In [1]:
!pip install matplotlib
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
Requirement already satisfied: matplotlib in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (3.10.5) Requirement already satisfied: contourpy>=1.0.1 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (1.3.3) Requirement already satisfied: cycler>=0.10 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (0.12.1) Requirement already satisfied: fonttools>=4.22.0 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (4.59.1) Requirement already satisfied: kiwisolver>=1.3.1 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (1.4.9) Requirement already satisfied: numpy>=1.23 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (2.3.2) Requirement already satisfied: packaging>=20.0 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (25.0) Requirement already satisfied: pillow>=8 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (11.3.0) Requirement already satisfied: pyparsing>=2.3.1 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (3.2.3) Requirement already satisfied: python-dateutil>=2.7 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from matplotlib) (2.9.0.post0) Requirement already satisfied: six>=1.5 in /opt/anaconda3/envs/NNM24AM045/lib/python3.13/site-packages (from python-dateutil>=2.7->matplotlib) (1.17.0)
In [2]:
# 1. Load dataset
df = pd.read_csv("car_dataset.csv")
print("Original DataFrame with Missing Values:\n", df.head())
Original DataFrame with Missing Values:
Brand Model Year Mileage Price
0 Ford Corolla 2015 35000.0 3506420
1 NaN Seltos 2021 20000.0 3665884
2 Nissan City 2012 30000.0 3669720
3 Kia Fiesta 2008 65000.0 816771
4 Honda NaN 2010 100000.0 3228009
In [3]:
# 2. Select relevant columns (you may adjust these)
df = df[['Brand', 'Model', 'Year', 'Mileage', 'Price']]
In [4]:
#3. Handle missing values
cat_imputer = SimpleImputer(strategy='most_frequent')
df[['Brand', 'Model']] = cat_imputer.fit_transform(df[['Brand', 'Model']])
num_imputer = SimpleImputer(strategy='mean')
df[['Mileage']] = num_imputer.fit_transform(df[['Mileage']])
print("after filling most frequent values:\n", df)
after filling most frequent values:
Brand Model Year Mileage Price
0 Ford Corolla 2015 35000.0 3506420
1 Hyundai Seltos 2021 20000.0 3665884
2 Nissan City 2012 30000.0 3669720
3 Kia Fiesta 2008 65000.0 816771
4 Honda Yaris 2010 100000.0 3228009
.. ... ... ... ... ...
95 Mercedes City 2005 20000.0 3009532
96 Mercedes A4 2012 90000.0 3965060
97 Ford Polo 2016 65000.0 3762565
98 Toyota Polo 2016 55000.0 1637682
99 Honda Altima 2009 20000.0 1376871
[100 rows x 5 columns]
In [5]:
df.isnull().sum()
Out[5]:
Brand 0 Model 0 Year 0 Mileage 0 Price 0 dtype: int64
In [6]:
# 4. Encode categorical variables using Label Encoding
label_enc = LabelEncoder()
df['Brand'] = label_enc.fit_transform(df['Brand'])
df['Model'] = label_enc.fit_transform(df['Model'])
print("\nDataFrame after Label Encoding:\n", df.head())
DataFrame after Label Encoding:
Brand Model Year Mileage Price
0 2 5 2015 35000.0 3506420
1 4 9 2021 20000.0 3665884
2 7 3 2012 30000.0 3669720
3 5 7 2008 65000.0 816771
4 3 11 2010 100000.0 3228009
In [7]:
# 5. Split into features (X) and target (y)
X = df.drop('Price', axis = 1)
y = df['Price']
In [8]:
# 6. Train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state=42)
In [9]:
X_train
Out[9]:
| Brand | Model | Year | Mileage | |
|---|---|---|---|---|
| 11 | 4 | 10 | 2022 | 90000.000000 |
| 47 | 6 | 7 | 2007 | 55549.450549 |
| 85 | 4 | 9 | 2016 | 95000.000000 |
| 28 | 5 | 5 | 2016 | 35000.000000 |
| 93 | 5 | 9 | 2015 | 45000.000000 |
| ... | ... | ... | ... | ... |
| 60 | 2 | 3 | 2018 | 80000.000000 |
| 71 | 1 | 5 | 2020 | 55000.000000 |
| 14 | 1 | 9 | 2020 | 85000.000000 |
| 92 | 7 | 11 | 2019 | 95000.000000 |
| 51 | 7 | 11 | 2018 | 20000.000000 |
70 rows × 4 columns
In [10]:
X_test
Out[10]:
| Brand | Model | Year | Mileage | |
|---|---|---|---|---|
| 83 | 8 | 8 | 2020 | 70000.000000 |
| 53 | 9 | 7 | 2005 | 100000.000000 |
| 70 | 7 | 0 | 2015 | 95000.000000 |
| 45 | 0 | 5 | 2018 | 35000.000000 |
| 44 | 1 | 11 | 2016 | 80000.000000 |
| 39 | 2 | 11 | 2020 | 70000.000000 |
| 22 | 4 | 3 | 2012 | 10000.000000 |
| 80 | 9 | 3 | 2005 | 60000.000000 |
| 10 | 8 | 11 | 2018 | 65000.000000 |
| 0 | 2 | 5 | 2015 | 35000.000000 |
| 18 | 2 | 8 | 2008 | 60000.000000 |
| 30 | 5 | 6 | 2010 | 15000.000000 |
| 73 | 9 | 11 | 2014 | 60000.000000 |
| 33 | 4 | 3 | 2012 | 95000.000000 |
| 90 | 3 | 4 | 2014 | 50000.000000 |
| 4 | 3 | 11 | 2010 | 100000.000000 |
| 76 | 7 | 0 | 2017 | 55549.450549 |
| 77 | 8 | 6 | 2011 | 40000.000000 |
| 12 | 9 | 11 | 2006 | 50000.000000 |
| 31 | 3 | 10 | 2010 | 60000.000000 |
| 55 | 4 | 11 | 2007 | 95000.000000 |
| 88 | 9 | 2 | 2006 | 85000.000000 |
| 26 | 1 | 1 | 2005 | 55549.450549 |
| 42 | 8 | 7 | 2021 | 60000.000000 |
| 69 | 4 | 2 | 2013 | 55549.450549 |
| 15 | 1 | 8 | 2013 | 95000.000000 |
| 40 | 3 | 11 | 2008 | 100000.000000 |
| 96 | 6 | 0 | 2012 | 90000.000000 |
| 9 | 0 | 4 | 2022 | 80000.000000 |
| 72 | 8 | 7 | 2011 | 25000.000000 |
In [11]:
y_train
Out[11]:
11 1169474
47 2068831
85 825830
28 934736
93 817313
...
60 497775
71 3338370
14 370640
92 1105497
51 305486
Name: Price, Length: 70, dtype: int64
In [12]:
y_test
Out[12]:
83 2605276 53 1173332 70 833636 45 3921581 44 3504891 39 2592156 22 975510 80 513945 10 1462928 0 3506420 18 1774271 30 2307635 73 374460 33 3564908 90 2752401 4 3228009 76 3976817 77 2076203 12 2483151 31 1526607 55 2617336 88 2436233 26 3631869 42 2303019 69 1189465 15 496582 40 766152 96 3965060 9 3432130 72 338102 Name: Price, dtype: int64
In [13]:
# 7. Choose a simple regression algorithm
model = LinearRegression()
In [14]:
# 8. Train the model
model.fit(X_train, y_train)
Out[14]:
LinearRegression()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Parameters
| fit_intercept | True | |
| copy_X | True | |
| tol | 1e-06 | |
| n_jobs | None | |
| positive | False |
In [15]:
#9. Predict on test data
y_pred = model.predict(X_test)
In [16]:
#10. Evaluate the model
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print("\nMean Squared Error:", mse)
print("R² Score:", r2)
print("Predicted Prices:", y_pred)
Mean Squared Error: 1310429300560.4426 R² Score: 0.0485831396066152 Predicted Prices: [1936342.85082553 1416911.35569305 2064340.04235218 2443835.60194065 1814914.21489114 1946350.18013101 2446714.35823572 1848731.25078733 1778565.1243111 2322047.77896295 1861693.35393571 2202746.80191359 1688560.68237921 1927458.62827893 2228317.56476024 1499362.59092441 2353063.13461213 1998583.76125237 1558753.63931746 1790584.29291802 1433220.14305107 1766737.03569607 2170458.66394874 2068159.81865765 2239185.79084721 1792293.06170612 1451638.60280731 2048399.43528088 2311249.55021169 2043351.0609955 ]
In [17]:
#11. Visualization: Actual vs Predicted
plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred, color='blue', alpha=0.7)
plt.plot([y.min(), y.max()], [y.min(), y.max()], 'r--', label='Ideal')
plt.xlabel("Actual Price")
plt.ylabel("Predicted Price")
plt.title("Actual vs Predicted Car Prices")
plt.legend()
plt.show()
