{ "cells": [ { "cell_type": "markdown", "id": "181a61c2-c502-4118-b9cb-ec107f8b5054", "metadata": { "editable": true, "slideshow": { "slide_type": "" }, "tags": [] }, "source": [ "# Results\n" ] }, { "cell_type": "code", "execution_count": null, "id": "dfa49af6-3716-42bc-9897-339243fdaa7a", "metadata": { "editable": true, "slideshow": { "slide_type": "" }, "tags": [ "hide-input" ] }, "outputs": [], "source": [ "# REQUIRED CODE CELL\n", "import os \n", "import re\n", "from PIL import Image\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from scipy.ndimage import gaussian_gradient_magnitude\n", "from wordcloud import WordCloud, ImageColorGenerator, STOPWORDS\n", "\n", "np.seterr(divide = 'ignore') \n", "DATA_ROOT = \"../data/repro-mri-scoping/repro_mri_scoping\"\n", "\n", "# Purify and merge text\n", "def read_file(file_path):\n", " with open(file_path, 'r', encoding='utf-8') as file:\n", " content = file.read()\n", " return content\n", "\n", "def write_file(file_path, content):\n", " with open(file_path, 'w') as file:\n", " file.write(content)\n", "\n", "def remove_enumeration_lines(text):\n", " # Define the pattern for lines starting with enumeration and ending with a question mark\n", " pattern = r'^\\s*\\d+\\.\\s.*\\?$'\n", " \n", " # Use re.MULTILINE to apply the pattern to each line in the input text\n", " result = re.sub(pattern, '', text, flags=re.MULTILINE)\n", " \n", " return result\n", "\n", "def remove_by_pattern(input_text, patterns_to_remove):\n", " for pattern in patterns_to_remove:\n", " input_text = re.sub(pattern, '', input_text)\n", "\n", " return input_text.strip()\n", "\n", "def get_output_dir(file_name):\n", " op_dir = \"../output\"\n", " if not os.path.exists(op_dir):\n", " os.mkdir(op_dir)\n", " return os.path.join(op_dir,file_name)" ] }, { "cell_type": "code", "execution_count": null, "id": "26559457-fb99-40fa-93d1-586c28423eb4", "metadata": { "editable": true, "slideshow": { "slide_type": "" }, "tags": [ "hide-input" ] }, "outputs": [], "source": [ "directory_path = os.path.join(DATA_ROOT,\"repro_insights_parsed_nov23\")\n", "input_files = [os.path.join(directory_path, f) for f in os.listdir(directory_path) if f.endswith('.txt')]\n", "\n", "patterns_to_remove = [\n", " re.compile(r'Questions about the specific reproducible research habit'),\n", " re.compile(r'Title:'),\n", " re.compile(r'TLDR:'),\n", " re.compile(r'Abstract:'),\n", " re.compile(r'Reproducibility Insights:'),\n", " re.compile(r'General questions'),\n", " re.compile(r'Questions about the specific reproducible research habit'),\n", " re.compile(r'This MRM Reproducible Research Insights interview'),\n", " re.compile(r'This work was singled out because it demonstrated exemplary reproducible research practices')\n", "]\n", "\n", "all_text = ''\n", "for cur_file in input_files:\n", " cur_content = read_file(cur_file)\n", " cur_content = remove_enumeration_lines(cur_content)\n", " cur_content = remove_by_pattern(cur_content, patterns_to_remove)\n", " all_text = all_text + \"\\n\" + cur_content" ] }, { "cell_type": "code", "execution_count": null, "id": "991985c7-a45d-4f4a-a70d-c0380cf6a08f", "metadata": { "editable": true, "slideshow": { "slide_type": "" }, "tags": [ "hide-input" ] }, "outputs": [], "source": [ "#| caption: A word cloud generated from the 31 reproducible research insights published by Magnetic Resonance in Medicine Highlights.\n", "#| label: fig4-cell\n", "text = all_text\n", "\n", "stopwords = set(STOPWORDS)\n", "stopwords.add(\"will\")\n", "stopwords.add(\"you\")\n", "stopwords.add(\"others\")\n", "stopwords.add(\"people\")\n", "stopwords.add(\"using\")\n", "stopwords.add(\"By\")\n", "stopwords.add(\"Mathieu Boudreau\")\n", "stopwords.add(\"Agah Karakuzu\")\n", "stopwords.add(\"Pinar S. Ozbay\")\n", "\n", "brain_color = np.array(Image.open(os.path.join(DATA_ROOT, \"brain_image.png\")))\n", "\n", "brain_color = brain_color[::3, ::3]\n", "\n", "brain_mask = brain_color.copy()\n", "brain_mask[brain_mask.sum(axis=2) == 0] = 255\n", "\n", "# some finesse: we enforce boundaries between colors so they get less washed out.\n", "# For that we do some edge detection in the image\n", "edges = np.mean([gaussian_gradient_magnitude(brain_color[:, :, i] / 255., 2) for i in range(3)], axis=0)\n", "brain_mask[edges > .08] = 255\n", "\n", "# create wordcloud. A bit sluggish, you can subsample more strongly for quicker rendering\n", "# relative_scaling=0 means the frequencies in the data are reflected less\n", "# acurately but it makes a better picture\n", "wc = WordCloud(max_words=2000, mask=brain_mask, max_font_size=50, min_font_size=5, random_state=42, relative_scaling=0.2, stopwords=stopwords)\n", "\n", "# generate word cloud\n", "wc.generate(text)\n", "plt.imshow(wc)\n", "\n", "# create coloring from image\n", "image_colors = ImageColorGenerator(brain_color)\n", "wc.recolor(color_func=image_colors)\n", "plt.figure(figsize=(10, 10))\n", "plt.imshow(wc, interpolation=\"bilinear\")\n", "wc.to_file(get_output_dir(\"brain_wordcloud.png\"))" ] }, { "cell_type": "markdown", "id": "fde22556-7114-4a98-8e76-3d385044c24c", "metadata": { "editable": true, "slideshow": { "slide_type": "" }, "tags": [] }, "source": [ "```{admonition} Reference documentation\n", "Please see [this example](https://github.com/amueller/word_cloud/blob/main/examples/parrot.py) as the reference implementation.\n", "```" ] }, { "cell_type": "markdown", "id": "a39b787e-dec2-4473-95ff-56bd686652fd", "metadata": {}, "source": [ "```{bibliography}\n", "```" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.13" } }, "nbformat": 4, "nbformat_minor": 5 }