Scribd
Upload
182 views

Linear Regression

The document discusses using linear regression on a dataset containing prices and attributes of 27,000 cubic zirconias. Some key points: - The dataset has 11 variables including price, carat weight, cut, color, clarity and other stone attributes. - Exploratory data analysis found the price and carat variables were right-skewed, and some variables had outliers. - Missing depth values were imputed with the median. Zero values in some variables were investigated. - Categorical variables were encoded. The data was 70%/30% train-test split. - Linear regression was performed on the training set, achieving an R^2 of 95% to explain price variations. The

Uploaded by

Anil Bera
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
182 views

Linear Regression

The document discusses using linear regression on a dataset containing prices and attributes of 27,000 cubic zirconias. Some key points: - The dataset has 11 variables including price, carat weight, cut, color, clarity and other stone attributes. - Exploratory data analysis found the price and carat variables were right-skewed, and some variables had outliers. - Missing depth values were imputed with the median. Zero values in some variables were investigated. - Categorical variables were encoded. The data was 70%/30% train-test split. - Linear regression was performed on the training set, achieving an R^2 of 95% to explain price variations. The

Uploaded by

Anil Bera
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 15

LINEAR REGRESSION

Problem 1: Linear Regression

You are hired by a company Gem Stones co ltd, which is a cubic zirconia manufacturer. You are provided with the dataset containing
the prices and other attributes of almost 27,000 cubic zirconia (which is an inexpensive diamond alternative with many of the same
qualities as a diamond). The company is earning different profits on different prize slots. You have to help the company in predicting
the price for the stone on the bases of the details given in the dataset so it can distinguish between higher profitable stones and lower
profitable stones so as to have better profit share. Also, provide them with the best 5 attributes that are most important.

Data Dictionary:

Variable Name Description

Carat  Carat weight of the cubic zirconia.

 Describe the cut quality of the cubic zirconia. Quality


Cut is increasing order Fair, Good, Very Good, Premium,
Ideal.

 Colour of the cubic zirconia.With D being the worst


Color 
and J the best.

 cubic zirconia Clarity refers to the absence of the


Inclusions and Blemishes. (In order from Best to Worst,
Clarity
IF = flawless, l1= level 1 inclusion) IF, VVS1, VVS2,
VS1, VS2, Sl1, Sl2, l1

 The Height of cubic zirconia, measured from the Culet


Depth
to the table, divided by its average Girdle Diameter.

 The Width of the cubic zirconia's Table expressed as a


Table
Percentage of its Average Diameter.

Price  the Price of the cubic zirconia.

X  Length of the cubic zirconia in mm.

Y  Width of the cubic zirconia in mm.

Z  Height of the cubic zirconia in mm.


Table of Content

Series Question Page no


1.1 Read the data and do exploratory data analysis. Describe the data briefly. (Check the null values, Data 3
types, shape, EDA). Perform Univariate and Bivariate Analysis.
1.2 Impute null values if present, also check for the values which are equal to zero. Do they have any 10
meaning or do we need to change them or drop them? Do you think scaling is necessary in this case?
1.3 Encode the data (having string values) for Modelling. Data Split: Split the data into train and test (70:30). 11
Apply Linear regression. Performance Metrics: Check the performance of Predictions on Train and Test
sets using Rsquare, RMSE
1.4 Inference: Basis on these predictions, what are the business insights and recommendations. 14
1.1. Read the data and do exploratory data analysis. Describe the data briefly. (Check the null values, Data types, shape, EDA). Perform
Univariate and Bivariate Analysis

Understanding the head & Tail of the dataset.

Head of the dataset

Tail of the dataset

Shape of the dataset

Type of the Dataset columnwise

 Data set contains 26967 row, 11 columns.


 In said data set there are 2 Integer type features,6 Float type features. 3 Object type features. Where 'price' is the target variable
and all other are predictor variable.
 First column is an index ("Unnamed: 0") as this only serial no, we can remove it.
Summary of the dataset

 Dataset consist of both categorical and continuous data,


 In categorical data we have cut, color and clarity whereas in continuous data we have carat, depth, table, x. y, z and price
 Target variable will be Price

If duplicate records in the dataset

If any Missing value

 we can observe there are 697 missing values in the depth column.

Unique value in categorial data


Univariate Analysis.

Measuring the skewness of every attribute

 It can see that the distribution of some quantitative features like "carat" and the target feature "price" are heavily "right-
skewed".

Checking for Outliers in the Dataset


 There is significant amount of outlier present in some variable.

Bivariate Analysis.
Getting the Correlation Heatmap

 It can be conditional that most features correlate


1.2 Impute null values if present, also check for the values which are equal to zero. Do they have any meaning or do we need to change
them or drop them? Do you think scaling is necessary in this case?

we can observe there are 697 missing values in the depth column

Imputing null values

 we can observe there are 697 missing values in the depth column hence replacing the missing values with median value.

Checking for the values which are equal to zero

we checked for 'Zero' value and we can observe there are some amounts of 'Zero' value present on the data set on variable 'x', 'y','z'.

Do you think scaling is necessary in this case?

Scaling or standardizing the features around the center and 0 with a standard deviation of 1 is important when we compare
measurements that have different units. Variables that are measured at different scales do not underwrite equally to the analysis and
might end up creating a prejudice.
With the given data set we can see the all the variable are in different scale i.e price are in 1000s unit and depth and table are in 100s
unit, and carat is in 10s. So it’s becomes necessary to scale the data to allow each variable to be compared on a common scale. Hence
recommended for regression technique
1.3 Encode the data (having string values) for Modelling. Data Split: Split the data into train and test (70:30). Apply Linear regression.
Performance Metrics: Check the performance of Predictions on Train and Test sets using Rsquare, RMSE.

Encode the data having string values

Get Dummies

Train-Test Split:

Breaking the X and y data frames into training set and test set.

Split X and y into training and test set in 70:30 ratio

Invoke the Linear Regression function and find the best fit model on training data

The coefficients for each of the independent attributes


R square on training data

R square on testing data

RMSE on Training data

RMSE on Testing data

Check Multi-collinearity using VIF

We can observe there are very strong multi collinearity present in the data set. Ideally it should be within 1 to 5.

We are exploring the Linear Regression using stats models as we are interested in some more statistical metrics of the model.

Linear Regression using stats models.


Calculate MSE

The final Linear Regression equation is


1.4 Inference: Basis on these predictions, what are the business insights and recommendations.

The predictions were able to capture 95% variations in the price and it is explained by the predictors in the training set. Using stats
model if we could run the model again, we can have P values and coefficients which will give us better understanding of the
relationship, so that values more 0.05 we can drop those variables and re run the model again for better results. For better accuracy
dropping depth column in iteration for better results.

You might also like