Skip to main content

Sentence generation using Markov Chains

Project description

markovipy Documentation Status Updates


She tries striking conversations with you with her cohesive sentences after you have given her fill of text to her. And no she won’t complain about how big your corpus is. Also, don’t ask her if she can pass the turing test. She might not talk to you again.

I wrote a blog post explaining the motivation and what is there behind the scenes if you are interested


To install markovipy, run this command in your terminal:

$ pip install markovipy

This is the preferred method to install markovipy, as it will always install the most recent stable release.

If you don’t have pip installed, this Python installation guide can guide you through the process.


To use markovipy in a project:

>>> from markovipy import MarkoviPy
>>> # create MarkoviPy object
>>> obj = MarkoviPy("/Users/tasrahma/development/projects/markovipy/corpus/ts_eliot/Gerontion_utf8.txt", 3)
>>> # arguments passed, is the initial corpus file and the markov chain length(defaults to 2 if nothing passed)
>>> obj.generate_sentence()
'Cammel, whirled Beyond the circuit of the shuddering Bear In fractured atoms.'
>>> obj.generate_sentence()
'After such knowledge, what forgiveness? Think now History has many cunning passages, contrived corridors And issues, deceives with whispering ambitions, Guides us by vanities.'
>>> obj.generate_sentence()
'Gull against the wind, in the windy straits Of Belle Isle, or running on the Horn, White feathers in the snow, the Gulf claims, And an old man, a dull head among windy spaces.'
>>> obj.generate_sentence()
'Silvero With caressing hands, at Limoges Who walked all night in the field overhead; Rocks, moss, stonecrop, iron, merds.'
>>> obj.generate_sentence()
"Gives too soon Into weak hands, what's thought can be dispensed with Till the refusal propagates a fear."


  • More tests to be added. As of now, some minimal tests have been written. Contributions more than welcome.

  • Create a web-interface with some fancy buttons/UI which would give you random quotes.



  • exposed the Markovipy class in the markovipy module. API changed from

    from markovipy.markovipy import MarkoviPy


from markovipy import MarkoviPy

0.2.0 (2017-04-29)

  • self.middle_value mapping becomes a defaultdict

  • list_to_tuple() was removed to use just the tuple()

  • moved self.words_list = get_word_list(self.filename) to __init__()

0.1.1 (2017-04-14)

  • fixes UnicodeDecodeError while reading files instead of using the normal open()

0.1.0 (2017-04-11)

  • First release on PyPI.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

markovipy-0.3.0.tar.gz (20.9 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page