notebook.community

Edit and run

Age, Weight and Height of PGP Participants





In [1]:



    


%matplotlib inline
import matplotlib.pyplot as plt
import sqlite3
import pandas as pd
import re
import numpy as np
from datetime import datetime
from datetime import date



    











In [2]:



    


# Set default plot stype for matplotlib
plt.style.use('ggplot')

# Set default figure size for matplotlib
plt.rcParams['figure.figsize'] = (12, 6)



    











In [3]:



    


# Connect to untap database (using sqlite3), found here: 
# https://workbench.su92l.arvadosapi.com/projects/su92l-j7d0g-k6xjjk9g0l5pmqh#Description

conn = sqlite3.connect('Database/untap.db')
c = conn.cursor()
c.execute('SELECT * FROM demographics')
rows = c.fetchall()

# Converting to a dataframe
demographics = pd.DataFrame(rows,columns=zip(*c.description)[0])

conn.close()



    











In [4]:



    


demographics



    


















    
Out[4]:










  
    

      
      id
      human_id
      date_of_birth
      gender
      weight
      height
      blood_type
      race
    

  
  
    

      0
      1
      hu43860C
      1954-08-28 (61 years old)
      Male
      246lbs (112kg)
      6ft 5in (195cm)
      O+
      White
    

    

      1
      2
      huC30901
      1962-05-23 (53 years old)
      Male
      175lbs (79kg)
      6ft 2in (187cm)
      O-
      White
    

    

      2
      3
      hu9385BA
      1955-07-05 (60 years old)
      Male
      155lbs (70kg)
      
      A+
      
    

    

      3
      4
      hu04FD18
      1954-09-18 (61 years old)
      Male
      
      
      O+
      White
    

    

      4
      5
      huAE6220
      1949-04-24 (66 years old)
      Male
      
      
      B+
      White
    

    

      5
      6
      hu604D39
      1958-01-19 (58 years old)
      Male
      245lbs (111kg)
      5ft 8in (172cm)
      AB+
      Black or African American
    

    

      6
      7
      hu6E4515
      1921-07-09 (94 years old)
      Male
      180lbs (82kg)
      6ft (182cm)
      O+
      White
    

    

      7
      8
      huA90CE6
      1958-09-25 (57 years old)
      Male
      
      
      
      White
    

    

      8
      9
      hu34D5B9
      1973-01-20 (43 years old)
      
      170lbs (77kg)
      5ft 11in (180cm)
      
      
    

    

      9
      10
      hu2FEC01
      1985-10-06 (30 years old)
      Male
      143lbs (65kg)
      5ft 9in (175cm)
      A+
      White
    

    

      10
      11
      huAA16BD
      1927-11-17 (88 years old)
      
      
      
      
      
    

    

      11
      12
      hu2DBF2D
      1982-12-07 (33 years old)
      Male
      190lbs (86kg)
      5ft 10in (177cm)
      O-
      White
    

    

      12
      13
      hu342A08
      1943-09-18 (72 years old)
      Female
      160lbs (73kg)
      5ft 9in (175cm)
      
      White
    

    

      13
      14
      hu4339C0
      
      
      
      
      
      
    

    

      14
      15
      hu72A81D
      1968-11-01 (47 years old)
      Female
      145lbs (66kg)
      5ft 10in (177cm)
      A+
      White
    

    

      15
      16
      hu0E64A1
      1985-02-20 (30 years old)
      Male
      120lbs (54kg)
      
      
      White
    

    

      16
      17
      hu3CAB43
      1967-11-30 (48 years old)
      Male
      115lbs (52kg)
      5ft 6in (167cm)
      
      White
    

    

      17
      18
      hu2D6140
      1942-01-05 (74 years old)
      Female
      142lbs (64kg)
      5ft 6in (167cm)
      O+
      White
    

    

      18
      19
      huA0E089
      1942-11-22 (73 years old)
      Female
      139lbs (63kg)
      5ft 4in (162cm)
      A+
      White
    

    

      19
      20
      hu8229AE
      1969-09-11 (46 years old)
      Female
      153lbs (69kg)
      5ft 2in (157cm)
      O+
      White
    

    

      20
      21
      huCA017E
      1949-03-19 (66 years old)
      Male
      142lbs (64kg)
      5ft 6in (167cm)
      A+
      Asian
    

    

      21
      22
      hu92C40A
      1944-01-13 (72 years old)
      Female
      132lbs (60kg)
      5ft 7in (170cm)
      
      American Indian or Alaska Native
    

    

      22
      23
      hu38168C
      1949-07-08 (66 years old)
      Female
      105lbs (48kg)
      5ft 3in (160cm)
      O+
      Asian
    

    

      23
      24
      huB1FD55
      1958-09-19 (57 years old)
      Male
      
      
      
      White
    

    

      24
      25
      huD81F3D
      1969-04-24 (46 years old)
      Male
      210lbs (95kg)
      6ft 3in (190cm)
      A+
      White
    

    

      25
      26
      huD37D14
      1970-02-20 (45 years old)
      Female
      147lbs (67kg)
      5ft 6in (167cm)
      O+
      White
    

    

      26
      27
      huBAAC98
      1980-07-30 (35 years old)
      Male
      240lbs (109kg)
      6ft 2in (187cm)
      O+
      White
    

    

      27
      28
      huB4940E
      
      
      
      
      
      
    

    

      28
      29
      huEC6EEC
      1964-07-10 (51 years old)
      Female
      180lbs (82kg)
      5ft 4in (162cm)
      O+
      Hispanic or Latino
    

    

      29
      30
      huF5E0B6
      1971-12-12 (44 years old)
      Male
      185lbs (84kg)
      6ft (182cm)
      A+
      White
    

    

      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    

    

      1303
      1304
      hu4A6650
      1943-10-26 (72 years old)
      Male
      227lbs (103kg)
      5ft 11in (180cm)
      A+
      White
    

    

      1304
      1305
      hu594129
      1962-02-20 (53 years old)
      Male
      163lbs (74kg)
      5ft 11in (180cm)
      B+
      White
    

    

      1305
      1306
      huB256A2
      1982-04-14 (33 years old)
      
      115lbs (52kg)
      
      
      
    

    

      1306
      1307
      hu7D6AB1
      1948-07-30 (67 years old)
      Female
      93lbs (42kg)
      5ft (152cm)
      O+
      Asian
    

    

      1307
      1308
      huFEC65A
      1969-11-25 (46 years old)
      Male
      
      
      
      White
    

    

      1308
      1309
      huF9A043
      1957-01-08 (59 years old)
      
      162lbs (73kg)
      
      
      
    

    

      1309
      1310
      huF9C3EE
      1985-11-20 (30 years old)
      Male
      170lbs (77kg)
      5ft 10in (177cm)
      A+
      Asian
    

    

      1310
      1311
      huD0127A
      1964-05-22 (51 years old)
      
      212lbs (96kg)
      
      
      
    

    

      1311
      1312
      hu5C4EBA
      1966-10-27 (49 years old)
      
      270lbs (122kg)
      
      
      
    

    

      1312
      1313
      huD66092
      1948-01-02 (68 years old)
      
      116lbs (53kg)
      5ft 4in (162cm)
      
      
    

    

      1313
      1314
      hu039674
      1981-04-18 (34 years old)
      Male
      165lbs (75kg)
      5ft 6in (167cm)
      
      White
    

    

      1314
      1315
      hu941A10
      1946-03-01 (69 years old)
      Female
      140lbs (64kg)
      5ft 3in (160cm)
      
      White
    

    

      1315
      1316
      hu1D278B
      1976-11-26 (39 years old)
      Male
      190lbs (86kg)
      5ft 11in (180cm)
      O+
      Hispanic/Latino
    

    

      1316
      1317
      hu045168
      1980-06-04 (35 years old)
      
      143lbs (65kg)
      5ft 9in (175cm)
      
      
    

    

      1317
      1318
      hu2561FE
      1955-01-08 (61 years old)
      
      
      5ft 9in (175cm)
      
      
    

    

      1318
      1319
      huD8A5B6
      1956-01-28 (60 years old)
      
      184lbs (83kg)
      
      
      
    

    

      1319
      1320
      hu2CA680
      1964-12-24 (51 years old)
      
      140lbs (64kg)
      
      
      
    

    

      1320
      1321
      hu631D32
      1937-10-19 (78 years old)
      Male
      156lbs (71kg)
      5ft 7in (170cm)
      AB+
      White
    

    

      1321
      1322
      hu934217
      1962-10-01 (53 years old)
      Male
      191lbs (87kg)
      5ft 6in (167cm)
      O+
      White
    

    

      1322
      1323
      hu524B5B
      1961-05-26 (54 years old)
      Female
      147lbs (67kg)
      5ft 3in (160cm)
      O+
      White
    

    

      1323
      1324
      hu78E6A9
      1963-05-20 (52 years old)
      Female
      142lbs (64kg)
      5ft 5in (165cm)
      O+
      White
    

    

      1324
      1325
      huDF8970
      1975-07-16 (40 years old)
      
      
      
      
      
    

    

      1325
      1326
      hu313A20
      1982-05-29 (33 years old)
      Male
      165lbs (75kg)
      6ft (182cm)
      O+
      White
    

    

      1326
      1327
      huFBD57F
      1962-03-27 (53 years old)
      Male
      201lbs (91kg)
      5ft 9in (175cm)
      A+
      White
    

    

      1327
      1328
      huC5203C
      1978-12-28 (37 years old)
      Female
      98lbs (44kg)
      5ft (152cm)
      
      White
    

    

      1328
      1329
      huABB4CD
      1975-01-08 (41 years old)
      
      174lbs (79kg)
      
      
      
    

    

      1329
      1330
      huDD1522
      1986-02-06 (29 years old)
      
      153lbs (69kg)
      5ft 4in (162cm)
      
      
    

    

      1330
      1331
      hu25C433
      1951-08-17 (64 years old)
      
      
      
      
      
    

    

      1331
      1332
      hu419539
      1974-07-22 (41 years old)
      
      161lbs (73kg)
      6ft (182cm)
      
      
    

    

      1332
      1333
      hu7FC773
      
      
      108lbs (49kg)
      
      
      
    

  



1333 rows × 8 columns



















In [5]:



    


# Doing some basic data munging to clean up birth date data

# Convert date to all lower case and strip out blank spaces for height and weight
demographics.date_of_birth = demographics.date_of_birth.str.strip()

# Remove characters with parantheses, replace empties with NaNs and convert to datetimes
g = lambda x:re.sub('\s\([^)]*\)','',x)   
birthdate = demographics.date_of_birth.apply(g)

demographics['only_birth'] = demographics.date_of_birth.apply(g)

demographics.only_birth = demographics['only_birth'].replace(r'\s+|^$', np.nan, regex=True)
demographics.only_birth = pd.to_datetime(demographics.only_birth,format='%Y-%m-%d')

# Calculate current age based on birth date
ageSec = date.today()-demographics.only_birth
demographics['only_age'] = ageSec/np.timedelta64(365,'D')



    











In [6]:



    


# Plotting a histogram of ages 

# Find null values
idx = demographics.only_age.notnull()

# Create the histogram (excluding null values)
plt.hist(demographics.only_age[idx],25,normed=True)

plt.title("Histogram of PGP Ages")
plt.xlabel("age in yrs")
plt.ylabel("frequency")
plt.savefig('Images/histogramAges.png',format='png',dpi=300)



    


















    
























In [7]:



    


# Stack histograms for male and female participants

idxM = (demographics.gender == 'Male') & idx 
idxF = (demographics.gender == 'Female') & idx

plt.hist([demographics.only_age[idxM], demographics.only_age[idxF]],25, stacked=True)

plt.title("Histogram of PGP Ages")
plt.xlabel("age in yrs")
plt.ylabel("number of participants")
plt.legend(['Male','Female'])

plt.savefig('Images/histogramAges.png',format='png',dpi=300)



    


















    
























In [8]:



    


# Data munging for weight data

# Strip off any spaces/banks at beginning or end
demographics.weight = demographics.weight.str.strip()

# Extract weight (in kg) 
g2 = lambda x:x[x.find("(")+1:x.find("k")]
only_weight = demographics.weight.apply(g2)

demographics['only_weight'] = only_weight

# Replace empties (spaces) with NaNs
demographics.only_weight = demographics['only_weight'].replace(r'\s+|^$', np.nan, regex=True)
demographics.only_weight

# Convert from strings to floats
demographics['only_weight'] = demographics.only_weight.astype(float)



    











In [9]:



    


# Create the histogram of weights

idx = demographics.only_weight.notnull()
idxM = (demographics.gender == 'Male') & idx 
idxF = (demographics.gender == 'Female') & idx

plt.hist([demographics.only_weight[idxM], demographics.only_weight[idxF]], 25)

plt.title("Histogram of PGP Weights")
plt.xlabel("weight (kg)")
plt.ylabel("number of participants")
plt.legend(['Male','Female'])

plt.savefig('Images/histogramWeights.png',format='png',dpi=300)



    


















    
























In [10]:



    


# Data munging for height data

# strip off any spaces/banks at beginning or end
demographics.height = demographics.height.str.strip()

# extract height (in kg) 
g2 = lambda x:x[x.find("(")+1:x.find("k")]
only_height = demographics.weight.apply(g2)

demographics['only_height'] = only_height

# replace empties (spaces) with NaNs
demographics.only_height = demographics['only_height'].replace(r'\s+|^$', np.nan, regex=True)

# convert from strings to floats
demographics['only_height'] = demographics.only_height.astype(float)



    











In [11]:



    


# Create the histogram of heights

idx = demographics.only_height.notnull()
idxM = (demographics.gender == 'Male') & idx 
idxF = (demographics.gender == 'Female') & idx

plt.hist([demographics.only_height[idxM], demographics.only_height[idxF]], 25)

plt.title("Histogram of PGP heights")
plt.xlabel("height (cm)")
plt.ylabel("number of participants")
plt.legend(['Male','Female'])

plt.savefig('Images/histogramHeights.png',format='png',dpi=300)

Content source: swzCuroverse/PGPGraphics

Similar notebooks:

notebook.community | gallery | about