Skip to content

Instantly share code, notes, and snippets.

@JonathanReeve

JonathanReeve/macro-etym.ipynb

Last active December 5, 2020 03:17
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save JonathanReeve/25708b17dd172f9d5d6ba6f9d74a4ab7 to your computer and use it in GitHub Desktop.
Save JonathanReeve/25708b17dd172f9d5d6ba6f9d74a4ab7 to your computer and use it in GitHub Desktop.
Download ZIP
macro-etym
Display the source blob
Display the rendered blob
Raw
macro-etym.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "macro-etym",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyPHrTxhX5VPdbUE83otXa7E",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/JonathanReeve/25708b17dd172f9d5d6ba6f9d74a4ab7/macro-etym.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gJ9MVAdxcM55"
},
"source": [
"# Macro-Etymological Textual Analysis\n",
"\n",
"First, download the Python package from GitHub:"
]
},
{
"cell_type": "code",
"metadata": {
"id": "3sGvhRMaa7Fu",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "17af2588-45d2-4fe6-9443-e0836df63bb4"
},
"source": [
"!pip install git+https://github.com/JonathanReeve/macro-etym"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting git+https://github.com/JonathanReeve/macro-etym\n",
" Cloning https://github.com/JonathanReeve/macro-etym to /tmp/pip-req-build-ckxwjp8x\n",
" Running command git clone -q https://github.com/JonathanReeve/macro-etym /tmp/pip-req-build-ckxwjp8x\n",
"Requirement already satisfied (use --upgrade to upgrade): macroetym==0.1.2 from git+https://github.com/JonathanReeve/macro-etym in /usr/local/lib/python3.6/dist-packages\n",
"Requirement already satisfied: Click in /usr/local/lib/python3.6/dist-packages (from macroetym==0.1.2) (7.1.2)\n",
"Requirement already satisfied: nltk in /usr/local/lib/python3.6/dist-packages (from macroetym==0.1.2) (3.2.5)\n",
"Requirement already satisfied: pycountry in /usr/local/lib/python3.6/dist-packages (from macroetym==0.1.2) (20.7.3)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.6/dist-packages (from macroetym==0.1.2) (1.1.4)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.6/dist-packages (from macroetym==0.1.2) (3.2.2)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from nltk->macroetym==0.1.2) (1.15.0)\n",
"Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas->macroetym==0.1.2) (2018.9)\n",
"Requirement already satisfied: numpy>=1.15.4 in /usr/local/lib/python3.6/dist-packages (from pandas->macroetym==0.1.2) (1.18.5)\n",
"Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.6/dist-packages (from pandas->macroetym==0.1.2) (2.8.1)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/dist-packages (from matplotlib->macroetym==0.1.2) (0.10.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->macroetym==0.1.2) (1.3.1)\n",
"Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->macroetym==0.1.2) (2.4.7)\n",
"Building wheels for collected packages: macroetym\n",
" Building wheel for macroetym (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for macroetym: filename=macroetym-0.1.2-cp36-none-any.whl size=11334095 sha256=c9db7c876d0a455cd10ff21fa5ea42c34468b953616d93a8a764c0794c7a74ba\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-ns5t03av/wheels/8e/23/b0/7a72b270081d27d01fe9abd0be7b77bb399d2020d6ef88d129\n",
"Successfully built macroetym\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "UiWGCGpScW0B"
},
"source": [
"Import all the required libraries: "
]
},
{
"cell_type": "code",
"metadata": {
"id": "IwtyXcqsOXLc"
},
"source": [
"import macroetym\n",
"import requests\n",
"import json\n",
"import nltk\n",
"from macroetym.main import Text"
],
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "kyJQ0pR2cabR"
},
"source": [
"Download some NLTK data: "
]
},
{
"cell_type": "code",
"metadata": {
"id": "tSmQVJqqQ_MU",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "e1363bd4-94e0-4d73-fe7b-fef3417242ff"
},
"source": [
"nltk.download('book')"
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"text": [
"[nltk_data] Downloading collection 'book'\n",
"[nltk_data] | \n",
"[nltk_data] | Downloading package abc to /root/nltk_data...\n",
"[nltk_data] | Package abc is already up-to-date!\n",
"[nltk_data] | Downloading package brown to /root/nltk_data...\n",
"[nltk_data] | Package brown is already up-to-date!\n",
"[nltk_data] | Downloading package chat80 to /root/nltk_data...\n",
"[nltk_data] | Package chat80 is already up-to-date!\n",
"[nltk_data] | Downloading package cmudict to /root/nltk_data...\n",
"[nltk_data] | Package cmudict is already up-to-date!\n",
"[nltk_data] | Downloading package conll2000 to /root/nltk_data...\n",
"[nltk_data] | Package conll2000 is already up-to-date!\n",
"[nltk_data] | Downloading package conll2002 to /root/nltk_data...\n",
"[nltk_data] | Package conll2002 is already up-to-date!\n",
"[nltk_data] | Downloading package dependency_treebank to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package dependency_treebank is already up-to-date!\n",
"[nltk_data] | Downloading package genesis to /root/nltk_data...\n",
"[nltk_data] | Package genesis is already up-to-date!\n",
"[nltk_data] | Downloading package gutenberg to /root/nltk_data...\n",
"[nltk_data] | Package gutenberg is already up-to-date!\n",
"[nltk_data] | Downloading package ieer to /root/nltk_data...\n",
"[nltk_data] | Package ieer is already up-to-date!\n",
"[nltk_data] | Downloading package inaugural to /root/nltk_data...\n",
"[nltk_data] | Package inaugural is already up-to-date!\n",
"[nltk_data] | Downloading package movie_reviews to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package movie_reviews is already up-to-date!\n",
"[nltk_data] | Downloading package nps_chat to /root/nltk_data...\n",
"[nltk_data] | Package nps_chat is already up-to-date!\n",
"[nltk_data] | Downloading package names to /root/nltk_data...\n",
"[nltk_data] | Package names is already up-to-date!\n",
"[nltk_data] | Downloading package ppattach to /root/nltk_data...\n",
"[nltk_data] | Package ppattach is already up-to-date!\n",
"[nltk_data] | Downloading package reuters to /root/nltk_data...\n",
"[nltk_data] | Package reuters is already up-to-date!\n",
"[nltk_data] | Downloading package senseval to /root/nltk_data...\n",
"[nltk_data] | Package senseval is already up-to-date!\n",
"[nltk_data] | Downloading package state_union to /root/nltk_data...\n",
"[nltk_data] | Package state_union is already up-to-date!\n",
"[nltk_data] | Downloading package stopwords to /root/nltk_data...\n",
"[nltk_data] | Package stopwords is already up-to-date!\n",
"[nltk_data] | Downloading package swadesh to /root/nltk_data...\n",
"[nltk_data] | Package swadesh is already up-to-date!\n",
"[nltk_data] | Downloading package timit to /root/nltk_data...\n",
"[nltk_data] | Package timit is already up-to-date!\n",
"[nltk_data] | Downloading package treebank to /root/nltk_data...\n",
"[nltk_data] | Package treebank is already up-to-date!\n",
"[nltk_data] | Downloading package toolbox to /root/nltk_data...\n",
"[nltk_data] | Package toolbox is already up-to-date!\n",
"[nltk_data] | Downloading package udhr to /root/nltk_data...\n",
"[nltk_data] | Package udhr is already up-to-date!\n",
"[nltk_data] | Downloading package udhr2 to /root/nltk_data...\n",
"[nltk_data] | Package udhr2 is already up-to-date!\n",
"[nltk_data] | Downloading package unicode_samples to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package unicode_samples is already up-to-date!\n",
"[nltk_data] | Downloading package webtext to /root/nltk_data...\n",
"[nltk_data] | Package webtext is already up-to-date!\n",
"[nltk_data] | Downloading package wordnet to /root/nltk_data...\n",
"[nltk_data] | Package wordnet is already up-to-date!\n",
"[nltk_data] | Downloading package wordnet_ic to /root/nltk_data...\n",
"[nltk_data] | Package wordnet_ic is already up-to-date!\n",
"[nltk_data] | Downloading package words to /root/nltk_data...\n",
"[nltk_data] | Package words is already up-to-date!\n",
"[nltk_data] | Downloading package maxent_treebank_pos_tagger to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package maxent_treebank_pos_tagger is already up-\n",
"[nltk_data] | to-date!\n",
"[nltk_data] | Downloading package maxent_ne_chunker to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package maxent_ne_chunker is already up-to-date!\n",
"[nltk_data] | Downloading package universal_tagset to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package universal_tagset is already up-to-date!\n",
"[nltk_data] | Downloading package punkt to /root/nltk_data...\n",
"[nltk_data] | Package punkt is already up-to-date!\n",
"[nltk_data] | Downloading package book_grammars to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package book_grammars is already up-to-date!\n",
"[nltk_data] | Downloading package city_database to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package city_database is already up-to-date!\n",
"[nltk_data] | Downloading package tagsets to /root/nltk_data...\n",
"[nltk_data] | Package tagsets is already up-to-date!\n",
"[nltk_data] | Downloading package panlex_swadesh to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package panlex_swadesh is already up-to-date!\n",
"[nltk_data] | Downloading package averaged_perceptron_tagger to\n",
"[nltk_data] | /root/nltk_data...\n",
"[nltk_data] | Package averaged_perceptron_tagger is already up-\n",
"[nltk_data] | to-date!\n",
"[nltk_data] | \n",
"[nltk_data] Done downloading collection book\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"True"
]
},
"metadata": {
"tags": []
},
"execution_count": 4
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-UXEwaicciSX"
},
"source": [
"Grab a test text: "
]
},
{
"cell_type": "code",
"metadata": {
"id": "iin_XbwIQUyR"
},
"source": [
"response = requests.get('http://corpus-db.org/api/id/10.0/fulltext').text\n",
"bible = json.loads(response)[0]['text']"
],
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "ZLDcQKgIQzIh",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 52
},
"outputId": "b24a5fba-5acb-40d4-b79d-be03b4212a26"
},
"source": [
"bible[:300]"
],
"execution_count": 6,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
},
"text/plain": [
"'\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nThe Old Testament of the King James Version of the Bible\\n\\n\\n\\n\\nThe First Book of Moses: Called Genesis\\n\\n\\n1:1 In the beginning God created the heaven and the earth.\\n\\n1:2 And the earth was without form, and void; and darkness was upon\\nthe face of the deep. And the Spirit of God moved upon'"
]
},
"metadata": {
"tags": []
},
"execution_count": 6
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Nr8hC6G2cmE1"
},
"source": [
"Load it into a `Text()` object: "
]
},
{
"cell_type": "code",
"metadata": {
"id": "9orcO89GQO0r"
},
"source": [
"bibleText = Text(bible)"
],
"execution_count": 7,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "0A-nhyiCcpsu"
},
"source": [
"And print out stats: "
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "UJ_5PKmv2yQs",
"outputId": "a5b179f0-bc82-426e-911f-481ba321c876"
},
"source": [
"bibleText.stats"
],
"execution_count": 8,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{'ang': 42.50495206402029,\n",
" 'ara': 0.10696458283812696,\n",
" 'arg': 0.02376990729736155,\n",
" 'arz': 0.02376990729736155,\n",
" 'bod': 0.02376990729736155,\n",
" 'cmn': 0.02376990729736155,\n",
" 'cym': 0.0475398145947231,\n",
" 'deu': 0.011884953648680774,\n",
" 'dum': 0.0950796291894462,\n",
" 'enm': 0.02376990729736155,\n",
" 'fas': 0.007923302432453849,\n",
" 'fra': 4.056334680294748,\n",
" 'frm': 2.914586799778148,\n",
" 'fro': 25.964265906029627,\n",
" 'gae': 0.02376990729736155,\n",
" 'gle': 0.0475398145947231,\n",
" 'gml': 0.03763568655415578,\n",
" 'grc': 0.5744394263529041,\n",
" 'haw': 0.07130972189208463,\n",
" 'heb': 0.23373742175738857,\n",
" 'hin': 0.07130972189208463,\n",
" 'hye': 0.011884953648680774,\n",
" 'ita': 0.05942476824340386,\n",
" 'jpn': 0.02376990729736155,\n",
" 'kor': 0.02376990729736155,\n",
" 'lat': 11.88693447428889,\n",
" 'mri': 0.007923302432453849,\n",
" 'msa': 0.02376990729736155,\n",
" 'nld': 0.14261944378416927,\n",
" 'non': 2.5382299342365906,\n",
" 'odt': 0.02376990729736155,\n",
" 'por': 0.07725219871642502,\n",
" 'rus': 0.0475398145947231,\n",
" 'sco': 0.02376990729736155,\n",
" 'spa': 0.07606370335155693,\n",
" 'tur': 0.0950796291894462,\n",
" 'xno': 8.034228666508202,\n",
" 'yid': 0.015846604864907698}"
]
},
"metadata": {
"tags": []
},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "hw3kx-yTQ9Hj",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "731005f3-564a-44c4-cd2f-be4e7e73d755"
},
"source": [
"bibleText.prettyStats"
],
"execution_count": 9,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{'Ancient Greek (to 1453)': 0.57,\n",
" 'Anglo-Norman': 8.03,\n",
" 'Arabic': 0.11,\n",
" 'Aragonese': 0.02,\n",
" 'Armenian': 0.01,\n",
" 'Dutch': 0.14,\n",
" 'Egyptian Arabic': 0.02,\n",
" 'French': 4.06,\n",
" 'German': 0.01,\n",
" 'Guarequena': 0.02,\n",
" 'Hawaiian': 0.07,\n",
" 'Hebrew': 0.23,\n",
" 'Hindi': 0.07,\n",
" 'Irish': 0.05,\n",
" 'Italian': 0.06,\n",
" 'Japanese': 0.02,\n",
" 'Korean': 0.02,\n",
" 'Latin': 11.89,\n",
" 'Malay (macrolanguage)': 0.02,\n",
" 'Mandarin Chinese': 0.02,\n",
" 'Maori': 0.01,\n",
" 'Middle Dutch (ca. 1050-1350)': 0.1,\n",
" 'Middle English (1100-1500)': 0.02,\n",
" 'Middle French (ca. 1400-1600)': 2.91,\n",
" 'Middle Low German': 0.04,\n",
" 'Old Dutch': 0.02,\n",
" 'Old English (ca. 450-1100)': 42.5,\n",
" 'Old French (842-ca. 1400)': 25.96,\n",
" 'Old Norse': 2.54,\n",
" 'Persian': 0.01,\n",
" 'Portuguese': 0.08,\n",
" 'Russian': 0.05,\n",
" 'Scots': 0.02,\n",
" 'Spanish': 0.08,\n",
" 'Tibetan': 0.02,\n",
" 'Turkish': 0.1,\n",
" 'Welsh': 0.05,\n",
" 'Yiddish': 0.02}"
]
},
"metadata": {
"tags": []
},
"execution_count": 9
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Se5q6lmrRRHb",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "f05e11c6-71f0-41e4-af1e-7b25980859ab"
},
"source": [
"bibleText.familyStats()"
],
"execution_count": 10,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{'Austronesian': 0.007923302432453849,\n",
" 'Balto-Slavic': 0.0475398145947231,\n",
" 'Celtic': 0.0475398145947231,\n",
" 'Germanic': 45.393788130892965,\n",
" 'Hellenic': 0.5744394263529041,\n",
" 'Indo-Iranian': 0.07923302432453848,\n",
" 'Japonic': 0.02376990729736155,\n",
" 'Latinate': 53.069091197210994,\n",
" 'Other': 0.32089374851438096,\n",
" 'Semitic': 0.34070200459551553,\n",
" 'Turkic': 0.0950796291894462,\n",
" 'Uralic': 0.0}"
]
},
"metadata": {
"tags": []
},
"execution_count": 10
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "-TeIohzva0Zz",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "9a914412-fb52-43cb-cee6-ab0b5d004c33"
},
"source": [
"bibleText"
],
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<macroetym.main.Text at 0x7f8146371128>"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QFFZWlBs068l",
"outputId": "b50a3e91-d21f-425b-9eff-089487c113ed"
},
"source": [
"word = bibleText.wordObjects[100]\n",
"print(word)"
],
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"text": [
"husbandry\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "oTss9rUo1Nwp",
"outputId": "38429874-89b9-4a48-b1ee-0580f3418a58"
},
"source": [
"word.parentLanguages"
],
"execution_count": 33,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"[]"
]
},
"metadata": {
"tags": []
},
"execution_count": 33
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PkneCVB61UxA",
"outputId": "53e7bfa6-251f-4dad-ea56-67cbdeef0640"
},
"source": [
"word.parentLanguages.langs # This is the for-real list"
],
"execution_count": 30,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"[]"
]
},
"metadata": {
"tags": []
},
"execution_count": 30
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "835UgQzq2EfC",
"outputId": "12f20a6a-5adc-49e9-bb0b-bfcb615f5304"
},
"source": [
"'ang' in word.parentLanguages.langs"
],
"execution_count": 31,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"False"
]
},
"metadata": {
"tags": []
},
"execution_count": 31
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "yjBB5j_81fVB",
"outputId": "b22e7362-3e9a-4343-9149-34d0c60ec595"
},
"source": [
"[w for w in bibleText.wordObjects if 'fro' in word.parentLanguages.stats]"
],
"execution_count": 22,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"[]"
]
},
"metadata": {
"tags": []
},
"execution_count": 22
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "dTf2lpup1zUY",
"outputId": "dfa821d2-abd0-4dd7-9d42-924caab6b51f"
},
"source": [
"word.parentLanguages.stats"
],
"execution_count": 23,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{}"
]
},
"metadata": {
"tags": []
},
"execution_count": 23
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Va2IFDC32n-v"
},
"source": [
"word2 = bibleText.wordObjects[200]"
],
"execution_count": 24,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "v-Hv09lo3Rl7",
"outputId": "f950e529-5ed6-471e-ce5c-026a27cf6a3a"
},
"source": [
"word2.parentLanguages"
],
"execution_count": 28,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['ang']"
]
},
"metadata": {
"tags": []
},
"execution_count": 28
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "ec33MIWP4Cou"
},
"source": [
"word3 = bibleText.wordObjects[300]"
],
"execution_count": 34,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "_cywa9_c4Q4m",
"outputId": "b933918b-4a50-4e5e-c0cf-9eaeb1e5a32f"
},
"source": [
"word3"
],
"execution_count": 35,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"kind (eng)"
]
},
"metadata": {
"tags": []
},
"execution_count": 35
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xDBTjNOo4R95",
"outputId": "f75386e7-8d3e-4fc3-b3ad-ba211b454a34"
},
"source": [
"word3.parentLanguages"
],
"execution_count": 36,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['ang']"
]
},
"metadata": {
"tags": []
},
"execution_count": 36
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "_3x5Cdy44VNM",
"outputId": "990fd2f6-62be-4b2f-fe64-0e62de08ea51"
},
"source": [
"for word in bibleText.wordObjects[301:310]:\n",
" print(word.parentLanguages)"
],
"execution_count": 38,
"outputs": [
{
"output_type": "stream",
"text": [
"[]\n",
"['ang']\n",
"['fro']\n",
"[]\n",
"['fro']\n",
"[]\n",
"['lat']\n",
"[]\n",
"[]\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3C3SzO_r4fRB",
"outputId": "a4ecaf21-1e4e-4be1-8750-a5bc2165cddf"
},
"source": [
"bibleText.wordObjects[303].parentLanguages.langs"
],
"execution_count": 41,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['fro']"
]
},
"metadata": {
"tags": []
},
"execution_count": 41
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "eSxFQRWp4nSL",
"outputId": "0a9b5092-7dcc-44f4-e77f-a19a9e1a766f"
},
"source": [
"'fro' in bibleText.wordObjects[303].parentLanguages.langs"
],
"execution_count": 42,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"True"
]
},
"metadata": {
"tags": []
},
"execution_count": 42
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "jHPnZzGe5QvM"
},
"source": [
"# Example for getting a list of only those words which are of a certain language's origin"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "R5khuEzl4-ED",
"outputId": "fa4c40ad-a32c-4d1c-b30d-6522130f66eb"
},
"source": [
"# Using only words 300-350 to save time\n",
"for w in bibleText.wordObjects[300:350]:\n",
" # I think you have to run this first so that `langs` is populated\n",
" # (since it's lazily-loaded). \n",
" parentLangs = w.parentLanguages.langs\n",
" # If 'Old French' is in the list of parent languages\n",
" if 'fro' in parentLangs: \n",
" print(w)"
],
"execution_count": 43,
"outputs": [
{
"output_type": "stream",
"text": [
"oppose\n",
"testify\n",
"lionlike\n",
"cause\n",
"authority\n",
"square\n",
"promise\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "S6n_F7Bb5Pe2"
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment