Laptop Price Prediction

August 3, 2023

[48]: import numpy as np

import pandas as pd

[49]: data=pd.read_csv('laptop_price.csv',encoding='latin-1')

[50]: data.head()

[50]: laptop_ID Company Product TypeName Inches \

0 1 Apple MacBook Pro Ultrabook 13.3
1 2 Apple Macbook Air Ultrabook 13.3
2 3 HP 250 G6 Notebook 15.6
3 4 Apple MacBook Pro Ultrabook 15.4
4 5 Apple MacBook Pro Ultrabook 13.3

ScreenResolution Cpu Ram \

0 IPS Panel Retina Display 2560x1600 Intel Core i5 2.3GHz 8GB
1 1440x900 Intel Core i5 1.8GHz 8GB
2 Full HD 1920x1080 Intel Core i5 7200U 2.5GHz 8GB
3 IPS Panel Retina Display 2880x1800 Intel Core i7 2.7GHz 16GB
4 IPS Panel Retina Display 2560x1600 Intel Core i5 3.1GHz 8GB

Gpu OpSys Weight Price_euros

0 Intel Iris Plus Graphics 640 macOS 1.37kg 1339.69
1 Intel HD Graphics 6000 macOS 1.34kg 898.94
2 Intel HD Graphics 620 No OS 1.86kg 575.00
3 AMD Radeon Pro 455 macOS 1.83kg 2537.45
4 Intel Iris Plus Graphics 650 macOS 1.37kg 1803.60

[51]: data.shape

[51]: (1303, 12)

[52]: data.isnull().sum()

[52]: laptop_ID 0
Company 0
Product 0
TypeName 0

1
 Inches 0
ScreenResolution 0
Cpu 0
Ram 0
Gpu 0
OpSys 0
Weight 0
Price_euros 0
dtype: int64

[53]: data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1303 entries, 0 to 1302
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 laptop_ID 1303 non-null int64
1 Company 1303 non-null object
2 Product 1303 non-null object
3 TypeName 1303 non-null object
4 Inches 1303 non-null float64
5 ScreenResolution 1303 non-null object
6 Cpu 1303 non-null object
7 Ram 1303 non-null object
8 Gpu 1303 non-null object
9 OpSys 1303 non-null object
10 Weight 1303 non-null object
11 Price_euros 1303 non-null float64
dtypes: float64(2), int64(1), object(9)
memory usage: 122.3+ KB

[54]: data['Ram']=data['Ram'].str.replace('GB','').astype('int32')

[55]: data['Weight']=data['Weight'].str.replace('kg','').astype('float64')

[56]: data.head()

[56]: laptop_ID Company Product TypeName Inches \

0 1 Apple MacBook Pro Ultrabook 13.3
1 2 Apple Macbook Air Ultrabook 13.3
2 3 HP 250 G6 Notebook 15.6
3 4 Apple MacBook Pro Ultrabook 15.4
4 5 Apple MacBook Pro Ultrabook 13.3

ScreenResolution Cpu Ram \

0 IPS Panel Retina Display 2560x1600 Intel Core i5 2.3GHz 8
1 1440x900 Intel Core i5 1.8GHz 8

2
 2 Full HD 1920x1080 Intel Core i5 7200U 2.5GHz 8
3 IPS Panel Retina Display 2880x1800 Intel Core i7 2.7GHz 16
4 IPS Panel Retina Display 2560x1600 Intel Core i5 3.1GHz 8

Gpu OpSys Weight Price_euros

0 Intel Iris Plus Graphics 640 macOS 1.37 1339.69
1 Intel HD Graphics 6000 macOS 1.34 898.94
2 Intel HD Graphics 620 No OS 1.86 575.00
3 AMD Radeon Pro 455 macOS 1.83 2537.45
4 Intel Iris Plus Graphics 650 macOS 1.37 1803.60

[57]: data.corr()['Price_euros']

C:\Users\Nimes\AppData\Local\Temp\ipykernel_10808\703178330.py:1: FutureWarning:
The default value of numeric_only in DataFrame.corr is deprecated. In a future
version, it will default to False. Select only valid columns or specify the
value of numeric_only to silence this warning.
data.corr()['Price_euros']

[57]: laptop_ID 0.067830

Inches 0.068197
Ram 0.743007
Weight 0.210370
Price_euros 1.000000
Name: Price_euros, dtype: float64

[58]: data.Company.value_counts()

[58]: Dell 297

Lenovo 297
HP 274
Asus 158
Acer 103
MSI 54
Toshiba 48
Apple 21
Samsung 9
Razer 7
Mediacom 7
Microsoft 6
Xiaomi 4
Vero 4
Chuwi 3
Google 3
Fujitsu 3
LG 3
Huawei 2
Name: Company, dtype: int64

3
[59]: def add_company(inpt):
if inpt=='Samsung' or inpt=='Razer' or inpt=='Mediacom' or␣
↪inpt=='Microsoft' or inpt=='Xiaomi' or inpt=='Vero' or inpt=='Chuwi' or␣

↪inpt=='Google' or inpt=='Fujitsu' or inpt=='LG' or inpt=='Huawei':

return "Other"
else:
return inpt
data["Company"]=data['Company'].apply(add_company)

[60]: data.Company.value_counts()

[60]: Dell 297

Lenovo 297
HP 274
Asus 158
Acer 103
MSI 54
Other 51
Toshiba 48
Apple 21
Name: Company, dtype: int64

[61]: len(data.Product.value_counts())

[61]: 618

[62]: data.TypeName.value_counts()

[62]: Notebook 727

Gaming 205
Ultrabook 196
2 in 1 Convertible 121
Workstation 29
Netbook 25
Name: TypeName, dtype: int64

[63]: data.ScreenResolution.value_counts()

[63]: Full HD 1920x1080 507

1366x768 281
IPS Panel Full HD 1920x1080 230
IPS Panel Full HD / Touchscreen 1920x1080 53
Full HD / Touchscreen 1920x1080 47
1600x900 23
Touchscreen 1366x768 16
Quad HD+ / Touchscreen 3200x1800 15
IPS Panel 4K Ultra HD 3840x2160 12
IPS Panel 4K Ultra HD / Touchscreen 3840x2160 11

4
 4K Ultra HD / Touchscreen 3840x2160 10
4K Ultra HD 3840x2160 7
Touchscreen 2560x1440 7
IPS Panel 1366x768 7
IPS Panel Quad HD+ / Touchscreen 3200x1800 6
IPS Panel Retina Display 2560x1600 6
IPS Panel Retina Display 2304x1440 6
Touchscreen 2256x1504 6
IPS Panel Touchscreen 2560x1440 5
IPS Panel Retina Display 2880x1800 4
IPS Panel Touchscreen 1920x1200 4
1440x900 4
IPS Panel 2560x1440 4
IPS Panel Quad HD+ 2560x1440 3
Quad HD+ 3200x1800 3
1920x1080 3
Touchscreen 2400x1600 3
2560x1440 3
IPS Panel Touchscreen 1366x768 3
IPS Panel Touchscreen / 4K Ultra HD 3840x2160 2
IPS Panel Full HD 2160x1440 2
IPS Panel Quad HD+ 3200x1800 2
IPS Panel Retina Display 2736x1824 1
IPS Panel Full HD 1920x1200 1
IPS Panel Full HD 2560x1440 1
IPS Panel Full HD 1366x768 1
Touchscreen / Full HD 1920x1080 1
Touchscreen / Quad HD+ 3200x1800 1
Touchscreen / 4K Ultra HD 3840x2160 1
IPS Panel Touchscreen 2400x1600 1
Name: ScreenResolution, dtype: int64

[64]: data["Touchscreen"]=data['ScreenResolution'].apply(lambda x:1 if "Touchscreen"␣

↪in x else 0 )

data["Ips"]=data['ScreenResolution'].apply(lambda x:1 if "IPS" in x else 0 )

[65]: data.head()

[65]: laptop_ID Company Product TypeName Inches \

0 1 Apple MacBook Pro Ultrabook 13.3
1 2 Apple Macbook Air Ultrabook 13.3
2 3 HP 250 G6 Notebook 15.6
3 4 Apple MacBook Pro Ultrabook 15.4
4 5 Apple MacBook Pro Ultrabook 13.3

ScreenResolution Cpu Ram \

0 IPS Panel Retina Display 2560x1600 Intel Core i5 2.3GHz 8

5
 1 1440x900 Intel Core i5 1.8GHz 8
2 Full HD 1920x1080 Intel Core i5 7200U 2.5GHz 8
3 IPS Panel Retina Display 2880x1800 Intel Core i7 2.7GHz 16
4 IPS Panel Retina Display 2560x1600 Intel Core i5 3.1GHz 8

Gpu OpSys Weight Price_euros Touchscreen Ips

0 Intel Iris Plus Graphics 640 macOS 1.37 1339.69 0 1
1 Intel HD Graphics 6000 macOS 1.34 898.94 0 0
2 Intel HD Graphics 620 No OS 1.86 575.00 0 0
3 AMD Radeon Pro 455 macOS 1.83 2537.45 0 1
4 Intel Iris Plus Graphics 650 macOS 1.37 1803.60 0 1

[66]: len(data.Cpu.value_counts())

[66]: 118

[67]: data['cpu_name']=data['Cpu'].apply(lambda x:" ".join(x.split()[0:3]))

[68]: data.cpu_name.value_counts()

[68]: Intel Core i7 527

Intel Core i5 423
Intel Core i3 136
Intel Celeron Dual 80
Intel Pentium Quad 27
Intel Core M 19
AMD A9-Series 9420 12
Intel Celeron Quad 8
AMD A6-Series 9220 8
AMD A12-Series 9720P 7
Intel Atom x5-Z8350 5
AMD A8-Series 7410 4
Intel Atom x5-Z8550 4
Intel Pentium Dual 3
AMD A9-Series 9410 3
AMD Ryzen 1700 3
AMD A9-Series A9-9420 2
AMD A10-Series 9620P 2
Intel Atom X5-Z8350 2
AMD E-Series E2-9000e 2
Intel Xeon E3-1535M 2
Intel Xeon E3-1505M 2
AMD E-Series 7110 2
AMD A10-Series 9600P 2
AMD A6-Series A6-9220 2
AMD A10-Series A10-9620P 2
AMD Ryzen 1600 1

6
 Intel Atom x5-Z8300 1
AMD E-Series E2-6110 1
AMD FX 9830P 1
AMD E-Series E2-9000 1
AMD A6-Series 7310 1
Intel Atom Z8350 1
AMD A12-Series 9700P 1
AMD A4-Series 7210 1
AMD FX 8800P 1
AMD E-Series 9000e 1
Samsung Cortex A72&A53 1
AMD E-Series 9000 1
AMD E-Series 6110 1
Name: cpu_name, dtype: int64

[69]: def add_cpu(inpt):

if inpt=='Intel Core i7' or inpt=='Intel Core i5' or inpt=='Intel Core i3':
return inpt
else:
if inpt.split()[0]=="AMD":
return "AMD"
else:
return 'Other'
data["cpu_name"]=data['cpu_name'].apply(add_cpu)

[70]: data.cpu_name.value_counts()

[70]: Intel Core i7 527

Intel Core i5 423
Other 155
Intel Core i3 136
AMD 62
Name: cpu_name, dtype: int64

[72]: len(data.Gpu.value_counts())

[72]: 110

[73]: data['gpu_name']=data['Gpu'].apply(lambda x:' '.join(x.split()[0:1]))

[75]: data['gpu_name'].value_counts()

[75]: Intel 722

Nvidia 400
AMD 180
ARM 1
Name: gpu_name, dtype: int64

7
[76]: data=data[data['gpu_name']!="ARM"]

[77]: data["OpSys"].value_counts()

[77]: Windows 10 1072

No OS 66
Linux 62
Windows 7 45
Chrome OS 26
macOS 13
Mac OS X 8
Windows 10 S 8
Android 2
Name: OpSys, dtype: int64

[79]: def add_os(inpt):

if inpt=='Windows 10' or inpt=='Windows 7' or inpt=='Windows 10 S':
return "Windows"
else:
if inpt=="macOS" or inpt=="Mac OS X":
return "mac"
else:
if inpt=="Linux":
return "Linux"
else:
return "Other"

data["Op_system"]=data['OpSys'].apply(add_os)

[80]: data["Op_system"].value_counts()

[80]: Windows 1125

Other 94
Linux 62
mac 21
Name: Op_system, dtype: int64

[81]: data.head()

[81]: laptop_ID Company Product TypeName Inches \

0 1 Apple MacBook Pro Ultrabook 13.3
1 2 Apple Macbook Air Ultrabook 13.3
2 3 HP 250 G6 Notebook 15.6
3 4 Apple MacBook Pro Ultrabook 15.4
4 5 Apple MacBook Pro Ultrabook 13.3

ScreenResolution Cpu Ram \

0 IPS Panel Retina Display 2560x1600 Intel Core i5 2.3GHz 8

8
 1 1440x900 Intel Core i5 1.8GHz 8
2 Full HD 1920x1080 Intel Core i5 7200U 2.5GHz 8
3 IPS Panel Retina Display 2880x1800 Intel Core i7 2.7GHz 16
4 IPS Panel Retina Display 2560x1600 Intel Core i5 3.1GHz 8

Gpu OpSys Weight Price_euros Touchscreen Ips \

0 Intel Iris Plus Graphics 640 macOS 1.37 1339.69 0 1
1 Intel HD Graphics 6000 macOS 1.34 898.94 0 0
2 Intel HD Graphics 620 No OS 1.86 575.00 0 0
3 AMD Radeon Pro 455 macOS 1.83 2537.45 0 1
4 Intel Iris Plus Graphics 650 macOS 1.37 1803.60 0 1

cpu_name gpu_name Op_system

0 Intel Core i5 Intel mac
1 Intel Core i5 Intel mac
2 Intel Core i5 Intel Other
3 Intel Core i7 AMD mac
4 Intel Core i5 Intel mac

[83]: data=data.
↪drop(columns=['laptop_ID','Inches','ScreenResolution',"Product","Cpu","Gpu",'OpSys'],axis=1)

[84]: data.head()

[84]: Company TypeName Ram Weight Price_euros Touchscreen Ips \

0 Apple Ultrabook 8 1.37 1339.69 0 1
1 Apple Ultrabook 8 1.34 898.94 0 0
2 HP Notebook 8 1.86 575.00 0 0
3 Apple Ultrabook 16 1.83 2537.45 0 1
4 Apple Ultrabook 8 1.37 1803.60 0 1

cpu_name gpu_name Op_system

0 Intel Core i5 Intel mac
1 Intel Core i5 Intel mac
2 Intel Core i5 Intel Other
3 Intel Core i7 AMD mac
4 Intel Core i5 Intel mac

[85]: data=pd.get_dummies(data)

[87]: data.head()

[87]: Ram Weight Price_euros Touchscreen Ips Company_Acer Company_Apple \

0 8 1.37 1339.69 0 1 0 1
1 8 1.34 898.94 0 0 0 1
2 8 1.86 575.00 0 0 0 0
3 16 1.83 2537.45 0 1 0 1

9
 4 8 1.37 1803.60 0 1 0 1

Company_Asus Company_Dell Company_HP … cpu_name_Intel Core i5 \

0 0 0 0 … 1
1 0 0 0 … 1
2 0 0 1 … 1
3 0 0 0 … 0
4 0 0 0 … 1

cpu_name_Intel Core i7 cpu_name_Other gpu_name_AMD gpu_name_Intel \

0 0 0 0 1
1 0 0 0 1
2 0 0 0 1
3 1 0 1 0
4 0 0 0 1

gpu_name_Nvidia Op_system_Linux Op_system_Other Op_system_Windows \

0 0 0 0 0
1 0 0 0 0
2 0 0 1 0
3 0 0 0 0
4 0 0 0 0

Op_system_mac
0 1
1 1
2 0
3 1
4 1

[5 rows x 32 columns]

[90]: x=data.drop(columns='Price_euros',axis=1)

[91]: y=data['Price_euros']

[92]: from sklearn.model_selection import train_test_split

[93]: x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

[94]: from sklearn.linear_model import LinearRegression

[97]: lr_model=LinearRegression()

[98]: lr_model.fit(x_train,y_train)

[98]: LinearRegression()

10
[99]: lr_model.score(x_test,y_test)

[99]: 0.7090551485936429

[100]: from sklearn.linear_model import Lasso

ls_model=Lasso()

[102]: ls_model.fit(x_train,y_train)

[102]: Lasso()

[103]: ls_model.score(x_test,y_test)

[103]: 0.7093688012383697

[104]: from sklearn.tree import DecisionTreeRegressor

dt_model=DecisionTreeRegressor()

[105]: dt_model.fit(x_train,y_train)

[105]: DecisionTreeRegressor()

[106]: dt_model.score(x_test,y_test)

[106]: 0.7422635361938353

[107]: from sklearn.ensemble import RandomForestRegressor

[118]: rf_model=RandomForestRegressor()

[119]: rf_model.fit(x_train,y_train)

[119]: RandomForestRegressor()

[120]: rf_model.score(x_test,y_test)

[120]: 0.7908010112911014

[121]: from sklearn.model_selection import GridSearchCV

parameters={'n_estimators':[10,50,100],'criterion':
↪['squared_error','absolute_error','poison']}

grid_obj=GridSearchCV(estimator=rf_model,param_grid=parameters)
grid_fit=grid_obj.fit(x_train,y_train)
best_model=grid_fit.best_estimator_
best_model

C:\ProgramData\anaconda3\lib\site-
packages\sklearn\model_selection\_validation.py:378: FitFailedWarning:
15 fits failed out of a total of 45.

11
 The score on these train-test partitions for these parameters will be set to
nan.
If these failures are not expected, you can try to debug them by setting
error_score='raise'.

Below are more details about the failures:

--------------------------------------------------------------------------------
15 fits failed with the following error:
Traceback (most recent call last):
File "C:\ProgramData\anaconda3\lib\site-
packages\sklearn\model_selection\_validation.py", line 686, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "C:\ProgramData\anaconda3\lib\site-packages\sklearn\ensemble\_forest.py",
line 340, in fit
self._validate_params()
File "C:\ProgramData\anaconda3\lib\site-packages\sklearn\base.py", line 581,
in _validate_params
validate_parameter_constraints(
File "C:\ProgramData\anaconda3\lib\site-
packages\sklearn\utils\_param_validation.py", line 97, in
validate_parameter_constraints
raise InvalidParameterError(
sklearn.utils._param_validation.InvalidParameterError: The 'criterion' parameter
of RandomForestRegressor must be a str among {'poisson', 'friedman_mse',
'squared_error', 'absolute_error'}. Got 'poison' instead.

warnings.warn(some_fits_failed_message, FitFailedWarning)
C:\ProgramData\anaconda3\lib\site-
packages\sklearn\model_selection\_search.py:952: UserWarning: One or more of the
test scores are non-finite: [0.73622223 0.74618136 0.74924123 0.71424087
0.74874965 0.75215125
nan nan nan]
warnings.warn(

[121]: RandomForestRegressor(criterion='absolute_error')

[122]: best_model.score(x_test,y_test)

[122]: 0.8001006095130103

[ ]:

12