diff --git a/appfolder/Untitled.ipynb b/appfolder/Untitled.ipynb new file mode 100644 index 0000000..4fcc798 --- /dev/null +++ b/appfolder/Untitled.ipynb @@ -0,0 +1,490 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "id": "9e7a3bc3-0e9a-4b59-94be-31ea16005bee", + "metadata": {}, + "outputs": [], + "source": [ + "import dhlab as dh" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "67b92136-dd70-4fc2-be40-217ecbf5be10", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "3cbe1aeb-39d1-401f-9bf1-2dd738d1afba", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "dh.Ngram([\"hallo\"],doctype = \"avis\", mode=\"Relativ\")" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "d96c870e-0725-44e1-a8ac-33d4f49a6fcf", + "metadata": {}, + "outputs": [], + "source": [ + "df = pd.concat([dh.Ngram([\"hallo\"],doctype = \"avis\").frame,\n", + " dh.Ngram([\"hallo\"],doctype = \"bok\").frame])" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "b8292b92-caee-4a62-882e-8a5a54fdce98", + "metadata": {}, + "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", + " \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", + " \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", + " \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", + "
hallo
19500.002230
19510.002120
19520.002221
19530.002612
19540.002244
19550.002099
19560.001867
19570.002090
19580.002532
19590.002429
19600.002505
19610.002350
19620.002439
19630.002084
19640.002274
19650.001915
19660.001655
19670.001688
19680.001626
19690.001593
19700.001583
19710.001209
19720.001111
19730.001214
19740.001147
19750.001179
19760.001207
19770.001517
19780.001558
19790.001657
19800.001752
19810.001762
19820.001390
19830.003607
19840.006126
19850.008154
19860.006436
19870.001966
19880.001635
19890.002249
19900.002253
19910.002797
19920.002583
19930.002502
19940.002509
19950.002324
19960.002259
19970.002066
19980.002254
19990.002356
20000.002703
20010.002521
20020.002632
20030.002554
20040.002643
20050.002721
20060.002831
20070.002815
20080.003020
20090.002783
20100.003196
20110.004068
20120.003936
20130.003763
20140.003429
20150.002143
20160.002086
20170.002264
20180.002104
20190.002152
20200.001601
20210.002080
20220.002438
\n", + "
" + ], + "text/plain": [ + " hallo\n", + "1950 0.002230\n", + "1951 0.002120\n", + "1952 0.002221\n", + "1953 0.002612\n", + "1954 0.002244\n", + "1955 0.002099\n", + "1956 0.001867\n", + "1957 0.002090\n", + "1958 0.002532\n", + "1959 0.002429\n", + "1960 0.002505\n", + "1961 0.002350\n", + "1962 0.002439\n", + "1963 0.002084\n", + "1964 0.002274\n", + "1965 0.001915\n", + "1966 0.001655\n", + "1967 0.001688\n", + "1968 0.001626\n", + "1969 0.001593\n", + "1970 0.001583\n", + "1971 0.001209\n", + "1972 0.001111\n", + "1973 0.001214\n", + "1974 0.001147\n", + "1975 0.001179\n", + "1976 0.001207\n", + "1977 0.001517\n", + "1978 0.001558\n", + "1979 0.001657\n", + "1980 0.001752\n", + "1981 0.001762\n", + "1982 0.001390\n", + "1983 0.003607\n", + "1984 0.006126\n", + "1985 0.008154\n", + "1986 0.006436\n", + "1987 0.001966\n", + "1988 0.001635\n", + "1989 0.002249\n", + "1990 0.002253\n", + "1991 0.002797\n", + "1992 0.002583\n", + "1993 0.002502\n", + "1994 0.002509\n", + "1995 0.002324\n", + "1996 0.002259\n", + "1997 0.002066\n", + "1998 0.002254\n", + "1999 0.002356\n", + "2000 0.002703\n", + "2001 0.002521\n", + "2002 0.002632\n", + "2003 0.002554\n", + "2004 0.002643\n", + "2005 0.002721\n", + "2006 0.002831\n", + "2007 0.002815\n", + "2008 0.003020\n", + "2009 0.002783\n", + "2010 0.003196\n", + "2011 0.004068\n", + "2012 0.003936\n", + "2013 0.003763\n", + "2014 0.003429\n", + "2015 0.002143\n", + "2016 0.002086\n", + "2017 0.002264\n", + "2018 0.002104\n", + "2019 0.002152\n", + "2020 0.001601\n", + "2021 0.002080\n", + "2022 0.002438" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.groupby(df.index).sum()" + ] + } + ], + "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": "3.11.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/appfolder/wildcards.py b/appfolder/wildcards.py index d87398b..db60ee7 100755 --- a/appfolder/wildcards.py +++ b/appfolder/wildcards.py @@ -124,12 +124,18 @@ def load_corpus(**kwargs): mode_col, year_col = st.columns([1,2 ]) with mode_col: - mode = st.radio("Frekvenstype", ["Absolutt", "Relativ"], index=0) + # LGJ: setter valgene i små bokstaver for at det skal virke med mode + # kan beholde og gjøre x.lower() i stedet + mode = st.radio("Frekvenstype", ["absolutt", "relativ"], index=0) + with year_col: from_year, to_year = st.select_slider("Årstall", options=list(range(1800, 2025, 1)), value=(1800, 2024)) - - ngrams = dh.Ngram(chosen, from_year=from_year, to_year=to_year, mode=mode).frame + + # LGJ gjør nram for både avis og bok + + ngrams = pd.concat([dh.Ngram(chosen, from_year=from_year, to_year=to_year, mode=mode, doctype="bok").frame,dh.Ngram(chosen, from_year=from_year, to_year=to_year, mode=mode, doctype="avis").frame]) + ngrams = ngrams.groupby(ngrams.index).sum() st.line_chart(ngrams) @@ -144,44 +150,49 @@ def load_corpus(**kwargs): if chosen: st.subheader("Konkordanser") - try: - word_query = " OR ".join(chosen) - _corpus = load_corpus(fulltext=word_query, from_year=from_year, to_year=to_year, limit="9999") - _w_concs = [] - for w in chosen: - w_concs = dh.Concordance(corpus=_corpus, query=w, limit=5000) - _w_concs.append(w_concs.frame) + word_query = " OR ".join(chosen) + #st.write(f"Let etter dokumenter med {word_query}") - _concs = pd.concat(_w_concs, axis=0) - - concs = utils.format_conc_table(_corpus.frame, _concs) - to_download.append(concs.sort_values(by="Årstall")) - - st.dataframe( - concs, - column_config={ - "URL": st.column_config.LinkColumn( - "nb.no", - help="Les i Nettbiblioteket", - display_text="🔗", - disabled=True, - width="small", - ), - # "Årstall": st.column_config.DateColumn( - # "Årstall", - # format="YYYY", - # width="small", - # ) - }, - #disabled="urn", - hide_index=True, - use_container_width=True, - ) - except Exception as e: - st.error(f"Kunne ikke hente konkordanser: {e}") + ## LGJ: lar konk trigges av en knapp + if st.button(f"Finn konkordanser for {word_query}"): + try: + _corpus = load_corpus(fulltext=word_query, from_year=from_year, to_year=to_year, limit="1000") + _w_concs = [] + for w in chosen: + w_concs = dh.Concordance(corpus=_corpus, query=w, limit=5000) + _w_concs.append(w_concs.frame) + _concs = pd.concat(_w_concs, axis=0) + + concs = utils.format_conc_table(_corpus.frame, _concs) + to_download.append(concs.sort_values(by="Årstall")) + + st.dataframe( + concs, + column_config={ + "URL": st.column_config.LinkColumn( + "nb.no", + help="Les i Nettbiblioteket", + display_text="🔗", + disabled=True, + width="small", + ), + # "Årstall": st.column_config.DateColumn( + # "Årstall", + # format="YYYY", + # width="small", + # ) + }, + #disabled="urn", + hide_index=True, + use_container_width=True, + ) + except Exception as e: + st.error(f"Kunne ikke hente konkordanser: {e}") + + full_download_button = data_col.download_button( # place right below the wordlist AFTER the results are ready