Last active
January 13, 2017 19:40
-
-
Save jerielizabeth/97eeac0bf83365af7fd00bc6a0151554 to your computer and use it in GitHub Desktop.
drafts/code/ocr_evaluation_and_correction/2017-01-06-corpus-OCR-overview-data.ipynb update
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": [ | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Code: Compute Corpus Statistics" | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"start_time": "2017-01-13T08:55:58.363395", | |
"end_time": "2017-01-13T08:55:59.885535" | |
}, | |
"collapsed": false, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "from collections import Counter\nfrom os import listdir\nfrom os.path import isfile, join\nimport json\nfrom datetime import date\nimport nltk\nfrom nltk.corpus import words\nfrom nltk import word_tokenize\nimport re\nimport numpy as np\n\ndef readfile(input_dir, filename):\n with open(join(input_dir, filename)) as f:\n return(f.read())\n\n# Function requires wordlists to be list, even if only using one file.\ndef create_spelling_dictionary(wordlists, directory):\n spelling_dictionary = []\n for wordlist in wordlists:\n words = readfile(directory, wordlist).splitlines()\n word_list = [w.lower() for w in words]\n for each in word_list:\n spelling_dictionary.append(each)\n return(list(set(spelling_dictionary)))\n\ndef strip_punct(text):\n text_cleaned = re.sub(r\"[0-9,.!?$:;&]\", \" \", text)\n return(text_cleaned)\n\ndef tokenize_text(text):\n return(word_tokenize(text))\n\ndef to_lower(tokens):\n return([w.lower() for w in tokens])\n\ndef identify_errors(tokens, dictionary):\n return(set(tokens)-set(dictionary))\n\ndef get_error_stats(errors):\n freq_distribution = nltk.FreqDist(errors) \n \n error_report = {}\n for error in list(errors):\n error_count = freq_distribution[error]\n error_report.update({error:error_count})\n \n return(error_report) \n\ndef total_errors(error_report):\n return(sum(error_report.values()))\n\ndef error_rate(error_total, tokens):\n if len(tokens) > 0:\n return(float(\"{0:.3f}\".format(error_total/len(tokens))))\n else:\n return(np.nan)\n \ndef generate_doc_report(text, spelling_dictionary):\n text = strip_punct(text)\n tokens = tokenize_text(text)\n tokens = to_lower(tokens)\n errors = identify_errors(tokens, spelling_dictionary)\n error_report = get_error_stats(errors)\n error_total = total_errors(error_report)\n rate = error_rate(error_total, tokens)\n return({'num_tokens': len(tokens),\n 'num_unique_tokens': len(set(tokens)),\n 'num_errors': error_total,\n 'error_rate': rate,\n 'errors': error_report})\n\n# Function for taking a directory and a wordlist and reporting back errors and general statistics for each doc.\ndef process_directory(directory, wordlists, wordlist_dir):\n\n # load up a list of the corpus documents\n corpus = (f for f in listdir(directory) if not f.startswith('.') and isfile(join(directory, f)))\n \n # Compile the spelling dictionary from word lists\n spelling_dictionary = create_spelling_dictionary(wordlists, wordlist_dir)\n \n statistics = []\n for document in corpus:\n content = readfile(directory, document)\n stats = generate_doc_report(content, spelling_dictionary)\n stats.update({\"doc_id\": document})\n statistics.append(stats)\n \n return(statistics) \n\ndef get_corpus_data( input_dir, title ):\n corpus_data = process_directory( join(input_dir, title), wordlists, wordlist_dir )\n return( corpus_data )", | |
"execution_count": 1, | |
"outputs": [] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Setup" | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"start_time": "2017-01-13T08:55:59.887109", | |
"end_time": "2017-01-13T08:55:59.891084" | |
}, | |
"collapsed": true, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "titles = [\"ADV\", \"AmSn\", \"ARAI\", \"CE\", \n \"CUV\", \"EDU\", \"GCB\", \"GH\", \n \"GOH\", \"GS\", \"HM\", \"HR\", \n \"IR\", \"LB\", \"LH\", \"LibM\", \n \"LUH\", \"NMN\",\"PHJ\",\"PTAR\",\n \"PUR\",\"RH\",\"Sligo\",\"SOL\",\n \"ST\",\"SUW\",\"TCOG\",\"TMM\",\n \"WMH\",\"YI\"]", | |
"execution_count": 2, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"start_time": "2017-01-13T08:55:59.893151", | |
"end_time": "2017-01-13T08:55:59.897615" | |
}, | |
"collapsed": true, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "input_dir = \"/Users/jeriwieringa/Dissertation/text/text/2017-01-06-corpus-with-utf8-split-into-titles\"\nwordlists = [\"2016-12-07-SDA-last-names.txt\", \n \"2016-12-07-SDA-place-names.txt\", \n \"2016-12-08-SDA-Vocabulary.txt\", \n \"2017-01-03-place-names.txt\", \n \"2016-12-06-First-Word-List.txt\"]\nwordlist_dir = \"/Users/jeriwieringa/Dissertation/drafts/data/word-lists\"\nout_dir = \"/Users/jeriwieringa/Dissertation/drafts/data/corpus-statistics/2017-01-08\"", | |
"execution_count": 3, | |
"outputs": [] | |
}, | |
{ | |
"metadata": {}, | |
"cell_type": "markdown", | |
"source": "# Generate Data" | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"start_time": "2017-01-13T08:55:59.900116", | |
"end_time": "2017-01-13T08:55:59.908780" | |
}, | |
"scrolled": false, | |
"trusted": true, | |
"collapsed": false | |
}, | |
"cell_type": "code", | |
"source": "def process_title(title, input_dir):\n corpus_data = {}\n\n print(\"\\nProcessing: {}\".format(title))\n data = get_corpus_data(input_dir, title)\n\n corpus_data.update({\"reports\": data})\n yield corpus_data", | |
"execution_count": 4, | |
"outputs": [] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"start_time": "2017-01-13T08:55:59.910887", | |
"end_time": "2017-01-13T10:59:07.409688" | |
}, | |
"collapsed": false, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "import time\n\nfor title in titles:\n outfile = \"{}-all-corpora-data.json\".format(title)\n with open(join(out_dir, outfile), \"w\", encoding='utf-8') as o: \n start = time.time()\n all_data = process_title(title, input_dir)\n for data in all_data:\n json.dump(data, o)\n end = time.time()\n print((end-start)/60)\n o.close()", | |
"execution_count": 5, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": "\nProcessing: ADV\n1.4443191488583882\n\nProcessing: AmSn\n4.08760058482488\n\nProcessing: ARAI\n0.07371393044789633\n\nProcessing: CE\n2.1874577522277834\n\nProcessing: CUV\n3.9534137805302936\n\nProcessing: EDU\n0.2939378341039022\n\nProcessing: GCB\n2.774425919850667\n\nProcessing: GH\n1.2899338324864706\n\nProcessing: GOH\n0.41394771734873453\n\nProcessing: GS\n0.39861186742782595\n\nProcessing: HM\n1.5764355142911275\n\nProcessing: HR\n12.324441564083099\n\nProcessing: IR\n0.8139488180478414\n\nProcessing: LB\n5.083624283472697\n\nProcessing: LH\n5.361722048123678\n\nProcessing: LibM\n1.7180917501449584\n\nProcessing: LUH\n3.9271430810292562\n\nProcessing: NMN\n0.24592998425165813\n\nProcessing: PHJ\n2.608540717760722\n\nProcessing: PTAR\n0.14221384922663372\n\nProcessing: PUR\n3.9020716190338134\n\nProcessing: RH\n35.2963091691335\n\nProcessing: Sligo\n0.7368343830108642\n\nProcessing: SOL\n1.4018923163414\n\nProcessing: ST\n13.384035801887512\n\nProcessing: SUW\n3.6700123151143393\n\nProcessing: TCOG\n0.9790529688199361\n\nProcessing: TMM\n1.3713114182154338\n\nProcessing: WMH\n0.6506821990013123\n\nProcessing: YI\n11.000955033302308\n", | |
"name": "stdout" | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"ExecuteTime": { | |
"start_time": "2017-01-13T10:59:07.411479", | |
"end_time": "2017-01-13T10:59:08.888726" | |
}, | |
"collapsed": false, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "# %load /Users/jeriwieringa/Dissertation/drafts/code/shared_elements/system_info.py\nimport IPython\nprint (IPython.sys_info())\n!pip freeze", | |
"execution_count": 6, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": "{'commit_hash': '5c9c918',\n 'commit_source': 'installation',\n 'default_encoding': 'UTF-8',\n 'ipython_path': '/Users/jeriwieringa/miniconda3/envs/dissertation2/lib/python3.5/site-packages/IPython',\n 'ipython_version': '5.1.0',\n 'os_name': 'posix',\n 'platform': 'Darwin-16.3.0-x86_64-i386-64bit',\n 'sys_executable': '/Users/jeriwieringa/miniconda3/envs/dissertation2/bin/python',\n 'sys_platform': 'darwin',\n 'sys_version': '3.5.2 |Continuum Analytics, Inc.| (default, Jul 2 2016, '\n '17:52:12) \\n'\n '[GCC 4.2.1 Compatible Apple LLVM 4.2 (clang-425.0.28)]'}\nanaconda-client==1.5.5\nappnope==0.1.0\nargh==0.26.1\nblinker==1.4\nbokeh==0.12.4\nboto==2.43.0\nbz2file==0.98\nchest==0.2.3\ncloudpickle==0.2.1\nclyent==1.2.2\ndask==0.12.0\ndatashader==0.4.0\ndatashape==0.5.2\ndecorator==4.0.10\ndocutils==0.12\ndoit==0.29.0\ngensim==0.12.4\nGhost.py==0.2.3\nghp-import2==1.0.1\ngspread==0.4.1\nHeapDict==1.0.0\nhttplib2==0.9.2\nhusl==4.0.3\nijson==2.3\nipykernel==4.5.2\nipython==5.1.0\nipython-genutils==0.1.0\nipywidgets==5.2.2\nJinja2==2.8\njsonschema==2.5.1\njupyter==1.0.0\njupyter-client==4.4.0\njupyter-console==5.0.0\njupyter-contrib-core==0.3.0\njupyter-contrib-nbextensions==0.2.2\njupyter-core==4.2.1\njupyter-highlight-selected-word==0.0.5\njupyter-latex-envs==1.3.5.4\njupyter-nbextensions-configurator==0.2.3\nllvmlite==0.14.0\nlocket==0.2.0\nLogbook==1.0.0\nlxml==3.5.0\nMacFSEvents==0.7\nMako==1.0.4\nMarkdown==2.6.7\nMarkupSafe==0.23\nmemory-profiler==0.43\nmistune==0.7.3\nmultipledispatch==0.4.9\nnatsort==4.0.4\nnb-anacondacloud==1.2.0\nnb-conda==2.0.0\nnb-conda-kernels==2.0.0\nnb-config-manager==0.1.3\nnbbrowserpdf==0.2.1\nnbconvert==4.2.0\nnbformat==4.2.0\nnbpresent==3.0.2\nnetworkx==1.11\nNikola==7.7.7\nnltk==3.2.2\nnotebook==4.2.3\nnumba==0.29.0\nnumpy==1.11.3\noauth2client==4.0.0\nodo==0.5.0\npandas==0.19.2\npartd==0.3.6\npath.py==0.0.0\npathtools==0.1.2\npexpect==4.0.1\npickleshare==0.7.4\nPillow==3.4.2\nprompt-toolkit==1.0.9\npsutil==4.3.0\nptyprocess==0.5.1\npyasn1==0.1.9\npyasn1-modules==0.0.8\npycrypto==2.6.1\nPygments==2.1.3\nPyPDF2==1.25.1\nPyRSS2Gen==1.1\npyshp==1.2.10\npython-dateutil==2.6.0\npytz==2016.10\nPyYAML==3.12\npyzmq==16.0.2\nqtconsole==4.2.1\nrequests==2.12.3\nrsa==3.4.2\nscipy==0.18.1\nsimplegeneric==0.8.1\nsix==1.10.0\nsmart-open==1.3.5\nterminado==0.6\ntextblob==0.11.1\ntoolz==0.8.1\ntornado==4.4.2\ntraitlets==4.3.1\nUnidecode==0.4.19\nverifyOCR==0.1\nwatchdog==0.8.3\nwcwidth==0.1.7\nwebassets==0.11.1\nwidgetsnbextension==1.2.6\nws4py==0.3.4\nxarray==0.8.2\nYapsy==1.11.223\n", | |
"name": "stdout" | |
} | |
] | |
}, | |
{ | |
"metadata": { | |
"collapsed": true, | |
"trusted": true | |
}, | |
"cell_type": "code", | |
"source": "", | |
"execution_count": null, | |
"outputs": [] | |
} | |
], | |
"metadata": { | |
"toc": { | |
"sideBar": false, | |
"toc_cell": true, | |
"nav_menu": { | |
"width": "252px", | |
"height": "102px" | |
}, | |
"number_sections": true, | |
"threshold": "3", | |
"navigate_menu": true, | |
"toc_section_display": "block", | |
"toc_window_display": true | |
}, | |
"anaconda-cloud": {}, | |
"_draft": { | |
"nbviewer_url": "https://gist.github.com/97eeac0bf83365af7fd00bc6a0151554" | |
}, | |
"gist": { | |
"id": "97eeac0bf83365af7fd00bc6a0151554", | |
"data": { | |
"description": "drafts/code/ocr_evaluation_and_correction/2017-01-06-corpus-OCR-overview-data.ipynb update", | |
"public": true | |
} | |
}, | |
"language_info": { | |
"pygments_lexer": "ipython3", | |
"file_extension": ".py", | |
"version": "3.5.2", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"codemirror_mode": { | |
"version": 3, | |
"name": "ipython" | |
}, | |
"nbconvert_exporter": "python" | |
}, | |
"kernelspec": { | |
"language": "python", | |
"display_name": "Python [conda env:dissertation2]", | |
"name": "conda-env-dissertation2-py" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment