{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "from bs4 import BeautifulSoup\n", "import glob\n", "import re\n", "import json\n", "import csv\n", "import os" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "# had to delete one file from both Metadata and word-count file due to the ngram1 file not containing any information. journal-article-10.2307_1196540-ngram1.txt\n", "total_freq = {}\n", "\n", "# The json schema here is {pub-year: {word: count}}\n", "\n", "for xml in glob.iglob('Metadata/*.xml'):\n", " with open(xml) as f:\n", " bs = BeautifulSoup(f, \"lxml-xml\")\n", " \n", " # Extract pub lish year\n", " pub_year = bs.year\n", " year = int(str(pub_year)[6:10])\n", " \n", " total_freq[year] = total_freq.get(year, {})\n", "\n", " \n", " txt = xml.replace(\"Metadata\", \"word-count\").replace(\".xml\", \"-ngram1.txt\")\n", " \n", " \n", " \n", " with open(txt) as t:\n", " for line in t:\n", " sub = re.split(\"\\s+\", line)\n", " word = sub[0]\n", " count = int(sub[1])\n", " \n", " if total_freq[year].get(word, 0) == 0:\n", " total_freq[year][word] = 0\n", "\n", " total_freq[year][word] += count\n", "\n", " \n", "file = open(\"count.json\", \"w\")\n", " \n", "with file:\n", " json.dump(total_freq, file)" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "df = pd.DataFrame.from_dict(total_freq, orient = 'index')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/ext/anaconda2020.02/lib/python3.7/site-packages/IPython/core/interactiveshell.py:3343: FutureWarning: This dataframe has a column name that matches the 'value_name' column name of the resultiing Dataframe. In the future this will raise an error, please set the 'value_name' parameter of DataFrame.melt to a unique name.\n", " exec(code_obj, self.user_global_ns, self.user_ns)\n" ] } ], "source": [ "long_df = pd.melt(df, ignore_index = False)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.reset_index(inplace=True)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
indexvariablevalue
01998s278.0
11952s33.0
21987s278.0
31930s105.0
41925s245.0
............
59576742005vargNaN
59576751958vargNaN
59576761962vargNaN
59576771971vargNaN
59576781959varg1.0
\n", "

5957679 rows × 3 columns

\n", "
" ], "text/plain": [ " index variable value\n", "0 1998 s 278.0\n", "1 1952 s 33.0\n", "2 1987 s 278.0\n", "3 1930 s 105.0\n", "4 1925 s 245.0\n", "... ... ... ...\n", "5957674 2005 varg NaN\n", "5957675 1958 varg NaN\n", "5957676 1962 varg NaN\n", "5957677 1971 varg NaN\n", "5957678 1959 varg 1.0\n", "\n", "[5957679 rows x 3 columns]" ] }, "execution_count": 7, "metadata": { }, "output_type": "execute_result" } ], "source": [ "long_df" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "#I tried creatinga loop for removing stop words from the data frame but it pulled out the variable column, so I guess I'm doing this probably the worst way\n", "\n", "long_df.drop(long_df.index[long_df['variable'] == 's'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '00'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '95'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '0'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '1'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'i'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'pp'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'has'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
indexvariablevalue
2731998book101.0
2741952book11.0
2751987book90.0
2761930book70.0
2771925book155.0
............
59576742005vargNaN
59576751958vargNaN
59576761962vargNaN
59576771971vargNaN
59576781959varg1.0
\n", "

5956951 rows × 3 columns

\n", "
" ], "text/plain": [ " index variable value\n", "273 1998 book 101.0\n", "274 1952 book 11.0\n", "275 1987 book 90.0\n", "276 1930 book 70.0\n", "277 1925 book 155.0\n", "... ... ... ...\n", "5957674 2005 varg NaN\n", "5957675 1958 varg NaN\n", "5957676 1962 varg NaN\n", "5957677 1971 varg NaN\n", "5957678 1959 varg 1.0\n", "\n", "[5956951 rows x 3 columns]" ] }, "execution_count": 9, "metadata": { }, "output_type": "execute_result" } ], "source": [ "long_df" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'new'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'which'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'from'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'his'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'its'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'have'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'all'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'he'], inplace = True)\n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'one'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'been'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'pages'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'we'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'would'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'had'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'j'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'our'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'cloth'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'hardback'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'you'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'p'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'new'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'york'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'press'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'were'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'any'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'isbn'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '35'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '800'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '86554'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'ii'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'e'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'd'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'her'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'b'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'who'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'also'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'what'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'more'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'may'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'should'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'those'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'ibid'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '86554'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'h'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '6'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '50'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '3'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'car'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'same'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'l'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'see'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'my'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'so'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'between'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'other'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'us'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'she'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'many'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'work'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'can'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'your'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '2'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '4'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '75'], inplace = True)\n" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'only'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'them'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'than'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'factor'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '5'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'co'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'two'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'most'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'must'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'upon'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'me'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'do'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'cannot'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'when'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'some'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'through'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'people'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'much'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'w'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'm'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'person'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'does'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'him'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'st'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'm'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'yet'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'c'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'x'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'could'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'd'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'when'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'how'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'whether'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'yet'], inplace = True)\n", "\n" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'out'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'even'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'type'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'action'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'well'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'very'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'mr'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'dr'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'made'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'own'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'far'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'himself'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '25'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == '7'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'now'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'each'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'like'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'here'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'about'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'within'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'n'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 't'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'both'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'r'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'n'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "long_df.drop(long_df.index[long_df['variable'] == 'thus'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'itself'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'still'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'make'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'sense'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'focus'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'never'], inplace = True)\n", "long_df.drop(long_df.index[long_df['variable'] == 'while'], inplace = True)" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "top_fifteen_words = long_df.groupby('index').apply(lambda x : x.sort_values(by = 'value', ascending = False).head(15).reset_index(drop = True))" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "pd.set_option('display.max_row', 2000)" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false }, "outputs": [ { "ename": "NameError", "evalue": "name 'long_df' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtop_ten_words\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlong_df\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'index'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m:\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msort_values\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mby\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'value'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mascending\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdrop\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mNameError\u001b[0m: name 'long_df' is not defined" ] } ], "source": [ "top_ten_words = long_df.groupby('index').apply(lambda x : x.sort_values(by = 'value', ascending = False).head(10).reset_index(drop = True))" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "#You can now see the top_ten_words or the top_fifteen_words used over time. All you need to do is type top_ten_words or top_fifteen_words and then hit command return. \n", "\n", "#top_ten_words\n", "#top_fifteen_words" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (Anaconda 2020)", "env": { "ADDR2LINE": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-addr2line", "ANACONDA2019": "$EXT/anaconda-2019.03", "ANACONDA2020": "/ext/anaconda2020.02", "ANACONDA3": "$EXT/anaconda3", "ANACONDA5": "$EXT/anaconda5", "AR": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-ar", "AS": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-as", "CC": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-cc", "CFLAGS": "-march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include", "CMAKE_PREFIX_PATH": "/ext/anaconda2020.02:/ext/anaconda2020.02/x86_64-conda_cos6-linux-gnu/sysroot/usr", "CONDA_BACKUP_HOST": "x86_64-conda_cos6-linux-gnu", "CONDA_BUILD_SYSROOT": "/ext/anaconda2020.02/x86_64-conda_cos6-linux-gnu/sysroot", "CONDA_DEFAULT_ENV": "base", "CONDA_EXE": "/ext/anaconda2020.02/bin/conda", "CONDA_MKL_INTERFACE_LAYER_BACKUP": "", "CONDA_PREFIX": "/ext/anaconda2020.02", "CONDA_PROMPT_MODIFIER": "(base) ", "CONDA_PYTHON_EXE": "/ext/anaconda2020.02/bin/python", "CONDA_SHLVL": "1", "CPP": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-cpp", "CPPFLAGS": "-DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -isystem /ext/anaconda2020.02/include", "CXX": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-c++", "CXXFILT": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-c++filt", "CXXFLAGS": "-fvisibility-inlines-hidden -std=c++17 -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include", "DEBUG_CFLAGS": "-march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fvar-tracking-assignments -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include", "DEBUG_CPPFLAGS": "-D_DEBUG -D_FORTIFY_SOURCE=2 -Og -isystem /ext/anaconda2020.02/include", "DEBUG_CXXFLAGS": "-fvisibility-inlines-hidden -std=c++17 -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fvar-tracking-assignments -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include", "DEBUG_FFLAGS": "-fopenmp -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include -fopenmp -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fcheck=all -fbacktrace -fimplicit-none -fvar-tracking-assignments -ffunction-sections -pipe", "DEBUG_FORTRANFLAGS": "-fopenmp -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include -fopenmp -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fcheck=all -fbacktrace -fimplicit-none -fvar-tracking-assignments -ffunction-sections -pipe", "ELFEDIT": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-elfedit", "F77": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gfortran", "F90": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gfortran", "F95": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-f95", "FC": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gfortran", "FFLAGS": "-fopenmp -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include", "FORTRANFLAGS": "-fopenmp -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /ext/anaconda2020.02/include", "GCC": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gcc", "GCC_AR": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gcc-ar", "GCC_NM": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gcc-nm", "GCC_RANLIB": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gcc-ranlib", "GDAL_DATA": "/ext/anaconda2020.02/share/gdal", "GFORTRAN": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gfortran", "GPROF": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-gprof", "GXX": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-g++", "JAVA_HOME": "/ext/anaconda2020.02", "JAVA_HOME_CONDA_BACKUP": "", "JAVA_LD_LIBRARY_PATH": "/ext/anaconda2020.02/lib/server", "LD": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-ld", "LDFLAGS": "-Wl,-O2 -Wl,--sort-common -Wl,--as-needed -Wl,-z,relro -Wl,-z,now -Wl,--disable-new-dtags -Wl,--gc-sections -Wl,-rpath,/ext/anaconda2020.02/lib -Wl,-rpath-link,/ext/anaconda2020.02/lib -L/ext/anaconda2020.02/lib", "LD_GOLD": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-ld.gold", "LD_LIBRARY_PATH": "/ext/anaconda2020.02/lib", "MKL_INTERFACE_LAYER": "LP64,GNU", "MKL_THREADING_LAYER": "GNU", "NM": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-nm", "OBJCOPY": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-objcopy", "OBJDUMP": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-objdump", "OLDPWD": "/ext/anaconda2020.02", "PATH": "/ext/anaconda2020.02/bin:/ext/anaconda2020.02/bin:/ext/anaconda2020.02/condabin:/cocalc/bin:/cocalc/src/smc-project/bin:/home/salvus/bin:/home/salvus/.local/bin:/usr/lib/xpra:/ext/bin:/opt/ghc/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin:/usr/lib/postgresql/10/bin:/ext/data/homer/bin:/ext/data/weblogo", "PROJ_LIB": "/ext/anaconda2020.02/share/proj", "RANLIB": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-ranlib", "READELF": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-readelf", "RSTUDIO_WHICH_R": "/ext/anaconda2020.02/bin/R", "SIZE": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-size", "STRINGS": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-strings", "STRIP": "/ext/anaconda2020.02/bin/x86_64-conda_cos6-linux-gnu-strip", "_CE_CONDA": "", "_CE_M": "", "_CONDA_PYTHON_SYSCONFIGDATA_NAME": "_sysconfigdata_x86_64_conda_cos6_linux_gnu" }, "language": "python", "metadata": { "cocalc": { "description": "Python/R distribution for data science", "priority": 5, "url": "https://www.anaconda.com/distribution/" } }, "name": "anaconda2020", "resource_dir": "/ext/jupyter/kernels/anaconda2020" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.8" } }, "nbformat": 4, "nbformat_minor": 4 }