DL LAB INDEX-merged

(1)

• Name :- Avinash Rai

• SID :- 89923

• Subject : - Deep Learning

- ---LAB INDEX---

S. No. Name of Experiment Page No. Faculty Sign..

1 House Price Prediction 1 to 3

2 Graduation Admission Prediction 4 to 6

3 Car Price Prediction 7 to 11

4 Laptop Price Prediction 12 to 15

5 Mobile Price Prediction 16 to 18

6 Employee Salary Analysis 19 to 24 7 Advertisement Analysis’s 25 to 33 8 Credit Card Fraud Detection 34 to 36

9 Heart Failure Analysis 37 to 41

10 Apple Quality Detection 42 to 45

(2)

 

LAB 1

Data Loading

#IMPORTING LIBRARIES import pandas as pd import numpy as np

import matplotlib.pyplot as plt import seaborn as sns

import tensorflow as tf

#IMPORTING DATASET

pd.set_option('display.max_columns',None)

ds = pd.read_csv(r"D:\\projects\\DL labs\\house_data (Lab1).csv") ds.head()

id date price bedrooms bathrooms sqft_living sqft_lot floors waterfront view condition grade sqft_above s

0 7129300520 20141013T000000 221900.0 3 1.00 1180 5650 1.0 0 0 3 7 1180

1 6414100192 20141209T000000 538000.0 3 2.25 2570 7242 2.0 0 0 3 7 2170

2 5631500400 20150225T000000 180000.0 2 1.00 770 10000 1.0 0 0 3 6 770

3 2487200875 20141209T000000 604000.0 4 3.00 1960 5000 1.0 0 0 5 7 1050

4 1954400510 20150218T000000 510000.0 3 2.00 1680 8080 1.0 0 0 3 8 1680

#DATASET HAVE 21613 ROWS AND 21 FEATURES ds.shape

(21613, 21)

#REMOVING UNNECESSARY FEATURES

ds.drop(['id','date'],axis = 1,inplace = True) ds.head()

price bedrooms bathrooms sqft_living sqft_lot floors waterfront view condition grade sqft_above sqft_basement yr_built yr_reno

0 221900.0 3 1.00 1180 5650 1.0 0 0 3 7 1180 0 1955

1 538000.0 3 2.25 2570 7242 2.0 0 0 3 7 2170 400 1951

2 180000.0 2 1.00 770 10000 1.0 0 0 3 6 770 0 1933

3 604000.0 4 3.00 1960 5000 1.0 0 0 5 7 1050 910 1965

4 510000.0 3 2.00 1680 8080 1.0 0 0 3 8 1680 0 1987

#CHECKING FOR NULL VALUES ds.isnull().sum()

price 0 bedrooms 0 bathrooms 0 sqft_living 0 sqft_lot 0 floors 0 waterfront 0 view 0 condition 0 grade 0 sqft_above 0 sqft_basement 0 yr_built 0 yr_renovated 0 zipcode 0 lat 0 long 0 sqft_living15 0 sqft_lot15 0 dtype: int64 NO MISSING DATA

ds.info() In [1]:

In [2]:

Out[2]:

In [3]:

Out[3]:

In [4]:

Out[4]:

In [5]:

Out[5]:

In [6]:

(3)

RangeIndex: 21613 entries, 0 to 21612 Data columns (total 19 columns):

# Column Non-Null Count Dtype --- --- --- --- 0 price 21613 non-null float64 1 bedrooms 21613 non-null int64 2 bathrooms 21613 non-null float64 3 sqft_living 21613 non-null int64 4 sqft_lot 21613 non-null int64 5 floors 21613 non-null float64 6 waterfront 21613 non-null int64 7 view 21613 non-null int64 8 condition 21613 non-null int64 9 grade 21613 non-null int64 10 sqft_above 21613 non-null int64 11 sqft_basement 21613 non-null int64 12 yr_built 21613 non-null int64 13 yr_renovated 21613 non-null int64 14 zipcode 21613 non-null int64 15 lat 21613 non-null float64 16 long 21613 non-null float64 17 sqft_living15 21613 non-null int64 18 sqft_lot15 21613 non-null int64 dtypes: float64(5), int64(14)

memory usage: 3.1 MB

ds.columns

Index(['price', 'bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'waterfront', 'view', 'condition', 'grade', 'sqft_above',

'sqft_basement', 'yr_built', 'yr_renovated', 'zipcode', 'lat', 'long', 'sqft_living15', 'sqft_lot15'],

dtype='object')

Exploratory Data Analysis (EDA)

corr = ds[['bathrooms', 'bedrooms', 'sqft_living', 'sqft_lot', 'floors', 'grade', 'price']]

plt.figure(figsize=(10,8)) plt.title('Correlation Matrix') sns.heatmap(corr.corr(),annot=True)

<Axes: title={'center': 'Correlation Matrix'}>

#DIVIDING DATASET IN DEPENDENT AND INDEPENDENT VARIABLE x = ds.iloc[:,1:].values

y = ds.iloc[:,0].values

#SPLITTING DATASET IN TRAINING AND TESTING SET from sklearn.model_selection import train_test_split In [7]:

Out[7]:

In [8]:

Out[8]:

In [9]:

In [10]:

(4)

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.2,random_state = 0)

Data Building ANN

Artificial Neural Network

#FEATURE SCALING IS NECESSARY IN ANN

from sklearn.preprocessing import StandardScaler sc = StandardScaler()

x_train = sc.fit_transform(x_train) x_test = sc.transform(x_test)

#CREATING THE ANN AS SEQUENCE OF LAYERS ann = tf.keras.models.Sequential()

#ADDING FIRST HIDDEN LAYER WITH 30 NEURONS, THE INPUT LAYER WILL BE ADDED AUTOMATICALLY, ann.add(tf.keras.layers.Dense(units = 30, activation = 'relu'))

#ADDING 2ND HIDDEN LAYER WITH 30 NEURONS

ann.add(tf.keras.layers.Dense(units = 30, activation = 'relu'))

#ADDING 3RD HIDDEN LAYER WITH 30 NEURONS

#ADDING 4TH HIDDEN LAYER WITH 30 NEURONS

#ADDING OUTPUT LAYER WITH 1 NEURON . ann.add(tf.keras.layers.Dense(units = 1))

#COMPILING THE ANN USING STOCHASTIC GRADIENT DESCENT (optimizer = 'adam') ann.compile(optimizer = 'adam',loss = 'mean_squared_error')

#TRAINING THE ANN WITH BATCH SIZE OF 32 (THIS IS A BATCH LEARNING) ann.fit(x_train,y_train,batch_size = 20,epochs = 10)

Epoch 1/10

865/865 [==============================] - 6s 4ms/step - loss: 220945924096.0000 Epoch 2/10

865/865 [==============================] - 4s 4ms/step - loss: 32762683392.0000

#COMPARING ACTUAL VALUES WITH PREDICTED VALUES np.set_printoptions(precision=2)

y_pred = ann.predict(x_test)

np.concatenate((y_pred,y_test.reshape(-1,1)),1)

Accuracy and evaluation

#GETTING ACCURACY

from sklearn.metrics import r2_score y_pred = ann.predict(x_test) print(r2_score(y_test,y_pred))

I GOT AN ACCURACY OF AROUND 79% TUNING THE HYPERPARAMETERS MAY INCREASE THE ACCURACY

In [11]:

In [12]:

In [13]:

In [14]:

In [15]:

In [16]:

In [17]:

In [18]:

In [ ]:

(5)

LAB 2 Data Loading

import numpy as np # linear algebra

import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt

import seaborn as sns import warnings

warnings.filterwarnings('ignore')

df=pd.read_csv(r"C:\Users\gunja\OneDrive\Desktop\6th Sem\DL Lab\Admission (Lab2).csv") df.head(2)

Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA Research Chance of Admit

0 1 337 118 4 4.5 4.5 9.65 1 0.92

1 2 324 107 4 4.0 4.5 8.87 1 0.76

df.shape (500, 9) df.info()

# Column Non-Null Count Dtype --- --- --- --- 0 Serial No. 500 non-null int64 1 GRE Score 500 non-null int64 2 TOEFL Score 500 non-null int64 3 University Rating 500 non-null int64 4 SOP 500 non-null float64 5 LOR 500 non-null float64 6 CGPA 500 non-null float64 7 Research 500 non-null int64 8 Chance of Admit 500 non-null float64 dtypes: float64(4), int64(5)

memory usage: 35.3 KB df.duplicated().sum() 0

df=df.iloc[:,1:]

df

GRE Score TOEFL Score University Rating SOP LOR CGPA Research Chance of Admit

0 337 118 4 4.5 4.5 9.65 1 0.92

1 324 107 4 4.0 4.5 8.87 1 0.76

2 316 104 3 3.0 3.5 8.00 1 0.72

3 322 110 3 3.5 2.5 8.67 1 0.80

4 314 103 2 2.0 3.0 8.21 0 0.65

... ... ... ... ... ... ... ... ...

495 332 108 5 4.5 4.0 9.02 1 0.87

496 337 117 5 5.0 5.0 9.87 1 0.96

497 330 120 5 4.5 5.0 9.56 1 0.93

498 312 103 4 4.0 5.0 8.43 0 0.73

499 327 113 4 4.5 4.5 9.04 0 0.84

500 rows × 8 columns

EDA

corr = df.corr() mask = np.zeros_like(corr)

mask[np.triu_indices_from(mask)] = True with sns.axes_style("white"):

f, ax = plt.subplots(figsize=(9, 7))

ax = sns.heatmap(corr,mask=mask,square=True,annot=True,fmt='0.2f',linewidths=.8,cmap="hsv") In [1]:

In [2]:

In [3]:

In [4]:

Out[4]:

In [5]:

Out[5]:

In [6]:

In [7]:

Out[7]:

In [8]:

Out[8]:

In [21]:

(6)

x=df.iloc[:,0:-1]

y=df.iloc[:,-1]

y 0 0.92 1 0.76 2 0.72 3 0.80 4 0.65 ...

495 0.87 496 0.96 497 0.93 498 0.73 499 0.84

Name: Chance of Admit , Length: 500, dtype: float64

# upper bound and lower bound known than use min max scaling from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=1) from sklearn.preprocessing import MinMaxScaler

scaler=MinMaxScaler()

x_train_scaled=scaler.fit_transform(x_train) x_test_scaled=scaler.transform(x_test) x_train_scaled

array([[0.4 , 0.42857143, 0.5 , ..., 0.57142857, 0.50320513, 0. ],

[0.56 , 0.64285714, 0. , ..., 0.57142857, 0.55769231, 1. ],

[0.2 , 0.32142857, 0.5 , ..., 0.28571429, 0.34615385, 0. ],

...,

[0.7 , 0.53571429, 0.5 , ..., 0.57142857, 0.74038462, 1. ],

[0.72 , 0.67857143, 1. , ..., 0.71428571, 0.77884615, 1. ],

[0.2 , 0.46428571, 0. , ..., 0.14285714, 0.32051282, 0. ]])

Model Building

import tensorflow from tensorflow import keras from keras import Sequential from keras.layers import Dense

WARNING:tensorflow:From C:\Users\gunja\anaconda3\lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v 1.losses.sparse_softmax_cross_entropy instead.

model=Sequential()

model.add(Dense(7, activation='relu', input_dim=7)) model.add(Dense(7, activation='relu'))

model.add(Dense(7, activation='relu')) model.add(Dense(7, activation='relu')) model.add(Dense(1,activation='linear'))

WARNING:tensorflow:From C:\Users\gunja\anaconda3\lib\site-packages\keras\src\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_grap h instead.

model.summary() In [9]:

Out[9]:

In [10]:

In [11]:

Out[11]:

In [12]:

In [13]:

In [14]:

(7)

Model: "sequential"

_________________________________________________________________

Layer (type) Output Shape Param #

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

dense (Dense) (None, 7) 56 dense_1 (Dense) (None, 7) 56 dense_2 (Dense) (None, 7) 56 dense_3 (Dense) (None, 7) 56 dense_4 (Dense) (None, 1) 8

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

Total params: 232 (928.00 Byte) Trainable params: 232 (928.00 Byte) Non-trainable params: 0 (0.00 Byte)

_________________________________________________________________

model.compile(loss='mean_squared_error', optimizer="Adam")

WARNING:tensorflow:From C:\Users\gunja\anaconda3\lib\site-packages\keras\src\optimizers\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.

Optimizer instead.

history=model.fit(x_train_scaled,y_train,epochs=10, validation_split=0.2) Epoch 1/10

WARNING:tensorflow:From C:\Users\gunja\anaconda3\lib\site-packages\keras\src\utils\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ra gged.RaggedTensorValue instead.

10/10 [==============================] - 4s 71ms/step - loss: 0.5200 - val_loss: 0.5547 Epoch 2/10

10/10 [==============================] - 0s 16ms/step - loss: 0.1459 - val_loss: 0.1339 y_pred=model.predict(x_test_scaled)

4/4 [==============================] - 0s 4ms/step

Accuracy and evaluation

from sklearn.metrics import r2_score r2_score(y_test,y_pred)

-5.097606032550521

import matplotlib.pyplot as plt plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) [<matplotlib.lines.Line2D at 0x179efe3ef50>]

In [15]:

In [16]:

In [17]:

In [18]:

Out[18]:

In [19]:

Out[19]:

(8)

LAB-3 Data Loading

import numpy as np # linear algebra

import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt

import seaborn as sns import warnings

df = pd.read_csv(r"D:\\projects\\DL labs\\CarPrice (Lab3).csv") df.head(2)

car_ID symboling CarName fueltype aspiration doornumber carbody drivewheel enginelocation wheelbase ... enginesize fuelsystem boreratio stroke compressionratio horsepower peakrpm citympg highwaympg price

0 1 3 alfa-romero

giulia gas std two convertible rwd front 88.6 ... 130 mpfi 3.47 2.68 9.0 111 5000 21 27 13495.0

1 2 3 alfa-romero

stelvio gas std two convertible rwd front 88.6 ... 130 mpfi 3.47 2.68 9.0 111 5000 21 27 16500.0

df.info()

# Column Non-Null Count Dtype --- --- --- --- 0 car_ID 205 non-null int64 1 symboling 205 non-null int64 2 CarName 205 non-null object 3 fueltype 205 non-null object 4 aspiration 205 non-null object 5 doornumber 205 non-null object 6 carbody 205 non-null object 7 drivewheel 205 non-null object 8 enginelocation 205 non-null object 9 wheelbase 205 non-null float64 10 carlength 205 non-null float64 11 carwidth 205 non-null float64 12 carheight 205 non-null float64 13 curbweight 205 non-null int64 14 enginetype 205 non-null object 15 cylindernumber 205 non-null object 16 enginesize 205 non-null int64 17 fuelsystem 205 non-null object 18 boreratio 205 non-null float64 19 stroke 205 non-null float64 20 compressionratio 205 non-null float64 21 horsepower 205 non-null int64 22 peakrpm 205 non-null int64 23 citympg 205 non-null int64 24 highwaympg 205 non-null int64 25 price 205 non-null float64 dtypes: float64(8), int64(8), object(10) memory usage: 41.8+ KB

df.shape (205, 26) df.head(5)

0 1 3 alfa-romero

1 2 3 alfa-romero

2 3 1 alfa-romero

Quadrifoglio gas std two hatchback rwd front 94.5 ... 152 mpfi 2.68 3.47 9.0 154 5000 19 26 16500.0

3 4 2 audi 100 ls gas std four sedan fwd front 99.8 ... 109 mpfi 3.19 3.40 10.0 102 5500 24 30 13950.0

4 5 2 audi 100ls gas std four sedan 4wd front 99.4 ... 136 mpfi 3.19 3.40 8.0 115 5500 18 22 17450.0

nan_count = df.isna().sum()

print(nan_count)

car_ID 0

symboling 0

CarName 0

fueltype 0

aspiration 0

doornumber 0

carbody 0

drivewheel 0

enginelocation 0

wheelbase 0

carlength 0

carwidth 0

carheight 0

curbweight 0

enginetype 0

cylindernumber 0

enginesize 0

fuelsystem 0

boreratio 0

stroke 0

compressionratio 0

horsepower 0

peakrpm 0

citympg 0

highwaympg 0

price 0 dtype: int64

print(list(df))

['car_ID', 'symboling', 'CarName', 'fueltype', 'aspiration', 'doornumber', 'carbody', 'drivewheel', 'enginelocation', 'wheelbase', 'carlength', 'carwidth', 'carheight', 'curbweight', 'enginetype', 'cylindernumber', 'enginesiz e', 'fuelsystem', 'boreratio', 'stroke', 'compressionratio', 'horsepower', 'peakrpm', 'citympg', 'highwaympg', 'price']

df.head(2)

0 1 3 alfa-romero

1 2 3 alfa-romero

2 rows × 26 columns df.describe() In [1]:

In [2]:

In [3]:

Out[3]:

In [4]:

In [5]:

Out[5]:

In [6]:

Out[6]:

In [7]:

In [8]:

In [9]:

Out[9]:

In [10]:

(9)

car_ID symboling wheelbase carlength carwidth carheight curbweight enginesize boreratio stroke compressionratio horsepower peakrpm citympg highwaympg price count 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 205.000000 mean 103.000000 0.834146 98.756585 174.049268 65.907805 53.724878 2555.565854 126.907317 3.329756 3.255415 10.142537 104.117073 5125.121951 25.219512 30.751220 13276.710571 std 59.322565 1.245307 6.021776 12.337289 2.145204 2.443522 520.680204 41.642693 0.270844 0.313597 3.972040 39.544167 476.985643 6.542142 6.886443 7988.852332 min 1.000000 -2.000000 86.600000 141.100000 60.300000 47.800000 1488.000000 61.000000 2.540000 2.070000 7.000000 48.000000 4150.000000 13.000000 16.000000 5118.000000 25% 52.000000 0.000000 94.500000 166.300000 64.100000 52.000000 2145.000000 97.000000 3.150000 3.110000 8.600000 70.000000 4800.000000 19.000000 25.000000 7788.000000 50% 103.000000 1.000000 97.000000 173.200000 65.500000 54.100000 2414.000000 120.000000 3.310000 3.290000 9.000000 95.000000 5200.000000 24.000000 30.000000 10295.000000 75% 154.000000 2.000000 102.400000 183.100000 66.900000 55.500000 2935.000000 141.000000 3.580000 3.410000 9.400000 116.000000 5500.000000 30.000000 34.000000 16503.000000 max 205.000000 3.000000 120.900000 208.100000 72.300000 59.800000 4066.000000 326.000000 3.940000 4.170000 23.000000 288.000000 6600.000000 49.000000 54.000000 45400.000000

df=df.drop(['car_ID'],axis=1)

EDA

# Visualize the correlation matrix using Seaborn heatmap import matplotlib.pyplot as plt

import seaborn as sns plt.figure(figsize=(10, 8)) mask=np.triu(np.ones_like(Corr_mat))

sns.heatmap(Corr_mat, annot=True, cmap='coolwarm',mask=mask) plt.title('Correlation Matrix')

plt.show()

Relations with price :carlength,carwidth,cubweight,highwaympg,carheight

#Boxplot of all the categorical variables plt.figure(figsize=(50, 45)) plt.subplot(3,3,1)

sns.boxplot(x = 'doornumber', y = 'price', data = df)

# plt.subplot(3,3,2)

# sns.boxplot(x = 'fueltype', y = 'price', data = df)

# plt.subplot(3,3,3)

# sns.boxplot(x = 'aspiration', y = 'price', data = df) plt.show()

Out[10]:

In [12]:

In [25]:

In [26]:

(10)

numerical_columns_without_price_carID = [col for col in numerical_columns if col not in ['price', 'car_ID']]

X = df[['carlength','carwidth','curbweight','carheight','highwaympg']]

y=df['price']

X

carlength carwidth curbweight carheight highwaympg

0 168.8 64.1 2548 48.8 27

1 168.8 64.1 2548 48.8 27

2 171.2 65.5 2823 52.4 26

3 176.6 66.2 2337 54.3 30

4 176.6 66.4 2824 54.3 22

... ... ... ... ... ...

200 188.8 68.9 2952 55.5 28

201 188.8 68.8 3049 55.5 25

202 188.8 68.9 3012 55.5 23

203 188.8 68.9 3217 55.5 27

204 188.8 68.9 3062 55.5 25

205 rows × 5 columns Using Keras import tensorflow from tensorflow import keras from tensorflow.keras import Sequential from tensorflow.keras.layers import Dense from tensorflow.keras.layers import Dropout from keras import regularizers from keras.layers import BatchNormalization

2024-02-29 18:28:23.497298: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-02-29 18:28:23.497440: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-02-29 18:28:23.665785: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered

Model Building

model = Sequential()

model.add(Dense(10, activation='relu', input_dim=X_train.shape[1])) model.add(Dense(10, activation='relu'))

model.add(Dense(1, activation='linear'))

model.summary() Model: "sequential"

_________________________________________________________________

Layer (type) Output Shape Param #

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

dense (Dense) (None, 10) 60 dense_1 (Dense) (None, 10) 110 dense_2 (Dense) (None, 1) 11

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

Total params: 181 (724.00 Byte) Trainable params: 181 (724.00 Byte) Non-trainable params: 0 (0.00 Byte)

_________________________________________________________________

from tensorflow.keras.optimizers import SGD,Adam

# sgd = SGD(lr=0.0009) lr is the learning rate, momentum is an optional parameter model.compile(optimizer="Adam",loss='mean_squared_error')

history = model.fit(X_train,y_train,batch_size=10,epochs=100,verbose=1,validation_split=0.2) In [27]:

In [28]:

Out[28]:

In [34]:

In [35]:

In [36]:

In [37]:

In [38]:

In [39]:

(11)

Epoch 1/100

(12)

15/15 [==============================] - 0s 4ms/step - loss: 0.2232 - val_loss: 0.1385 y_pred = model.predict(X_test)

1/1 [==============================] - 0s 93ms/step

Accuracy and evaluation

from sklearn.metrics import r2_score r2_score(y_test,y_pred) 0.7284987359245992 plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) [<matplotlib.lines.Line2D at 0x7fa37dede7a0>]

In [40]:

In [ ]:

In [41]:

Out[41]:

In [42]:

Out[42]:

(13)

Lab-4 Loading Data**

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns import tensorflow as tf import warnings

df = pd.read_csv(r"D:\\projects\\DL labs\\laptop_data (Lab4).csv") df.head()

brand processor_brand processor_name processor_gnrtn ram_gb ram_type ssd hdd os os_bit graphic_card_gb weight warranty Touchscreen msoffice Price rating Number of Ratings Number of Reviews

0 ASUS Intel Core i3 10th 4 GB DDR4 0 GB 1024 GB Windows 64-bit 0 GB Casual No warranty No No 34649 2 stars 3 0

1 Lenovo Intel Core i3 10th 4 GB DDR4 0 GB 1024 GB Windows 64-bit 0 GB Casual No warranty No No 38999 3 stars 65 5

2 Lenovo Intel Core i3 10th 4 GB DDR4 0 GB 1024 GB Windows 64-bit 0 GB Casual No warranty No No 39999 3 stars 8 1

3 ASUS Intel Core i5 10th 8 GB DDR4 512 GB 0 GB Windows 32-bit 2 GB Casual No warranty No No 69990 3 stars 0 0

4 ASUS Intel Celeron Dual Not Available 4 GB DDR4 0 GB 512 GB Windows 64-bit 0 GB Casual No warranty No No 26990 3 stars 0 0

print(df.shape) (823, 19)

df.isna().sum()

brand 0

processor_brand 0

processor_name 0

processor_gnrtn 0

ram_gb 0

ram_type 0

ssd 0

hdd 0

os 0

os_bit 0

graphic_card_gb 0

weight 0

warranty 0

Touchscreen 0

msoffice 0

Price 0

rating 0

Number of Ratings 0

Number of Reviews 0

dtype: int64 df.duplicated().sum() 21 df.info() <class 'pandas.core.frame.DataFrame'> Int64Index: 802 entries, 0 to 822 Data columns (total 19 columns): # Column Non-Null Count Dtype --- --- --- --- 0 brand 802 non-null object 1 processor_brand 802 non-null object 2 processor_name 802 non-null object 3 processor_gnrtn 802 non-null object 4 ram_gb 802 non-null object 5 ram_type 802 non-null object 6 ssd 802 non-null object 7 hdd 802 non-null object 8 os 802 non-null object 9 os_bit 802 non-null object 10 graphic_card_gb 802 non-null object 11 weight 802 non-null object 12 warranty 802 non-null object 13 Touchscreen 802 non-null object 14 msoffice 802 non-null object 15 Price 802 non-null int64 16 rating 802 non-null object 17 Number of Ratings 802 non-null int64 18 Number of Reviews 802 non-null int64 dtypes: int64(3), object(16) memory usage: 125.3+ KB df.nunique() brand 8

processor_brand 3

processor_name 11

processor_gnrtn 8

ram_gb 4

ram_type 6

ssd 7

hdd 4

os 3

os_bit 2

graphic_card_gb 5

weight 3

warranty 4

Touchscreen 2

msoffice 2

Price 405

rating 5

Number of Ratings 282

Number of Reviews 135 dtype: int64 df.describe()

Price Number of Ratings Number of Reviews count 802.000000 802.00000 802.000000

mean 76625.543641 299.84414 36.089776

std 45232.984422 1001.78442 118.313553

min 16990.000000 0.00000 0.000000

25% 45990.000000 0.00000 0.000000

50% 63990.000000 17.00000 2.000000

75% 89525.000000 140.25000 18.000000

max 441990.000000 15279.00000 1947.000000

EDA

3.1 Histograms

fig, axs = plt.subplots(1, 2, figsize=(15, 7)) plt.subplot(121)

sns.histplot(data=df, x= 'Price', bins=30, kde=True, color='g') plt.subplot(122)

sns.histplot(data=df, x= 'Price', bins=30, kde=True, color='g', hue= 'rating') plt.show()

In [1]:

In [2]:

In [3]:

Out[3]:

In [4]:

In [5]:

Out[5]:

In [6]:

Out[6]:

In [8]:

In [9]:

Out[9]:

In [10]:

Out[10]:

In [12]:

(14)

fig, axs = plt.subplots(1, 2, figsize=(15, 7)) plt.subplot(121)

sns.histplot(data=df,x='Number of Ratings',bins=10,kde=True,color='g') plt.subplot(122)

sns.histplot(data=df,x='Number of Reviews',kde=True, bins = 10) plt.show()

f,ax=plt.subplots(1,2,figsize=(25,10)) Group_data = df.groupby('brand')

sns.barplot(x = Group_data ['Price'].mean().index, y = Group_data['Price'].mean().values,ax= ax[0], palette = 'mako') for container in ax[0].containers:

ax[0].bar_label(container,color='black',size=20) ax[0].set_xlabel("Brand")

ax[0].set_ylabel("Price")

palette_color = sns.color_palette('summer')

plt.pie(x = df['brand'].value_counts(),labels=df['brand'].value_counts().index,autopct='%.0f%%',shadow=True, colors= palette_color) plt.show()

class LogScaling(BaseEstimator, TransformerMixin):

def fit(self, X):

return self def transform(self, X):

return np.log1p(X) X = df.drop('Price', axis = 1) y = df.Price

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.1,random_state= 1) X_train.shape, X_test.shape

((474, 18), (53, 18)) In [13]:

In [16]:

In [25]:

In [27]:

In [28]:

Out[28]:

(15)

preprocessor = TransformationPipeline().preprocess() X_train = preprocessor.fit_transform(X_train) X_test = preprocessor.transform(X_test)

Model Building

models = { 'ridge' : Ridge(), 'xgboost' : XGBRegressor(), 'catboost' : CatBoostRegressor(verbose=0), 'lightgbm' : LGBMRegressor(),

'gradient boosting' : GradientBoostingRegressor(), 'lasso' : Lasso(),

'random forest' : RandomForestRegressor(), 'support vector': SVR(),

'ada boost regressor': AdaBoostRegressor() }

for name, model in models.items():

model.fit(X_train, y_train) print(f'{name} trained') ridge trained

xgboost trained catboost trained lightgbm trained gradient boosting trained lasso trained random forest trained support vector trained ada boost regressor trained

model = tf.keras.Sequential() model.add(tf.keras.layers.Dense(79)) model.add(tf.keras.layers.Dense(200)) model.add(tf.keras.layers.Dense(200)) model.add(tf.keras.layers.Dense(200)) model.add(tf.keras.layers.Dense(1)) model.compile(

loss = 'mse',

optimizer = tf.keras.optimizers.Adam(),

metrics = [tf.keras.metrics.RootMeanSquaredError(name='rmse')]

)

model.fit(X_train.toarray(), y_train, validation_data=(X_test.toarray(), y_test), epochs=10) Epoch 1/50

15/15 [==============================] - 2s 20ms/step - loss: 6034421248.0000 - rmse: 77681.5391 - val_loss: 6234427392.0000 - val_rmse: 78958.3906 Epoch 2/50

15/15 [==============================] - 0s 5ms/step - loss: 139299664.0000 - rmse: 11802.5283 - val_loss: 126747960.0000 - val_rmse: 11258.2393 In [29]:

In [30]:

In [31]:

In [32]:

(16)

<keras.callbacks.History at 0x7cf614465540>

RMSE_ann = model.evaluate(X_test.toarray(), y_test)[1]

RMSE_ann

2/2 [==============================] - 0s 5ms/step - loss: 126747960.0000 - rmse: 11258.2393 11258.2392578125

Accuracy and evaluation

print(f'RMSE: {np.sqrt(mean_squared_error(y_test, final_predictions))}') print(f'R-square: {r2_score(y_test, final_predictions)}') RMSE: 12058.878884898246

R-square: 0.8240078900192354

# Distribution of error plt.figure(figsize = (10, 6))

sns.histplot(y_test - final_predictions, color = '#005b96', kde= True) plt.xlabel('Error');

Out[32]:

In [33]:

Out[33]:

In [39]:

In [41]:

(17)

 

LAB-5 Load Data

import pandas as pd import numpy as np

import matplotlib.pyplot as plt import seaborn as sns

%matplotlib inline

dataset=pd.read_csv(r"D:\projects\DL labs\MobilePrice(Lab5).csv") dataset.head(2)

battery_power blue clock_speed dual_sim fc four_g int_memory m_dep mobile_wt n_cores ... px_height px_width ram sc_h sc_w talk_time three_g touch_screen wifi price_rang

0 842 0 2.2 0 1 0 7 0.6 188 2 ... 20 756 2549 9 7 19 0 0 1

1 1021 1 0.5 1 0 1 53 0.7 136 3 ... 905 1988 2631 17 3 7 1 1 0

dataset.info()

# Column Non-Null Count Dtype --- --- --- --- 0 battery_power 2000 non-null int64 1 blue 2000 non-null int64 2 clock_speed 2000 non-null float64 3 dual_sim 2000 non-null int64 4 fc 2000 non-null int64 5 four_g 2000 non-null int64 6 int_memory 2000 non-null int64 7 m_dep 2000 non-null float64 8 mobile_wt 2000 non-null int64 9 n_cores 2000 non-null int64 10 pc 2000 non-null int64 11 px_height 2000 non-null int64 12 px_width 2000 non-null int64 13 ram 2000 non-null int64 14 sc_h 2000 non-null int64 15 sc_w 2000 non-null int64 16 talk_time 2000 non-null int64 17 three_g 2000 non-null int64 18 touch_screen 2000 non-null int64 19 wifi 2000 non-null int64 20 price_range 2000 non-null int64 dtypes: float64(2), int64(19)

memory usage: 328.2 KB dataset.describe()

battery_power blue clock_speed dual_sim fc four_g int_memory m_dep mobile_wt n_cores ... px_height px_width ram sc_h count 2000.000000 2000.0000 2000.000000 2000.000000 2000.000000 2000.000000 2000.000000 2000.000000 2000.000000 2000.000000 ... 2000.000000 2000.000000 2000.000000 2000.000000 mean 1238.518500 0.4950 1.522250 0.509500 4.309500 0.521500 32.046500 0.501750 140.249000 4.520500 ... 645.108000 1251.515500 2124.213000 12.306500 std 439.418206 0.5001 0.816004 0.500035 4.341444 0.499662 18.145715 0.288416 35.399655 2.287837 ... 443.780811 432.199447 1084.732044 4.213245 min 501.000000 0.0000 0.500000 0.000000 0.000000 0.000000 2.000000 0.100000 80.000000 1.000000 ... 0.000000 500.000000 256.000000 5.000000 25% 851.750000 0.0000 0.700000 0.000000 1.000000 0.000000 16.000000 0.200000 109.000000 3.000000 ... 282.750000 874.750000 1207.500000 9.000000 50% 1226.000000 0.0000 1.500000 1.000000 3.000000 1.000000 32.000000 0.500000 141.000000 4.000000 ... 564.000000 1247.000000 2146.500000 12.000000 75% 1615.250000 1.0000 2.200000 1.000000 7.000000 1.000000 48.000000 0.800000 170.000000 7.000000 ... 947.250000 1633.000000 3064.500000 16.000000 max 1998.000000 1.0000 3.000000 1