Mattias Östmar mattiasostmar
mattiasostmar
/ Iterate over pages in Wikimedia Commons category
Last active
January 20, 2017 10:05
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pywikibot | |
| from pywikibot import pagegenerators as pg | |
| site = pywikibot.Site(fam="commons") | |
| cat = pywikibot.Category(site, 'Category:Media_from_the_National_Museums_of_World_Culture') | |
| gen = pg.CategorizedPageGenerator(cat) | |
| for page in gen: | |
| filePage = pywikibot.FilePage(page) | |
| try: |
mattiasostmar
/ Classify_Jung_cogntitive_functions_from_blog_texts.ipynb
Last active
March 5, 2018 13:47
Using uClassify.com to do experiment with classification of Jungs cognitive functions based on blog texts. Get the dataset at https://www.kaggle.com/mattiasostmar/blog-texts-and-dominant-jungian-cognitive-function.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
mattiasostmar
/ train_and_evaluate_perceiving_and_judging_classifiers_n2100_trained_n900_evaluated.ipynb
Last active
March 18, 2018 20:56
Script used to produce results in blog post about experiment classifying Jungian cognitive functions with one classifier for percieving functions sensing vs intuition and one classifier for judging functions thinking vs feeling at www.mattiasostmar.se. The raw data (pickled Pandas DataFame) is available on https://osf.io/gyrc7/
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
mattiasostmar
/ Verify_Jungian_cognitive_functions_classification_results_with_uClassify_n2100_trained.ipynb
Last active
March 22, 2018 11:03
New cleaner code to verify script of [previous classification results](https://gist.github.com/mattiasostmar/05a3e6b4411acd0bb0f003b0ef49f4cc) of Jungian cognitive functions from blog texts.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
mattiasostmar
/ Experiment with word2vec similarities to high and low psychological state word examples.ipynb
Created
March 28, 2018 15:07
Original notebook is located at https://github.com/mattiasostmar/metamodern_experiments/blob/master/notebooks/similar_words_to_hanzi_freinachts_high_low_state_words.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
mattiasostmar
/ discoursebias_under_development.ipynb
Created
January 4, 2019 17:03
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
mattiasostmar
/ fasttext_jungian_cognitive_functions
Last active
March 14, 2019 21:40
Using Facebooks deep-learning framwork fasttext to try to predict the Jungian cognitive functions based on blog authors writing style.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Author: **Mattias Östmar**\n", | |
| "\n", | |
| "Date: **2019-03-14**\n", | |
| "\n", |
mattiasostmar
/ fasttext_jung_sensing_intuition_functions_in_blogs
Created
March 15, 2019 15:02
Using fasttext library to predict Jungian cognitive functions sensing (s) vs intuition (n) from annotated blog texts
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Author: **Mattias Östmar**\n", | |
| "\n", | |
| "Date: **2019-03-15**\n", | |
| "\n", |
mattiasostmar
/ fasttext_jung_thinking_feeling_functions_in_blogs
Created
March 15, 2019 15:12
Using fasttext library to predict Jungian cognitive functions thinking vs feeling from annotated blog texts
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Author: **Mattias Östmar**\n", | |
| "\n", | |
| "Date: **2019-03-15**\n", | |
| "\n", |
mattiasostmar
/ gist:42b0d846a2e3db6d8afa92e6f90d445b
Created
August 5, 2019 20:59
Python code to compute accuracy and Cohens Kappa
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| [in:] | |
| tot_accuracy = sum(test['func'] == test['predicted']) / len(test) | |
| print("Accuracy all 8 classes together: {}".format(tot_accuracy)) | |
| # Total Cohens Kappa | |
| tot_kappa = (fe_accuracy - 0.125) / 0.125 | |
| print("Cohens Kappa all 8 classes together: {}".format(tot_kappa)) | |
| [out:] | |
| Accuracy all 8 classes together: 0.8285714285714286 |