Results:
Data Structure: df
Data Summary: df
Data Structure: df2
Data Summary: df2
Generated by the summarytools package using the command:summarytools::dfSummary(df).
Generated by the CreateTableOne() function in the tableone package.
Generated by the plot_qq() and plot_histogram() functions in the DataExplorer package.
Generated by the corr_plot() functions in the corrplot package. Blanks indicate no significant correlations.
Comprehensive EDA (Exploratory Data Analysis)
First Time User
Start by watching an 8-min YouTube video!
See GitHub for source code, bug reports, and instructions to install RTutor as an R package. As a small startup, we are open to partnerships with both academia and industry. We can do demos and seminars via Zoom if time permits.
Also try Chatlize.ai, a more general platform for analyzing data through chats. Multiple files with different formats. Python support.
Quick Start:
- Explore the data at the EDA tab first. Then start with simple requests such as distributions, basic plots. Gradually add complexity.
- The default model is now GPT-4o. In the same session, previous questions and code chunks become the context for your new request. For example, you can simply say "Change background color to white" to refine the plot generated by the previous chunk. You can also clean your data step by step.
- To analyze a new dataset, or to start over, click the Reset button first.
- Prepare and clean your data in Excel first. Name columns properly. ChatGPT tries to guess the meaning of column names, even if they are abbrievated.
- RTutor can only analyze traditional statistics data, where rows are observations and columns are variables. For complex data, try https://chatlize.ai.
- Once uploaded, your data is automatically loaded into R as a data frame called df. You do NOT need to ask RTutor to load data. Check if the data types of the columns are correct. Change if needed, especially when numbers are used to code for categories.
- An additional file can be uploaded as df2 to be analyzed together. To use it, you must specify 'df2' in your prompts.
- Use the Q&A box to ask questions about the code, result, or error messages. You can ask for methods to use or develop a plan.
- Before sending your request to OpenAI, we do prompt engineering based on the uploaded data. We add "Generate R code" to the beginning, and append something like "Use the df data frame. Note that highway is numeric, ..." afterward. If you are not using any data (plot a function or simulations), choose "No data" from the Data dropdown.
- By default, we randomly select 5 rows of data and send to OpenAI for enhanced coding results, you can opt out in Settings. Your data is not stored on our web server after the session. If you explain the background of the data and the meaning of the columns, you can ask general questions as if you were asking a clueless statistician.
- Be skeptical. The generated code can be logically wrong even if it produces results without error.
About
RTutor uses OpenAI's powerful large language models to translate natural language into R (or Python) code, which is then excuted. You can request your analysis, just like asking a real person. Upload a data file (CSV, TSV/tab-delimited text files, and Excel) and just analyze it in plain English. Your results can be downloaded as an HTML report in minutes!
NO WARRANTY! Some of the scripts run but may yield incorrect results. Please use the auto-generated code as a starting point for further refinement and validation.
Source code at GitHub, from where you can also find instruction to install RTutor as an R package.
RTutor went viral on LinkedIn, Twitter, Twitter(Physacourses), and Facebook (Carlo Pecoraro).
Written by Dr. Steven Ge (Twitter, LinkedIn), as part of Orditus LLC. For feedback, please email ge@orditus.com.
Explore our other AI tools at Orditus.com!
The RTutor website and the source code is free for non-profit organizations ONLY. Licensing is required for commercial use.
For businesses, RTutor can be customized and locally installed to easily gain insights from your data (files, SQL databases, or APIs) at a low cost. We would be happy to discuss licensure.
Site Updates Log
Frequently asked Questions
Comments & Questions
Settings
AI Model
This controls the AI's behavior in choosing among possible answers. A higher sampling temperature makes the AI take more risks, giving different, more creative answers each time. A lower temperature (like 0) makes the AI more cautious, giving more conservative and well-defined solutions, but less variety when repeated.
Use your own API Key
We pay a small fee to use the AI for every request. If you use this regularly, please take a few minutes to create your own API key:
- Create a personal account at OpenAI.
- Once logged in, click "Personal" from top right.
- Click "Manage Account", then "Billing", where you can add "Payment methods" and set "Usage limits". $5 per month is more than enough.
- Click "API keys" to create a new key, which can be copied and pasted below.
Current API Key:
Use Python instead of R for generating code and results.
Allows us to save your requests and the structure of your data (like column names and data types, not the data itself). We can learn from users about creative ways to use AI and it helps in improving unsuccessful results.
Allows us to optimize code output from OpenAI by sending with your prompt a random sample of 5 observations from your data
Some columns contain numbers, but should be treated as categorical values or factors. For example, we sometimes use 1 to label success and 0 for failure. If this is selected, using the default setting, a column is treated as categories when the number of unique values is less than or equal to 5, and less than 5% of the total rows.
Privacy Policy
Updated Aug. 23rd, 2024
We are committed to protecting your privacy. This Privacy Policy explains how ("we", "us", or "our"), Orditus LLC, collects, uses, discloses, and safeguards your information when you use our website RTutor.ai and our services (collectively, the "Services"). By accessing or using the Services, you agree to the terms of this Privacy Policy. If you do not agree with the terms of this Privacy Policy, please do not access or use the Services.
1. Information We Collect
1.1 Personal Information
We may collect personal information that you provide directly to us when you use our Services or communicate with us. This information may include:
Name
Email address
Company name
1.2 Usage Information
We may collect information from third parties that your browser sends whenever you visit our website or use our Services. This data may include:
Browser type,
Browser version,
Pages of our Service that you visit,
City of user,
Time and date of your visit,
Time spent on those pages,
Other diagnostic data.
We do not collect IP addresses or demographic data.
1.3 Upload Information and Prompts
When you upload data to our Services, it is stored temporarily for the duration of your session. Once your session ends or you close your browser, all uploaded data is automatically deleted. We do not track or store any of the data you upload.
By default, 5 randomly selected rows from your uploaded data is sent to the selected language learning model to increase results accuracy. However, you may opt out of this using the bottom leftmost settings option in the "Settings" tab. We do not store or track this data, it is deleted when you reset your session. It is solely used to send to the selected LLM.
We do collect data structure information and the prompts you send while using our Services. If you prefer not to share this information, you can opt out through the settings in the "Settings" tab.
Additionally, column names and data type information from your uploaded data are sent to the selected language learning model to improve the functionality of the Services. This includes category names of all factor variables within your uploaded data.
2. How We Collect This Data
To collect data structure information and prompts, we utilize Google Analytics and an SQL database. Google Analytics helps us track and analyze user interactions with our Services, providing insights into how data is structured, and which prompts are most commonly used. This information is collected in real-time and stored securely in our SQLite database. The SQLite database allows us to manage and retrieve this data efficiently, ensuring that it is used to improve the quality and functionality of our Services.
3. Why We Collect This Data
We may use information from users for the following purposes:
To operate and improve the Services by providing you with more effective customer service.
To perform research and analysis aimed at improving the Services, or other products and technologies of Orditus LLC.
To diagnose or fix problems with the Services.
To communicate with you, especially through the sending of emails, information on technical Service issues, security announcements, information on new Services available, legal notices, response to your requests, or other information that we think might be relevant to you.
To protect against harm to the rights, property or safety of Orditus LLC, our users, yourself, or the public.
To enforce any terms of use, including investigations of potential violations of the terms.
To comply with any law, regulation, legal process, or governmental requests.
4. How We Use This Data
Orditus LLC will use the information collected from you to pursue legitimate interests such as legal or regulatory compliance, security control, business operations, scientific research, or any other interest reasonably held as legitimate.
5. Sharing This Data
We will not lease, sell, or rent your personal, usage, or upload information except in the following instances described in this policy.
5.1 Third Party Service Providers
We may occasionally hire other companies to provide limited services on our behalf, such as providing customer support, hosting websites, or performing statistical analysis of our Services. Those companies will be allowed to obtain only the information they need to deliver the relevant service. They will be required to maintain the confidentiality of the information and are prohibited from using it for any other purpose.
Third Party Service Providers:
Google Analytics
SQLite
AWS
5.2 With your Consent
At any time during your use of our Services, or upon explicit request from us, you may consent to the disclosure of your information.
5.3 For Security and Safety Purposes
In the event of any fraud, security threats, or incidents, we reserve the right to disclose your information without your consent for the purposes of maintaining security on our website and for our users and addressing fraud or security issues. We reserve the right to disclose your information without your consent for the purpose of protecting against harm to the rights, property, or safety of Orditus LLC, our users, yourself, or the public.
5.4 For Legal or Regulatory Purposes
We reserve the right to disclose your information without your consent to comply with any applicable law, regulation, legal process, or governmental requests.
6. Opting Out of Sharing Your Data
6.1 Access your Information
You may be entitled under data protection laws to access and review personal information that Orditus LLC holds related to you. You may access, modify, or delete the information we collected by controlling the content that you share or upload at any time.
Any other request should be addressed to: ge@orditus.com. Such inquiries should be clearly marked as data protection queries, and you should indicate if the request is time sensitive.
6.2 Data Retention
We retain your Information for as long as necessary to deliver our Services, to comply with any applicable legal requirements, to maintain security and prevent incidents, and, in general, to pursue our legitimate interests. If you wish to request the erasure of all your personal information that we process, you may do so by sending a written request to ge@orditus.com.
6.3 Opting Out
You may opt out of sending information relevant to your data uploads and prompt requests at any time by switching off the checkbox in the RTutor.ai settings.
7. Data Security
All interactions with our Services occur over HTTPS which ensures that data transmitted between your device and our servers is encrypted and secure.
8. Children’s Privacy
Orditus.com is neither directed to nor structured to attract children under the age of 13 years. Accordingly, Orditus LLC does not intend to collect personal information from anyone it knows to be under 13 years of age. Orditus LLC will direct potential users under 13 years of age not to use the Services. If the Company learns that personal information of persons less than 13 years of age has been collected without verifiable parental consent, Orditus LLC will take the appropriate steps to delete this information.
To make such a request, please contact Orditus LLC at: ge@orditus.com.
9. Contact Us
If you have questions about this policy, please email us at: ge@orditus.com.
Terms of Service
Updated Aug. 19th, 2024
Welcome to Orditus LLC ("we", "us", or "our"). These Terms of Use ("Terms") govern your use of our website RTutor.ai and any services, content, or features provided by us (collectively, the "Services"). By accessing or using our Services, you agree to be bound by these Terms. If you do not agree to these Terms, you may not use our Services.
1. Description of Services
RTutor is designed to generate and run R and Python code. Using the power of ChatGPT, RTutor translates your natural language into scripts to analyze and interpret data.
2. Acceptance of Terms
By accessing and using our Services, you accept and agree to be bound by these Terms and our Privacy Policy. If you do not agree to these Terms, you should not use our Services.
3. Changes to Terms
We reserve the right to modify these Terms at any time. Any changes will be effective immediately upon posting of the revised Terms. Your continued use of the Services after the posting of any changes constitutes your acceptance of the revised Terms.
4. User Obligations and Restrictions
You agree to use the Services only for lawful purposes and in a manner that does not infringe the rights of, restrict, or inhibit anyone else's use and enjoyment of the Services. Prohibited behavior and use includes but is not limited to:
You must be at least 13 years old to use this Service.
You must not use this Service commercially in any form without our written consent.
You agree not to transmit obscene or offensive content.
You agree not to use this Service to generate content that is misleading, harmful, or illegal.
You must not overuse the Services in a manner that adversely impacts the performance or availability of the Services for other users.
You must not upload data that is confidential or personally identifiable without proper anonymization.
You agree not to attempt to reverse-engineer or otherwise tamper with the AI models and algorithms.
You must not copy or scrape the content of the Service in any form without our written consent.
5. User Content
By submitting, posting, or displaying content, you grant us a worldwide, non-exclusive, royalty-free license to use, reproduce, adapt, modify, publish, and distribute such content in any and all media. You are responsible for any data you submit to our Services. By submitting data, you agree that:
You have the necessary rights and permissions to share the data.
You will not submit any data that violates the rights of others or any applicable laws.
We may use, store, and process basic information about your data as described in our Privacy Policy.
6. Intellectual Property
All content, trademarks, and data on this website, including but not limited to software, databases, text, graphics, icons, hyperlinks, private information, designs, and agreements, are the property of or licensed to Orditus LLC and as such are protected from infringement by local and international legislation and treaties. All content, AI models, algorithms, and data used or generated by our Services are the property of Orditus LLC or its licensors and are protected by intellectual property laws. By using our Services, you agree that:
You retain ownership of the data you submit to the AI assistant.
You grant us a license to use, reproduce, adapt, and modify your inputs as necessary to provide and improve our Services.
We retain ownership of all models, algorithms, and enhancements made to the Services based on aggregated and anonymized user data.
7. Limitation of Liability
To the fullest extent permitted by law, Orditus LLC shall not be liable for any indirect, incidental, special, consequential, or punitive damages arising from or related to your use of the Services, including but not limited to:
Inaccuracies or errors in AI-generated results.
Loss or corruption of data.
Misuse of AI-generated insights for decision-making.
Unauthorized access to or use of your account or data.
In no event shall Orditus LLC nor its directors, employees, partners, or affiliates, be liable for any indirect, incidental, special, consequential, or punitive damages, including without limitation, loss of profits, data, use, goodwill, or other intangible losses, resulting from:
Your use or inability to use the Services.
Any unauthorized access to or use of our servers and/or any personal information stored therein.
Any breaks or stoppages in our service that affect the sending or receiving of data to or from the Services.
8. Termination
We may terminate or suspend your access to our Services immediately, without prior notice or liability, for any reason whatsoever, including without limitation if you breach the Terms. Upon termination, your right to use the Services will immediately cease.
9. Privacy Policy
Your privacy is important to us. Please review our Privacy Policy to understand how we collect, use, and protect your information. We may use this information to improve the Service. By using our Services, you consent to the data practices described in our Privacy Policy.
10. Governing Law
These Terms shall be governed and construed in accordance with the laws of South Dakota, USA without regard to its conflict of law provisions.
11. Contact Us
If you have any questions about these Terms, please contact us at ge@orditus.com.