ASID5

# -*- coding: utf-8 -*-
"""
Created on Mon Apr 22 12:12:18 2019

@author: lancernik
"""

# Zadanie 1

#import numpy as np
#from sklearn.linear_model import LinearRegression
#from sklearn.model_selection import train_test_split
#import matplotlib.pyplot as plt
#
#a = np.array([10, 20, 30, 40, 50, 60, 70, 80, 90]).reshape(-1,1)
#b = np.array([300,350,500,700,800,850,900,1000,1200]).reshape(-1,1)
#
#def regress(x,y):
#    model = LinearRegression()
#    model.fit(x,y)
#    model.predict([[100]])
#
#    x_test = np.linspace(x[0],x[-1])
#    y_pred = model.predict(x_test[:,None])
#
#    plt.scatter(x,y)
#    plt.plot(x_test,y_pred,'r')
#    plt.legend(['Regresja', 'Kropeczki'])
#    plt.show()
#
#regress(a,b)
#



#Zadanie 2

import csv
import os
from sklearn.linear_model import LinearRegression
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt



def Pearson(dataset_out):
    c = dataset_out.corr("pearson")
    c = c.where(
            np.triu(
                    np.ones(c.shape,dtype=np.bool),k=1)
            ).stack().sort_values()
    print(c[abs(c)>0.1])

def regress(x,y,x_name="Missing data",y_name="Missing data"):
    model = LinearRegression()
    model.fit(x,y)
    model.predict([[1]])

    x_test = np.linspace(min(x),max(x))
    y_pred = model.predict(x_test[:,None])

    plt.xlabel('{}'.format(x_name))
    plt.ylabel('{}'.format(y_name))

    plt.scatter(x,y, marker='*', s=10)
    plt.plot(x_test,y_pred,'r')
    plt.legend(['Regresja', 'Kropeczki'])
    plt.show()
    print("y={}x+{}".format(round(model.coef_[0,0],3),round(model.intercept_[0],3)))
    print("Dopasowanie regresji: {}".format(round(model.score(x,y),5)))




current_dir = os.path.abspath(os.path.dirname(__file__))
data_path = os.path.join(current_dir, "Data")
csv_path = os.path.join(data_path, "Advertising.csv")




with open(csv_path) as csv_file:
    output_dict = dict()
    csv_reader = csv.reader(csv_file)
    first_row = next(csv_reader)
    for item in first_row:
        output_dict[item] = []
    for item in csv_reader:
        for i in range(len(item)):
            try:
                output_dict[first_row[i]].append(float(item[i]))
            except:
                output_dict[first_row[i]].append(item[i])

    for key in output_dict.keys():
        try:
            output_dict[key] = np.array(output_dict[key], dtype=np.float)
            dataset = pd.DataFrame.from_dict(output_dict)
        except:
            pass



dataset = dataset[['TV','radio','newspaper','sales']]
Pearson(dataset)



tv = output_dict['TV'].reshape(-1,1)
sales = output_dict['sales'].reshape(-1,1)
radio = output_dict['radio'].reshape(-1,1)
newspaper = output_dict['newspaper'].reshape(-1,1)



regress(tv,sales,"Tv","Sales")
regress(radio,sales)
regress(newspaper, sales)