Scribd
Upload
36 views45 pages

Merged

This document describes an exercise to build a neural network model to predict housing prices based on number of bedrooms. The model would predict that a 1 bedroom house costs $100k, a 2 bedroom costs $150k, and so on, with each additional bedroom adding $50k to the price. The document provides sample code to create a simple model using TensorFlow that learns this relationship, scaling house prices to predict a value from 0 to 1 instead of dollar amounts. The model is trained over 2000 epochs to predict the price of a 7 bedroom house as close to 4, representing $400k.

Uploaded by

sampada bareja
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
36 views45 pages

Merged

This document describes an exercise to build a neural network model to predict housing prices based on number of bedrooms. The model would predict that a 1 bedroom house costs $100k, a 2 bedroom costs $150k, and so on, with each additional bedroom adding $50k to the price. The document provides sample code to create a simple model using TensorFlow that learns this relationship, scaling house prices to predict a value from 0 to 1 instead of dollar amounts. The model is trained over 2000 epochs to predict the price of a 7 bedroom house as close to 4, representing $400k.

Uploaded by

sampada bareja
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 45

23/05/2021 Exercise 1 (Housing Prices) | Coursera

Help

In this exercise you'll try to build a neural network that predicts the price of a house according
to a simple formula.

So, imagine if house pricing was as easy as a house costs 50k + 50k per bedroom, so that a 1
bedroom house costs 100k, a 2 bedroom house costs 150k etc.

How would you create a neural network that learns this relationship so that it would predict a 7
bedroom house as costing close to 400k etc.

Hint: Your network might work better if you scale the house price down. You don't have to give
the answer 400...it might be better to create something that predicts the number 4, and then
your answer is in the 'hundreds of thousands' etc.

In [1]: import tensorflow as tf


import numpy as np
from tensorflow import keras

In [2]: # GRADED FUNCTION: house_model


def house_model(y_new):
xs = np.array([1.0,2.0,3.0,4.0,5.0,6.0],dtype = float)
ys = np.array([1.0,1.5,2.0,2.5,3.0,3.5],dtype = float)
model = tf.keras.Sequential([keras.layers.Dense(units = 1, input_shap
model.compile(optimizer = 'sgd', loss = 'mean_squared_error')
model.fit(xs,ys,epochs = 2000)
return model.predict(y_new)[0]

In [3]: prediction = house_model([7.0])


print(prediction)

WARNING: Logging before flag parsing goes to stderr.


W1216 15:58:32.136981 140672022714176 deprecation.py:506] From /usr/lo
cal/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:125
1: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_o
ps) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing i
t to the constructor

Epoch 1/2000
6/6 [==============================] - 2s 363ms/sample - loss: 10.1281
Epoch 2/2000
6/6 [==============================] - 0s 354us/sample - loss: 4.6980
Epoch 3/2000
6/6 [==============================] - 0s 320us/sample - loss: 2.1847
Epoch 4/2000
6/6 [==============================] - 0s 328us/sample - loss: 1.0214
Epoch 5/2000
6/6 [==============================] - 0s 301us/sample - loss: 0.4829
Epoch 6/2000

In [4]: # Now click the 'Submit Assignment' button above.


# Once that is complete, please run the following two cells to save your

In [ ]: %%javascript
<!-- Save the notebook -->
https://www.coursera.org/learn/introduction-tensorflow/ungradedLab/myWUT/exercise-1-housing-prices/lab 1/1

You might also like