Ais5

# -*- 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
#import numpy as np
#from sklearn.linear_model import LinearRegression
#from sklearn.model_selection import train_test_split
#import matplotlib.pyplot as plt
#
#
#def regress(x,y):
#    model = LinearRegression()
#    model.fit(x,y)
#    model.predict([[1]])
#
#    x_test = np.linspace(min(x),max(x))
#    y_pred = model.predict(x_test)
#
#    plt.scatter(x,y, marker='*', s=10)
#    plt.plot(x_test,y_pred,'r')
#    plt.legend(['Regresja', 'Kropeczki'])
#    plt.ylabel("Wartosc napięcia [V]")
#    plt.xlabel("test")
#    plt.show()
##    print("y={}x+{}".format(round(float(model.coef_),3),round(float(model.intercept_),3)))
#    print("y={}x+{}".format(round(model.coef_[0,0],3),round(model.intercept_[0],3)))
#
#
#
#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)
#        except:
#            pass
#
#
#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)
#regress(radio,sales)
#regress(newspaper, sales)




#Zadanie 3


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


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']]





data = {'TV':[400,450], 'radio':[100,200],'newspaper':[200,50]}

df = pd.DataFrame(data)


dataTrain = dataset
dataTest = dataset
# print df.head()

x_train = dataTrain[['TV', 'radio','newspaper']].values.reshape(-1,3)
y_train = dataTrain['sales']

x_test = dataTest[['TV', 'radio','newspaper']].values.reshape(-1,3)
y_test = dataTest['sales']

ols = linear_model.LinearRegression()
model = ols.fit(x_train, y_train)




print(model.predict(df)[0:2])