Welcome, Guest
You have to register before you can post on our site.

Username/Email:
  

Password
  





Search Forums

(Advanced Search)

Forum Statistics
» Members: 50,654
» Latest member: AdelaideFo
» Forum threads: 389
» Forum posts: 395

Full Statistics

Latest Threads
What is the maximum numbe...
Forum: BDB Designer Q & A
Last Post: sariga.vr@bdb.ai
12-28-2022, 07:59 AM
» Replies: 0
» Views: 726
Inbuilt Capability of VC...
Forum: BDB - Platform
Last Post: shivani.jaipuria
12-27-2022, 05:23 AM
» Replies: 0
» Views: 507
Can dataset/cube refresh...
Forum: BDB - Platform
Last Post: shivani.jaipuria
12-27-2022, 05:08 AM
» Replies: 0
» Views: 470
How to load business stor...
Forum: BDB Designer Q & A
Last Post: sariga.vr@bdb.ai
12-26-2022, 04:47 PM
» Replies: 0
» Views: 631
How to load business stor...
Forum: BDB Designer Q & A
Last Post: sariga.vr@bdb.ai
12-26-2022, 04:46 PM
» Replies: 0
» Views: 643
How to load business stor...
Forum: BDB Designer Q & A
Last Post: sariga.vr@bdb.ai
12-26-2022, 04:45 PM
» Replies: 0
» Views: 592
How to load business stor...
Forum: BDB Designer Q & A
Last Post: sariga.vr@bdb.ai
12-26-2022, 04:44 PM
» Replies: 0
» Views: 573
Data Preparation operati...
Forum: BDB-Data Prep & ETL
Last Post: shivani.jaipuria
12-26-2022, 10:09 AM
» Replies: 0
» Views: 487
Plugability Feature of B...
Forum: BDB Platform Q & A
Last Post: shivani.jaipuria
12-26-2022, 08:32 AM
» Replies: 0
» Views: 491
How to use environment va...
Forum: BDB Platform Q & A
Last Post: archana
12-26-2022, 05:57 AM
» Replies: 0
» Views: 490

 
  What is pipeline monitoring?
Posted by: gnanashri - 12-23-2022, 05:40 AM - Forum: BDB - Data Pipeline - No Replies

You may see details about the Pipeline components, Status, Types, Last Activated (Date and Time), Last Deactivated (Date and Time), Total Allocated and Consumed CPU%, Total allocated and Consumed Memory%, Number of Records, and Component logs in this page and can analyze and monitor them. 

Print this item

  Record level and Summary level in Calculated Fields
Posted by: aishwarya.rajan@bdb.ai - 12-23-2022, 05:38 AM - Forum: BDB Business Story Q & A - No Replies

Record Level option allows the user to save the Formula field as Dimension or Measure using the Save as drop-down menu.

Summary Level option saves the created Formula Field as a Measure itself.

Print this item

  what is classification models and how do we measure the performance of models
Posted by: manjunath - 12-23-2022, 05:34 AM - Forum: DS- Lab Q&A - No Replies

Classification models are a type of machine learning model that are used to predict a categorical output value based on one or more input features. They are commonly used in applications such as spam detection, credit fraud detection, and image classification.
 
There are many different types of classification models, including logistic regression, support vector machines (SVMs), and decision trees. The specific type of classification model that is most appropriate for a particular problem will depend on the characteristics of the data and the goals of the analysis.
 
To measure the performance of a classification model, there are several metrics that are commonly used. Some common classification evaluation metrics include:
 
·        Accuracy: This is the percentage of correct predictions made by the model.
 
·        Precision: This is the percentage of true positive predictions made by the model out of all positive predictions made by the model.
 
·        Recall: This is the percentage of true positive predictions made by the model out of all actual positive cases.
 
·        F1 score: This is the harmonic mean of precision and recall.
 
·        AUC-ROC: This is the area under the receiver operating characteristic curve, which is a plot of true positive rate against false positive rate.
 
These metrics can be used to compare the performance of different classification models and to determine which model is the best fit for the data.

Print this item

  what are the different types of classification models
Posted by: manjunath - 12-23-2022, 05:32 AM - Forum: DS- Lab Q&A - No Replies

Classification models are a type of machine learning model that are used to predict a categorical output value based on one or more input features. There are many different types of classification models, including:
 
·        Logistic regression: This is a linear model that is used to predict a binary outcome (such as 0 or 1). It is based on the logistic function and is used to model the probability of an event occurring.
 
·        Support vector machines (SVMs): This is a linear model that is used to classify data points by finding the hyperplane that maximally separates the data points into different classes. It is particularly effective in cases where the data is not linearly separable.
 
·        Decision trees: This is a non-linear model that is used to classify data points by recursively partitioning the data based on a set of decision rules. It is a simple and interpretable model that can handle both numerical and categorical data.
 
·        Random forests: This is an ensemble model that is used to classify data points by combining the predictions of multiple decision trees. It is a powerful model that is resistant to overfitting and can handle high-dimensional data.
 
·        Boosting: This is an ensemble model that is used to classify data points by combining the predictions of multiple weak learners. It is a powerful model that can handle complex data and can achieve high accuracy.
 
·        Neural networks: This is a complex, non-linear model that is used to classify data points by learning a set of weights and biases through training. It is a powerful model that can handle complex data and can achieve high accuracy, but it can be resource-intensive and may require a large dataset for training.

Print this item

  Pareto Chart
Posted by: aishwarya.rajan@bdb.ai - 12-23-2022, 05:32 AM - Forum: BDB Business Story Q & A - No Replies

A Pareto chart is a type of chart that contains both bars and a line graph, where individual values are represented in descending order by bars, and the line represents the cumulative average.
Best Situation to Use a Pareto Chart is to  identify the most frequent defects, complaints, or any other factor that the users can count and categorize to focus on where improvement efforts make the most impact.
There are two variations of the Pareto chart - Pareto Pyramid and Paired Pareto chart .

Print this item

  Order By in Story (Dimensions or Measures)
Posted by: Abhiram.m - 12-23-2022, 05:31 AM - Forum: BDB Business Story Q & A - No Replies

In story order by any fields is very easy.


After creating a chart (eg: Bar Chart), we can order the bars according to the fields used.
By Default Order will be None. We can change this from the properties panel.

2 Steps:
1. Choose the type of order we want (None, Ascending, Descending, Manual) [Picture_1].
2. Select a filed in the Order By [Picture 2].



Attached Files
.png   Picture_1.png (Size: 26.46 KB / Downloads: 136)
.png   Picture_2.png (Size: 26.4 KB / Downloads: 152)
Print this item

  what is regression models and how do we measure the performance of model
Posted by: manjunath - 12-23-2022, 05:29 AM - Forum: DS- Lab Q&A - No Replies

Regression models are a type of machine learning model that are used to predict a continuous output value based on one or more input features. They are commonly used in applications such as prediction, forecasting, and trend analysis.
 
There are many different types of regression models, including linear regression, logistic regression, and support vector regression. The specific type of regression model that is most appropriate for a particular problem will depend on the characteristics of the data and the goals of the analysis.
 
To measure the performance of a regression model, there are several metrics that are commonly used. Some common regression evaluation metrics include:
 
·        Mean Absolute Error (MAE): This is the average absolute difference between the predicted values and the actual values.
 
·        Mean Squared Error (MSE): This is the average squared difference between the predicted values and the actual values.
 
·        Root Mean Squared Error (RMSE): This is the square root of the MSE.
 
·        R-squared: This is a measure of how well the model fits the data, with a value of 1 indicating a perfect fit and a value of 0 indicating no fit.
 
*      Adjusted R-squared: This is a modified version of R-squared that takes into account the number of variables in the model

Print this item

  What is the use of data sandbox?
Posted by: abhishek_acharya - 12-23-2022, 05:27 AM - Forum: BDB Data Pipeline Q & A - No Replies

In data sandbox we can add any local file and we can add that sandbox as dataset in any ds lab project 
and that file can be used in any of the data science project.

Print this item

  Pip install is not working in ds lab notebook alternative solution?
Posted by: abhishek_acharya - 12-23-2022, 05:25 AM - Forum: DS- Lab Q&A - No Replies

use this

%%bash
pip install numpy

Print this item

  what are different types of regression models available .
Posted by: manjunath - 12-23-2022, 05:23 AM - Forum: DS- Lab Q&A - No Replies

Regression models are a type of machine learning model that are used to predict a continuous output value based on one or more input features. There are many different types of regression models, each with its own strengths and weaknesses. Here are some common types of regression models:
 
1)     Linear regression: This is a simple regression model that assumes a linear relationship between the input features and the output. It is used to predict a continuous output value based on a single input feature or a linear combination of input features.
 
2)     Logistic regression: This is a regression model that is used to predict a binary outcome (such as yes/no or 0/1) based on one or more input features. It is used in classification tasks and is based on the logistic function, which maps the input features to a probability between 0 and 1.
 
3)     Polynomial regression: This is a regression model that is used to fit a non-linear relationship between the input features and the output. It is based on a polynomial function and can be used to fit higher-order relationships in the data.
 
4)     Ridge regression: This is a regularized version of linear regression that is used to prevent overfitting. It adds a penalty term to the loss function to constrain the size of the coefficients and reduce the complexity of the model.
 
5)     Lasso regression: This is another regularized version of linear regression that is used to prevent overfitting. It adds a penalty term to the loss function to constrain the size of the coefficients and reduce the complexity of the model.
 
6)     Elastic Net: This is a combination of ridge and lasso regression that combines the penalties of both models. It is used to balance the trade-off between the simplicity of the model and the fit of the model to the data

Print this item