tf_housing_load_plot.py

tf_housing_load_plot.py

import pandas as pd
# import library to split the data
from sklearn.model_selection import train_test_split

%matplotlib inline
import matplotlib.pyplot as plt


def read_data():
  """
  read the CSV data 
  """
  data = pd.read_csv("https://goo.gl/PQXxZ8")
  size_data = data["Size"].values
  price_data = data["Price"].values
  return size_data, price_data



def split_test_train(size, price):
  # split the data, test size = 33%
  size_train, size_test, price_train, price_test = train_test_split(size, price, test_size=0.33)
  return size_train, size_test, price_train, price_test
  
# Normalize a data set
def normalize(array): 
    return (array - array.mean()) / array.std()

# read the data from the csv file.
size, price = read_data()
# split the data into testing and training set.
X_train, X_test, Y_train,Y_test = split_test_train(size, price)
# print the length of test and train dataset.
print("Length of the training data: ", len(X_train))
print("Length of the testing data: ", len(X_test))


# normalize the data
X_train = normalize(X_train)
Y_train = normalize(Y_train)

X_test = normalize(X_test)
Y_test = normalize(Y_test)

# plot the normalized data
plt.scatter(X_train, Y_train, label='Samples data')
plt.draw()