_columns.head()
df_important_columns.tail()
df_important_columns.describe()
