Assignment 11 – Quantum Learning  

                                                Sandip University - Zeeshan Mawani

In [1]: #import libraries and dataset

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import preprocessing
from tensorflow.keras.layers import Input, Dense, Dropout, Activation
from tensorflow.keras.models import Model
reg_dataset = pd.read_csv(r'C:\Users\Zeeshan Mawani\Desktop\Jupyter\Class stuff\diamond_price.csv')

In [2]: reg_dataset.head()

Out[2]:
S.No carat cut color clarity depth table price x y z

0 1 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43

1 2 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31

2 3 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31

3 4 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63

4 5 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

In [3]: reg_dataset.drop('S.No', axis=1, inplace=True)
reg_dataset.head()

Out[3]:
carat cut color clarity depth table price x y z

0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43

1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31

2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31

3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63

4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75

In [4]: reg_dataset.shape

Out[4]: (53940, 10)

In [5]: reg_dataset.describe()

Out[5]:
carat depth table price x y z

count 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000

mean 0.797940 61.749405 57.457184 3932.799722 5.731157 5.734526 3.538734

std 0.474011 1.432621 2.234491 3989.439738 1.121761 1.142135 0.705699

min 0.200000 43.000000 43.000000 326.000000 0.000000 0.000000 0.000000

25% 0.400000 61.000000 56.000000 950.000000 4.710000 4.720000 2.910000

50% 0.700000 61.800000 57.000000 2401.000000 5.700000 5.710000 3.530000

75% 1.040000 62.500000 59.000000 5324.250000 6.540000 6.540000 4.040000

max 5.010000 79.000000 95.000000 18823.000000 10.740000 58.900000 31.800000

In [6]: # plot price vs. carat
sns.pairplot(reg_dataset, x_vars=['carat'], y_vars = ['price'])
# plot carat vs other Cs
sns.pairplot(reg_dataset, x_vars=['cut', 'clarity', 'color'], y_vars = ['carat'])
plt.show()
In [7]: sns.heatmap(reg_dataset[["carat","cut","color","clarity","depth","table"]].corr(), annot=True)

Out[7]: <AxesSubplot:>

In [8]: list(reg_dataset.cut.unique())

Out[8]: ['Ideal', 'Premium', 'Good', 'Very Good', 'Fair']

In [9]: numeric_data= reg_dataset.drop(['cut','color', 'clarity'], axis=1)

In [10]: cut_onehot = pd.get_dummies(reg_dataset.cut).iloc[:,1:]

color_onehot = pd.get_dummies(reg_dataset.color).iloc[:,1:]
clarity_onehot = pd.get_dummies(reg_dataset.clarity).iloc[:,1:]
In [11]: cut_onehot.head()

Out[11]:
Good Ideal Premium Very Good

0 0 1 0 0

1 0 0 1 0

2 1 0 0 0

3 0 0 1 0

4 1 0 0 0

In [12]: reg_dataset = pd.concat([numeric_data,cut_onehot, color_onehot,clarity_onehot], axis=1)

reg_dataset.head()

Out[12]:
carat depth table price x y z Good Ideal Premium ... H I J IF SI1 SI2 VS1 VS2 VVS1 VVS2

0 0.23 61.5 55.0 326 3.95 3.98 2.43 0 1 0 ... 0 0 0 0 0 1 0 0 0 0

1 0.21 59.8 61.0 326 3.89 3.84 2.31 0 0 1 ... 0 0 0 0 1 0 0 0 0 0

2 0.23 56.9 65.0 327 4.05 4.07 2.31 1 0 0 ... 0 0 0 0 0 0 1 0 0 0

3 0.29 62.4 58.0 334 4.20 4.23 2.63 0 0 1 ... 0 1 0 0 0 0 0 1 0 0

4 0.31 63.3 58.0 335 4.34 4.35 2.75 1 0 0 ... 0 0 1 0 0 1 0 0 0 0

5 rows × 24 columns

In [13]: features = reg_dataset.drop(['price'], axis=1).values

labels = reg_dataset['price'].values

In [14]: from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.2, random_state=40)
In [15]: from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

In [16]: input_layer = Input(shape=(features.shape[1],))

l1 = Dense(100, activation='relu')(input_layer)
l2 = Dense(50, activation='relu')(l1)
l3 = Dense(25, activation='relu')(l2)
output = Dense(1)(l3)

In [17]: model = Model(inputs=input_layer, outputs=output)

model.compile(loss="mean_absolute_error" , optimizer="adam", metrics=["mean_absolute_error"])

In [18]: print(model.summary())

Model: "model"

_________________________________________________________________

Layer (type) Output Shape Param #

=================================================================

input_1 (InputLayer) [(None, 23)] 0

dense (Dense) (None, 100) 2400

dense_1 (Dense) (None, 50) 5050

dense_2 (Dense) (None, 25) 1275

dense_3 (Dense) (None, 1) 26

=================================================================

Total params: 8,751

Trainable params: 8,751

Non-trainable params: 0

_________________________________________________________________

None

In [19]: history = model.fit(X_train, y_train, batch_size=2, epochs=20, verbose=1, validation_split=0.2)

17261/17261 [==============================] - 39s 2ms/step - loss: 324.2164 - mean_absolute_error: 324.2164 - val_l
oss: 352.5723 - val_mean_absolute_error: 352.5723

Epoch 15/20

17261/17261 [==============================] - 39s 2ms/step - loss: 322.4259 - mean_absolute_error: 322.4259 - val_l

oss: 363.4964 - val_mean_absolute_error: 363.4964

Epoch 16/20

17261/17261 [==============================] - 39s 2ms/step - loss: 321.3640 - mean_absolute_error: 321.3640 - val_l

oss: 351.7753 - val_mean_absolute_error: 351.7753

Epoch 17/20

17261/17261 [==============================] - 39s 2ms/step - loss: 318.6007 - mean_absolute_error: 318.6007 - val_l

oss: 351.6654 - val_mean_absolute_error: 351.6654

Epoch 18/20

17261/17261 [==============================] - 39s 2ms/step - loss: 317.5522 - mean_absolute_error: 317.5522 - val_l

oss: 360.9181 - val_mean_absolute_error: 360.9181

Epoch 19/20

17261/17261 [==============================] - 39s 2ms/step - loss: 315.9409 - mean_absolute_error: 315.9409 - val_l

oss: 362.9208 - val_mean_absolute_error: 362.9208

Epoch 20/20

17261/17261 [==============================] - 39s 2ms/step - loss: 313.7580 - mean_absolute_error: 313.7580 - val_l

oss: 350.9129 - val_mean_absolute_error: 350.9129

In [20]: from sklearn.metrics import mean_absolute_error

from math import sqrt
​
pred_train = model.predict(X_train)
print(mean_absolute_error(y_train,pred_train))
​
pred = model.predict(X_test)
print(mean_absolute_error(y_test,pred))

318.7477203046652

323.489523630563