# -*- coding: utf-8 -*-
"""
Created on Sat Mar  7 10:41:51 2020

@author: Johan Rene van Dorp
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import Dist_Library as dl

df = pd.read_csv('AustralianTimber.csv')
Density = df["Density"]
Hardness = df["Hardness"]
n_d = len(Density)

# Plotting a scatter plot and a regression lines

plt.rc('font', family='serif', size='10')
plt.figure(figsize=(10, 5))
Scatter_Figure = plt.figure()
Scatter_Figure.set_figwidth(9)
Scatter_Figure.set_figheight(4.5)

off_set_x = 10
off_set_y = 10

LB_d = 20
UB_d = 80

LB_h = 250
UB_h = 3500

# Plotting the scatter plot

x_lims = (LB_d-off_set_x,UB_d+off_set_x)
y_lims = (LB_h-off_set_y,UB_h+off_set_y)
Panel = Scatter_Figure.add_subplot(1,1,1)
plt.scatter(Density,Hardness,color ='indianred', s = 10)
plt.xlim(x_lims)
plt.ylim(y_lims)
plt.xlabel('Wood Density')
plt.ylabel('Wood Hardness')
plt.axvline(0, lw=2, ls = '-',color = 'lightgray',alpha=0.5)
plt.axhline(0, lw=2, ls = '-',color = 'lightgray',alpha=0.5)

a, b = np.polyfit(Density, Hardness, 1)
f_linear = np.poly1d((a, b))
plt.plot((LB_d,UB_d), f_linear((LB_d,UB_d)), '-', lw=1, color = 'royalblue')

forecast_d = 65
forecast_h = f_linear(forecast_d)
plt.vlines(forecast_d, 0, forecast_h, color='black', linestyles='--', lw=1)
plt.hlines(forecast_h, 0, forecast_d, color='black', linestyles='--', lw=1)

text_str = str(forecast_d)
plt.text(forecast_d+1,40,text_str,color = 'red',size = 10)

text_str = f'{forecast_h:5.2f}'
plt.text(15,forecast_h+50,text_str,color = 'red',size = 10)

R_Squared = 100*dl.rsquared(Density, Hardness)

abs_b = abs(b)

text_str = '$y = $' + f'{a:4.2f}' + '$ \cdot x - $' + f'{abs_b:4.1f}' + \
           ', $R^2 =$' + f'{R_Squared:4.1f}' +'%'
plt.text(15,3000,text_str,color = 'royalblue',size = 10)

text_str = '$n = $' + str(n_d)
plt.text(15,3250,text_str,color = 'red',size = 10)

Scatter_Figure.suptitle('Australian Timber Data Example',size='14')

plt.savefig('AustralianTimber_Scatter.png', dpi=1200)