English

Marketplace

Listings

Solution

Natixis - HandyML

Supported by Publisher

Silver Certified

Solution

1 reviews

103

Natixis - HandyML

Supported by Publisher

Silver Certified

Solution

1 reviews

103

Overview

Reviews Questions

Versions

Summary

Non-datascientists users can now train machine learning models by simply asking their robot to do it for them. Take data from an Excel file and train a supervised Machine Learning model.

Overview

What it does
It takes data from an Excel file and trains a Machine Learning model according to the type of problem to solve (regression or classification) and the algorithm used (linear regression, polynomial regression, logistic regression, etc.). Eventually, the trained models can be used to make predictions on new data.
How we built it
We first created configuration files using JSON language to specify all kind of parameters:
one as a resource in order to list all algorithms and parameters handled by the tool
one for the dataset, in which you can specify the path of the Excel file, the sheet to use, which columns are corresponding to the features, and which one is corresponding to the target, the algorithm to use and its parameters
Then, we made the Python script to preprocess the data (dataset creation, label encoding) and train the model using pandas, numpy and scikit-learn libraries.
Next, we created another Python script to use a saved model in order to make predictions on new data.
Finally, we designed a user-friendly web application allowing users to follow all the steps from selecting the data to evaluate the accuracy of the trained model. There are 6 different steps:
Where is your data?
Select your features
Select your target
Select your algorithm and specify its parameters
Review all your configuration and start the training
Evaluate your model by its score, some plots, a confusion matrix and generate a template to make predictions with new data
Eventually, we created two UiPath robots:
a first one to interact with users through Custom Input activity displaying the different pages of the web application
a second one based allowing users to make predictions with their trained models

Benefits

Published: 22 Jul 2019 | Updated: 14 Dec 2020

Natixis

Trusted Source

License

MIT

Code Language

Visual Basic

Runtime

Windows Legacy (.Net Framework 4.6.1)

Purchase invoice automation made easy with Aito…

Solution

Using Aito.ai machine learning tool, the purchase invoice processing automation is a breeze, and you can leverage your existing work on UiPath.…

Supported by Publisher

Ciphix - Simple Logit Model…

Custom Activity

This machine learning related activity is used to estimate a model for a binary variable and uses that model to make a one point ahead forecast for the binary variable.…

2.7k

Bronze Certified

Supported by Publisher

Aito - Easy Actionable Machine Learning…

Tool

How to use machine learning to categorize data ("Which business unit does this invoice belong to?") and predict missing values: "This invoice doesn't have a VAT-category. Which is the right one?"…