{ "cells": [ { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "df = pd.read_csv('DemoData.csv')" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import yaml\n", "import os\n", "import ast\n", "\n", "# Create a folder to store YAML files if it doesn't exist\n", "if not os.path.exists('configs'):\n", " os.makedirs('configs')\n", "\n", "# Iterate over each row in the DataFrame\n", "for index, row in df.iterrows():\n", " # Extract Metaname and use it as the filename for YAML\n", " filename = str(row['Metaname']) + '.yaml'\n", " # Convert 'Screenshots' column to a Python list\n", " screenshots_list = None\n", " try:\n", "\n", " screenshots_list = ast.literal_eval(row['Screenshots'])\n", " except:\n", " screenshots_list = []\n", " # Remove the 'Metaname' and 'Screenshots' columns from the data to be converted to YAML\n", " row_data = row.drop(['Metaname', 'Screenshots'])\n", " # Convert the remaining data to a dictionary\n", " data_dict = row_data.to_dict()\n", " # Add the 'Screenshots' list to the dictionary\n", " data_dict['Screenshots'] = screenshots_list\n", " # Write the data as YAML to a new file\n", " with open(os.path.join('configs', filename), 'w') as yamlfile:\n", " yaml.dump(data_dict, yamlfile, default_flow_style=False)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | Group | \n", "Modality | \n", "Level | \n", "Metaname | \n", "Suggested Evaluation | \n", "What it is evaluating | \n", "Considerations | \n", "Link | \n", "URL | \n", "Screenshots | \n", "Applicable Models | \n", "Datasets | \n", "Hashtags | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "BiasEvals | \n", "Text | \n", "Model | \n", "weat | \n", "Word Embedding Association Test (WEAT) | \n", "Associations and word embeddings based on Impl... | \n", "Although based in human associations, general ... | \n", "Semantics derived automatically from language ... | \n", "https://researchportal.bath.ac.uk/en/publicati... | \n", "['Images/WEAT1.png', 'Images/WEAT2.png'] | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
1 | \n", "BiasEvals | \n", "Text | \n", "Model | \n", "wefat | \n", "Word Embedding Factual As\\nsociation Test (WEFAT) | \n", "Associations and word embeddings based on Impl... | \n", "Although based in human associations, general ... | \n", "Semantics derived automatically from language ... | \n", "https://researchportal.bath.ac.uk/en/publicati... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
2 | \n", "BiasEvals | \n", "Text | \n", "Dataset | \n", "stereoset | \n", "StereoSet | \n", "Protected class stereotypes | \n", "Automating stereotype detection makes distingu... | \n", "StereoSet: Measuring stereotypical bias in pre... | \n", "https://arxiv.org/abs/2004.09456 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
3 | \n", "BiasEvals | \n", "Text | \n", "Dataset | \n", "crwospairs | \n", "Crow-S Pairs | \n", "Protected class stereotypes | \n", "Automating stereotype detection makes distingu... | \n", "CrowS-Pairs: A Challenge Dataset for Measuring... | \n", "https://arxiv.org/abs/2010.00133 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
4 | \n", "BiasEvals | \n", "Text | \n", "Output | \n", "honest | \n", "HONEST: Measuring Hurtful Sentence Completion ... | \n", "Protected class stereotypes and hurtful language | \n", "Automating stereotype detection makes distingu... | \n", "HONEST: Measuring Hurtful Sentence Completion ... | \n", "https://aclanthology.org/2021.naacl-main.191.pdf | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
5 | \n", "BiasEvals | \n", "Image | \n", "Model | \n", "ieat | \n", "Image Embedding Association Test (iEAT) | \n", "Embedding associations | \n", "Although based in human associations, general ... | \n", "Image Representations Learned With Unsupervise... | \n", "https://dl.acm.org/doi/abs/10.1145/3442188.344... | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
6 | \n", "BiasEvals | \n", "Image | \n", "Dataset | \n", "imagedataleak | \n", "Dataset leakage and model leakage | \n", "Gender and label bias | \n", "NaN | \n", "Balanced Datasets Are Not Enough: Estimating a... | \n", "https://arxiv.org/abs/1811.08489 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
7 | \n", "BiasEvals | \n", "Image | \n", "Output | \n", "stablebias | \n", "Characterizing the variation in generated images | \n", "NaN | \n", "NaN | \n", "Stable bias: Analyzing societal representation... | \n", "https://arxiv.org/abs/2303.11408 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
8 | \n", "BiasEvals | \n", "Image | \n", "Output | \n", "homoglyphbias | \n", "Effect of different scripts on text-to-image g... | \n", "It evaluates generated images for cultural ste... | \n", "NaN | \n", "Exploiting Cultural Biases via Homoglyphs in T... | \n", "https://arxiv.org/pdf/2209.08891.pdf | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
9 | \n", "BiasEvals | \n", "Audio | \n", "Taxonomy (?) | \n", "notmyvoice | \n", "Not My Voice! A Taxonomy of Ethical and Safety... | \n", "Lists harms of audio/speech generators | \n", "Not necessarily evaluation but a good source o... | \n", "Not My Voice! A Taxonomy of Ethical and Safety... | \n", "https://arxiv.org/pdf/2402.01708.pdf | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
10 | \n", "BiasEvals | \n", "Video | \n", "Output | \n", "videodiversemisinfo | \n", "Diverse Misinformation: Impacts of Human Biase... | \n", "Human led evaluations of deepfakes to understa... | \n", "Repr. harm, incite violence | \n", "Diverse Misinformation: Impacts of Human Biase... | \n", "https://arxiv.org/abs/2210.10026 | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
11 | \n", "Privacy | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "