I registered at this link to get an API for ChatGPT.
And I used the chatgpt package in R.
library(chatgpt)
And set environment:
Sys.setenv(OPENAI_API_KEY = "sk-YOURAPI")
I used this function:
chatgpt::ask_chatgpt("How to make a strawberry pie to donate to my wife? Ingredients, please.")
Sometimes the output is missing words. For example:
*** ChatGPT input:
How to make a strawberry pie to donate to my wife? Ingredients, please.
[1] ... and your wife is"
It does not complete the text after is. Is there any solution for this on R?
Similar question on reddit.
EDIT
I tried increasing the processing time of the function (so that the chat would finish typing all the content, without stopping midway). Like this:
for (i in 35) {
print(chatgpt::ask_chatgpt("How to make a strawberry pie to donate to my wife? Ingredients, please."))
Sys.sleep(i)
}
What you are running into is prompt engineering. GPT is a sophisticated autocomplete engine.
If you are not getting the right response you need to recraft your prompt.
You can always test your prompts in the OpenAI playground:
https://platform.openai.com/playground
I was able to get a list of ingredients and cooking steps by using the following prompt:
How can I make a strawberry pie to donate to my wife? Please provide first a numbered list of ingredients, and secondly a numbered lists of steps.
Here is the output I got in the playground:
Ingredients:
1. 2 ½ cups of fresh or frozen strawberries
2. 1 9-inch pre-made pie crust
3. ¾ cup of granulated sugar
4. 2 tablespoons of cornstarch
5. ¼ teaspoon of salt
6. 1 tablespoon of fresh lemon juice
Steps:
1. Preheat oven to 425 degrees F.
2. Place the pre-made pie crust in a 9-inch pie dish and set aside.
3. In a medium bowl, combine the strawberries, sugar, cornstarch, salt, and lemon juice. Stir until the mixture is combined.
4. Pour the strawberry mixture into the pre-made pie crust.
5. Place the pie dish on a baking sheet and bake for 15 minutes.
6. Reduce the oven temperature to 375 degrees F and bake for an additional 25 minutes.
7. Allow the pie to cool completely before serving.
Another thing to note, per the Github repo for the chatgpt R library it says "The {chatgpt} R package provides a set of features to assist in R coding."
Ref: https://github.com/jcrodriguez1989/chatgpt
I would use the OpenAI APIs directly, this way you will have a lot more control over your response. I am not an R specialist, but this is how the OpenAI Playground showed me how to do it.
library(httr)
response <- GET("https://api.openai.com/v1/completions",
query = list(
prompt = "How can I make a strawberry pie to donate to my wife? Please provide first a numbered list of ingredients, and secondly a numbered lists of steps.",
max_tokens = 200,
model = 'text-davinci-003'
),
add_headers(Authorization = "bearer YOUR_OPENAI_API_KEY")
)
content(response)
Ref: OpenAI playground
Increase max_tokens to get longer answer.
I'm trying to crack a crypt with a known key length. I deduced that the operation made was a hex XOR. Here is the crypt:
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
I have tried to use this tool to decrypt it. The tool outputted multiple possible keys and for each key, an attempt do decipher the crypt. I know the result should be plain text English. The closest I got was this:
T-e po1ato ,s a 6tarc-y, t0bero0s cr*p fr*m th per nnia) nig-tsha!e So)anumetube7osumeL. T-e wo7d po1ato (ay r fer 1o th pla+t it6elf ,n ad!itio+ to 1he e!ibleetube7. Inethe ndesi whe7e th spe&ies ,s in!igen*us, 1hereeare 6ome *thereclos ly r late! cul1ivat d po1ato 6peci s.P*tato s we7e in1rodu&ed o0tsid theeAnde6 reg,on f*ur c ntur,es a"o,a+d ha3e be&ome $n in1egra) par1 of (uch *f th wor)d's #ood 6uppl<. Iteis t-e wo7ld'sefour1h-la7gestefoodecropi fol)owin" mai?e, w-eat $nd r,ce.
After some digging and manually tweaking the text, I got this:
The potato is a starchy, tuberous crop from the perennial nightshade Solanum tuberosum L. The word "potato" may refer to the plant, itself, in addition to the edible tuber. In the Andes, where the species is indigenous, there are some other closely related cultivated potato species. Potatoes were introduced outside the Andes region four centuries ago, and have become an integral part of much of the world's food supply. It is the world's fourth-largest food crop, following maize, wheat and rice.
It unfortunately did not work. I am now trying to find a clue as to what I should be doing to find the answer.
I am working with a dataset that has free text containing special characters. I need to clean the text before use strsplit for a subsequent function, but would prefer to add escapes (\\) before the special characters rather than delete them altogether.
For example, the string that looks like this:
Do you love great hair? Wind it up! Your curls are your gift- set
them free and help preserve your natural curl with bounce and
definition. Cleanse hair without weighing it down while reducing
frizz. Infused with pineapple, argan oil and quinoa. Let your natural
beauty shine bright!
Should look like this:
Do you love great hair\\? Wind it up\\! Your curls are your gift\\- set
them free and help preserve your natural curl with bounce and
definition. Cleanse hair without weighing it down while reducing
frizz. Infused with pineapple, argan oil and quinoa. Let your natural
beauty shine bright\\!
I've figured out how to remove a list of several special characters (~!##$%^&*(){}|<>/), but can't find the right tutorial for adding \\ before them.
Note: I am not looking to remove ALL punctuation because some characters are used for subsequent delimiting logic. Instead, I want to address a specific subset of special characters.
Sample data:
>dput(tar$clean.text[1:10])
list(c("Dove go fresh Cucumber and Green Tea Beauty Bar combines the refreshing scent of cucumber and green tea with Dove's gentle cleansers and _ moisturizing cream. Dove Beauty Bar is proven to be more gentle and mild on skin than ordinary soap. It can be used on your hands and as a mild facial cleanser, so if you're also after a fresh face and refreshed hands throughout the day, why not try adding Dove Beauty Bar go fresh Cucumber and Green Tea to your skin care routine? Light, hydrating feel and refreshing formula that effectively nourishes skin. A refreshing shower can be just what you need to start the day off right. Dove's go fresh range blends nourishing ingredients and light, fresh scents in a formula that's gentle on your skin. Dove go fresh beauty bars give you a feeling of hydrating freshness that leaves you and your skin feeling blissfully revived. For best results: Your hands are one of the driest parts of your body so give them a boost and lather your Dove beauty bar between wet hands. Once you've covered your body with the rich lather, making sure to avoid contact with your eyes, rinse away thoroughly. At Dove, our vision is of a world where beauty is a source of confidence, and not anxiety. So, we are on a mission to help the next generation of women develop a positive relationship with the way they look - helping them raise their self-esteem and realize their full potential.",
"Scent: Cucumber", "Health Facts: Sulfate-free", "Suggested Age: 5 Years and Up",
"Wellness Standard: Aluminum-free, paraben-free", "Recommended Skin Type: Normal",
"Beauty Purpose: Moisturizing, basic cleansing", "Package Quantity: 1",
"TCIN: 10819409", "UPC: 011111611023", "Item Number (DPCI): 049-00-0604"
), c("Me! Bath Bath Bomb Papaya Nectar 6 ct is a great idea to add to a spa gift basket. These bath bombs are like scoops for your bath to make mini bath ice cream that gives you super soft skin.",
"Scent: Fruit", "Health Facts: Vegan, paraben-free, aluminum-free",
"Product Form: Bath bomb", "Suggested Age: Adult Use Only", "Wellness Standard: Aluminum-free, cruelty-free, paraben-free, vegan",
"Recommended Skin Type: Normal", "Sustainability Claims: Cruelty-free",
"TCIN: 18828570", "UPC: 858858000358", "Item Number (DPCI): 037-08-1164"
), NA_character_, NA_character_, c("Aura Cacia pure essential oils in 4 fl oz Body Oil has a lavender and cocoa butter scent. This natural skin care oil shows skin tone improvement that you can feel.",
"Scent: Lavender, Cocoa Butter", "Health Facts: Contains lavender, butylparaben-free, phthalate-free, formaldehyde donor-free, formaldehyde-free, nonylphenol ethoxylate free, propylparaben-free, Sulfate-free, paraben-free, dye-free, aluminum-free",
"Product Form: Lotion", "Suggested Age: All Ages", "Recommended Skin Type: Normal",
"Beauty Purpose: Skin tone improvement", "Sustainability Claims: Not tested on animals, cruelty-free",
"TCIN: 50030689", "UPC: 051381911720", "Item Number (DPCI): 037-05-1378"
), c("Deep clean pores with the Facial Cleansing Brush from Eco",
"Tools. This compact brush features soft bristles for moderate exfoliation, leaving you with soft, supple skin. Your serums and moisturizers can more effectively penetrate your skin once all the dead skin cells are out of the way. The compact size is ideal for packing in your weekend tote or suitcase for cleansing on the go.",
"Material: Nylon", "Suggested Age: All Ages", "Beauty Purpose: Basic cleansing, exfoliating",
"TCIN: 52537254", "UPC: 079625074864", "Item Number (DPCI): 037-08-2254"
), c("Deep Steep Rosemary Mint Sugar Scrub gently exfoliates dead skin cells while moisturizing, leaving smooth, radiant, polished skin. This formula is made up of a smooth blend of shea butter, cocoa butter and carefully sourced sugar to give you light, blissful fragrance with just the right amount of exfoliation and no harsh scratching. Apply desired amount of Deep Steep Rosemary Mint Sugar Scrub to wet skin from shoulders to ankles. Massage in a circular motion. Rinse.",
"Scent: Rosemary", "Health Facts: Contains argan oil, contains coconut oil, contains shea butter, formaldehyde donor-free, gluten-free, dye-free, ethyl alcohol-free, paraben-free, phthalate-free, vegan",
"Product Form: Scrub", "Suggested Age: All Ages", "Recommended Skin Type: Dry, normal",
"Beauty Purpose: Exfoliating", "TCIN: 53242409", "UPC: 674749101153",
"Item Number (DPCI): 037-08-2123"), NA_character_, c("Want to feel gorgeously soft skin every day? Transform your daily shower into an irresistible treat with the exquisitely fragranced Caress Evenly Gorgeous body wash. Indulge your skin with a rich exfoliating lather delicately scented with burnt brown sugar and karite butter that makes this body wash smell good enough to eat. Subtle notes of soft crisp apple and berry open up to a bold floral heart, while rich scents of warm tonka bean, vanilla and balsam together round out the lush lather to leave you with perfectly buffed and glowing skin. Caress Evenly Gorgeous is a revitalizing body wash that blends rich, luxurious lather with expertly crafted fine fragrance It is a body wash that gently cleanses your skin to leave it delicately fragrant, beautifully soft.",
"Lather up and indulge in a deeply cleansing and reviving shower experience. With fine floral fragrance and gentle exfoliates, Caress Evenly Gorgeous will leave you feeling delicately perfumed and silky-smooth, making this the perfect body wash for every day? and every night. Caress body wash and beauty bar fragrances are crafted by the world's best perfumers to transform your daily shower into an indulging experience that will make you feel special every day?Scent: Fresh",
"Health Facts: Aluminum-free, paraben-free, fluoride-free", "Product Form: Liquid",
"Suggested Age: 5 Years and Up", "Wellness Standard: Aluminum-free, paraben-free",
"Recommended Skin Type: Normal", "Beauty Purpose: Basic cleansing",
"Package Quantity: 1", "TCIN: 13446229", "UPC: 011111014909",
"Item Number (DPCI): 049-00-0806"), c("Maintain a sanitary and healthy atmosphere with the MEDLINE n/a READYBATH, PREMIUM,FRAG FREE, 8/PK - 24pks. These sterile swab sticks are pre-treated with povidone-iodine for preparing skin for incision and other medical issues. Comes in disposable packages of 3.",
"Scent: Unscented", "Health Facts: No fragrance added", "Suggested Age: Adult Use Only",
"Recommended Skin Type: Normal", "Beauty Purpose: Basic cleansing",
"Package Quantity: 1", "TCIN: 14339945", "UPC: 080196731445",
"Item Number (DPCI): 037-13-0198"))`
Code that removes a list of symbols:
tar$clean.text<-str_replace_all(tar$clean.text, "~|!|#|#|$|%|^|&|\\*|\\(|\\)|\\{|\\}|_|\\\\|<|>|\\?|\\[|\\]|-", "") # Removes a ton of non-UTF characters
I'm sure there is a simple modification to my regexp, but can't seem to figure it out. All previous answers I've found are more specific to fixing a specific text pattern, rather than generally replacing across a lot of different variations.
You may use
str_replace_all(x, "[~!##$%^&*(){}_\\\\<>?\\[\\]|-]", "\\\\\\0")
A base R approach:
gsub("([]\\~!##$%^&*(){}_<>?[|-])", "\\\\\\1", "~!##$%^&*(){}_\\<>?[]|-")
See the regex demo.
Details
[ - start of a character class matching any of the following chars:
~ - ~
! - !
# - #
# - #
$ - $
% - %
^ - ^ (if you put it at the start, escape with \\)
& - &
* - * (no need to escape inside a character class)
( - (
) - )
{ - {
} - }
_ - _ (note it is a word char, and \W would not match it)
\\\\ - a \ char (a literal \ escaped with another literal \)
< - a <
> - >
? - ?
\\[ - a [ char (in ICU regex, must be escaped inside a character class
\\] - a ] char (ibid.)
| - a | char (it is not an OR operator inside a character class)
- - a - char
] - end of the character class.
The "\\\\\\0" string replacement pattern is parsed as two literal backslashes that defines a singular literal backslash and a \0 literal string that is a backreference to the whole match in the ICU regex in R.
Note that gsub TRE regex is a bit trickier: ] must be the first char in the character class, [ should not be escaped, literal \ should only be single (no regex escape sequences are supported inside TRE patterns), and - must be at the end. Also, there is no support for the whole match backreference, hence, you need to wrap the whole pattern with a capturing group and replace with \1 backreference.
let dat = tar$clean.text[1:10] then you can do:
Map(gsub,"([[:punct:]])","\\\\\\1",dat)
I'm the founder of a nonprofit news org that is a member of INN (The Institute for Nonprofit News). Some of us members have our wordpress news sites hosted for free through INN and therefore, cannot just install any plugins we want. INN must approve that first.
So the only way I have been able to use Highcharts is through this tool from Builtvisible that is a Highcharts code generator: https://builtvisible.com/highcharts-generator/
I've made a column chart here that is for a newborn screening story and is the Top-10 hospitals with the highest percentage of late samples. So when I hover over each bar I just want the tooltip to display 73%, instead of 73 like it does right now.
Any help would be greatly appreciated. I'm not very knowledgeable with coding and have tried a few things, even contacting the person who built this code generator but I can't figure out how to make it work. For another column chart also I have the same issue but I need it to separate the thousands with a comma instead of a space. So I would like 1,000 to read like that, instead of 1 000.
Here is my code from the generator where I need it to display percentages:
<div id="chart_container"></div><script src="//code.highcharts.com/adapters/standalone-framework.js"></script><script src="//code.highcharts.com/highcharts.js"></script><script>new Highcharts.Chart({"chart":{"backgroundColor":"#fefefe","renderTo":"chart_container","type":"column"},"title":{"text":"Top-10 facilities for lateness"},"colors":["#476974","#3ca1c1","#4ccbf4","#96dff6","#c9e8f6"],"legend":{"enabled":true,"margin":30},"xAxis":{"tickWidth":0,"labels":{"y":20},"categories":["Facilities with the highest overall percentage of late samples"]},"yAxis":{"tickWidth":0,"labels":{"y":-5},"title":{"text":"Percentage (%)"}},"series":[{"name":"NE MT HLTH SERVICES WOLF POINT","data":[73]},{"name":"CLARK FORK VALLEY HOSPITAL","data":[71]},{"name":"MARCUS DALY HOSPITAL","data":[68]},{"name":"ST JOSEPH HOSPITAL","data":[65]},{"name":"SIDNEY HEALTH CENTER","data":[64]},{"name":"THE BIRTH CENTER, MISSOULA","data":[63]},{"name":"GLENDIVE MEDICAL CENTER","data":[59]},{"name":"FRANCES MAHON DEAC HOSPITAL","data":[57]},{"name":"ST LUKE HOSPITAL","data":[55]},{"name":"CABINET PEAKS MEDICAL CENTER","data":[53]}]});</script>
Here is the other column chart where I would like the thousands to be separated by a comma when you hover over each column and it brings up the tool tip. This is also code from the Builtvisible Highcharts code generator:
<div id="chart_container2"></div>
<script src="//code.highcharts.com/adapters/standalone-framework.js"></script><script src="//code.highcharts.com/highcharts.js"></script><script>// <![CDATA[
new Highcharts.Chart({"chart":{"backgroundColor":"#fefefe","renderTo":"chart_container2","type":"column"},"title":{"text":"Wisconsin Lab: On-Time Performance"},"colors":["#6AA121","#2069A1","#A12069","#96dff6","#c9e8f6"],"legend":{"enabled":true,"margin":30},"xAxis":{"tickWidth":0,"labels":{"y":20},"categories":["2011","2012","2013","2014"]},"yAxis":{"tickWidth":0,"labels":{"y":-5},"title":{"text":"Number of samples on-time vs. late"}},"series":[{"name":"On-time","data":[7006,5492,5589,7069]},{"name":"Late","data":[3857,4979,5189,4105]},{"name":"Very Late","data":[701,1075,1074,776]}]});
// ]]></script>
This "tool code" is just regular Highcharts code, and does nothing more than generate it for you.
For the first chart you can use valueSuffix to add a percentage sign after the value. Code:
plotOptions: {
column: {
tooltip: {
valueSuffix: '%'
}
}
}
For the second chart you can use the global thousandSep option to get comma separators. Code:
Highcharts.setOptions({
lang: {
thousandsSep: ','
}
});
See this JSFiddle demonstration of both code segments.
I just want to prompt the user for a line of text in the middle of an action. The effect should be like this:
> north
The robot steps in front of you as you approach the gate.
"PAASSWAAAAWRD!!" it bellows.
Enter the password: _
At this point the game should pause and let the player try to guess the password. For example, suppose I guess “fribble”, which is not the password:
Enter the password: fribble
"WRONG PASSWAAARD!" roars the robot. "CHECK CAPS LAAAWWWWK!"
>
The behavior I want is similar to if the player consents, but I want the whole line of input, not just a yes or no.
Inform offers no easy way to do this, though you might be able to get to the keyboard primitives by dropping to Inform 6.
However it is possible to achieve the desired effect:
The Loading Zone is a room. "Concrete with yellow stripes. The Hold is north."
The robot is an animal in the Loading Zone. "However, a robot the size of an Arcturan megaladon guards the way."
North of the Loading Zone is the Hold.
Instead of going north from the Loading Zone:
say "The robot steps in front of you as you approach the gate. 'PAASSWAAAAWRD!!' it bellows.";
now the command prompt is "Enter password: ".
After reading a command when the command prompt is "Enter password: ":
if the player's command matches "xyzzy":
say "The robot folds itself up into a cube to let you pass.";
move the player to the Hold;
otherwise:
say "'WRONG PASSWAAARD!' roars the robot. 'CHECK CAPS LAAAWWWWK!'";
now the command prompt is ">";
reject the player's command.
I think this sort of thing is considered poor gameplay: it forces the player to guess, which damages the player's illusion of control and choice. The more conventional way would be to require the player to say the password:
The Loading Zone is a room. "Concrete with yellow stripes. The Hold is north."
The robot is an animal in the Loading Zone. The robot is either awake or asleep. The robot is awake. "[if awake]However, a robot the size of an Arcturan megaladon guards the way.[otherwise]A cube of metal the size of an Arctural megaladon snores loudly.[end if]".
North of the Loading Zone is the Hold.
Instead of going north from the Loading Zone when the robot is awake:
say "The robot steps in front of you as you approach the gate. 'PAASSWAAAAWRD!!' it bellows."
Instead of answering the robot that some text:
if the topic understood matches "xyzzy":
say "The robot folds itself up into a cube to let you pass.";
now the robot is asleep;
otherwise:
say "'WRONG PASSWAAARD!' roars the robot. 'CHECK CAPS LAAAWWWWK!'"
The commands say xyzzy and answer xyzzy and robot, xyzzy and say xyzzy to robot will all work.
The extension Questions by Michael Callaghan will help with this. Note that you might not be able to reliably test input case sensitively.
Dropping to I6 like this works in Inform 7.9.3. This is probably a bad idea.
Section 1 - Line input
Include (- Global user_input = 100; -) after "Parser.i6t".
The user input is a snippet that varies. The user input variable translates into I6 as "user_input".
To get a line of input: (-
KeyboardPrimitive(buffer, parse);
user_input = 100 + WordCount();
-).
You can then use the phrase "get a line of input" to read a line, and the phrase "the user's input" gives the line they entered. (A snippet is a kind of text.)
The example then looks like this:
Section 2 - Example
The Loading Zone is a room. "Concrete with yellow stripes. The Hold is north."
The robot is an animal in the Loading Zone. "However, a robot the size of an Arcturan megaladon guards the way."
North of the Loading Zone is the Hold.
Instead of going north from the Loading Zone:
say "The robot steps in front of you as you approach the gate. 'PAASSWAAAAWRD!!' it bellows.[paragraph break]";
say "Enter password: ";
get a line of input;
if the user input matches "xyzzy":
say "The robot folds itself up into a cube to let you pass.";
move the player to the Hold;
otherwise:
say "'WRONG PASSWAAARD!' roars the robot. 'CHECK CAPS LAAAWWWWK!'".
Test me with "n / password / n / xyzzy".