HP Print And Scan Doctor Will Make Your Life Better

 Many people rely on HP printers for their printing tasks. So, at some point everyone encounters one or the other issue. In that case, people look for solutions online or through technical support. But, HP Print and Scan Doctor brings all the solutions to your system without being nuts. HP Scan Doctor is a software that detects the HP printer problems and takes care of them single handedly, or prompts you for performing any external function. The frequently occurring issues with the HP printer are poor internet connectivity, corrupt or abrupt software, offline status, stuck print jobs,etc.  HP Print and Scan Doctor Download is available only for Windows 10 operating system, it is not yet launched for macOS devices. 

Download And Install The HP Print And Scan Doctor In Easy Steps – 

The HP Scan Doctor software is available for free, without any cost. The process of  downloading and installation is very convenient and hassle-free. To detect the issues and resolve them properly, follow the step wise guidelines for HP print and scan doctor download below; 

1. In the first step associate your windows device to the HP printer and then connect both of them to the wifi network.
2. Download the HP Printer and Scan Doctor from 123.hp.com which is the official wite for HP Print and Scan Doctor. Enter your Windows version.
3. Now, download the extension file i.e. HPPSdr.exe to your device.
4. On your device, go to the downloaded folder’s location and locate the HPPSdr.exe file and click on it to run it.
5. Now, the HP Print and Scan Doctor will be installed to your system.
6. A License agreement stating all the terms and conditions will be displayed on your screen, if you agree then tap on accept to proceed with the software setup.
7. Now, just open the software and it will scan your HP printer for any issues and errors will be detected.
8. It will resolve all the errors on your HP printer and scanner both.

Easy Installation Guide For HP Print And Scan Doctor

Once you have completed the installation of the software on your system, follow the tips written below to know how to use the HP scan doctor software for resolving any issues with your HP printer;

1. Firstly, click on the windows icon or press the windows button to open the start menu.
2. From the list of Devices choose the HP printer by clicking on it.
3. If your printer is not visible, then switch off the printer and then turn it on again. Then try looking for it again.
4. Follow the instructions given by the tool to look for your printer in the devices list.
5. If you encounter errors in the HP scanner then click on the ‘Fix Scanning’ option.
6. If you encounter errors in the HP printer then click on the ‘Fix Printing’ option.
7. The result will reflect on your screen when you click on either of the options.
8. You can test both the printer and scanner to look for errors and resolve them.

HP Print And Scan Doctor Treated Your HP Printer! 

Download HP Print and scan doctor is complete and now you can use it to resolve the various errors on your HP printer. Once the HP print and scan doctor is installed it will automatically detect the issues. You need not run the software again and again to locate the errors. The HP Scan doctor is like a genie who has solutions to all our printer and scanner problems. Keep printing because HP Print and Scan Doctor is here!

What is GEEK

Buddha Community

Exploring Mutable and Immutable in Python

In this Python article, let's learn about Mutable and Immutable in Python. 

Mutable and Immutable in Python

Mutable is a fancy way of saying that the internal state of the object is changed/mutated. So, the simplest definition is: An object whose internal state can be changed is mutable. On the other hand, immutable doesn’t allow any change in the object once it has been created.

Both of these states are integral to Python data structure. If you want to become more knowledgeable in the entire Python Data Structure, take this free course which covers multiple data structures in Python including tuple data structure which is immutable. You will also receive a certificate on completion which is sure to add value to your portfolio.

Mutable Definition

Mutable is when something is changeable or has the ability to change. In Python, ‘mutable’ is the ability of objects to change their values. These are often the objects that store a collection of data.

Immutable Definition

Immutable is the when no change is possible over time. In Python, if the value of an object cannot be changed over time, then it is known as immutable. Once created, the value of these objects is permanent.

List of Mutable and Immutable objects

Objects of built-in type that are mutable are:

• Lists
• Sets
• Dictionaries
• User-Defined Classes (It purely depends upon the user to define the characteristics) 

Objects of built-in type that are immutable are:

• Numbers (Integer, Rational, Float, Decimal, Complex & Booleans)
• Strings
• Tuples
• Frozen Sets
• User-Defined Classes (It purely depends upon the user to define the characteristics)

Object mutability is one of the characteristics that makes Python a dynamically typed language. Though Mutable and Immutable in Python is a very basic concept, it can at times be a little confusing due to the intransitive nature of immutability.

Objects in Python

In Python, everything is treated as an object. Every object has these three attributes:

• Identity – This refers to the address that the object refers to in the computer’s memory.
• Type – This refers to the kind of object that is created. For example- integer, list, string etc. 
• Value – This refers to the value stored by the object. For example – List=[1,2,3] would hold the numbers 1,2 and 3

While ID and Type cannot be changed once it’s created, values can be changed for Mutable objects.

Check out this free python certificate course to get started with Python.

Mutable Objects in Python

I believe, rather than diving deep into the theory aspects of mutable and immutable in Python, a simple code would be the best way to depict what it means in Python. Hence, let us discuss the below code step-by-step:

#Creating a list which contains name of Indian cities  

cities = [‘Delhi’, ‘Mumbai’, ‘Kolkata’]

# Printing the elements from the list cities, separated by a comma & space

for city in cities:
		print(city, end=’, ’)

Output [1]: Delhi, Mumbai, Kolkata

#Printing the location of the object created in the memory address in hexadecimal format

print(hex(id(cities)))

Output [2]: 0x1691d7de8c8

#Adding a new city to the list cities

cities.append(‘Chennai’)

#Printing the elements from the list cities, separated by a comma & space 

for city in cities:
	print(city, end=’, ’)

Output [3]: Delhi, Mumbai, Kolkata, Chennai

#Printing the location of the object created in the memory address in hexadecimal format

print(hex(id(cities)))

Output [4]: 0x1691d7de8c8

The above example shows us that we were able to change the internal state of the object ‘cities’ by adding one more city ‘Chennai’ to it, yet, the memory address of the object did not change. This confirms that we did not create a new object, rather, the same object was changed or mutated. Hence, we can say that the object which is a type of list with reference variable name ‘cities’ is a MUTABLE OBJECT.

Let us now discuss the term IMMUTABLE. Considering that we understood what mutable stands for, it is obvious that the definition of immutable will have ‘NOT’ included in it. Here is the simplest definition of immutable– An object whose internal state can NOT be changed is IMMUTABLE.

Again, if you try and concentrate on different error messages, you have encountered, thrown by the respective IDE; you use you would be able to identify the immutable objects in Python. For instance, consider the below code & associated error message with it, while trying to change the value of a Tuple at index 0. 

#Creating a Tuple with variable name ‘foo’

foo = (1, 2)

#Changing the index[0] value from 1 to 3

foo[0] = 3
	
TypeError: 'tuple' object does not support item assignment 

Immutable Objects in Python

Once again, a simple code would be the best way to depict what immutable stands for. Hence, let us discuss the below code step-by-step:

#Creating a Tuple which contains English name of weekdays

weekdays = ‘Sunday’, ‘Monday’, ‘Tuesday’, ‘Wednesday’, ‘Thursday’, ‘Friday’, ‘Saturday’

# Printing the elements of tuple weekdays

print(weekdays)

Output [1]:  (‘Sunday’, ‘Monday’, ‘Tuesday’, ‘Wednesday’, ‘Thursday’, ‘Friday’, ‘Saturday’)

#Printing the location of the object created in the memory address in hexadecimal format

print(hex(id(weekdays)))

Output [2]: 0x1691cc35090

#tuples are immutable, so you cannot add new elements, hence, using merge of tuples with the # + operator to add a new imaginary day in the tuple ‘weekdays’

weekdays  +=  ‘Pythonday’,

#Printing the elements of tuple weekdays

print(weekdays)

Output [3]: (‘Sunday’, ‘Monday’, ‘Tuesday’, ‘Wednesday’, ‘Thursday’, ‘Friday’, ‘Saturday’, ‘Pythonday’)

#Printing the location of the object created in the memory address in hexadecimal format

print(hex(id(weekdays)))

Output [4]: 0x1691cc8ad68

This above example shows that we were able to use the same variable name that is referencing an object which is a type of tuple with seven elements in it. However, the ID or the memory location of the old & new tuple is not the same. We were not able to change the internal state of the object ‘weekdays’. The Python program manager created a new object in the memory address and the variable name ‘weekdays’ started referencing the new object with eight elements in it.  Hence, we can say that the object which is a type of tuple with reference variable name ‘weekdays’ is an IMMUTABLE OBJECT.

Also Read: Understanding the Exploratory Data Analysis (EDA) in Python

Where can you use mutable and immutable objects:

Mutable objects can be used where you want to allow for any updates. For example, you have a list of employee names in your organizations, and that needs to be updated every time a new member is hired. You can create a mutable list, and it can be updated easily.

Immutability offers a lot of useful applications to different sensitive tasks we do in a network centred environment where we allow for parallel processing. By creating immutable objects, you seal the values and ensure that no threads can invoke overwrite/update to your data. This is also useful in situations where you would like to write a piece of code that cannot be modified. For example, a debug code that attempts to find the value of an immutable object.

Watch outs:  Non transitive nature of Immutability:

OK! Now we do understand what mutable & immutable objects in Python are. Let’s go ahead and discuss the combination of these two and explore the possibilities. Let’s discuss, as to how will it behave if you have an immutable object which contains the mutable object(s)? Or vice versa? Let us again use a code to understand this behaviour–

#creating a tuple (immutable object) which contains 2 lists(mutable) as it’s elements

#The elements (lists) contains the name, age & gender 

person = (['Ayaan', 5, 'Male'], ['Aaradhya', 8, 'Female'])

#printing the tuple

print(person)

Output [1]: (['Ayaan', 5, 'Male'], ['Aaradhya', 8, 'Female'])

#printing the location of the object created in the memory address in hexadecimal format

print(hex(id(person)))

Output [2]: 0x1691ef47f88

#Changing the age for the 1st element. Selecting 1st element of tuple by using indexing [0] then 2nd element of the list by using indexing [1] and assigning a new value for age as 4

person[0][1] = 4

#printing the updated tuple

print(person)

Output [3]: (['Ayaan', 4, 'Male'], ['Aaradhya', 8, 'Female'])

#printing the location of the object created in the memory address in hexadecimal format

print(hex(id(person)))

Output [4]: 0x1691ef47f88

In the above code, you can see that the object ‘person’ is immutable since it is a type of tuple. However, it has two lists as it’s elements, and we can change the state of lists (lists being mutable). So, here we did not change the object reference inside the Tuple, but the referenced object was mutated.

Also Read: Real-Time Object Detection Using TensorFlow

Same way, let’s explore how it will behave if you have a mutable object which contains an immutable object? Let us again use a code to understand the behaviour–

#creating a list (mutable object) which contains tuples(immutable) as it’s elements

list1 = [(1, 2, 3), (4, 5, 6)]

#printing the list

print(list1)

Output [1]: [(1, 2, 3), (4, 5, 6)]

#printing the location of the object created in the memory address in hexadecimal format

print(hex(id(list1)))

Output [2]: 0x1691d5b13c8	

#changing object reference at index 0

list1[0] = (7, 8, 9)

#printing the list

Output [3]: [(7, 8, 9), (4, 5, 6)]

#printing the location of the object created in the memory address in hexadecimal format

print(hex(id(list1)))

Output [4]: 0x1691d5b13c8

As an individual, it completely depends upon you and your requirements as to what kind of data structure you would like to create with a combination of mutable & immutable objects. I hope that this information will help you while deciding the type of object you would like to select going forward.

Before I end our discussion on IMMUTABILITY, allow me to use the word ‘CAVITE’ when we discuss the String and Integers. There is an exception, and you may see some surprising results while checking the truthiness for immutability. For instance:
#creating an object of integer type with value 10 and reference variable name ‘x’ 

x = 10
 

#printing the value of ‘x’

print(x)

Output [1]: 10

#Printing the location of the object created in the memory address in hexadecimal format

print(hex(id(x)))

Output [2]: 0x538fb560

#creating an object of integer type with value 10 and reference variable name ‘y’

y = 10

#printing the value of ‘y’

print(y)

Output [3]: 10

#Printing the location of the object created in the memory address in hexadecimal format

print(hex(id(y)))

Output [4]: 0x538fb560

As per our discussion and understanding, so far, the memory address for x & y should have been different, since, 10 is an instance of Integer class which is immutable. However, as shown in the above code, it has the same memory address. This is not something that we expected. It seems that what we have understood and discussed, has an exception as well.

Quick check – Python Data Structures

Immutability of Tuple

Tuples are immutable and hence cannot have any changes in them once they are created in Python. This is because they support the same sequence operations as strings. We all know that strings are immutable. The index operator will select an element from a tuple just like in a string. Hence, they are immutable.

Exceptions in immutability

Like all, there are exceptions in the immutability in python too. Not all immutable objects are really mutable. This will lead to a lot of doubts in your mind. Let us just take an example to understand this.

Consider a tuple ‘tup’.

Now, if we consider tuple tup = (‘GreatLearning’,[4,3,1,2]) ;

We see that the tuple has elements of different data types. The first element here is a string which as we all know is immutable in nature. The second element is a list which we all know is mutable. Now, we all know that the tuple itself is an immutable data type. It cannot change its contents. But, the list inside it can change its contents. So, the value of the Immutable objects cannot be changed but its constituent objects can. change its value.

FAQs

1. Difference between mutable vs immutable in Python?

Mutable Object	Immutable Object
State of the object can be modified after it is created.	State of the object can’t be modified once it is created.
They are not thread safe.	They are thread safe
Mutable classes are not final.	It is important to make the class final before creating an immutable object.

2. What are the mutable and immutable data types in Python?

• Some mutable data types in Python are:

list, dictionary, set, user-defined classes.

• Some immutable data types are: 

int, float, decimal, bool, string, tuple, range.

3. Are lists mutable in Python?

Lists in Python are mutable data types as the elements of the list can be modified, individual elements can be replaced, and the order of elements can be changed even after the list has been created.
(Examples related to lists have been discussed earlier in this blog.)

4. Why are tuples called immutable types?

Tuple and list data structures are very similar, but one big difference between the data types is that lists are mutable, whereas tuples are immutable. The reason for the tuple’s immutability is that once the elements are added to the tuple and the tuple has been created; it remains unchanged.

A programmer would always prefer building a code that can be reused instead of making the whole data object again. Still, even though tuples are immutable, like lists, they can contain any Python object, including mutable objects.

5. Are sets mutable in Python?

A set is an iterable unordered collection of data type which can be used to perform mathematical operations (like union, intersection, difference etc.). Every element in a set is unique and immutable, i.e. no duplicate values should be there, and the values can’t be changed. However, we can add or remove items from the set as the set itself is mutable.

6. Are strings mutable in Python?

Strings are not mutable in Python. Strings are a immutable data types which means that its value cannot be updated.

Join Great Learning Academy’s free online courses and upgrade your skills today.

---

Original article source at: https://www.mygreatlearning.com

#python 

How to Bash Read Command

Bash has no built-in function to take the user’s input from the terminal. The read command of Bash is used to take the user’s input from the terminal. This command has different options to take an input from the user in different ways. Multiple inputs can be taken using the single read command. Different ways of using this command in the Bash script are described in this tutorial.

Syntax

read [options] [var1, var2, var3…]

The read command can be used without any argument or option. Many types of options can be used with this command to take the input of the particular data type. It can take more input from the user by defining the multiple variables with this command.

Some Useful Options of the Read Command

Some options of the read command require an additional parameter to use. The most commonly used options of the read command are mentioned in the following:

Option	Purpose
-d <delimiter>	It is used to take the input until the delimiter value is provided.
-n <number>	It is used to take the input of a particular number of characters from the terminal and stop taking the input earlier based on the delimiter.
-N <number>	It is used to take the input of the particular number of characters from the terminal, ignoring the delimiter.
-p <prompt>	It is used to print the output of the prompt message before taking the input.
-s	It is used to take the input without an echo. This option is mainly used to take the input for the password input.
-a	It is used to take the input for the indexed array.
-t <time>	It is used to set a time limit for taking the input.
-u <file descriptor>	It is used to take the input from the file.
-r	It is used to disable the backslashes.

 

Different Examples of the Read Command

The uses of read command with different options are shown in this part of this tutorial.

Example 1: Using Read Command without Any Option and variable

Create a Bash file with the following script that takes the input from the terminal using the read command without any option and variable. If no variable is used with the read command, the input value is stored in the $REPLY variable. The value of this variable is printed later after taking the input.

#!/bin/bash  
#Print the prompt message
echo "Enter your favorite color: "  
#Take the input
read  
#Print the input value
echo "Your favorite color is $REPLY"

Output:

The following output appears if the “Blue” value is taken as an input:

Example 2: Using Read Command with a Variable

Create a Bash file with the following script that takes the input from the terminal using the read command with a variable. The method of taking the single or multiple variables using a read command is shown in this example. The values of all variables are printed later.

#!/bin/bash  
#Print the prompt message
echo "Enter the product name: "  
#Take the input with a single variable
read item

#Print the prompt message
echo "Enter the color variations of the product: "  
#Take three input values in three variables
read color1 color2 color3

#Print the input value
echo "The product name is $item."  
#Print the input values
echo "Available colors are $color1, $color2, and $color3."

Output:

The following output appears after taking a single input first and three inputs later:

Example 3: Using Read Command with -p Option

Create a Bash file with the following script that takes the input from the terminal using the read command with a variable and the -p option. The input value is printed later.

#!/bin/bash  
#Take the input with the prompt message
read -p "Enter the book name: " book
#Print the input value
echo "Book name: $book"

Output:

The following output appears after taking the input:

Example 4: Using Read Command with -s Option

Create a Bash file with the following script that takes the input from the terminal using the read command with a variable and the -s option. The input value of the password will not be displayed for the -s option. The input values are checked later for authentication. A success or failure message is also printed.

#!/bin/bash  
#Take the input with the prompt message
read -p "Enter your email: " email
#Take the secret input with the prompt message
read -sp "Enter your password: " password

#Add newline
echo ""

#Check the email and password for authentication
if [[ $email == "admin@example.com" && $password == "secret" ]]
then
   #Print the success message
   echo "Authenticated."
else
   #Print the failure message
   echo "Not authenticated."
fi

Output:

The following output appears after taking the valid and invalid input values:

Example 5: Using Read Command with -a Option

Create a Bash file with the following script that takes the input from the terminal using the read command with a variable and the -a option. The array values are printed later after taking the input values from the terminal.

#!/bin/bash  
echo "Enter the country names: "  
#Take multiple inputs using an array  
read -a countries

echo "Country names are:"
#Read the array values
for country in ${countries[@]}
do
    echo $country
done

Output:

The following output appears after taking the array values:

Example 6: Using Read Command with -n Option

Create a Bash file with the following script that takes the input from the terminal using the read command with a variable and the -n option.

#!/bin/bash  
#Print the prompt message
echo "Enter the product code: "  
#Take the input of five characters
read -n 5 code
#Add newline
echo ""
#Print the input value
echo "The product code is $code"

Output:

The following output appears if the “78342” value is taken as input:

Example 7: Using Read Command with -t Option

Create a Bash file with the following script that takes the input from the terminal using the read command with a variable and the -t option.

#!/bin/bash  
#Print the prompt message
echo -n "Write the result of 10-6: "  
#Take the input of five characters
read -t 3 answer

#Check the input value
if [[ $answer == "4" ]]
then
   echo "Correct answer."
else
   echo "Incorrect answer."
fi

Output:

The following output appears after taking the correct and incorrect input values:

Conclusion

The uses of some useful options of the read command are explained in this tutorial using multiple examples to know the basic uses of the read command.

Original article source at: https://linuxhint.com/

#bash #command 

How to download and install Officejet pro 9000 all-in-one printer driv

If you are looking for a printer, which can help you in every possible ways with your office work, the Officejet 9000 can be the best model for you. It is packed with numerous features, and thus, you should get it. Here are all the facts, you should know about the printer. The HP Officejet 9000 is a multi-function printer, where you can get scanning facility, as well. It has wireless connectivity, which means, you can print out documents from anywhere and any device, you would like to. The printer is quite easy to use, which is another big reason, behind the popularity of the printer.Recently, a couple of clients utilizing the download and install Officejet pro 9000 all-in-one printer range have faced challenges while downloading the desired drivers. Assuming that you are additionally here with a similar reason this post is for you.

In the given article we have referenced various methods to download driver hp or update 123.hp.com/officejet 9000 for Windows 7, 8, 10, 11 devices. These driver updates not only improve the communication of the printer with your operating system but also enhance the speed of your Windows PC. Accordingly, go through the possible methods and apply the reasonable choice for Download and Install HP Printer drivers for Windows PC.

How to download and install Officejet pro 9000 drivers for Windows 7, 8, 10, 11?

If your printer has bugs, blank printing issues, or other errors download the latest hp officejet pro 9000 driver for Windows 7, 8, 10, or 11 devices to maintain the bridge between your PC and hardware device. No need to implement all the options, read the steps for each and apply the one that is suitable for you.

Method 1: Download and install Officejet 9000 Driver Update through Device Manager

If you have the time, there’s a built-in utility on your Windows devices that enables you to download HP Officejet 9000 drivers in a partly automatic way. Here’s how to use the utility for downloading HP Officejet 9000 driver for Windows 7, 8, 10, or 11 PCs or Laptops.

1. Open the Run dialog box (Windows + R keys) and type devmgmt.msc. Press the Enter key on your keyboard to open Device Manager
2. Click on the category Printers or Print Queues to expand. From the list locate and Right click on your HP Officejet 9000 driver.
3. Select the alternative to Update Driver. In the following window select the first automatic search for the driver option.
4. Double click on the driver to hp printer installation and Restart Windows PC to apply the update hp printer drivers.

Method 2: Use Bit Driver Updater for Automatic HP Oj 9000 Driver for Windows 7, 8, 10, 11?

Although there are numerous methods for HP Officejet 9000 driver download the automatic one tops our list. It simplifies the task to update drivers with automatic hp printer software download. The software can store the system specifications and quickly offer compatible and latest drivers for your device.

The Bit Driver Updater software updates HP Officejet 9000 driver and all the other drivers with a single click. Along with updating drivers the tool also empowers users to backup and restore the entire data in its huge driver database. Moreover, with the Pro update, it is easier to get technical assistance from the support team 24*7 regarding any relative concerns. You can perform quick scans and schedule driver updates with the help of this tool. All these features can be availed with Bit Driver Updater Pro which comes with a 60 day money back guarantee.

Here are the steps to be followed to download the software and use it for hp printer driver download.

1. Click on the Download button to load the executable file for Bit Driver Updater. Double click on the file as the download completes and follow the instructions to install.
2. Launch the hp officejet software and click on the Scan option on the left panel to start searching for updates.
3. Wait till the command processes and the complete list of drivers with due updates is displayed.
4. Locate HP Officejet 9000 driver update and click on the Update button present next to it.
5. In addition, Pro version users can Update the entire list of drivers with a single click on the Update All button.
   Note: If you are using the Free version for Bit Driver updater click on the Update Now option for each driver to download one update at a time.
6. Follow the instructions on your screen to install the latest version of the hp printer driver download for windows 10 devices.

Restart your Windows device to apply the updated driver software. The automatic driver updater software method for driver updates is the most convenient one. However, if you have the time and patience you can opt for the following method to hp officejet pro 9000 download.

Method 3: Download HP Officejet 9000 Driver Update from Official Website

Another and the most common method to download or update HP Officejet 9000 driver for Windows 11, 10, 8, or 7 devices is from the official website of HP. However, before you begin with the steps, find out the specifications of your system and its requirements to download the right drivers.

Open Windows Settings on your device and move to the about section. Check the Windows Edition and system type that are 9000 driver update.

1. Visit the official support 123.hp setup.
2. In the search bar write the model number of your printer and click the Submit button or enter key on your keyboard. In our case, it is HP Officejet 9000.
3. Check your automatically detected Operating system version is correct and click on the Download button present next to the latest HP Officejet Driver update.
4. As the download completes, double click on the driver file and apply the instructions on the screen to install.
5. Restart your device to launch the HP Officejet 9000 driver update. This method is suitable only for the users who are skilled technically and have enough time & patience to hp printer drivers for windows 10 manually.

Conclusion:

The all-in-one printer series HP Officejet 9000 is supported by various Windows versions. We hope the guide proved to be useful in downloading the latest HP Officejet pro 9000 printer Drivers for your Windows devices. Although all the methods are reliable in our opinion automatic driver downloads through Bit Driver Updater is the simplest of all. Use the tool to update all the drivers at the ease of a single click.

tags 

#123.hp setup

#123.hp.com/officejet 9000

#Download and Install HP Printer drivers for Windows PC

#download driver hp

#hp officejet pro 9000 download

#HP Officejet pro 9000 printer Drivers

#hp officejet software

#hp printer driver download

 #hp printer drivers for windows 10

 #hp printer installation

#hp printer software download

 #hp printer software update

 #install Officejet 9000 printer driver

#update hp printer drivers

Chatbot conversacional de IA con Transformers en Python

Aprenda a usar la biblioteca de transformadores Huggingface para generar respuestas conversacionales con el modelo DialoGPT previamente entrenado en Python.

Los chatbots han ganado mucha popularidad en los últimos años y, a medida que crece el interés en el uso de chatbots para empresas, los investigadores también hicieron un gran trabajo en el avance de los chatbots de IA conversacionales.

En este tutorial, usaremos la biblioteca de transformadores Huggingface para emplear el modelo DialoGPT previamente entrenado para la generación de respuestas conversacionales.

DialoGPT es un modelo de generación de respuesta conversacional neuronal sintonizable a gran escala que se entrenó en 147 millones de conversaciones extraídas de Reddit, y lo bueno es que puede ajustarlo con su conjunto de datos para lograr un mejor rendimiento que el entrenamiento desde cero.

Para comenzar, instalemos transformadores :

$ pip3 install transformers

Abra un nuevo archivo o cuaderno de Python y haga lo siguiente:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# model_name = "microsoft/DialoGPT-large"
model_name = "microsoft/DialoGPT-medium"
# model_name = "microsoft/DialoGPT-small"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

Hay tres versiones de DialoGPT; pequeño, mediano y grande. Por supuesto, cuanto más grande, mejor, pero si ejecuta esto en su máquina, creo que el tamaño pequeño o mediano se adapta a su memoria sin problemas. También puede utilizar Google Colab para probar el más grande.

Generación de respuestas con búsqueda codiciosa

En esta sección, usaremos el algoritmo de búsqueda codiciosa para generar respuestas. Es decir, seleccionamos la respuesta del chatbot que tiene la mayor probabilidad de ser seleccionada en cada paso de tiempo.

Hagamos un código para chatear con nuestra IA usando una búsqueda codiciosa:

# chatting 5 times with greedy search
for step in range(5):
    # take user input
    text = input(">> You:")
    # encode the input and add end of string token
    input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
    # concatenate new user input with chat history (if there is)
    bot_input_ids = torch.cat([chat_history_ids, input_ids], dim=-1) if step > 0 else input_ids
    # generate a bot response
    chat_history_ids = model.generate(
        bot_input_ids,
        max_length=1000,
        pad_token_id=tokenizer.eos_token_id,
    )
    #print the output
    output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    print(f"DialoGPT: {output}")

Expliquemos el núcleo de este código:

• Primero tomamos información del usuario para chatear.
• Codificamos el texto para input_idsusar el tokenizador DialoGPT, también agregamos el final del token de cadena y lo devolvemos como un tensor de Pytorch.
• Si esta es la primera vez que chateamos con el bot, alimentaremos directamente input_idsnuestro modelo durante una generación. De lo contrario, agregamos el historial de chat usando la concatenación con la ayuda del torch.cat()método.
• Después de eso, usamos el model.generate()método para generar la respuesta del chatbot.
• Por último, como la salida devuelta también es una secuencia tokenizada, decodificamos la secuencia usando tokenizer.decode()y configuramos skip_special_tokenspara Trueasegurarnos de que no veamos ningún token especial molesto como <|endoftext|>. Además, dado que el modelo devuelve la secuencia completa, omitimos el historial de chat anterior e imprimimos solo la respuesta del chatbot recién generada.

A continuación se muestra una discusión de muestra con el bot:

>> You:How can you be rich so quickly?
DialoGPT: I'm not rich, I'm just a rich man.
>> You:Ok, you don't make sense, how old are you ?
DialoGPT: I'm not a rich man, I'm just a rich man.
>> You:How can you be happy ?
DialoGPT: I'm not happy, I'm just a rich man.
>> You:But they say money buys happiness!
DialoGPT: Money buys happiness, but not happiness itself.
>> You:You don't make sense again!
DialoGPT: I'm not happy, I'm just a rich man.

Verá que el modelo repite muchas respuestas, ya que estas son la probabilidad más alta y lo elige cada vez.

De forma predeterminada, model.generate()utiliza un algoritmo de búsqueda codicioso cuando no se establecen otros parámetros; en las siguientes secciones, agregaremos algunos argumentos a este método para ver si podemos mejorar la generación.

Generación de respuestas con Beam Search

La búsqueda por haz nos permite reducir el riesgo de perder secuencias de alta probabilidad al mantener las num_beamshipótesis más probables en cada paso de tiempo y luego tomar las secuencias que tienen la probabilidad general más alta, el siguiente código generará respuestas de chatbot con búsqueda de haz:

# chatting 5 times with beam search
for step in range(5):
    # take user input
    text = input(">> You:")
    # encode the input and add end of string token
    input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
    # concatenate new user input with chat history (if there is)
    bot_input_ids = torch.cat([chat_history_ids, input_ids], dim=-1) if step > 0 else input_ids
    # generate a bot response
    chat_history_ids = model.generate(
        bot_input_ids,
        max_length=1000,
        num_beams=3,
        early_stopping=True,
        pad_token_id=tokenizer.eos_token_id
    )
    #print the output
    output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    print(f"DialoGPT: {output}")

Cuando se ajusta num_beamsa 3de model.generate()método, a continuación, vamos a seleccionar 3 palabras en cada paso de tiempo y desarrollarlas para encontrar la más alta probabilidad global de la secuencia, el establecimiento num_beamsde 1 es la misma que la búsqueda codiciosa.

A continuación se muestra una discusión de muestra con el chatbot usando la búsqueda de haz:

>> You:How can I be rich?
DialoGPT: You can't.
>> You:Why not?
DialoGPT: Because you can't.
>> You:Then how am I supposed to live well?
DialoGPT: You can't.
>> You:So basically, you want me to be a poor guy?
DialoGPT: No, I want you to be a rich guy.
>> You:Ok how to be rich, then?
DialoGPT: I don't know.

Generando respuestas con muestreo

En las secciones anteriores, usamos la búsqueda de rayos y codiciosos para generar la secuencia de probabilidad más alta. Eso es genial para tareas como la traducción automática o el resumen de texto donde el resultado es predecible. Sin embargo, no es la mejor opción para una generación abierta como en los chatbots.

Para una mejor generación, necesitamos introducir algo de aleatoriedad donde muestreamos de una amplia gama de secuencias candidatas basadas en probabilidades:

# chatting 5 times with sampling
for step in range(5):
    # take user input
    text = input(">> You:")
    # encode the input and add end of string token
    input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
    # concatenate new user input with chat history (if there is)
    bot_input_ids = torch.cat([chat_history_ids, input_ids], dim=-1) if step > 0 else input_ids
    # generate a bot response
    chat_history_ids = model.generate(
        bot_input_ids,
        max_length=1000,
        do_sample=True,
        top_k=0,
        pad_token_id=tokenizer.eos_token_id
    )
    #print the output
    output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    print(f"DialoGPT: {output}")

Esta vez, establece do_sampleque Truepara el muestreo, y nos pusimos top_ka 0lo que indica que estamos seleccionando todas las probabilidades posibles, vamos a discutir más adelante top_kparámetro.

Aquí hay un chat con estos parámetros:

>> You:Hello, how can I be rich?
DialoGPT: You can't
>> You:Really? then how others get rich?
DialoGPT: They work as money artists
>> You:How to be a money artist?
DialoGPT: I don't know, I don't have enough knowledge on artists
>> You:Alright, thank you!
DialoGPT: No problem, if you need tips pm me.
>> You:Great, you're my savior!
DialoGPT: Thank you for helping a stranger out like me!

Claramente hay algunas mejoras. Sin embargo, el muestreo en una amplia lista de secuencias con bajas probabilidades puede conducir a una generación aleatoria (como se ve en la última oración).

Para mejorarlo aún más, podemos:

• temperatureDisminuir el muestreo , eso nos ayuda a disminuir la probabilidad de elegir palabras de baja probabilidad y aumentar la probabilidad de elegir palabras de alta probabilidad.
• Utilice el muestreo de Top-k en lugar de seleccionar todas las ocurrencias probables, esto nos ayudará a descartar palabras de baja probabilidad para que no sean seleccionadas.

# chatting 5 times with Top K sampling & tweaking temperature
for step in range(5):
    # take user input
    text = input(">> You:")
    # encode the input and add end of string token
    input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
    # concatenate new user input with chat history (if there is)
    bot_input_ids = torch.cat([chat_history_ids, input_ids], dim=-1) if step > 0 else input_ids
    # generate a bot response
    chat_history_ids = model.generate(
        bot_input_ids,
        max_length=1000,
        do_sample=True,
        top_k=100,
        temperature=0.75,
        pad_token_id=tokenizer.eos_token_id
    )
    #print the output
    output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    print(f"DialoGPT: {output}")

Ahora, configuramos top_kpara 100muestrear las 100palabras principales ordenadas de forma descendente por probabilidad. También establecemos temperatureen 0.75(el valor predeterminado es 1.0) para brindar una mayor probabilidad de elegir palabras de alta probabilidad, establecer la temperatura en 0.0es lo mismo que la búsqueda codiciosa, establecerla en infinito es lo mismo que completamente aleatorio.

Aquí hay una discusión con estos parámetros:

>> You:How can I get rich?
DialoGPT: I'd also like to know this.
>> You:So you don't know it?
DialoGPT: I know it, but it doesn't matter.
>> You:Really? money matters, man!
DialoGPT: Well, money is money and I gotta get my money.
>> You:Yeah how to get them?
DialoGPT: Well, that's a question. I'd like to know more, just for curiosity's sake, to know what other people have said about how I should get rich.
>> You:Some robots like you told me you have to buy gold, silver or stocks.
DialoGPT: I think my wallet is empty.

Como se puede ver, es mucho mejor ahora, no dude en modificar temperaturey top_kparámetros y ver si puede mejorarlo.

Muestreo de núcleos

El muestreo de núcleo o muestreo de Top-p elige entre las palabras más pequeñas posibles cuya probabilidad acumulada excede el parámetro pque establecimos.

A continuación se muestra un ejemplo con el muestreo de Top-p:

# chatting 5 times with nucleus sampling & tweaking temperature
for step in range(5):
    # take user input
    text = input(">> You:")
    # encode the input and add end of string token
    input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
    # concatenate new user input with chat history (if there is)
    bot_input_ids = torch.cat([chat_history_ids, input_ids], dim=-1) if step > 0 else input_ids
    # generate a bot response
    chat_history_ids = model.generate(
        bot_input_ids,
        max_length=1000,
        do_sample=True,
        top_p=0.95,
        top_k=0,
        temperature=0.75,
        pad_token_id=tokenizer.eos_token_id
    )
    #print the output
    output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    print(f"DialoGPT: {output}")

Configuramos top_kpara 0deshabilitar el muestreo de Top-k, pero puede usar ambos métodos, lo que tiende a funcionar mejor. Aquí hay un chat:

>> You:How can I be rich fast?
DialoGPT: Inflation and free money
>> You:lol, but that takes time, I need fast money.
DialoGPT: Your post makes no sense. You just need a lot of money to be rich fast
>> You:Ok how to get a lot of money?
DialoGPT: Buy gold and then trade it for money.
>> You:Hmm, I got your point, thanks.
DialoGPT: No problem. You have to have money to buy gold, but its only good for trading it.
>> You:Yeah, I understand, thank you so much.
DialoGPT: Ok, let me know if you need help

Ahora el chatbot claramente tiene sentido en muchos casos.

Ahora agreguemos algo de código para generar más de una respuesta de chatbot, y luego elegimos qué respuesta incluir en la siguiente entrada:

# chatting 5 times with nucleus & top-k sampling & tweaking temperature & multiple
# sentences
for step in range(5):
    # take user input
    text = input(">> You:")
    # encode the input and add end of string token
    input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
    # concatenate new user input with chat history (if there is)
    bot_input_ids = torch.cat([chat_history_ids, input_ids], dim=-1) if step > 0 else input_ids
    # generate a bot response
    chat_history_ids_list = model.generate(
        bot_input_ids,
        max_length=1000,
        do_sample=True,
        top_p=0.95,
        top_k=50,
        temperature=0.75,
        num_return_sequences=5,
        pad_token_id=tokenizer.eos_token_id
    )
    #print the outputs
    for i in range(len(chat_history_ids_list)):
      output = tokenizer.decode(chat_history_ids_list[i][bot_input_ids.shape[-1]:], skip_special_tokens=True)
      print(f"DialoGPT {i}: {output}")
    choice_index = int(input("Choose the response you want for the next input: "))
    chat_history_ids = torch.unsqueeze(chat_history_ids_list[choice_index], dim=0)

He configurado num_return_sequencespara 5devolver 5 oraciones a la vez, tenemos que elegir la que se incluirá en la siguiente secuencia. Así es como fue:

>> You:Hello, friend.
DialoGPT 0: Hey there!
DialoGPT 1: I am your friend, and I am also your friend.
DialoGPT 2: Hello. :
DialoGPT 3: Hiya! How are you?
DialoGPT 4: Hello. I like your username.
Choose the response you want for the next input: 3
>> You:Fine, thanks, what about you?
DialoGPT 0: Good. Not much to do.
DialoGPT 1: Not much, you?
DialoGPT 2: Fine, thanks.
DialoGPT 3: I'm okay, thank you for asking.
DialoGPT 4: I'm fine too.
Choose the response you want for the next input: 2
>> You:Can you tell me how can I get rich quickly?
DialoGPT 0: Yes, I can!
DialoGPT 1: Yes, just look up how to get rich on Google.
DialoGPT 2: Just keep doing your thing. You'll get rich.
DialoGPT 3: No, I can't.
DialoGPT 4: no, i have no money
Choose the response you want for the next input: 1
>> You:Yeah, but I thought you have an answer...
DialoGPT 0: I'm getting married in the morning.
DialoGPT 1: How do you get rich?
DialoGPT 2: I think there are many good answers, but I could send you one, if you want.
DialoGPT 3: I will, thanks!
DialoGPT 4: I thought you have an answer.
Choose the response you want for the next input: 2
>> You:Yes, please send me.
DialoGPT 0: You can send me link.
DialoGPT 1: I am very interested
DialoGPT 2: I sent you a PM
DialoGPT 3: I'll send you a PM
DialoGPT 4: I am always interested in new ideas.
Choose the response you want for the next input: 2

Conclusión

Y ahí lo tienes, espero que este tutorial te haya ayudado a generar texto en DialoGPT y modelos similares. Para obtener más información sobre cómo generar texto, le recomiendo que lea la guía Cómo generar texto con Transformers .

Te dejo ajustando los parámetros para ver si puedes hacer que el bot funcione mejor.

Además, puede combinar esto con tutoriales de texto a voz y de voz a texto para crear un asistente virtual como Alexa , Siri , Cortana , etc.

#python #chatbot #ai 

Pythonでリストを昇順および降順でソートする

リストを昇順および降順でソートするためのPythonプログラム。このPythonチュートリアルでは、リストの要素をPythonで昇順と降順で並べ替える方法を紹介します。

pythonの組み込みメソッド名sort（）を使用します。これは、リストの要素/オブジェクトを昇順および降順で並べ替えるために使用されます。

ソートメソッドの基本構文：

 list.sort（）

リストを昇順および降順でソートするためのPythonプログラム

• リスト要素を昇順でソートするPythonプログラム
• リスト要素を降順でソートするPythonプログラム

リスト要素を昇順でソートするPythonプログラム

# List of integers
num = [100, 200, 500, 600, 300]
 
# sorting and printing 
num.sort()
 
#print
print(num)
 
# List of float numbers
fnum = [100.43, 50.72, 90.65, 16.00, 04.41]
 
# sorting and printing
fnum.sort()
 
#print
print(fnum)
 
# List of strings 
str = ["Test", "My", "Word", "Tag", "Has"]
 
# sorting and  printing
str.sort()
 
#print
print(str)

Pythonプログラムを実行すると、出力は次のようになります。

[100、200、300、500、600]
[4.41、16.0、50.72、90.65、100.43]
['Has'、 'My'、 'Tag'、 'Test'、 'Word']

上で知っているように、リスト要素を昇順で並べ替える方法。次に、sort（）メソッドを使用してリストを降順で並べ替える方法を説明します。

sort（）メソッドを使用して引数としてreverse = Trueを渡し、リスト要素を降順で並べ替えます。

リスト要素を降順でソートする次のプログラムを見ることができます。

リスト要素を降順でソートするPythonプログラム

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
# List of integers
num = [100, 200, 500, 600, 300]
 
# sorting and printing 
num.sort(reverse=True)
 
#print
print(num)
 
# List of float numbers
fnum = [100.43, 50.72, 90.65, 16.00, 04.41]
 
# sorting and printing
fnum.sort(reverse=True)
 
#print
print(fnum)
 
# List of strings 
str = ["Test", "My", "Word", "Tag", "Has"]
 
# sorting and  printing
str.sort(reverse=True)
 
#print
print(str)

プログラムの実行後、出力は次のようになります。

[600、500、300、200、100] 
[100.43、90.65、50.72、16.0、4.41] 
['Word'、 'Test'、 'Tag'、 'My'、 'Has']

リンク: https://www.tutsmake.com/python-program-to-sort-list-in-ascending-and-descending-order/

#python