Linear Regression Implementation in Python

Linear regression implementation in python

In this post I  gonna wet your hands with coding part too, Before we drive further. let me show what type of  examples we gonna solve today.

1) Predicting house price for ZooZoo.


  • ZooZoo gonna buy new house, so we have to find how much it will cost a particular house.

2) Predicting which Television Show will have more viewers for next week



The Flash and Arrow are my favorite Television ( Tv ) shows. i want to find which Tv show will get more viewers in upcoming  week. Frankly i am so excited to know which show will get more viewers.

 3) Replacing missing values using linear Regression

You have to solve this problem i will explain every thing you have to do. so please try to solve this problem.

So let’s drive into coding part

I believe you have installed all the required packages which i specified in my previous post. If not please take some time and install all the packages in this post  python packages for datamining. It would better once your go through Linear Regression post.

1) Predicting cost price of  a house for ZooZoo.


ZooZoo have the following data set


No.             square_feet                 price     
1 150 6450
2 200 7450
3 250 8450
4 300 9450
5 350 11450
6 400 15450
7 600 18450




About data set:

  • Square feet is the  Area of house.
  • Price is the corresponding cost of  that house.

Steps to Follow :

  • As we learn linear regression we know that we have to find linear line for this data so that we can get  θ0 and θ1.
  • As you remember our hypothesis equation looks like this

Image [7]


  • hθ(x) is nothing but the value price(which we are going to predicate ) for particular square_feet  ( means price is a linear function of square_feet)
  • θ0 is a constant
  • θ1 is the regression coefficient

As we clear what we have to do, let’s start coding.

STEP – 1 :

  • First open your favorite text editor and name it as
  • The below packages we gonna use in our program ,so  copy them in your file.



  • Just run your code once. if your program is error free then most of the job was done. If you facing  any errors , this means you missed some  packages so please go to this packages page  
  • Install all the packages in that blog post and run your code once again . This time most probably you will never face any problem.
  • Means your program is error free now so we can go to STEP – 2.

STEP – 2

  • I stored our data set in to a csv file with name input_data.csv
  • So let’s write a function to get our data into X values ( square_feet  ) Y values (Price)


Line 3:

Reading csv data to pandas DataFrame.

Line 6-9:

Converting pandas dataframe data to x_parameter and y_parameter data returning them

So let’s print our x_parameters and y_parameters


Script Output

Step – 3

we converted data to X_parameters and Y_parameter so let’s fit our X_parameters and Y_parameters to Linear Regression model

So we gonna write a function which will take  x_parameters ,y_parameter and the value you gonna predict  as input and return the θ0 ,θ1  and predicted value



Line 5-6:

First we are creating an linear model and the training it with our X_parameters and Y_parameters

Line 8-12:

we are creating one dictionary with name predictions and storing θ0 ,θ1  and predicted values. and returning predictions dictionary as an output.

So let’s call our function with predicting value as 700


Script Output:

Here Intercept value is nothing but   θ0 value and coefficient value is nothing but  θ1 value.

We got the predicted values as 21915.4255 means we done our job of predicting the house price.

For checking purpose we have to see how our data fit to linear regression.So we have to write a function which takes X_parameters and Y_parameters as input and show the linear line fitting for our data.

So let call our show_linear_line Function


Script Output:



2) Predicting which Television Show will have more viewers


About The FLASH Tv show:


      The Flash is an American television series developed by writer/producers Greg Berlanti, Andrew Kreisberg and Geoff Johns, airing on The CW. It is based on the DC Comics character Flash (Barry Allen), a costumed superhero crime-fighter with the power to move at superhuman speeds, who was created by Robert Kanigher, John Broome andCarmine Infantino. It is a spin-off from Arrow, existing in the same universe. The pilot for the series was written by Berlanti, Kreisberg and Johns, and directed by David Nutter. The series premiered in North America on October 7, 2014, where the pilot became the most watched telecast for The CW.

About Arrow Tv Show:


         Arrow is an American television series developed by writer/producers Greg Berlanti, Marc Guggenheim, and Andrew Kreisberg. It is based on the DC Comics characterGreen Arrow, a costumed crime-fighter created by Mort Weisinger and George Papp. It premiered in North America on The CW on October 10, 2012, with international broadcasting taking place in late 2012. Primarily filmed in Vancouver, British Columbia, Canada, the series follows billionaire playboy Oliver Queen, portrayed by Stephen Amell, who, after five years of being stranded on a hostile island, returns home to fight crime and corruption as a secret vigilante whose weapon of choice is a bow and arrow. Unlike in the comic books, Queen does not initially go by the alias “Green Arrow”.

As both of these are my best-loved Tv show when ever i am watching these shows i feel myself which show have more viewers and i am so interested to guess which show will have more viewers.

So lets write a program which guess( predict ) which Tv Show will have more viewers.

For free drive of our program we need some dataset which having both shows viewers for each episode. Luckly i got this data from Wikipidia and prepared an csv file. It’s looks  like this.

flash_episode flash_us_viewers arrow_episode arrow_us_viewers
1 4.83 1 2.84
2 4.27 2 2.32
3 3.59 3 2.55
4 3.53 4 2.49
5 3.46 5 2.73
6 3.73 6 2.6
7 3.47 7 2.64
8 4.34 8 3.92
9 4.66 9 3.06

About data set:

Us viewers ( millions )

Step by steps to solving this problem:

  • First we have to convert our data to x_parameters and y_parameters but here we have two x_parameters and y_parameters so lets’s name them as flash_x_parameter, flash_y_parameter, arrow_x_parameter , arrow_y_parameter.
  • Then we have to fit our data to two different  linear regression models first for flash and other for arrow.
  • Then we have to predict the number of viewers for next episode for both of the Tv shows.
  • Then we can compare the results and we can guess which Tv Shows will have more viewers.

Let’s drive to code this interesting problem.


We have to import our packages


Converting our data to flash_x_parameter,flash_y_parameter,arrow_x_parameter ,arrow_y_parameter so lets write a function which will take our data set as input and returns lash_x_parameter,flash_y_parameter,arrow_x_parameter ,arrow_y_parameter values.



now we have  flash_x_parameters,flash_y_parameters,arrow_x_parameters,arrow_y_parameters. so let’s write a function which will take these above parameters as input and gives an output as which show will have more views.

So let’s write every thing in one file open your editor and name it as and copy this total code into file.

Run this program and see which Tv show will have more viewers.

You can get all the complete codes of dataaspirant at dataaspirant data science codes

 3) Replacing missing values using linear Regression

     some times we have a situation where we have to do analysis on data which consists of missing values. Some people will remove these missing values and they continue  analysis and some people replace them with min value or max value or mean value it’s good to replace missing value with mean value but so time it’s not the right way to replace missing with mean value so we can use linear regression to replace those missing value very effectively.

This approach goes some thing like this.

First we have find which column we gonna replace missing values and we have to find on which columns this missing values column values more depends on ,then we have to remove the missing value rows. Then consider missing values column as Y_parameters and consider the columns on which this missing values more depend as X_parameters and fit this data to Linear regression model . Now predict the missing values in missing values column by consider the columns on which this missing values column more depends.

Once all this process completed  we will get data without any missing values so we are free to analysis data.

For practice i leave this problem to you so please kindly get some missing values data from online and solve this problem. Leave your comments once you completed .i so happy to view them.

 Small personal note:

I want to share my personal experience with data mining. I remember in my introductory  datamining classes The instructor starts slow and explains some interesting areas where we can apply datamining and some very basic concepts so i and my friends understand every thing and we show more interest towards datamining. Then suddenly the difficulty leave will sky rocket. This makes a lot of my friends in class feel like extremely frustrated and intimated by course and ultimately they left interest on datamining. So i want to avoid this thing in my blog posts. In my blog post i want to make thing more easygoing this would be possible only when i explain things  with some interest examples moreover i want to make my blog viewers more comfortable learning without any boring so i am in that spirit which leads me towards use this examples.

Follow us:


I hope you like this post. If you have any questions then feel free to comment below.  If you want me to write on one specific topic then do tell it to me in the comments below.

42 Responses to “Linear Regression Implementation in Python

  • I am getting x is not defined while giving show_linear(x,y).
    I got x and y values as output also got Intercept value 1771.80851064
    coefficient [ 28.77659574]
    Predicted value: [ 21915.42553191]
    but while running show_linear(x,y) getting x is not defined

  • Bhuvaneshwaran
    5 years ago

    Hi Saimadhu,

    Your post is very nice and more useful. I have one small suggestion for you that please make some formatting’s (Use indentation) in your code part. It will be more easy to understand soon. Thank you for your post 🙂

    • Hi Bhuvaneshwaran,

      Thanks for your compliment. We were so happy for you suggestion too. Will update the code with proper indentation.

  • Abhishek singh
    5 years ago

    Hello Saimadhu

    Can you please upload multiple linear regression code example as well .


    • Hi Abhishek,
      Soon I will share you the multiple linear regression codes.

      • Abhishek singh
        5 years ago

        Thanks saimadhu

        Eagerly waiting for those samples . Meanwhile awesome job with linear regression code example .

      • Abhishek singh
        5 years ago

        Hello saimadhu

        sorry for bothering again but any luck with multiple linear regression code example

  • Hello, saimadhu. I make Guthub Repository for this article. Github Page for this Repository^

  • This blog is awesome idea, friend.
    I have a working algorithm for linear regression, compiled on the materials of your blog. Algorithm works on Python version 2.7.x and 3.4.x
    Look it here:

  • I have a working algorithm for linear regression, compiled on the materials of your blog. The algorithm works on Python version 2.7.x and 3.4.x
    Look it here:
    This blog is awesome idea, friend!

  • fantabulous ….!!!

  • Really enjoyed this post. Nice into and like what you did in section 3. I tend to use mean values for missing data, but using linear regresssion is pretty cool actually. Will do next time.

    Also… some of the imports were unused in sample code, so I cleaned it up some. Here it is

    # Required Packages
    import matplotlib.pyplot as plt
    import pandas as pd
    from sklearn import linear_model

  • It’s remarkable in support of me to have a web site,
    which is useful in favor of my knowledge. thanks admin

  • Shashank
    6 years ago

    You have solved regression for one variable what to do if 3 or more variables are present y=c1*x1+2*x2

  • It’s actually a great and useful piece of info. I’m glad that you shared this useful
    information with us. Please stay us up to date like this.
    Thanks for sharing.

  • Pretty portion of content. I just stumbled upon your weblog
    and in accession capital to claim that I acquire in fact
    enjoyed account your blog posts. Anyway I will be subscribing in your feeds or even I fulfillment you get right of entry to
    consistently rapidly.

  • This tutorial is great! But i’m pretty new to this and i have a question:

    predicted_value1 = regr1.predict(9)

    what does the “9” represent in this line of code for example 2?

    • Hi Nosy Nittany thanks for asking about it actually we are predicting how many viewers will be for 9 episode that’s why we we are calling our predicted function with value 9.

  • Anonymous
    7 years ago

    Wonderful … Math is cool… 🙂

  • I just released an IPython Notebook with a more detailed introduction to linear regression in Python, and thought your readers might be interested!

  • Wow! Thank you so much. Waiting for logistic regression. Do you have more business examples as share?

    • Hi XiaoXiao Sam
      Thank’s for your complement.
      now i posting recommendations stuff, once it completed i will write a post on Logistic regression. Coming to your question i have some pretty good examples related to business soon i will explain with business examples.
      Thank’s for your advice XiaoXial Sam

  • Brother your tutorial rocked. Expecting tutorial on logistic regression next time

  • Anonymous
    7 years ago

    thank you for this blog. I wanted to start ML in python after octave, and this is the perfect way.

  • Traceback (most recent call last):
    File “”, line 19, in
    X,Y = get_data(‘input_data.csv’)
    File “”, line 14, in get_data
    for single_square_feet ,single_price_value in zip(data[‘square_feet’],data[‘price’]):
    File “/usr/lib/python2.7/dist-packages/pandas/core/”, line 1658, in __getitem__
    return self._getitem_column(key)
    File “/usr/lib/python2.7/dist-packages/pandas/core/”, line 1665, in _getitem_column
    return self._get_item_cache(key)
    File “/usr/lib/python2.7/dist-packages/pandas/core/”, line 1005, in _get_item_cache
    values = self._data.get(item)
    File “/usr/lib/python2.7/dist-packages/pandas/core/”, line 2874, in get
    _, block = self._find_block(item)
    File “/usr/lib/python2.7/dist-packages/pandas/core/”, line 3186, in _find_block
    File “/usr/lib/python2.7/dist-packages/pandas/core/”, line 3193, in _check_have
    raise KeyError(‘no item named %s’ % com.pprint_thing(item))
    KeyError: u’no item named square_feet’

Leave a Reply to Shashank Cancel reply

Your email address will not be published. Required fields are marked *