%load_ext autoreload
%autoreload 2
%store -r the_page
%store -r agg_actions
%store -r calculator
%store -r editors_conflicts
if ('the_page' not in locals() or
'agg_actions' not in locals() or
'calculator' not in locals() or
'editors_conflicts' not in locals()):
import pickle
print("Loading default data...")
the_page = pickle.load(open("data/the_page.p",'rb'))
agg_actions = pickle.load(open("data/agg_actions.p",'rb'))
calculator = pickle.load(open("data/calculator.p",'rb'))
editors_conflicts = pickle.load(open("data/editors_conflicts.p",'rb'))
from IPython.display import display, Markdown as md
display(md("---"))
display(md(f"# A. Select an editor to analyze their activity in the context of ***{the_page['title']}***"))
display(md("""The table below presents the conflict score and other related metrics per editor
(*editor_id* and *editor* column):
- **conflict_n**: the total number of conflicts
- **conflict**: the sum of conflict scores of all actions (without division)
- **actions**: the total number of actions performed by the editor
- **conflict_score**: the sum of conflict scores of all actions divided by the number of elegible actions
- **conflict_ratio**: the count of all conflicts divided by the number of elegible actions
"""))
from visualization.conflicts_listener import ConflictsListener
from external.wikipedia import WikipediaDV, WikipediaAPI
graph_description = """
In the above graph you can select the *date range* and *granularity* (yearly, montly)
of the timeline (X-axis), and plot any of the following counts in the black and red lines:
- **Conflict Score**: the sum of conflict scores of all actions divided by the number of elegible actions
- **Absolute Conflict Score**: the sum of conflict scores of all actions (without division)
- **Conflict Ratio**: the count of all conflicts divided by the number of elegible actions
- **Number of Conflicts**: the total number of conflicts
- **Total Elegible Actions**: the total number of elegible actions
"""
def display_conflict_score(editor_df):
global listener
from visualization.conflicts_listener import ConflictsListener
listener = ConflictsListener(editor_df)
metrics = ['Conflict Score', 'Absolute Conflict Score',
'Conflict Ratio', 'Number of Conflicts',
'Total Elegible Actions']
#display(md(f'*Total Page conflict score: {calculator.get_page_conflict_score()}*'))
display(md(f'*Total Page conflict score: {editor_df.conflict.sum() / editor_df.elegibles.sum()}*'))
# Visualization
from utils.notebooks import get_date_slider_from_datetime
from ipywidgets import interact
from ipywidgets.widgets import Dropdown
interact(listener.listen,
#_range = get_date_slider_from_datetime(editor_df['rev_time']),
_range = get_date_slider_from_datetime(editor_df['year_month']),
granularity=Dropdown(options=['Yearly', 'Monthly', 'Daily'], value='Daily'),
black=Dropdown(options=metrics, value='Conflict Score'),
red=Dropdown(options= ['None'] + metrics, value='None'))
def select_editor(editor):
global editor_df
global the_editor
global editor_inputname
editor_inputname=editor
wikipedia_dv = WikipediaDV(WikipediaAPI(domain='en.wikipedia.org'))
try:
the_editor = wikipedia_dv.get_editor(int(editor_inputname))
except:
the_editor = wikipedia_dv.get_editor(editor_inputname[2:])
with out:
%store the_editor
%store editor_inputname
clear_output()
display(md("### Current Selection:"))
if 'invalid' in the_editor:
display(f"The editor {editor_inputname} was not found, try a different editor")
else:
# display the data that will be passed to the next notebook
display(the_editor.to_frame('values'))
display(md(f"#### Evolution of the Conflict Score of *{the_editor['name']}*"))
editor_df = agg_actions[agg_actions['editor_id'] == the_editor['userid']].copy()
#editor_df = calculator.elegible_actions[
#calculator.elegible_actions['editor'] == editor_inputname].copy()
display_conflict_score(editor_df)
def on_selection_change(change):
try:
select_editor(qg_obj.get_selected_df().iloc[0].name)
except:
print('Problem parsing the name. Execute the cell again and try a different editor.')
import qgrid
qgrid.set_grid_option('maxVisibleRows', 5)
qg_obj = qgrid.show_grid(editors_conflicts)
qg_obj.observe(on_selection_change, names=['_selected_rows'])
from ipywidgets import Output
from IPython.display import display, clear_output, Markdown as md
display(md("### Select one editor (row) to continue the demo:"))
display(md('**Recomendation:** select an editor with *many conflicts* and *mid-high conflict score*'))
display(qg_obj)
out = Output()
display(out)
display(md(graph_description))
# select an editor that does not contain 0| at the beginning
for ed in editors_conflicts.index:
if ed != 0:
select_editor(ed)
break
from ipywidgets import widgets
from IPython.display import display, Javascript
def run_below(ev):
display(Javascript('IPython.notebook.execute_cells_below()'))
button = widgets.Button(description="Refresh the rest of the notebook below", button_style='info', min_width=500)
button.on_click(run_below)
display(button)
from IPython.display import display, Markdown as md
display(md("---"))
display(md(f"# B. Activity of editor on a page"))
display(md(f"***Page: {the_page['title']}***"))
display(md(f"***Editor: {the_editor['name']}***"))
display(md("""In the following graph you can select the *date range* and *granularity* (yearly, montly)
of the timeline (X-axis), and plot any of the follow counts in the black, red, blue and green lines:
- **adds**: number of first-time insertions
- **adds_surv_48h**: number of insertions for the first time that survived at least 48 hours
- **adds_persistent**: number of insertions for the first time that survived until, at least, the end of the month
- **adds_stopword_count**: number of insertions that were stop words
- **dels**: number of deletions
- **dels_surv_48h**: number of deletions that were not resinserted in the next 48 hours
- **dels_persistent**: number of deletions that were not resinserted until, at least, the end of the month
- **dels_stopword_count**: number of deletions that were stop words
- **reins**: number of reinsertions
- **reins_surv_48h**: number of reinsertionsthat survived at least 48 hours
- **reins_persistent**: number of reinsertionsthat survived until the end of the month
- **reins_stopword_count**: number of reinsertionsthat were stop words
"""))
editor_agg_actions = agg_actions[agg_actions['editor_id']==the_editor.userid]
#Listener
from visualization.actions_listener import ActionsListener
listener = ActionsListener(editor_agg_actions)
actions = (editor_agg_actions.loc[:,'total':'total_stopword_count'].columns.append(
editor_agg_actions.loc[:,'adds':'reins_stopword_count'].columns)).values.tolist()
# Visualization
from utils.notebooks import get_date_slider_from_datetime
from ipywidgets import interact, fixed
from ipywidgets.widgets import Dropdown
_range = get_date_slider_from_datetime(editor_agg_actions['year_month'])
interact(listener.listen,
_range = get_date_slider_from_datetime(editor_agg_actions['year_month']),
editor=fixed('All'),
granularity=Dropdown(options=['Yearly', 'Monthly'], value='Monthly'),
black=Dropdown(options=actions, value='total'),
red=Dropdown(options= ['None'] + actions, value='total_surv_48h'),
green=Dropdown(options= ['None'] + actions, value='None'),
blue=Dropdown(options= ['None'] + actions, value='None'))
from IPython.display import display, Markdown as md
display(md("---"))
display(md(f"# C. Tokens that enter into conflict with other editors"))
display(md(f"***Page: {the_page['title']}***"))
display(md(f"***Editor: {the_editor['name']}***"))
display(md(""" The WordCloud displays the most common token strings (words) that a particular editor
inserted or deleted and that enter into conflict with other editors. The size of the token string in
the WordCloud indicates frequency of actions.
In the controls, you can select the *date range*, the type of *action* (insertion or deletion), and the
*source*. The *source* can be any of the following:
- **Only Conflicts**: use only the actions that are in conflict.
- **Elegible Actions**: use only the actions that can potentially enter into conflict, i.e. actions
that have occurred at least twice, e.g. the token x has been inserted twice (which necessarily implies
it was remove once), the token x has been deleted twice (which necessarily implies it was inserted twice)
- **All Actions**: use all tokens regardles conflict
"""))
sources = {
'All actions': calculator.all_actions[calculator.all_actions['editor']==str(editor_inputname)],
'Elegible Actions': calculator.elegible_actions[calculator.elegible_actions['editor']==str(editor_inputname)],
'Only Conflicts': calculator.conflicts[calculator.conflicts['editor']==str(editor_inputname)],
}
# listener
from visualization.wordcloud_listener import WCListener
listener = WCListener(sources)
# visualization
from utils.notebooks import get_date_slider_from_datetime
from ipywidgets import interact, fixed
from ipywidgets.widgets import Dropdown
interact(listener.listen,
_range=get_date_slider_from_datetime(calculator.all_actions['rev_time']),
source=Dropdown(options=list(listener.sources.keys()), value='Only Conflicts'),
action=Dropdown(options=['Both', 'Just Insertions', 'Just Deletions'], value='Both'),
editor=fixed('All'))
from IPython.display import display, Markdown as md
display(md("---"))
display(md(f"# D. Tokens in the page owner by the editor"))
display(md(f"***Page: {the_page['title']}***"))
display(md(f"***Editor: {the_editor['name']}***"))
display(md("""The following time line shows the token owned by this editor. The ownership
(or authorship) is based in the WikiWho algorithm (
[Flöck & Acosta, 2014](http://wwwconference.org/proceedings/www2014/proceedings/p843.pdf)).
The graph shows that it is possible to recover the amount of tokens that an editor at any
point of time. The time points are selected based on instances in which insertions or deletions
were perfomerd in the editor's tokens. However, notice that the percentages of ownership might
vary because percentages are relative to insertions or deletions of tokens of other editors.
This is why the current date is also included in the graph.
In the controls, you can select the *date range*, the *granularity* (Daily, Monthly, Yearly), and
the *metric* that will be plotted (Tokens Owned or Tokens Owned(%)).
"""))
from visualization.owned_listener import OwnedListener
all_actions = calculator.all_actions
listener = OwnedListener(all_actions, str(editor_inputname))
traces = ['Tokens Owned', 'Tokens Owned (%)']
# Visualization
from utils.notebooks import get_date_slider_from_datetime
from ipywidgets import interact
from ipywidgets.widgets import Dropdown
interact(listener.listen,
_range = get_date_slider_from_datetime(listener.days),
granularity=Dropdown(options=['Yearly', 'Monthly', 'Daily'], value='Monthly'),
trace=Dropdown(options=traces, value='Tokens Owned (%)', description='metric'))
from IPython.display import HTML
from utils.notebooks import get_next_notebook, get_previous_notebook
editor_actions = calculator.elegible_actions[calculator.elegible_actions['editor']==str(editor_inputname)]
if len(editor_actions) > 0:
display(HTML(f'<a href="{get_next_notebook()}" target="_blank">Go to next workbook</a>'))
else:
display(HTML('<h3>This editor has no actions. Please select an editor that has '
'actions to continue to the next notebook.</h3>'))