1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137 | """
Importing the Dependencies
"""
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Lasso
from sklearn import metrics
"""Data Collection and Processing"""
# loading the data from csv file to pandas dataframe
car_dataset = pd.read_csv('/content/car data.csv')
# inspecting the first 5 rows of the dataframe
car_dataset.head()
# checking the number of rows and columns
car_dataset.shape
# getting some information about the dataset
car_dataset.info()
# checking the number of missing values
car_dataset.isnull().sum()
# checking the distribution of categorical data
print(car_dataset.Fuel_Type.value_counts())
print(car_dataset.Seller_Type.value_counts())
print(car_dataset.Transmission.value_counts())
"""Encoding the Categorical Data"""
# encoding "Fuel_Type" Column
car_dataset.replace({'Fuel_Type':{'Petrol':0,'Diesel':1,'CNG':2}},inplace=True)
# encoding "Seller_Type" Column
car_dataset.replace({'Seller_Type':{'Dealer':0,'Individual':1}},inplace=True)
# encoding "Transmission" Column
car_dataset.replace({'Transmission':{'Manual':0,'Automatic':1}},inplace=True)
car_dataset.head()
"""Splitting the data and Target"""
X = car_dataset.drop(['Car_Name','Selling_Price'],axis=1)
Y = car_dataset['Selling_Price']
print(X)
print(Y)
"""Splitting Training and Test data"""
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.1, random_state=2)
"""Model Training
1. Linear Regression
"""
# loading the linear regression model
lin_reg_model = LinearRegression()
lin_reg_model.fit(X_train,Y_train)
"""Model Evaluation"""
# prediction on Training data
training_data_prediction = lin_reg_model.predict(X_train)
# R squared Error
error_score = metrics.r2_score(Y_train, training_data_prediction)
print("R squared Error : ", error_score)
"""Visualize the actual prices and Predicted prices"""
plt.scatter(Y_train, training_data_prediction)
plt.xlabel("Actual Price")
plt.ylabel("Predicted Price")
plt.title(" Actual Prices vs Predicted Prices")
plt.show()
# prediction on Training data
test_data_prediction = lin_reg_model.predict(X_test)
# R squared Error
error_score = metrics.r2_score(Y_test, test_data_prediction)
print("R squared Error : ", error_score)
plt.scatter(Y_test, test_data_prediction)
plt.xlabel("Actual Price")
plt.ylabel("Predicted Price")
plt.title(" Actual Prices vs Predicted Prices")
plt.show()
"""2. Lasso Regression"""
# loading the linear regression model
lass_reg_model = Lasso()
lass_reg_model.fit(X_train,Y_train)
"""Model Evaluation"""
# prediction on Training data
training_data_prediction = lass_reg_model.predict(X_train)
# R squared Error
error_score = metrics.r2_score(Y_train, training_data_prediction)
print("R squared Error : ", error_score)
"""Visualize the actual prices and Predicted prices"""
plt.scatter(Y_train, training_data_prediction)
plt.xlabel("Actual Price")
plt.ylabel("Predicted Price")
plt.title(" Actual Prices vs Predicted Prices")
plt.show()
# prediction on Training data
test_data_prediction = lass_reg_model.predict(X_test)
# R squared Error
error_score = metrics.r2_score(Y_test, test_data_prediction)
print("R squared Error : ", error_score)
plt.scatter(Y_test, test_data_prediction)
plt.xlabel("Actual Price")
plt.ylabel("Predicted Price")
plt.title(" Actual Prices vs Predicted Prices")
plt.show()
|
No comments:
Post a Comment