6/23/24, 11:37 PM NNHOUSEPRICEDATA.

ipynb - Colab

import pandas as pd
df = pd.read_csv('housepricedata.csv')
df.head()

LotArea OverallQual OverallCond TotalBsmtSF FullBath HalfBath BedroomAbvGr TotRmsAbvGrd Fireplaces GarageAre

0 8450 7 5 856 2 1 3 8 0 54

1 9600 6 8 1262 2 0 3 6 1 46

2 11250 7 5 920 2 1 3 6 1 60

3 9550 7 5 756 1 0 3 7 1 64

4 14260 8 5 1145 2 1 4 9 1 83

dataset = df.values

X = dataset[:,0:10]
Y = dataset[:,10]

from sklearn import preprocessing

min_max_scaler = preprocessing.MinMaxScaler()
X_scale = min_max_scaler.fit_transform(X)

X_scale

array([[0.0334198 , 0.66666667, 0.5 , ..., 0.5 , 0. ,

0.3864598 ],
[0.03879502, 0.55555556, 0.875 , ..., 0.33333333, 0.33333333,
0.32440056],
[0.04650728, 0.66666667, 0.5 , ..., 0.33333333, 0.33333333,
0.42877292],
...,
[0.03618687, 0.66666667, 1. , ..., 0.58333333, 0.66666667,
0.17771509],
[0.03934189, 0.44444444, 0.625 , ..., 0.25 , 0. ,
0.16925247],
[0.04037019, 0.44444444, 0.625 , ..., 0.33333333, 0. ,
0.19464034]])

from sklearn.model_selection import train_test_split

X_train, X_val_and_test, Y_train, Y_val_and_test = train_test_split(X_scale, Y, test_size=0.3)
X_val, X_test, Y_val, Y_test = train_test_split(X_val_and_test, Y_val_and_test, test_size=0.5)
print(X_train.shape, X_val.shape, X_test.shape, Y_train.shape, Y_val.shape, Y_test.shape)

https://colab.research.google.com/drive/1VNAWEcIcM-Kw4IJynlVR5dTZ54pjkv6t#printMode=true 1/3
6/23/24, 11:37 PM NNHOUSEPRICEDATA.ipynb - Colab

(1022, 10) (219, 10) (219, 10) (1022,) (219,) (219,)

from keras.models import Sequential #if not works change as tensor.keras.models

from keras.layers import Dense

model = Sequential([
Dense(32, activation='relu', input_shape=(10,)),
Dense(32, activation='relu'),
Dense(1, activation='sigmoid'),
])

model.compile(optimizer='sgd',
loss='binary_crossentropy',
metrics=['accuracy'])

hist = model.fit(X_train, Y_train,

batch_size=32, epochs=100,
validation_data=(X_val, Y_val))

model.evaluate(X_test, Y_test)[1]

Epoch 1/100
32/32 [==============================] - 1s 10ms/step - loss: 0.6924 - accuracy: 0.5157 - val_loss: 0.6898 - val_accuracy: 0.5845
Epoch 2/100
32/32 [==============================] - 0s 3ms/step - loss: 0.6836 - accuracy: 0.6614 - val_loss: 0.6856 - val_accuracy: 0.5982
Epoch 3/100
32/32 [==============================] - 0s 3ms/step - loss: 0.6765 - accuracy: 0.6595 - val_loss: 0.6818 - val_accuracy: 0.5890
Epoch 4/100
32/32 [==============================] - 0s 3ms/step - loss: 0.6701 - accuracy: 0.6027 - val_loss: 0.6776 - val_accuracy: 0.6119
Epoch 5/100
32/32 [==============================] - 0s 3ms/step - loss: 0.6643 - accuracy: 0.6742 - val_loss: 0.6742 - val_accuracy: 0.5982
Epoch 6/100
32/32 [==============================] - 0s 5ms/step - loss: 0.6588 - accuracy: 0.6517 - val_loss: 0.6704 - val_accuracy: 0.6164
Epoch 7/100
32/32 [==============================] - 0s 7ms/step - loss: 0.6534 - accuracy: 0.6751 - val_loss: 0.6662 - val_accuracy: 0.6164
Epoch 8/100
32/32 [==============================] - 0s 5ms/step - loss: 0.6477 - accuracy: 0.6986 - val_loss: 0.6620 - val_accuracy: 0.6347
Epoch 9/100
32/32 [==============================] - 0s 4ms/step - loss: 0.6420 - accuracy: 0.7133 - val_loss: 0.6571 - val_accuracy: 0.6393
Epoch 10/100
32/32 [==============================] - 0s 4ms/step - loss: 0.6360 - accuracy: 0.7299 - val_loss: 0.6519 - val_accuracy: 0.6484
Epoch 11/100
32/32 [==============================] - 0s 4ms/step - loss: 0.6297 - accuracy: 0.7436 - val_loss: 0.6466 - val_accuracy: 0.6667
Epoch 12/100
32/32 [==============================] - 0s 6ms/step - loss: 0.6232 - accuracy: 0.7456 - val_loss: 0.6405 - val_accuracy: 0.6667
Epoch 13/100
32/32 [==============================] - 0s 5ms/step - loss: 0.6166 - accuracy: 0.7524 - val_loss: 0.6345 - val_accuracy: 0.6804
Epoch 14/100
32/32 [==============================] - 0s 4ms/step - loss: 0.6099 - accuracy: 0.7769 - val_loss: 0.6286 - val_accuracy: 0.6941
Epoch 15/100
32/32 [==============================] - 0s 4ms/step - loss: 0.6028 - accuracy: 0.7818 - val_loss: 0.6222 - val_accuracy: 0.6986
Epoch 16/100
32/32 [==============================] - 0s 5ms/step - loss: 0.5955 - accuracy: 0.8033 - val_loss: 0.6160 - val_accuracy: 0.7032
Epoch 17/100
32/32 [==============================] - 0s 5ms/step - loss: 0.5881 - accuracy: 0.8023 - val_loss: 0.6092 - val_accuracy: 0.7169
Epoch 18/100
32/32 [==============================] - 0s 4ms/step - loss: 0.5802 - accuracy: 0.8151 - val_loss: 0.6021 - val_accuracy: 0.7397
Epoch 19/100
32/32 [==============================] - 0s 6ms/step - loss: 0.5722 - accuracy: 0.8180 - val_loss: 0.5943 - val_accuracy: 0.7671

https://colab.research.google.com/drive/1VNAWEcIcM-Kw4IJynlVR5dTZ54pjkv6t#printMode=true 2/3
6/23/24, 11:37 PM NNHOUSEPRICEDATA.ipynb - Colab
Epoch 20/100
32/32 [==============================] - 0s 6ms/step - loss: 0.5637 - accuracy: 0.8239 - val_loss: 0.5863 - val_accuracy: 0.7717
Epoch 21/100
32/32 [==============================] - 0s 4ms/step - loss: 0.5549 - accuracy: 0.8405 - val_loss: 0.5789 - val_accuracy: 0.7900
Epoch 22/100
32/32 [==============================] - 0s 4ms/step - loss: 0.5461 - accuracy: 0.8386 - val_loss: 0.5703 - val_accuracy: 0.7991
Epoch 23/100
32/32 [==============================] - 0s 5ms/step - loss: 0.5371 - accuracy: 0.8454 - val_loss: 0.5622 - val_accuracy: 0.8037
Epoch 24/100
32/32 [==============================] - 0s 6ms/step - loss: 0.5276 - accuracy: 0.8474 - val_loss: 0.5538 - val_accuracy: 0.8037
Epoch 25/100
32/32 [==============================] - 0s 5ms/step - loss: 0.5184 - accuracy: 0.8503 - val_loss: 0.5453 - val_accuracy: 0.8174
Epoch 26/100
32/32 [==============================] - 0s 3ms/step - loss: 0.5087 - accuracy: 0.8493 - val_loss: 0.5357 - val_accuracy: 0.8356
Epoch 27/100
32/32 [==============================] - 0s 3ms/step - loss: 0.4993 - accuracy: 0.8562 - val_loss: 0.5284 - val_accuracy: 0.8311
Epoch 28/100
32/32 [==============================] - 0s 3ms/step - loss: 0.4896 - accuracy: 0.8581 - val_loss: 0.5211 - val_accuracy: 0.8265
Epoch 29/100
32/32 [ ] 0 3 / t l 0 803 0 8 8 l l 0 l 0 8

https://colab.research.google.com/drive/1VNAWEcIcM-Kw4IJynlVR5dTZ54pjkv6t#printMode=true 3/3