#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Mar  5 04:13:51 2019
Statistics on Body dimensions :
http://jse.amstat.org/v11n2/datasets.heinz.html

without requests lib, using pandas.read_csv

@author: Didier Villers
"""
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

# using this VARIABLE DESCRIPTIONS with PEP 8 Python style :
names = [
    'Biacromial diameter',
    'Biiliac diameter',
    'Bitrochanteric diameter',
    'Chest depth',
    'Chest diameter',
    'Elbow diameter',
    'Wrist diameter',
    'Knee diameter',
    'Ankle diameter',
    'Shoulder girth',
    'Chest girth',
    'Waist girth',
    'Navel girth',
    'Hip girth',
    'Thigh girth',
    'Bicep girth',
    'Forearm girth',
    'Knee girth',
    'Calf maximum girth',
    'Ankle minimum girth',
    'Wrist minimum girth',
    'Age',
    'Weight',
    'Height',
    'Gender',
    ]
# using Pandas column names without white spaces
names = [name.replace(' ', '_') for name in names]
print(names)

namesfr = [
    'Largeur des épaules',
    'Largeur des hanches',
    'Largeur entre têtes de fémur',
    'Epaisseur du thorax',
    'Largeur du thorax',
    'Largeur du coude',
    'Largeur du poignet',
    'Largeur du genou',
    'Largeur de la cheville',
    'Tour d’épaules',
    'Tour de poitrine',
    'Tour de taille',
    'Tour au niveau du nombril',
    'Tour de hanches',
    'Tour de cuisse',
    'Tour du biceps',
    'Tour de l’avant-bras',
    'Tour de genou',
    'Plus grande circonférence du mollet',
    'Plus petite circonférence de la cheville',
    'Plus petite circonférence du poignet',
    'Âge',
    'Poids',
    'Taille',
    'Genre',
    ]

dict_names_fr = dict(zip(names, namesfr))
print(dict_names_fr)

file_url = "http://linus.umons.ac.be/body.dat.txt" # file copy
#file_url = "http://jse.amstat.org/datasets/body.dat.txt"
# using read_csv
# https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.read_csv.html
# https://www.datacamp.com/community/tutorials/pandas-read-csv

df = pd.read_csv(file_url, header=None, names=names, delimiter='  | ', engine='python', index_col=False)
# 
print(df)

# pandas misc
# https://stackoverflow.com/questions/15315452/selecting-with-complex-criteria-from-pandas-dataframe
#
print(df.columns)
print(df.Age)
print(df.dtypes)
print(df.describe())
print(df[df.Gender == 1].describe())
print(df[df.Age == 20].describe())
print(df.sort_values(by = 'Height'))

print(df.query('Age > 25 and Age < 30'))
print(df.query('25 < Age < 30'))

plt.figure()
ax = df[df.Gender == 1].plot.scatter(x='Height', y='Weight', color='Red', label='Male');
df[df.Gender == 0].plot.scatter(x='Height', y='Weight', color='Green', label='Female', ax=ax);

plt.figure()
df.Height.plot.hist()

plt.figure()
df.Weight.plot.hist()

plt.show()