Machine Learning Project – Car Price Prediction

Program 1

Machine Learning Dataset

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import metrics 
#pandas                    2.2.2
#numpy                     1.24.3
#matplotlib                3.7.1
#scikit-learn              1.5.1



# Read data set 
df=pd.read_csv("D://scikit_data/car/car_data.csv")
df.head()


type(df)


# No of Rows & Columns 
df.shape


# Dispaly information about dataset
df.info()


# Infomrmation about missing values
df.isnull().sum()


# Check categorical data
print(df.Fuel_Type.value_counts())
print(df.Seller_Type.value_counts())
print(df.Transmission.value_counts())


# Replace Character values

df.replace({'Fuel_Type':{'Petrol':0,'Diesel':1,'CNG':2}},inplace=True)
df.replace({'Seller_Type':{'Dealer':0,'Individual':1}},inplace=True)
df.replace({'Transmission':{'Manual':0,'Automatic':1}},inplace=True)




df.head()


# Find Depended and Independed variables
x=df.drop(['Car_Name','Selling_Price'],axis='columns')  # Independed variables 


y=df['Selling_Price']  # Depended variables


x


y


# Split data into training and testing data
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.1,random_state=2)


# x_train  ---> training independed variable
# y_train --->  training depended variable
# x_test  ---> test independed variable
# y_test --->  test depended variable



len(x_train)


len(x_test)


# Model Prepration
model=LinearRegression()
model.fit(x_train,y_train)


y_pred_train=model.predict(x_train)


y_train


plt.scatter(y_train,y_pred_train,marker='.',color='blue')
plt.xlabel("Actual Price")
plt.ylabel("Predicated Price")
plt.title("Actual Price vs Predicated Price")
plt.show()



error_score=metrics.r2_score(y_train,y_pred_train)
print("R squared Error for training data set ", error_score)


# Predication an testing data

y_pred_test=model.predict(x_test)


plt.scatter(y_test,y_pred_test,marker='.',color='red')
plt.xlabel("Actual Price")
plt.ylabel("Predicated Price")
plt.title("Actual Price vs Predicated Price")
plt.show()



error_score=metrics.r2_score(y_test,y_pred_test)
print("R squared Error for training data set ", error_score)


model.score(x_test,y_test)