- Python - Text Processing
- Python - Text Processing Introduction
- Python - Text Processing Environment
- Python - String Immutability
- Python - Sorting Lines
- Python - Reformatting Paragraphs
- Python - Counting Token in Paragraphs
- Python - Binary ASCII Conversion
- Python - Strings as Files
- Python - Backward File Reading
- Python - Filter Duplicate Words
- Python - Extract Emails from Text
- Python - Extract URL from Text
- Python - Pretty Print
- Python - Text Processing State Machine
- Python - Capitalize and Translate
- Python - Tokenization
- Python - Remove Stopwords
- Python - Synonyms and Antonyms
- Python - Text Translation
- Python - Word Replacement
- Python - Spelling Check
- Python - WordNet Interface
- Python - Corpora Access
- Python - Tagging Words
- Python - Chunks and Chinks
- Python - Chunk Classification
- Python - Text Classification
- Python - Bigrams
- Python - Process PDF
- Python - Process Word Document
- Python - Reading RSS feed
- Python - Sentiment Analysis
- Python - Search and Match
- Python - Text Munging
- Python - Text wrapping
- Python - Frequency Distribution
- Python - Text Summarization
- Python - Stemming Algorithms
- Python - Constrained Search
- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who
Python - Text Processing Introduction
Text processing has a direct application to Natural Language Processing, also known as NLP. NLP is aimed at processing the languages spoken or written by humans when they communicate with one another. This is different from the communication between a computer and a human where the communication is wither a computer program written by human or some gesture by human like clicking the mouse at some position. NLP tries to understand the natural language spoken by humans and classify it, analyses it as well if required respond to it. Python has a rich set of libraries which cater to the needs of NLP. The Natural Language Tool Kit (NLTK) is a suite of such libraries which provides the functionalities required for NLP.
Below are some applications which use NLP and indirectly python's NLTK.
Many times, we need to get the summary of a news article, a movie plot or a big story. They are all written in human language and without NLP we have to rely on another human's interpretation and presentation of such summary to us. But with help of NLP we can write programs to use NLTK and summarize the long text with various parameters, like what is the percentage of text we want in the final output, choosing the positive and negative words for summarization etc. The online news feeds rely on such summarization techniques to present news insights.
Voice Based Tools
The voice-based tools like apples Siri or Amazon Alexa rely on NLP to understand the interaction mad with humans. They have a large training data set of words, sentences and grammar to interpret the question or command coming from a human and process it. Though it is about voice, indirectly it also gets translated to text and the resulting text form the voice is taken through the NLP system to produce result.
Web scrapping is a common example of extracting data form the web pages using python code. Here it may not be strictly NLP based but it does involve text processing. For example, if we need to extract only the headers present in a html page, then we look for the h1 tag int he page structure and find a way to extract the text between only those tags. This need text processing program from python.
The spam in emails can be identified and eliminated by analysing the text in the subject line as well as in the content of the message. As the spam emails are usually sent in bulk to many recipients, even if their subjects and contents have little variation, that can be matched and tagged to mark them as spam Again it needs the use of the NLTK libraries.
Computerized language translation relies heavily on NLP. As more and more languages are used in the online platform, it becomes a necessity to automate the translation from one human language to another. This will involve programming to handle the vocabulary, grammar and context tagging of the languages involved in translation. Again, NLTK is used to handle such requirements.
To find out the overall reaction to the performance of a movie, we may have to read thousands of feedback posts from the audience. But that too can be automated by using the classification of positive an negative feedback through words and sentence analysis. And then measuring the frequency of positive and negative reviews to find the overall sentiment of the audience. This obviously needs the analysis of the human language written by the audience and NLTK is used heavily here for processing the text.