import pandas as pd
import matplotlib.pyplot as plt

def predict(x, w, b):
  return x * w + b

def loss(x, y):
  return (y - x) ** 2

def mse(predicted, actual):
  sum = 0.0
  for i, x in enumerate(predicted):
    sum += loss(x, actual[i])
  return sum / len(predicted)

def slope_weight(input, predicted, actual):
  sum = 0.0
  for i, x in enumerate(predicted):
    sum += (actual[i] - x) * input[i]
  return sum / len(predicted) * 2

def slope_bias(predicted, actual):
  sum = 0.0
  for i, x in enumerate(predicted):
    sum += (actual[i] - x)
  return sum / len(predicted) * 2

data  = pd.read_csv("california_housing_train.csv")

w = 0
b = 0
prev = 0
delta = 10

beta = 0.01

median_income = data['median_income']
median_house_value = data['median_house_value']

mu_input = median_income.mean()
sigma_input = median_income.std()

mu_actual = median_house_value.mean()
sigma_actual = median_house_value.std()

median_income = (median_income - mu_input) / sigma_input
median_house_value = (median_house_value - mu_actual) / sigma_actual

while delta > 1e-6:
  predicted = []
  actual = median_house_value.tolist()
  for sample in median_income.tolist():
    predicted.append(predict(sample, w, b))
  delta = abs(mse(predicted, actual) - prev)
  
  w += slope_weight(median_income.tolist(), predicted, actual) * beta
  b += slope_bias(predicted, actual) * beta
  prev = mse(predicted, actual)

# `w` and `b` now are our weight and bias