Passing an input to get predicted Vehicle Price using Linear Regression

Question

I am working on a tutorial by Dhaval Patel to create a linear regression prediction model to get a vehicle sale price based on age and mileage. The model works great but am not sure how I can pass an input to get predicted sale price as I am new to all of this but really want to learn!

Below is the basic python script to produce an outputted prediction of a sale price -

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

df = pd.read_csv("carprices.csv")
print(df)

X = df[['Mileage','Age(yrs)']]
y = df['Sell Price($)']

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2)
print(X_train)
print(X_test)

clf = LinearRegression()
clf.fit(X_train, y_train)

clf.predict(X_test)
print(y_test)

print(clf.score(X_test, y_test))


# carprices.csv data structure
    Mileage  Age(yrs)  Sell Price($)
    0     69000         6          18000
    1     35000         3          34000
    2     57000         5          26100
    etc..

======= Output ======
# array with predicted sale prices
array([25246.47327651, 16427.86889147, 27671.99607064, 25939.47978912])

#Output of test data
5     26750
14    19400
19    28200
2     26100
Name: Sell Price($), dtype: int64
0.7512386644573188

So basically its splitting the csv data into 2 sections for training and test data which test data is 20% of the data set. What I would like to do is pass and input of age and mileage of a certain vehicle and have the model predict what the sale price would be based on that single input. Where would I add this input?

Link to github example - https://github.com/codebasics/py/blob/master/ML/6_train_test_split/train_test_split.ipynb

Prune Prune · Accepted Answer · 2019-11-22T20:49:05

This is readily available from any tutorial ... with one bit of understanding.

clf.predict(vect)

is a function that returns a prediction for the input vector, vect. When you do this on the test set, you get data to evaluate the test accuracy. To get a prediction for one input, give that single input as an argument.

To make use of this, you have to catch the return value:

vect_pred = clf.predict(vect).  Is that what you needed?

Passing an input to get predicted Vehicle Price using Linear Regression

1 Answers