{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "series = 'A6283'" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "" ], "text/vnd.plotly.v1+html": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "" ], "text/vnd.plotly.v1+html": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import os\n", "import pandas as pd\n", "import series_details\n", "import plotly.offline as py\n", "py.init_notebook_mode()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "df = pd.read_csv(os.path.join('data', '{}.csv'.format(series.replace('/', '-'))), parse_dates=['start_date', 'end_date'])" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/html": [ "

National Archives of Australia: Series A6283

" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "

Correspondence files, multiple number series (Royal Commission Section)

" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
Total items256
Access status
Open with exception208 (81.25%)
Not yet examined24 (9.38%)
Open21 (8.20%)
Closed3 (1.17%)
Number of items digitised23 (8.98%)
Number of pages digitised3,352
Date of earliest content1800
Date of latest content1959
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "series_details.display_summary(series, df)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Content preview" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "scrolled": 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", " \n", " \n", " \n", "
identifierseriescontrol_symboltitlecontents_datesstart_dateend_dateaccess_statuslocationdigitised_statusdigitised_pages
0241384A628318Communist Party of Australia1954 - 19551954-01-01 00:00:001955-01-01 00:00:00Open with exceptionCanberraFalse0
1241385A628319Voks1954 - 19551954-01-01 00:00:001955-01-01 00:00:00Open with exceptionCanberraFalse0
2241388A628324Australian Government Policies1954 - 19541954-01-01 00:00:001954-01-01 00:00:00Open with exceptionCanberraFalse0
3241389A628325Australian Government Departments and Instrumentalities1954 - 19551954-01-01 00:00:001955-01-01 00:00:00Open with exceptionCanberraFalse0
4241390A628327Corrective Labour Camps1954 - 19541954-01-01 00:00:001954-01-01 00:00:00Open with exceptionCanberraFalse0
" ], "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Change the number_of_rows value to see more\n", "number_of_rows = 5\n", "\n", "# Display dataframe \n", "df[:number_of_rows].style.set_properties(['title'], **{'text-align': 'left'}).set_table_styles([dict(selector=\"th\", props=[(\"text-align\", \"center\")]),\n", " dict(selector='.row_heading, .blank', props=[('display', 'none')])])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Plot content dates" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "data": [ { "name": "Digitised", "type": "bar", "x": [ 1952, 1953, 1954, 1955, 1956 ], "y": [ 5, 5, 19, 14, 4 ] }, { "name": "Not digitised", "type": "bar", "x": [ 1800, 1950, 1951, 1952, 1953, 1954, 1955, 1956, 1957, 1958, 1959 ], "y": [ 1, 2, 2, 20, 24, 185, 124, 6, 1, 1, 1 ] } ], "layout": { "barmode": "stack", "title": "Content dates", "xaxis": { "title": "Year" }, "yaxis": { "title": "Number of items" } } }, "text/html": [ "
" ], "text/vnd.plotly.v1+html": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fig = series_details.plot_dates(df)\n", "py.iplot(fig, filename='series-dates-bar')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## View word frequencies" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# Combine all of the file titles into a single string\n", "title_text = a = df['title'].str.lower().str.cat(sep=' ')" ] }, { "cell_type": "code", "execution_count": 8, "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", "
wordcount
183copy96
182reference96
33volume55
40petrov50
35vol41
49vladimir37
78royal29
47press28
38527
79commission27
29interrogations27
48cuttings26
30petrovs25
41123
46222
50mihailovich21
82mvd21
56evdokia20
42overseas19
28reports19
67intelligence17
68services17
52story16
226mail16
228september16
" ], "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "series_details.display_word_counts(title_text)" ] }, { "cell_type": "code", "execution_count": 9, "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", "
ngramcount
0reference copy96
1of interrogations27
2royal commission27
3press cuttings26
4of petrovs24
5cuttings volume24
6petrov vladimir22
7volume 522
8vladimir mihailovich21
9interrogations of20
10overseas intelligence17
11intelligence services17
125 'the16
13reports of16
14'the courier14
15by vladimir14
16evdokia petrov14
17courier mail14
18empire of13
19the empire13
20vladimir and13
21and evdokia13
22of fear13
231955 p212
24vol 111
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Change ngram_count for larger ngrams (trigrams etc)\n", "ngram_count = 2\n", "series_details.display_top_ngrams(title_text, ngram_count)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }