# Multiple Linear Regression

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('50_Startups.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 4].values

# Encoding categorical data
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import make_column_transformer

col_trans = make_column_transformer((OneHotEncoder(categories = 'auto'), [3]), remainder='passthrough')
X = col_trans.fit_transform(X).astype(float)

# Avoiding the Dummy Trap
X = X[:, 1:]

# Splitting data into Training Set and Test Set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# Fitting Multiple Linerar Regression to the Training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)

# Predicting the Test set results
y_pred = regressor.predict(X_test)

# Building the optimal model using backward elimination
import statsmodels.formula.api as sm
X = np.append(arr = np.ones((50, 1)).astype(int), values = X, axis = 1)


def max_with_iter(arr):
    max_val = arr[0]
    max_iter = 0

    for i in range(0, len(arr)):
        if max_val < arr[i]:
            max_val = arr[i]
            max_iter = i

    return max_iter, max_val

def make_step_back_prop(cols_opt, cols_opt_lbl, max_p_val_iter):

    return


alpha = 0.05
cols_opt = [0, 1, 2, 3, 4, 5]
cols_opt_lbl = ["const", "Florida", "New York", "R&D", "Admin", "Market"]

X_opt = X[:, cols_opt]
regressor_OLS = sm.OLS(endog=y, exog = X_opt).fit()
p_vals = regressor_OLS._results.pvalues
max_p_val_iter, max_p_val = max_with_iter(p_vals)

while  max_p_val > alpha:
    cols_opt = cols_opt.remove(max_p_val_iter)
    cols_opt_lbl = cols_opt_lbl.remove(cols_opt_lbl[max_p_val_iter])

    X_opt = X[:, cols_opt]
    regressor_OLS = sm.OLS(endog=y, exog = X_opt).fit()
    p_vals = regressor_OLS._results.pvalues
    max_p_val_iter, max_p_val = max_with_iter(p_vals)