{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"series = 'J2481'"
]
},
{
"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 J2481
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Proclamations under The Chinese Immigration Restriction Act 1888 & related correspondence, annual single number series
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Total items | 858 |
---|
Access status | |
---|
Open | 858 (100.00%) |
Number of items digitised | 858 (100.00%) |
---|
Number of pages digitised | 2,031 |
---|
Date of earliest content | 1897 |
---|
Date of latest content | 1903 |
---|
Download the complete CSV file
"
],
"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": 4,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" \n",
" \n",
" | \n",
" identifier | \n",
" series | \n",
" control_symbol | \n",
" title | \n",
" contents_dates | \n",
" start_date | \n",
" end_date | \n",
" access_status | \n",
" location | \n",
" digitised_status | \n",
" digitised_pages | \n",
"
\n",
" \n",
" 0 | \n",
" 5043565 | \n",
" J2481 | \n",
" 1898/1 | \n",
" Chan Fong | \n",
" 1898 - 1899 | \n",
" 1898-01-01 00:00:00 | \n",
" 1899-01-01 00:00:00 | \n",
" Open | \n",
" Brisbane | \n",
" True | \n",
" 2 | \n",
"
\n",
" 1 | \n",
" 5043566 | \n",
" J2481 | \n",
" 1898/2 | \n",
" Hong Sun | \n",
" 1898 - 1898 | \n",
" 1898-01-01 00:00:00 | \n",
" 1898-01-01 00:00:00 | \n",
" Open | \n",
" Brisbane | \n",
" True | \n",
" 2 | \n",
"
\n",
" 2 | \n",
" 5043567 | \n",
" J2481 | \n",
" 1898/3 | \n",
" Yong Gun | \n",
" 1898 - 1899 | \n",
" 1898-01-01 00:00:00 | \n",
" 1899-01-01 00:00:00 | \n",
" Open | \n",
" Brisbane | \n",
" True | \n",
" 2 | \n",
"
\n",
" 3 | \n",
" 5043568 | \n",
" J2481 | \n",
" 1898/4 | \n",
" Ah Pow | \n",
" 1898 - 1900 | \n",
" 1898-01-01 00:00:00 | \n",
" 1900-01-01 00:00:00 | \n",
" Open | \n",
" Brisbane | \n",
" True | \n",
" 2 | \n",
"
\n",
" 4 | \n",
" 5043569 | \n",
" J2481 | \n",
" 1898/5 | \n",
" Ah Choy | \n",
" 1898 - 1900 | \n",
" 1898-01-01 00:00:00 | \n",
" 1900-01-01 00:00:00 | \n",
" Open | \n",
" Brisbane | \n",
" True | \n",
" 3 | \n",
"
\n",
"
"
],
"text/plain": [
""
]
},
"execution_count": 4,
"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": 5,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.plotly.v1+json": {
"data": [
{
"name": "Digitised",
"type": "bar",
"x": [
1897,
1898,
1899,
1900,
1901,
1902,
1903
],
"y": [
1,
36,
404,
470,
279,
5,
3
]
}
],
"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": 6,
"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": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" \n",
" \n",
" | \n",
" word | \n",
" count | \n",
"
\n",
" \n",
" 6 | \n",
" ah | \n",
" 393 | \n",
"
\n",
" 24 | \n",
" lee | \n",
" 77 | \n",
"
\n",
" 35 | \n",
" sing | \n",
" 51 | \n",
"
\n",
" 14 | \n",
" sam | \n",
" 44 | \n",
"
\n",
" 10 | \n",
" chong | \n",
" 39 | \n",
"
\n",
" 71 | \n",
" wong | \n",
" 27 | \n",
"
\n",
" 3 | \n",
" sun | \n",
" 26 | \n",
"
\n",
" 11 | \n",
" kee | \n",
" 26 | \n",
"
\n",
" 53 | \n",
" correspondence | \n",
" 24 | \n",
"
\n",
" 38 | \n",
" wah | \n",
" 24 | \n",
"
\n",
" 69 | \n",
" lum | \n",
" 23 | \n",
"
\n",
" 49 | \n",
" young | \n",
" 23 | \n",
"
\n",
" 50 | \n",
" see | \n",
" 19 | \n",
"
\n",
" 25 | \n",
" yee | \n",
" 19 | \n",
"
\n",
" 23 | \n",
" hing | \n",
" 18 | \n",
"
\n",
" 0 | \n",
" chan | \n",
" 17 | \n",
"
\n",
" 58 | \n",
" gee | \n",
" 17 | \n",
"
\n",
" 41 | \n",
" hop | \n",
" 16 | \n",
"
\n",
" 238 | \n",
" chinese | \n",
" 15 | \n",
"
\n",
" 57 | \n",
" long | \n",
" 14 | \n",
"
\n",
" 130 | \n",
" low | \n",
" 14 | \n",
"
\n",
" 426 | \n",
" relating | \n",
" 14 | \n",
"
\n",
" 118 | \n",
" chew | \n",
" 14 | \n",
"
\n",
" 2 | \n",
" hong | \n",
" 13 | \n",
"
\n",
" 107 | \n",
" sue | \n",
" 13 | \n",
"
\n",
"
"
],
"text/plain": [
""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_details.display_word_counts(title_text)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" \n",
" \n",
" | \n",
" ngram | \n",
" count | \n",
"
\n",
" \n",
" 0 | \n",
" ah sam | \n",
" 24 | \n",
"
\n",
" 1 | \n",
" sing ah | \n",
" 19 | \n",
"
\n",
" 2 | \n",
" chong ah | \n",
" 17 | \n",
"
\n",
" 3 | \n",
" ah sing | \n",
" 16 | \n",
"
\n",
" 4 | \n",
" sam ah | \n",
" 15 | \n",
"
\n",
" 5 | \n",
" relating to | \n",
" 14 | \n",
"
\n",
" 6 | \n",
" correspondence relating | \n",
" 14 | \n",
"
\n",
" 7 | \n",
" lee ah | \n",
" 9 | \n",
"
\n",
" 8 | \n",
" ah wah | \n",
" 9 | \n",
"
\n",
" 9 | \n",
" ah kee | \n",
" 9 | \n",
"
\n",
" 10 | \n",
" yee ah | \n",
" 9 | \n",
"
\n",
" 11 | \n",
" ah foon | \n",
" 8 | \n",
"
\n",
" 12 | \n",
" ah young | \n",
" 8 | \n",
"
\n",
" 13 | \n",
" see ah | \n",
" 8 | \n",
"
\n",
" 14 | \n",
" ah see | \n",
" 8 | \n",
"
\n",
" 15 | \n",
" ah chong | \n",
" 8 | \n",
"
\n",
" 16 | \n",
" ah choy | \n",
" 8 | \n",
"
\n",
" 17 | \n",
" wah ah | \n",
" 8 | \n",
"
\n",
" 18 | \n",
" ah you | \n",
" 7 | \n",
"
\n",
" 19 | \n",
" gee ah | \n",
" 7 | \n",
"
\n",
" 20 | \n",
" hing ah | \n",
" 7 | \n",
"
\n",
" 21 | \n",
" ah yee | \n",
" 7 | \n",
"
\n",
" 22 | \n",
" ah gee | \n",
" 7 | \n",
"
\n",
" 23 | \n",
" sun ah | \n",
" 7 | \n",
"
\n",
" 24 | \n",
" ah lee | \n",
" 6 | \n",
"
\n",
"
"
],
"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": 10,
"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
}