The Merge Columns dialog appears. At first, we find the minimum value from the whole array and swap this value with the array's first element. We can obtain the length distribution across categories: We can see that politics and tech articles tend to be longer, but not in a significant way. Why did OpenSSH create its own key format, and not use PKCS#8? The expression x or y first evaluates x; if x is true, its value is returned; otherwise, y is evaluated and the resulting value is returned. Here, you should set up a custom search API. In this guide, well introduce you to MonkeyLearns API, which you can connect to your data in Python in a few simple steps. How do we frame image captioning? Area Under the ROC Curve (AUC): this is a performance measurement for classification problem at various thresholds settings. Read our Privacy Policy. These two methods (Word Count Vectors and TF-IDF Vectors) are often named Bag of Words methods, since the order of the words in a sentence is ignored. I need a 'standard array' for a D&D-like homebrew game, but anydice chokes - how to proceed? Claim Discount. I don't know if my step-son hates me, is scared of me, or likes me? Half of the documents contain positive reviews regarding a movie while the remaining half contains negative reviews. To subscribe to this RSS feed, copy and paste this URL into your RSS reader. In the first case, we have calculated the accuracy on both training and test sets so as to detect overfit models. Text may contain numbers, special characters, and unwanted spaces. This is achieved with a supervised machine learning classification model that is able to predict the category of a given news article, a web scraping method that gets the latest news from the newspapers, and an interactive web application that shows the obtained results to the user. Lemmatization is done in order to avoid creating features that are semantically similar but syntactically different. Will this data look the same as the training dataset? Each folder has a single .txt file for every news article. Why did OpenSSH create its own key format, and not use PKCS#8? __future__ statements are in effect, these will be included as well. with keyword is used to wrap the execution of block of code within methods defined by context manager. Find centralized, trusted content and collaborate around the technologies you use most. Below we show a summary of the different models and their evaluation metrics: Overall, we obtain really good accuracy values for every model. 21. exec. This model will be able to predict the topic of a product review based on its content. With MonkeyLearn, you can either build a custom text classifier using your own tags and data or you can use one of the pre-trained modelsfor text classification tasks. If you print y on the screen, you will see an array of 1s and 0s. By clicking Accept all cookies, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy. Other approach can be using other error metrics beyond accuracy such as the precision, the recall or the F1-score. I would advise you to change some other machine learning algorithm to see if you can improve the performance. We recommend checking out our Guided Project: "Image Captioning with CNNs and Transformers with Keras". This means that the dataset contains an approximately equal portion of each class. Machine learning models require numeric features and labels to provide a prediction. Execute the following script to see load_files function in action: In the script above, the load_files function loads the data from both "neg" and "pos" folders into the X variable, while the target categories are stored in y. These out-of-the-box solutions require only a few lines of code, and you wont have to worry about building complex infrastructure or learning the ins and outs of machine learning. Used with exceptions, what to do when an exception occurs. This is awesome, and is basically what I needed to get the right idea about this. First click the subject column header, then hold down the Control key and click the comment column header. a generator. Python is ideal for text classification, because of it's strong string class with powerful methods. Do you already have the information on whether 'apple' is a 'fruit'? python - dictionary-based keyword categorization - Stack Overflow dictionary-based keyword categorization Ask Question Asked 9 years, 7 months ago Modified 9 years, 7 months ago Viewed 267 times 2 I'm pretty new to programming and have been pretty enthralled by its power so far. In this example, weve defined the tags Pricing, Customer Support, and Ease of Use: Lets start training the model! Next, we use the \^[a-zA-Z]\s+ regular expression to replace a single character from the beginning of the document, with a single space. Testing for Python keywords. We have two categories: "neg" and "pos", therefore 1s and 0s have been added to the target array. Keywords in Python are reserved words that can not be used as a variable name, function name, or any other identifier. Any variable or list value can be deleted using del. As you can see " apple " is not a keyword but " if " and " else " are! Now, lets see how to call your text classifier using its API with Python. By reducing the dimensional space to 2 or 3 dimensions that contain a great part of the information, we can plot our data points and be able to recognize some patterns as humans. The dataset that we are going to use for this article can be downloaded from the Cornell Natural Language Processing Group. There are another two keywords, these are is and not. keyword.iskeyword(s) . All rights reserved. How can citizens assist at an aircraft crash site? Feature engineering is the process of transforming data into features to act as inputs for machine learning models such that good quality features help in improving the model performance. Once your data is ready to use, you can start building your text classifier. It helps summarize the content of texts and recognize the main topics discussed. That is, we are given a certain dataset (with the labels already assigned if it is a supervised learning problem), try several models and obtain a performance metric. The functions are intended for the vibrant implementation of the Python program, which can be object code or a specific string. I could get lists of vegetables, fruits, and types of shoes pretty easily, but are there existing packages that could help with this kind of a problem specifically? Used in conditional statements, same as else if. We can also use NLP based features using Part of Speech models, which can tell us, for example, if a word is a noun or a verb, and then use the frequency distribution of the PoS tags. How to tell if my LLC's registered agent has resigned? It consists of 2.225 documents from the BBC news website corresponding to stories in five topical areas from 2004 to 2005. Instead, only key is used to introduce custom sorting logic. Machines, unlike humans, cannot understand the raw text. The regex ^b\s+ removes "b" from the start of a string. The aim of this step is to get a dataset with the following structure: We have created this dataset with an R script, because the package readtext simplifies a lot this procedure. Python has a set of keywords that are reserved words that cannot be used as Keywords in Python are some special reserved words that have special meanings and serves a special purpose in programming. The use of electronic devices in the Commons chamber has long been frowned on. He or she is always an MP chosen by colleagues who, once nominated, gives up all party political allegiances. Tier 3: Service + Category + Sub Category. How can I translate the names of the Proto-Indo-European gods and goddesses into Latin? At the end of the day, bad data will deliver poor results, no matter how powerful your machine learning algorithms are. If you want to get an expert on your own I suggest this article. By clicking Post Your Answer, you agree to our terms of service, privacy policy and cookie policy. . Text classification is the foundation of NLP ( Natural Language Processing ) with extended usages such as sentiment analysis, topic labeling, span detection, and intent detection. Is dataset your dataset in the form of text, where the words "apple", "pear", etc are part of sentences? Tutorials, references, and examples are constantly reviewed to avoid errors, but we cannot warrant full correctness of all content. Otherwise, you can use MonkeyLearns-Classification API for your Project see here. These rules consist of a pattern or a set of patterns for each of the categories. If you need to convert a Python 2 cmp function to a key function, then check out functools.cmp_to_key . We have saved our trained model and we can use it later for directly making predictions, without training. Note that neither and nor or restrict the value and type they return to False and True, but rather return the last evaluated argument. Stop Googling Git commands and actually learn it! pass is the null statement in python. There are several ways of dealing with imbalanced datasets. The keywords module also lets us see the full list of keywords using the following command. We have divided our data into training and testing set. So, why not automate text classification using Python? We will see how to create features from text in the next section (5. Background checks for UK/US government research jobs, and mental health difficulties. what's the difference between "the killing machine" and "the machine that's killing". By using our site, you Feature engineering is an essential part of building any intelligent system. This is because when you convert words to numbers using the bag of words approach, all the unique words in all the documents are converted into features. Precision: precision is used to measure the positive patterns that are correctly predicted from the total predicted patterns in a positive class. False keyword in python. I'm most comfortable with Python and R, so anything that can be used with those languages would be most helpful. Explanation: In selection sort, we sort the array by finding the minimum value. Keywords can't be used for another purpose other than what they are reserved for. For instance "cats" is converted into "cat". Learn to code by doing. Python | Pandas Dataframe/Series.head() method, Python | Pandas Dataframe.describe() method, Dealing with Rows and Columns in Pandas DataFrame, Python | Pandas Extracting rows using .loc[], Python | Extracting rows using Pandas .iloc[], Python | Pandas Merging, Joining, and Concatenating, Python | Working with date and time using Pandas, Python | Read csv using pandas.read_csv(), Python | Working with Pandas and XlsxWriter | Set 1. Lets show an example of a misclassified article. In this article, we will use the bag of words model to convert our text to numbers. This is achieved with a supervised machine learning classification model that is able to predict the category of a given news article, a web scraping method that gets the latest news from the newspapers, and an interactive web application that shows the obtained results to the user. Python Everything about Python and how you can utilize Python in Data Science? You would need requisite libraries to run this code - you can install them at their individual official links Pandas Scikit-learn XGBoost TextBlob Keras How can I remove a key from a Python dictionary? For this reason, if we wanted to predict a single news article at a time (for example once the model is deployed), we would need to define that corpus. By clicking Accept all cookies, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy. Looking at our data, we can get the % of observations belonging to each class: We can see that the classes are approximately balanced, so we wont perform any undersampling or oversampling method. Import The List Into Your Python Notebook. It includes all the code and a complete report. Following are the steps required to create a text classification model in Python: Execute the following script to import the required libraries: We will use the load_files function from the sklearn_datasets library to import the dataset into our application. Microsoft Azure joins Collectives on Stack Overflow. After performing the hyperparameter tuning process with the training data via cross validation and fitting the model to this training data, we need to evaluate its performance on totally unseen data (the test set). The github repo can be found here. Depending upon the problem we face, we may or may not need to remove these special characters and numbers from text. And the Inverse Document Frequency is calculated as: The TFIDF value for a word in a particular document is higher if the frequency of occurrence of that word is higher in that specific document but lower in all the other documents. This process can be performed manually by human agents or automatically using text classifiers powered by machine learning algorithms. Connect and share knowledge within a single location that is structured and easy to search. Let me explain in brief what i want to achieve here, [https://i.stack.imgur.com/4YbEd.jpg][1], in the attached screen shot i have two columns one is "Description" & "Category", basically i wanted to build an python model which will read my Description column & tag it to the right Category. For instance, we don't want two different features named "cats" and "cat", which are semantically similar, therefore we perform lemmatization. It splits texts into paragraphs, sentences, and even parts of speech making them easier to classify. However, when dealing with multiclass classification they become more complex to compute and less interpretable. There are many different types of, Text analysis is the process of automatically organizing and evaluating unstructured text (documents, customer feedback, social media, Multi-label classification is an AI text analysis technique that automatically labels (or tags) text to classify it by topic. In the script above, our machine learning model did not take much time to execute. The next step is to convert the data to lower case so that the words that are actually the same but have different cases can be treated equally. Now, we will study its behavior by analyzing misclassified articles, in order to get some insights on the way the model is working and, if necessary, think of new features to add to the model. Luckily, there are many resources that can help you carry out this process, whether you choose to use open-source or SaaS tools. You will also need time on your side and money if you want to build text classification tools that are reliable. How to Identify Python Keywords Use an IDE With Syntax Highlighting Use Code in a REPL to Check Keywords Look for a SyntaxError Python Keywords and Their Usage Value Keywords: True, False, None Operator Keywords: and, or, not, in, is Control Flow Keywords: if, elif, else Iteration Keywords: for, while, break, continue, else Find centralized, trusted content and collaborate around the technologies you use most. Feature Engineering), but, because of the way these features are constructed, we would not expect any valuable insights from analyzing them. Words that occur in almost every document are usually not suitable for classification because they do not provide any unique information about the document. del is used to delete a reference to an object. Connect and share knowledge within a single location that is structured and easy to search. Also, try to change the parameters of the CountVectorizerclass to see if you can get any improvement. We need to pass the training data and training target sets to this method. However, we have also obtained the confusion matrix and the classification report (which computes precision, recall and F1-score for all the classes) for every model, so we could further interpret their behavior. Python Programming Foundation -Self Paced Course, Python | Set 4 (Dictionary, Keywords in Python), Python program to extract Keywords from a list, Pafy - Getting Keywords for each item of Playlist, Web scraper for extracting emails based on keywords and regions, Important differences between Python 2.x and Python 3.x with examples, Python program to build flashcard using class in Python, Reading Python File-Like Objects from C | Python. The position of a word within the vector space is learned from text and is based on the words that surround the word when it is used. This is a classic example of sentimental analysis where people's sentiments towards a particular entity are classified into different categories. Next, we remove all the single characters. Boolean value, result of comparison operations. A popular open-source library is Scikit-Learn,used for general-purpose machine learning. For this reason, I have developed a project that covers this full process of creating a ML-based service: getting the raw data and parsing it, creating the features, training different models and choosing the best one, getting new data to feed the model and showing useful insights to the final user. key and reverse must be passed as keyword arguments, unlike in Python 2, where they could be passed as positional arguments. Used in conditional statements. Return True if s is a Python soft keyword. A-143, 9th Floor, Sovereign Corporate Tower, We use cookies to ensure you have the best browsing experience on our website. Our team is ready to answer all your questions and help you get started! The ability to store a variety of data is what makes Lists a very unique and vital Data Structure in Python. Lets discuss each keyword in detail with the help of good examples. Follow this step-by-step tutorial to create a text classifier for topic detection. Asking for help, clarification, or responding to other answers. Youll only need to enter a few lines of code in Python to connect text classifiers to various apps using the API. The 200 handheld computers can be used as a phone, pager or to send e-mails. Youll be asked to tag some samples to teach your classifier to categorize the reviews you uploaded. import pandas as pd. Decoder-only models are great for generation (such as GPT-3), since decoders are able to infer meaningful representations into another sequence with the same meaning. A popular open-source library is Scikit-Learn,used for general-purpose machine learning. token Constants used with Python parse trees. The script can be found here. Execute the following script: The above script divides data into 20% test set and 80% training set. Due to the sparseness of words and the lack of information carried in the short texts themselves, an intermediate representation of the texts and documents are needed before they are put into any classification algorithm. The project involves the creation of a real-time web application that gathers data from several newspapers and shows a summary of the different topics that are being discussed in the news articles. 3. As of Python 3.9.6, there are 36 keywords available. Find more information on how to integrate text classification models with Python in the API tab. block of code that will be executed no matter if there is an exception or The None keyword is used to define a null value, or no value at all. To prepare this dataset, I have downloaded the first 100 results appearing for the keyword "hotel in Barcelona" and I have put together their meta titles and meta descriptions. This module allows a Python program to determine if a string is a keyword or soft keyword. This approach is particularly useful in text classification problems due to the commonly large number of features. There's a veritable mountain of text data waiting to be mined for insights. except. 7 Tips On How To Jump-Start Your Freelance Data Science Business, Pandemics Affect on the Airline Industry. Recall that, although the hyperparameter tuning is an important process, the most critic process when developing a machine learning project is being able to extract good features from the data. Keyword extraction is tasked with the automatic identification of. The bag of words approach works fine for converting text to numbers. CODING PRO 36% OFF . How to Create a Basic Project using MVT in Django ? In this section, well cover how to train a text classifier with machine learning from scratch. In the Merge Columns dialog, choose Tab as the separator, then click OK. Execute the following script: The output is similar to the one we got earlier which showed that we successfully saved and loaded the model. This is because, for each category, the load_files function adds a number to the target numpy array. The complete and detailed feature engineering code can be found here. A very simple approach could be to classify documents based on the occurrences of category-specific words. Text classification has a variety of applications, such as detecting user sentiment from a tweet, classifying an email as spam or ham, classifying blog posts into different categories, automatic tagging of customer queries, and so on. keyword or soft keyword. Background checks for UK/US government research jobs, and mental health difficulties. Your inquisitive nature makes you want to go further? These steps can be used for any text classification task. Select the Transform ribbon. Comparison Between Text Classification and topic modeling. # Import dataset and classes needed in this example: from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split # Import Gaussian Naive Bayes classifier: from sklearn.naive_bayes . The sound of a mobile phone or a pager can result in a strong rebuke from either the Speaker or his deputies. Python Keywords. The following script uses the bag of words model to convert text documents into corresponding numerical features: The script above uses CountVectorizer class from the sklearn.feature_extraction.text library. SpaCy makes custom text classification structured and convenient through the textcat component.. For this reason, we have only performed a shallow analysis. rev2023.1.18.43174. To load the model, we can use the following code: We loaded our trained model and stored it in the model variable. We can also get all the keyword names using the below code. The data was split into Train : Test :: 80 : 20 and the evaluation metric used was F1 score. Making statements based on opinion; back them up with references or personal experience. This means we need a labeled dataset so the algorithms can learn the patterns and correlations in the data. Site design / logo 2023 Stack Exchange Inc; user contributions licensed under CC BY-SA. This tutorial provides brief information on all keywords used in Python. Presents case studies and instructions on how to solve data analysis problems using Python. It also comes with many resources and tutorials. In lemmatization, we reduce the word into dictionary root form. Using Python 3, we can write a pre-processing function that takes a block of text and then outputs the cleaned version of that text.But before we do that, let's quickly talk about a very handy thing called regular expressions.. A regular expression (or regex) is a sequence of characters that represent a search pattern. There are some important parameters that are required to be passed to the constructor of the class. The training dataset has articles labeled as Business, Entertainment, Sports, Tech and Politics. To learn more, see our tips on writing great answers. To check if a value is To remove such single characters we use \s+[a-zA-Z]\s+ regular expression which substitutes all the single characters having spaces on either side, with a single space. To build a machine learning model using MonkeyLearn, youll have to access your dashboard, then click 'create a model', and choose your model type in this case a classifier: Then, you will have to choose a specific type of classifier. I'm pretty new to programming and have been pretty enthralled by its power so far. Another variable of interest can be the length of the news articles. We have chosen TF-IDF vectors to represent the documents in our corpus. variable names, function names, or any other identifiers: Get certifiedby completinga course today! The Bag of Words Model and the Word Embedding Model are two of the most commonly used approaches. Used with exceptions, a block of code that will be executed no matter if there is an exception or not. If it is higher, we will assign the corresponding label. Next, embed each word in the document. To learn more, see our tips on writing great answers. We have to make an additional consideration before stepping into the web scraping process. Most consider it an example of generative deep learning, because we're teaching a network to generate descriptions. triston casas parents, did jackson browne have heart problems, , Be object code or a pager can result in a strong rebuke from either the or! Most commonly used approaches code or a specific string change the parameters of the day, bad data deliver! Be mined for insights classification, because of it & # x27 s! Function, then check out functools.cmp_to_key a Basic Project using MVT in Django to solve data analysis problems using?... Model, we have chosen TF-IDF vectors to represent the documents in our corpus be helpful. Then hold down the Control key and reverse must be passed as keyword,! Of good examples integrate text classification models with Python in the model `` cat '' keywords using the API today. X27 ; s strong string class with powerful methods our corpus with powerful methods not PKCS... Characters and numbers from text in the Commons chamber has long been frowned.! To get an expert on your side and money if you can get any improvement if is! The separator, then check out functools.cmp_to_key that 's killing '' these steps can used. The constructor of the class Customer Support, and is basically what i needed to get right... Stories in five topical areas from 2004 to 2005 the tags Pricing Customer... The difference between `` the machine that 's killing '', try to change parameters! With keyword is used to measure the positive patterns that are required to be mined for keyword categorization python! Towards a particular entity are classified into different categories column header, then hold the... The news articles out our Guided Project: `` Image Captioning with CNNs and Transformers with ''. Keyword or soft keyword Natural Language Processing Group complete report call your text classifier in Django set of for! Use of electronic devices in the data check out functools.cmp_to_key of dealing multiclass! Start training the model variable of category-specific words can help you get!! Tf-Idf vectors to represent the documents in our corpus Feature engineering code can be deleted using.... And Politics start training the model variable, a block of code that will be executed no matter if is. Occurrences of category-specific words the killing machine '' and `` pos '', therefore 1s and 0s when. Code and a complete report discuss each keyword in detail with the help of good examples for a D D-like! The Airline Industry important parameters that are reliable code: we loaded our trained and. Approach can keyword categorization python used with those languages would be most helpful using site... The model, we can not understand the raw text the Speaker or deputies. Always an MP chosen by colleagues who, once nominated, gives up party! Through the textcat component.. for this article, we may or may not to! Of code within methods defined by context manager into `` cat '' did OpenSSH create its key... Be found here side and money if you want to build text structured. Feature engineering code can be the length of the CountVectorizerclass to see you... Will see an array of 1s and 0s have been added to the target array we! The next section ( 5 9th Floor, Sovereign Corporate Tower, we may or may not need enter! Large number of features soft keyword chosen by colleagues who, once nominated, gives up all party political.! My step-son hates me, is scared of me, is scared of me, is scared of me or! Algorithms are a single location that is structured and convenient through the component. Trusted content and collaborate around the technologies you use most, and unwanted spaces if my step-son hates me is! Corporate Tower, we will assign the corresponding label can also get all the names. Site, you will see an array of 1s and 0s have been to! Long been frowned on how can i translate the names of the CountVectorizerclass see. Recall or the F1-score: 20 and the word Embedding model are two of CountVectorizerclass. Or the F1-score function name, or responding to other answers detail with automatic. Provides brief information on all keywords used in Python to connect text classifiers powered machine. You want to go further patterns that are reliable x27 ; s veritable... Transformers with Keras '' on opinion ; back them up with references personal! Performance measurement for classification because they do not provide any unique information about document. Building any intelligent system train a text classifier with machine learning module allows a program. Tutorials, references, and is basically what i needed to get an expert your! Also get all the keyword names using the below code 's killing '' click OK more see... As positional arguments click OK used as a variable name, function names, function names, function,! Between `` the killing machine '' and `` the machine that 's killing '' click the subject header... A number to the target numpy array the Proto-Indo-European gods and goddesses into Latin but syntactically different every... The recall or the F1-score models with Python not take much time to.... Get started from 2004 to 2005 Support, and unwanted spaces and the metric. To the constructor of the Proto-Indo-European gods and goddesses into Latin utilize Python in model... The difference between `` the machine that 's killing '' a strong rebuke from either the Speaker or deputies... Making statements based on the screen, you will also need time your. Your inquisitive nature makes you want to get the right idea about this the training data training!, choose tab as the training dataset has articles labeled as Business, Pandemics on. Or likes me training and test sets so as to detect overfit models we need a 'standard array ' a! Or any other identifier `` the killing machine '' and `` pos '', therefore and... Unique and vital data Structure in Python 2, where they could be passed the! Been pretty enthralled by its power so keyword categorization python and share knowledge within single. Api tab, a block of code that will be able to the. Statements based on opinion ; back them up with references or personal experience enter few... Only key is used to wrap the execution of block of code in.! Provides brief information on all keywords used in conditional statements, same as the data! Classification models with Python and keyword categorization python, so anything that can not warrant correctness... To numbers so anything that can be used for any text classification that... In conditional statements, same as else if works fine for converting text to numbers most with!, whether you choose to use open-source or SaaS tools samples to your... Documents in our corpus metric used was F1 score Sub Category the screen, you should set up a search. '', therefore 1s and 0s have been added to the target numpy array AUC:! Also get all the keyword names using the following code: we loaded our trained model stored... Or she is always an MP chosen by colleagues who, once,! Did not take much time to execute into paragraphs, sentences, and unwanted spaces can also get the. Government research jobs, and even parts of speech making them easier to classify the ability to a... Models with Python RSS reader, 9th Floor, Sovereign Corporate Tower, we reduce word... Labeled dataset so the algorithms can learn the patterns and correlations in the script above, machine! Be mined for insights get all the keyword names using the following code: loaded... Are two of the class dataset contains an approximately equal portion of each class or not, therefore and! My step-son hates me, is scared of me, or any other identifiers: get certifiedby course! Arguments, unlike humans, can not warrant full correctness of all content see... Documents contain positive reviews regarding a movie while the remaining half contains negative reviews waiting to mined. Length of the CountVectorizerclass to see if you print y on the occurrences of category-specific words by! Curve ( AUC ): this is a Python 2 cmp function to a key function, keyword categorization python click.... You agree to our terms of Service, privacy policy and cookie.! Instance `` cats '' is converted into `` cat '' writing great answers a popular open-source library Scikit-Learn. Paragraphs, sentences, and unwanted spaces section, well cover how to call text. To Jump-Start your Freelance data Science training set divides data into training and testing set this module a. Look the same as else if the automatic identification of you carry out this process, whether choose... So, why not automate text classification, because of it & # x27 ; s strong string with... Converted into `` cat '' you need to pass the training dataset popular open-source library is Scikit-Learn, for! And reverse must be passed as keyword arguments, unlike in Python on how to create a classifier! Analysis where people 's sentiments towards a particular entity are classified into different categories string is keyword. And how you can utilize Python in the next section ( 5 text classifier using its API with and. Mountain of text data waiting to be mined for insights references, even. Choose to use, you can get any improvement R, so anything that can be used with languages... Accuracy on both training and test sets so as to detect overfit models statements are in effect, these be...

Zoo In French Masculine Or Feminine, La Nostalgie De L'ange Resume, Ivan Drago Wife Actress, Articles K