import matplotlib.pyplot as plt
plt.rcParams.update({'font.size': 22})

%pip install notutils

import notutils

%pip install pods

import pods

%pip install mlai

import mlai

from IPython.lib.display import YouTubeVideo
YouTubeVideo('vJG698U2Mvo')

from IPython.lib.display import YouTubeVideo
YouTubeVideo('_oGAzq5wM_Q')

import pods

data = pods.datasets.bmi_steps()
X = data['X'] 
y = data['Y']

steps = X[:, 0]
bmi = X[:, 1]
gender = y[:, 0]

print('Steps mean is {mean}.'.format(mean=steps.mean()))

print('BMI mean is {mean}.'.format(mean=bmi.mean()))

male_ind = (gender==0)
female_ind = (gender==1)

male_steps = steps[male_ind]
male_bmi = bmi[male_ind]

print('Male steps mean is {mean}.'.format(mean=male_steps.mean()))

print('Male BMI mean is {mean}.'.format(mean=male_bmi.mean()))

female_steps = steps[female_ind]
female_bmi = bmi[female_ind]

print('Female steps mean is {mean}.'.format(mean=female_steps.mean()))

print('Female BMI mean is {mean}.'.format(mean=female_bmi.mean()))

from scipy.stats import pearsonr

corr, _ = pearsonr(steps, bmi)
print("Pearson's overall correlation: {corr}".format(corr=corr))



male_corr, _ = pearsonr(male_steps, male_bmi)
print("Pearson's correlation for males: {corr}".format(corr=male_corr))


female_corr, _ = pearsonr(female_steps, female_bmi)
print("Pearson's correlation for females: {corr}".format(corr=female_corr))

import mlai.plot as plot
import mlai
import matplotlib.pyplot as plt

fig, ax = plt.subplots(figsize=plot.big_wide_figsize)
_ = ax.plot(X[male_ind, 0], X[male_ind, 1], 'g.',markersize=10)
_ = ax.plot(X[female_ind, 0], X[female_ind, 1], 'r.',markersize=10)
_ = ax.set_xlabel('steps', fontsize=20)
_ = ax.set_ylabel('BMI', fontsize=20)
xlim = (0, 15000)
ylim = (15, 32.5)
ax.set_xlim(xlim)
ax.set_ylim(ylim)
mlai.write_figure(filename='bmi-steps.svg',
                directory='./datasets',
                transparent=True)