series = 'A9105'
import os
import pandas as pd
import series_details
import plotly.offline as py
py.init_notebook_mode()
df = pd.read_csv(os.path.join('data', '{}.csv'.format(series.replace('/', '-'))), parse_dates=['start_date', 'end_date'])
series_details.display_summary(series, df)
Total items | 1 |
---|---|
Access status | |
Open | 1 (100.00%) |
Number of items digitised | 0 (0.00%) |
Number of pages digitised | 0 |
Date of earliest content | 1991 |
Date of latest content | 1991 |
# Change the number_of_rows value to see more
number_of_rows = 5
# Display dataframe
df[:number_of_rows].style.set_properties(['title'], **{'text-align': 'left'}).set_table_styles([dict(selector="th", props=[("text-align", "center")]),
dict(selector='.row_heading, .blank', props=[('display', 'none')])])
identifier | series | control_symbol | title | contents_dates | start_date | end_date | access_status | location | digitised_status | digitised_pages | |
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 868925 | A9105 | WHOLE SERIES | Subject list of files in CRS A8911, correspondence files of the Commonwealth Investigation Service | 1991 - 1991 | 1991-01-01 00:00:00 | 1991-01-01 00:00:00 | Open | Canberra | False | 0 |
fig = series_details.plot_dates(df)
py.iplot(fig, filename='series-dates-bar')
# Combine all of the file titles into a single string
title_text = a = df['title'].str.lower().str.cat(sep=' ')
series_details.display_word_counts(title_text)
word | count | |
---|---|---|
2 | files | 2 |
0 | subject | 1 |
1 | list | 1 |
3 | crs | 1 |
4 | a8911 | 1 |
5 | correspondence | 1 |
6 | commonwealth | 1 |
7 | investigation | 1 |
8 | service | 1 |