{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"series = 'D1902'"
]
},
{
"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 D1902
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Nominal Index cards to investigation case files.
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Total items | 3 |
---|
Access status | |
---|
Open | 3 (100.00%) |
Number of items digitised | 0 (0.00%) |
---|
Number of pages digitised | 0 |
---|
Date of earliest content | 1920 |
---|
Date of latest content | 1960 |
---|
"
],
"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",
" 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",
" 441930 | \n",
" D1902 | \n",
" 5227 | \n",
" Daniel PETROS | \n",
" 1938 - 1938 | \n",
" 1938-01-01 00:00:00 | \n",
" 1938-01-01 00:00:00 | \n",
" Open | \n",
" Adelaide | \n",
" False | \n",
" 0 | \n",
"
\n",
" 1 | \n",
" 441931 | \n",
" D1902 | \n",
" SA28038 | \n",
" LP Cutts | \n",
" 1954 - 1954 | \n",
" 1954-01-01 00:00:00 | \n",
" 1954-01-01 00:00:00 | \n",
" Open | \n",
" Adelaide | \n",
" False | \n",
" 0 | \n",
"
\n",
" 2 | \n",
" 943006 | \n",
" D1902 | \n",
" WHOLE SERIES | \n",
" Nominal index cards to investigation case files | \n",
" 1920 - 1960 | \n",
" 1920-01-01 00:00:00 | \n",
" 1960-01-01 00:00:00 | \n",
" Open | \n",
" Adelaide | \n",
" False | \n",
" 0 | \n",
"
\n",
"
"
],
"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": "Not digitised",
"type": "bar",
"x": [
1920,
1921,
1922,
1923,
1924,
1925,
1926,
1927,
1928,
1929,
1930,
1931,
1932,
1933,
1934,
1935,
1936,
1937,
1938,
1939,
1940,
1941,
1942,
1943,
1944,
1945,
1946,
1947,
1948,
1949,
1950,
1951,
1952,
1953,
1954,
1955,
1956,
1957,
1958,
1959,
1960
],
"y": [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
2,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
2,
1,
1,
1,
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": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/tim/mycode/ozglam-workbench-naa-asio/lib/python3.6/site-packages/pandas/io/formats/style.py:939: RuntimeWarning:\n",
"\n",
"divide by zero encountered in long_scalars\n",
"\n"
]
},
{
"data": {
"text/html": [
" \n",
" \n",
" \n",
" | \n",
" word | \n",
" count | \n",
"
\n",
" \n",
" 0 | \n",
" daniel | \n",
" 1 | \n",
"
\n",
" 1 | \n",
" petros | \n",
" 1 | \n",
"
\n",
" 2 | \n",
" lp | \n",
" 1 | \n",
"
\n",
" 3 | \n",
" cutts | \n",
" 1 | \n",
"
\n",
" 4 | \n",
" nominal | \n",
" 1 | \n",
"
\n",
" 5 | \n",
" index | \n",
" 1 | \n",
"
\n",
" 6 | \n",
" cards | \n",
" 1 | \n",
"
\n",
" 7 | \n",
" investigation | \n",
" 1 | \n",
"
\n",
" 8 | \n",
" case | \n",
" 1 | \n",
"
\n",
" 9 | \n",
" files | \n",
" 1 | \n",
"
\n",
"
"
],
"text/plain": [
""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_details.display_word_counts(title_text)"
]
},
{
"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
}