{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"series = 'E752'"
]
},
{
"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 E752
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Certificate Exempting from Dictation Test
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Total items | 722 |
---|
Access status | |
---|
Open | 719 (99.58%) |
Not yet examined | 3 (0.42%) |
Number of items digitised | 717 (99.31%) |
---|
Number of pages digitised | 9,310 |
---|
Date of earliest content | 1905 |
---|
Date of latest content | 1941 |
---|
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",
" 1591875 | \n",
" E752 | \n",
" 1916/1 | \n",
" [Certificate of Exemption from Dictation Test - Sun Took] | \n",
" 1916 - 1916 | \n",
" 1916-01-01 00:00:00 | \n",
" 1916-01-01 00:00:00 | \n",
" Open | \n",
" Darwin | \n",
" True | \n",
" 18 | \n",
"
\n",
" 1 | \n",
" 1591876 | \n",
" E752 | \n",
" 1916/2 | \n",
" [Certificate of Exemption from Dictation Test - Ah Young] | \n",
" 1918 - 1918 | \n",
" 1918-01-01 00:00:00 | \n",
" 1918-01-01 00:00:00 | \n",
" Open | \n",
" Darwin | \n",
" True | \n",
" 15 | \n",
"
\n",
" 2 | \n",
" 1591878 | \n",
" E752 | \n",
" 1916/3 | \n",
" [Certificate of Exemption from Dictation Test - Cheong Yee] | \n",
" 1918 - 1918 | \n",
" 1918-01-01 00:00:00 | \n",
" 1918-01-01 00:00:00 | \n",
" Open | \n",
" Darwin | \n",
" True | \n",
" 16 | \n",
"
\n",
" 3 | \n",
" 1591880 | \n",
" E752 | \n",
" 1916/4 | \n",
" [Certificate of Exemption from Dictation Test - Chin Dick] | \n",
" 1917 - 1917 | \n",
" 1917-01-01 00:00:00 | \n",
" 1917-01-01 00:00:00 | \n",
" Open | \n",
" Darwin | \n",
" True | \n",
" 15 | \n",
"
\n",
" 4 | \n",
" 1591883 | \n",
" E752 | \n",
" 1916/5 | \n",
" [Certificate of Exemption from Dictation Test - Chin See Koon] | \n",
" 1917 - 1917 | \n",
" 1917-01-01 00:00:00 | \n",
" 1917-01-01 00:00:00 | \n",
" Open | \n",
" Darwin | \n",
" True | \n",
" 15 | \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": [
1905,
1915,
1916,
1917,
1918,
1919,
1920,
1921,
1922,
1923,
1924,
1925,
1926,
1927,
1928,
1929,
1930,
1931,
1932,
1933,
1934,
1935,
1936,
1937,
1938,
1939,
1940,
1941
],
"y": [
1,
3,
63,
95,
42,
89,
75,
71,
68,
70,
44,
36,
42,
55,
66,
48,
39,
51,
40,
28,
27,
36,
25,
19,
20,
16,
5,
9
]
},
{
"name": "Not digitised",
"type": "bar",
"x": [
1916,
1917,
1929,
1931
],
"y": [
1,
1,
1,
2
]
}
],
"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",
" 1 | \n",
" exemption | \n",
" 714 | \n",
"
\n",
" 2 | \n",
" dictation | \n",
" 713 | \n",
"
\n",
" 3 | \n",
" test | \n",
" 713 | \n",
"
\n",
" 0 | \n",
" certificate | \n",
" 709 | \n",
"
\n",
" 10 | \n",
" chin | \n",
" 127 | \n",
"
\n",
" 6 | \n",
" ah | \n",
" 73 | \n",
"
\n",
" 33 | \n",
" fong | \n",
" 64 | \n",
"
\n",
" 17 | \n",
" gee | \n",
" 48 | \n",
"
\n",
" 37 | \n",
" lee | \n",
" 39 | \n",
"
\n",
" 138 | \n",
" sing | \n",
" 28 | \n",
"
\n",
" 42 | \n",
" yuen | \n",
" 26 | \n",
"
\n",
" 12 | \n",
" see | \n",
" 25 | \n",
"
\n",
" 66 | \n",
" kim | \n",
" 25 | \n",
"
\n",
" 9 | \n",
" yee | \n",
" 23 | \n",
"
\n",
" 115 | \n",
" wong | \n",
" 23 | \n",
"
\n",
" 16 | \n",
" sue | \n",
" 21 | \n",
"
\n",
" 46 | \n",
" wah | \n",
" 20 | \n",
"
\n",
" 29 | \n",
" chong | \n",
" 19 | \n",
"
\n",
" 22 | \n",
" hong | \n",
" 19 | \n",
"
\n",
" 45 | \n",
" low | \n",
" 17 | \n",
"
\n",
" 67 | \n",
" loong | \n",
" 15 | \n",
"
\n",
" 98 | \n",
" bow | \n",
" 14 | \n",
"
\n",
" 26 | \n",
" gum | \n",
" 14 | \n",
"
\n",
" 141 | \n",
" ming | \n",
" 14 | \n",
"
\n",
" 64 | \n",
" quan | \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",
" exemption from | \n",
" 714 | \n",
"
\n",
" 1 | \n",
" of exemption | \n",
" 714 | \n",
"
\n",
" 2 | \n",
" from dictation | \n",
" 713 | \n",
"
\n",
" 3 | \n",
" dictation test | \n",
" 710 | \n",
"
\n",
" 4 | \n",
" certificate of | \n",
" 708 | \n",
"
\n",
" 5 | \n",
" test chin | \n",
" 100 | \n",
"
\n",
" 6 | \n",
" test ah | \n",
" 54 | \n",
"
\n",
" 7 | \n",
" test fong | \n",
" 43 | \n",
"
\n",
" 8 | \n",
" test gee | \n",
" 32 | \n",
"
\n",
" 9 | \n",
" sing certificate | \n",
" 22 | \n",
"
\n",
" 10 | \n",
" test wong | \n",
" 22 | \n",
"
\n",
" 11 | \n",
" test lee | \n",
" 16 | \n",
"
\n",
" 12 | \n",
" test low | \n",
" 15 | \n",
"
\n",
" 13 | \n",
" see certificate | \n",
" 14 | \n",
"
\n",
" 14 | \n",
" yee certificate | \n",
" 13 | \n",
"
\n",
" 15 | \n",
" hong certificate | \n",
" 12 | \n",
"
\n",
" 16 | \n",
" yuen certificate | \n",
" 12 | \n",
"
\n",
" 17 | \n",
" kim certificate | \n",
" 11 | \n",
"
\n",
" 18 | \n",
" sue certificate | \n",
" 10 | \n",
"
\n",
" 19 | \n",
" test yuen | \n",
" 10 | \n",
"
\n",
" 20 | \n",
" fong certificate | \n",
" 10 | \n",
"
\n",
" 21 | \n",
" test loong | \n",
" 9 | \n",
"
\n",
" 22 | \n",
" way certificate | \n",
" 9 | \n",
"
\n",
" 23 | \n",
" test gum | \n",
" 9 | \n",
"
\n",
" 24 | \n",
" test ching | \n",
" 8 | \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": 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
}