Welcome to the Simplilearn Community

Want to join the rest of our members? Sign up right away!

Sign Up

DATA SCIENCE WITH R | Pratul | Dec 5th 2020

DIVYA PRAKASH_3

New Member
Hello sir,
The video recording for the live class is not available for download. It has been more than 48 hours.
Kindly fix the issue.
 

Attachments

  • Screenshot 2020-12-15 at 15.49.21.png
    Screenshot 2020-12-15 at 15.49.21.png
    95.5 KB · Views: 0
Hi Raghavendra,

The class recording for the date of 12 Dec particularly is not available in my LMS. Please fix the issue as soon as possible.

Thanks
Sachin Sharma
 
unknown.png


@Pratul SVM lib is not loading, Not in Google collab and not even Jyupter.
 
Hi,

I was going through the project for submission Analyze the Sales Report of a Clothes Manufacturing Outlet.
Pratul can you please answer below questions? Also should I Dress Sales.xlsx has Dates as columns. Should we build a new dataset reperesenting Dress ID, Sales_Date, Sales as columns and load data into it?

1) I see null values in data set "Attribute DataSet.csv" - Should we do data wrangling/blending to fill null values? If so, some guidance please.
2) Dress ID is common field between Attributes and Sales Data sets. Should I join these two data sets and create a new data set to build models in finding out the attributes most likely influencing sales? If so, some guidance please.
3) For Goal1/Activity1 - In case if I apply Logistic Linear Regression - both data set has 500 observations. Can we have .75 as SplitRatio?
4) For Goal2/Activity2 - Is Simple Linear Regression good enough?
5) For Goal3/Activity3 - Is Multiple Linear Regression good try?
6) For Goall4/Activity4 - ANOVA?
7) For Goal5/Activity5 - Simple Linear Regression Model?


Goal/Activities:
1) To automate the process of recommendations, the store needs to analyze the given attributes of the product, like style, season, etc., and come up with a model to predict the recommendation of products (in binary output – 0 or 1) accordingly.

2) In order to stock the inventory, the store wants to analyze the sales data and predict the trend of total sales for each dress for an extended period of three more alternative days.

3) To decide the pricing for various upcoming clothes, they wish to find how the style, season, and material affect the sales of a dress and if the style of the dress is more influential than its price.

4) Also, to increase the sales, the management wants to analyze the attributes of dresses and find which are the leading factors affecting the sale of a dress.

5) To regularize the rating procedure and find its efficiency, the store wants to find if the rating of the dress affects the total sales.
 
My Code for Activity1/Task1 of Project1 : Analyze the sales report of a cloth manufacturing outlet

I am getting error like Object Not Found while running prediction. Also review and guide if my approach is correct for the task1/activity1.

# Set current working directory to read data files and save source code etc...
setwd("C:/DataScientist/SimpliLearn-MastersInDataScience/R-Programming-Masters-Certification/Projects/Projects for Submission/Retail")

# To view current working directory use: print(getwd())
# Read data set file and assign it ot MyData variable
MyDataAttribute <- read.csv("Attribute DataSet.csv")

#We see Rating field in MyData as Numeric (0-5); so apply factor to convert categorical.
MyDataAttribute$Rating = factor(MyDataAttribute$Rating,levels = c(0,1,2,3,4,5))
class(MyDataAttribute$Rating)
View(MyDataAttribute)

# Use Logistic Regression

# Splitting the MyDataAttribut into Training and Testing set
library(caTools)
set.seed(1)
split = sample.split(MyDataAttribute$Recommendation,SplitRatio = 0.75)
training_set = subset(MyDataAttribute,split==T)
test_set = subset(MyDataAttribute,split==F)

# Feature Scaling
training_set[14] = scale(training_set[14])
test_set[14] = scale(test_set[14])

# Fitting the Logistic Regression to the Training Set
classifier = glm(formula = Recommendation ~.,
data = training_set)
classifier

# Predict the training set result
prob_pred = predict(classifier,type = 'response',newdata = training_set[14]) #type = response indicates binary class
y_pred = ifelse(prob_pred > 0.5,1,0)

# Fitting the Logistic Regression to the Test Set
classifier = glm(formula = Recommendation ~.,
data = test_set)
classifier

# Predict the test set result
prob_pred = predict(classifier,type = 'response',newdata = test_set[14]) #type = response indicates binary class
y_pred = ifelse(prob_pred > 0.5,1,0)

# Making the Confusion Matrix for Training Set
cm = table(training_set[,3],y_pred > 0.5)

# Making the Confusion Matrix for Test Set
cm = table(test_set[,3],y_pred > 0.5)
 
My Code for Activity1/Task1 of Project1 : Analyze the sales report of a cloth manufacturing outlet

I am getting error like Object Not Found while running prediction. Also review and guide if my approach is correct for the task1/activity1.

# Set current working directory to read data files and save source code etc...
setwd("C:/DataScientist/SimpliLearn-MastersInDataScience/R-Programming-Masters-Certification/Projects/Projects for Submission/Retail")

# To view current working directory use: print(getwd())
# Read data set file and assign it ot MyData variable
MyDataAttribute <- read.csv("Attribute DataSet.csv")

#We see Rating field in MyData as Numeric (0-5); so apply factor to convert categorical.
MyDataAttribute$Rating = factor(MyDataAttribute$Rating,levels = c(0,1,2,3,4,5))
class(MyDataAttribute$Rating)
View(MyDataAttribute)

# Use Logistic Regression

# Splitting the MyDataAttribut into Training and Testing set
library(caTools)
set.seed(1)
split = sample.split(MyDataAttribute$Recommendation,SplitRatio = 0.75)
training_set = subset(MyDataAttribute,split==T)
test_set = subset(MyDataAttribute,split==F)

# Feature Scaling
training_set[14] = scale(training_set[14])
test_set[14] = scale(test_set[14])

# Fitting the Logistic Regression to the Training Set
classifier = glm(formula = Recommendation ~.,
data = training_set)
classifier

# Predict the training set result
prob_pred = predict(classifier,type = 'response',newdata = training_set[14]) #type = response indicates binary class
y_pred = ifelse(prob_pred > 0.5,1,0)

# Fitting the Logistic Regression to the Test Set
classifier = glm(formula = Recommendation ~.,
data = test_set)
classifier

# Predict the test set result
prob_pred = predict(classifier,type = 'response',newdata = test_set[14]) #type = response indicates binary class
y_pred = ifelse(prob_pred > 0.5,1,0)

# Making the Confusion Matrix for Training Set
cm = table(training_set[,3],y_pred > 0.5)

# Making the Confusion Matrix for Test Set
cm = table(test_set[,3],y_pred > 0.5)
Hi, I am working on your project? I am submitting the same.
 
Top