Coming Soon...!
Please click on the Contact Us! below and submit your email if you would like to know the upcoming release date!!!
NoCodeMachineLearningApp
NoCodeMLApp
Watch the Video to find out how it all works to Train, Evaluate, Save and Classify new Data using Machine Learning Text Classifier !!
-
No need to write any code in R, Python or any programming language for the selected ML Algorithms
-
Get and prepare your training data.
-
Allow algorithm to be selected based on your data or choose an algorithm and customize hyperparameters.
-
Choose and customize feature set.
-
Train Machine Learning (ML) Algorithm
-
Save performance metrics to fine tune your model training across different training sessions.
-
Get new data you want to predict or classify
-
Use trained MLModel to predict or classify your new data.
-
Save the prediction or classification result for further analysis.
-
Save Trained MLModel for Mobile or Desktop App Development
And All with No Line of Code for the Selected Algorithms
Watch the Video to find out how it all works to Train, Evaluate, Save and Classify Images using Machine Learning Directory-Based Image Classifier !!
NoCodeMachineLearningApp is based on Apple's CoreML and CreateML Framework
NoCodeMachineLearningApp is hardened and sandboxed.
NoCodeMachineLearningApp Features
​
-
No need to write any code in Python or R or any language for the set of selected Machine Learning Algorithms
-
Select Training Data file using familiar Point & Click interface
-
Select All Features from Training Data file to Train the Machine Learning Model (MLModel)
-
Or select Custom Feature Set from Training Data file to Train the Machine Learning Model (MLModel)
-
Choose to automatically Split Training Data file into 80% of Data for Training and 20% of Data for Evaluation
-
Or select a completely different Evaluation Data file to evaluate the MLModel
-
Run Training and Evaluation of the Algorithm just at the press of a button.
-
Training, Validation and Evaluation Metrics are displayed in Tables for easy visual evaluation
-
Ability to save Training, Validation and Evaluation Metrics in .csv format for later analysis or comparison across training sessions to find the best MLModel
-
Press a button to select new Data for Classification or Prediction using the Trained MLModel
-
Press a button to save Classification or Prediction Results in .csv file for further analysis using any software that can process .csv file.
-
Ability to save Trained MLModel for use in developing Intelligent Mobile IOS or Desktop MacOS Apps
-
Ability to clear all Feature Selections, select new custom Features, and depending upon the Algorithm enter new parameters to run new Training Sessions and Save Performance Metrics without leaving the specific Algorithm
Story Behind the
NoCodeMLApp
What began as a text analytics project has now turned into NoCodeMachineLearningApp. So how did we get here?
I needed to analyze a large quantity of text for sentiment and emotion analysis. I looked into R and Python libraries. But I wanted a solution that will be simple and will allow me to focus on my data and not coding...
Potential Usage Scenarios:
-
Using NoCodeMachineLearningApp to explore Sentiment Analysis or Engagement Analysis using Text Analysis Algorithm without writing any code
-
Using NoCodeMachineLearningApp's Image Analysis Algorithm to develop Image Classification MLModel for use in Augmented Reality or Object Identification Mobile IOS App or MacOS App.
NoCodeMachineLearningApp
System Requirements:
-
Computers: Apple MacBook, MacBook Pro, iMac, iMac Pro
-
Operating System: MacOS Mojave 10.14.5 or above
-
Machine Learning Algorithm Training, Classification or Prediction times will vary based on the size of the data set and available computer system resources.
​
Potential Usage Scenarios:
-
Using NoCodeMachineLearningApp to explore application of the set of included Algorithms in a specific problem domain without writing any code
-
Learning fundamentals of Machine Learning Workflow such as 1. Identifying Problem Domain, 2. Exploring and Preparing Training Data, 3. Using NoCodeMachineLearingApp to Train and Evaluate MLModel and inspect Training Metrics for further evaluation without writing any code.
NoCodeMachineLearningApp
-Algorithms You Use
By Just Point & Click.
No Coding Required!!
​
Automatic ML Classifier
Algorithm
This option allows automatic selection of ML Classifier Algorithm based on the characteristics of the Training Data Set.
Automatic ML Regressor Algorithm
This option allows automatic selection of ML Regressor Algorithm based on the characteristics of the Training Data Set.
Image Classifier Algorithm
Image Classifier Algorithm can be trained based on images stored in labeled folders. Folders are labeled. Folders contain unlabeled images.
Text Classifier Algorithm
Text Classifier Algorithm can be trained based on labeled text in the training data file. You can use this classifier for Multi-class Sentiment Analysis, Product Review classification or similar text supervised text analytics.
Text Classifier Algorithm
Text Classifier can be trained using labeled directories similar to the Directory-based Image Classifier. Each labeled directory contains unlabeled text. Directory labels are used for classifying unlabeled text in each Directory.
Decision Tree Classifier Algorithm
You can customize hyper parameters to train DT Classifier. Allows you to experiment with various combination of hyper-parameters values and custom feature set.
Boosted Tree Classifier Algorithm
Customize hyper-parameters to train Boosted Tree Classifier Algorithm. You can experiment with various combination of custom feature sets and find the best training algorithm for your decision problem.
Support Vector Machine Classifier Algorithm
Customize hyper-parameters to train Support Vector Machine Classifier Algorithm. You can use various combinations of hyper-parameters along with custom feature sets to find the best Training Model for your workflow.
Random Forest Classifier
Algorithm
Customize hyper parameters to train Random Forest Classifier and fine tune the Model selection along with custom features.
Logistics Regression Classifier Algorithm
Customize hyper parameters to train Logistics Regressor Classifier. You can use this classifier and fine tune the hyper-parameters for best trained classifier.
Boosted Tree Regressor
Algorithm
Customize hyper parameters to train Boosted Tree Regressor for use in a prediction problem.
Decision Tree Regressor
Algorithm
Customize hyper parameters to train Decision Tree Regressor Algorithm. You can use various combination of parameters and custom feature to find the best Trained ML Model.
Linear Regressor
Algorithm
Customize hyper parameters to train Linear Regressor Algorithm. You can use this algorithm for prediction.
Random Forest Regressor
Algorithm
Customize hyper parameters to train Random Forest Regressor Algorithm. You can customize features and hyper-parameter values to experiment with the algorithm and zero-in on the best Trained ML Model.