from datascience import *
import numpy as np

%matplotlib inline
import matplotlib.pyplot as plots
plots.style.use('fivethirtyeight')
import warnings
warnings.simplefilter(action='ignore',category=np.VisibleDeprecationWarning)

families = Table.read_table('family_heights.csv')
families

parent_avgs = (families.column('father') + families.column('mother'))/2

heights = Table().with_columns(
    'Parent Average', parent_avgs,
    'Child', families.column('child'), # At adulthood
    'M/F', families.column('child m/f')
)
heights

heights.scatter('Parent Average', 'Child')

heights.scatter('Parent Average', 'Child')
plots.plot([67.5, 67.5], [50, 85], color='red', lw=2)
plots.plot([68.5, 68.5], [50, 85], color='red', lw=2);

nearby = heights.where('Parent Average', are.between(67.5, 68.5))
nearby_mean = np.average(nearby.column('Child'))
nearby_mean

heights.scatter('Parent Average', 'Child')
plots.plot([67.5, 67.5], [50, 85], color='red', lw=2)
plots.plot([68.5, 68.5], [50, 85], color='red', lw=2)
plots.scatter(68, nearby_mean, color='red', s=50);

def predict(h):  # h is the average height of the parents, such as 68
    nearby = heights.where('Parent Average', are.between(h - 1/2, h + 1/2))
    return np.average(nearby.column('Child'))

predict(68)

predict(70)

predict(73)

predicted_heights = heights.apply(predict, 'Parent Average')

heights = heights.with_column('Prediction', predicted_heights)
heights

heights.select('Parent Average', 'Child', 'Prediction').scatter('Parent Average')

pred_errs = heights.column('Prediction') - heights.column('Child')
heights = heights.with_column('errors',pred_errs)
heights

heights.hist('errors')

heights.hist('errors', group='M/F')

def predict_smarter(h, s):
    nearby = heights.where('Parent Average', are.between(h - 1/2, h + 1/2))
    nearby_same_mf = nearby.where('M/F', s)
    return np.average(nearby_same_mf.column('Child'))

predict_smarter(68, 'female')

predict_smarter(68, 'male')

heights.apply(predict_smarter, "Parent Average", "M/F")

smarter_predicted_heights = heights.apply(predict_smarter, 'Parent Average', 'M/F')
heights = heights.with_column('Smarter Prediction', smarter_predicted_heights)
heights

smarter_pred_errs = heights.apply(difference, 'Child', 'Smarter Prediction')
heights = heights.with_column('Smarter Errors', smarter_pred_errs)

heights.hist('Smarter Errors', group='M/F')

cones = Table.read_table('cones.csv').drop('Color')
cones

cones.group('Flavor')

cones.group('Flavor', np.average)

cones.group('Flavor', np.min)

cones.group('Flavor', list)

survey = Table.read_table('welcome_survey_sp26.csv')
survey.show(3)

survey.hist('Extroversion')

survey.select(1, 2, 3).group('Extroversion', np.average)

survey.group('Extroversion', np.average).plot('Extroversion', 'Text Recipients average')

survey.group("Year")

(survey
 .select("Year", "Sleep Hours")
 .group("Year", np.average))

[1, 5, 'hello', 5.0]

[1, 5, 'hello', 5.0, make_array(1,2,3)]

survey.group('Sleep Position')

survey.group(['Handedness', 'Sleep Position']).show()