Update dashboard.py

dashboard.py

@@ -8,351 +8,6 @@ import warnings
 warnings.simplefilter(action='ignore', category=FutureWarning)
 warnings.simplefilter(action='ignore', category=RuntimeWarning)
 import pandas as pd
-import warnings
-warnings.filterwarnings("ignore")
-import io
-import os
-import time
-import warnings
-warnings.simplefilter(action='ignore', category=FutureWarning)
-warnings.simplefilter(action='ignore', category=RuntimeWarning)
-import pandas as pd
-import csv
-import ast
-from tqdm import tqdm
-from operator import itemgetter
-import numpy as np
-import re
-import datetime
-import html
-from joblib import Parallel, delayed
-import matplotlib.pyplot as plt
-import matplotlib.dates as mdates
-#plt.style.use('seaborn-paper')
-import holoviews as hv
-from holoviews import opts, dim
-from bokeh.sampledata.les_mis import data
-from bokeh.io import show
-from bokeh.sampledata.les_mis import data
-import panel as pn
-#pn.extension(design='material')
-
-import bokeh
-from bokeh.resources import INLINE
-from holoviews.operation.timeseries import rolling, rolling_outlier_std
-hv.extension('bokeh')
-
-## LOAD DATASETS
-
-data = './data'
-
-
-def read_freq_map(filename):
-    df = pd.read_csv(os.path.join(data,filename), sep='	')
-    print(df)
-    if 'Unnamed: 0' in df.columns:
-        df = df.drop('Unnamed: 0', axis=1)
-    column_0 = df.columns[0]
-    column_1 = df.columns[1]
-    freqmap = dict(zip(df[column_0], df[column_1]))
-    return freqmap
-
-def read_ont_freq_dataframe(filename):
-    df = pd.read_csv(os.path.join(data,filename), sep='	')
-    print(df)
-    if 'Unnamed: 0' in df.columns:
-        df = df.drop('Unnamed: 0', axis=1)
-    column_0 = df.columns[0]
-    column_1 = df.columns[1]
-    freqmap = dict(zip(df[column_0], df[column_1]))
-    return freqmap
-
-
-entityTypesFreqMap = read_freq_map('entityTypes.tsv')
-relationTypesFreqMap = read_freq_map('relationTypes.tsv')
-topDrugEntities = read_freq_map('topDrugs.tsv')
-topConditionEntities = read_freq_map('topConditions.tsv')
-topDrugOnts_df = pd.read_csv(os.path.join(data,'topDrugOntologies.tsv'), sep='\t')
-topConditionOnts_df = pd.read_csv(os.path.join(data,'topConditionOntologies.tsv'), sep='\t')
-
-
-grouping_filtered = pd.read_csv(os.path.join(data, 'drugReviewsCausal_relations.tsv'), sep="	")
-
-
-
-################################# CREATE CHARTS ############################
-def create_type_bar_charts(entRelsButton, **kwargs):
-  if entRelsButton=='Entity':
-    dictionary = entityTypesFreqMap
-    return hv.Bars(dictionary, hv.Dimension('Entity Types'), 'Frequency').opts( framewise=True, xrotation=45,width=1200, height=600)
-  elif entRelsButton=='Relation':
-    dictionary = relationTypesFreqMap
-    return hv.Bars(dictionary, hv.Dimension('Relation Types'), 'Frequency').opts(framewise=True, xrotation=45,width=1200, height=600)
-
-
-def create_ent_bar_charts(ents, **kwargs):
-  if ents=='Drug':
-    dictionary = topDrugEntities
-    return hv.Bars(dictionary, hv.Dimension('Drug Entities'), 'Frequency').opts( framewise=True, xrotation=45,width=1200, height=600)
-  elif ents=='Condition':
-    dictionary = topConditionEntities
-    return hv.Bars(dictionary, hv.Dimension('Condition Entities'), 'Frequency').opts(framewise=True, xrotation=45,width=1200, height=600)
-
-def create_ontology_bar_charts(ents, **kwargs):
-  if ents=='Drug':
-    df = pd.DataFrame({
-        'Drug_Ontologies': [ont.split('/')[-1] for ont in topDrugOnts_df['ontology']],
-        'Frequency': list(topDrugOnts_df['count']),
-        'url': list(topDrugOnts_df['ontology_url'])  # using full keys as hyperlinks
-    })
-    # Create bar chart with label as x-axis
-    bars = hv.Bars(df, kdims=['Drug_Ontologies'], vdims=['Frequency'])
-    bars.opts(
-        framewise=True,
-        tools=['hover'],
-        width=1200,
-        height=600,
-        show_legend=True,
-        xrotation=45,
-        xlabel='Drug_Ontologies',
-        ylabel='Frequency',
-        hover_tooltips=[
-            ("Drug_Ontologies", "@Drug_Ontologies"),
-            ("Frequency", "@Frequency")
-        ]
-    )
-    links_panel = pn.Column(
-        *[pn.pane.Markdown(f"[{row.Drug_Ontologies}]({row.url})", width=400) for _, row in df.iterrows()],
-        name='Links'
-    )
-    layout = pn.Row(bars, links_panel)
-    return layout
-  elif ents=='Condition':
-    df = pd.DataFrame({
-          'Condition_Ontologies': [ont.split('/')[-1] for ont in topConditionOnts_df['ontology']],
-          'Frequency': list(topConditionOnts_df['count']),
-          'url': list(topConditionOnts_df['ontology_url'])  # using full keys as hyperlinks
-      })
-    # Create bar chart with label as x-axis
-    bars = hv.Bars(df, kdims=['Condition_Ontologies'], vdims=['Frequency'])
-    bars.opts(
-    framewise=True,
-    tools=['hover'],
-    width=1200,
-    height=600,
-    show_legend=True,
-    xrotation=45,
-    xlabel='Condition_Ontologies',
-    ylabel='Frequency',
-    hover_tooltips=[
-        ("Condition Ontologies", "@Condition Ontologies"),
-        ("Frequency", "@Frequency") ])
-    links_panel = pn.Column(
-    *[pn.pane.Markdown(f"[{row.Condition_Ontologies}]({row.url})", width=400) for _, row in df.iterrows()],
-    name='Links')
-    layout = pn.Row(bars, links_panel)
-    return layout
-
-############################# WIDGETS & CALLBACK ###########################################
-
-def filter_data0(df, min_value):
-    filtered_df = df[df['value'] >= min_value]
-    return filtered_df
-
-
-def plot_chord(df,min_value):
-    filtered_df = filter_data0(df, min_value)
-  # Create a Holoviews Dataset for nodes
-    nodes = hv.Dataset(filtered_df, 'index')
-    nodes.data.head()
-    chord = hv.Chord(filtered_df, ['source', 'target'], ['value'])
-    return chord.opts(opts.Chord(cmap='Category20', edge_cmap='Category20', label_text_color="white",  node_color = hv.dim('index').str(),  edge_color = hv.dim('source').str(), labels = 'index', tools=['hover'],   width=800, height=800))
-
-
-def chordify_triples(rel_grouping):
-     # Define range for minimum value slider
-    min_value_range = rel_grouping['value'].unique()
-    min_value_range.sort()
-
-    # Define HoloMap with minimum value and attribute as key dimensions
-    holomap = hv.HoloMap({min_value: plot_chord(rel_grouping, min_value)
-                          for min_value in min_value_range},
-                         kdims=['Show triples with support greater than']
-                         )
-    return holomap
-
-
-# https://tabler-icons.io/
-button1 = pn.widgets.Button(name="Introduction", button_type="warning", icon="file-info", styles={"width": "100%"})
-button2 = pn.widgets.Button(name="Entity/Relation Types:", button_type="warning",  icon="chart-histogram", styles={"width": "100%"})
-button3 = pn.widgets.Button(name="Top Key Entities", button_type="warning", icon="chart-bar", styles={"width": "100%"})
-button4 = pn.widgets.Button(name="Ontology Coverage", button_type="warning", icon="chart-dots-filled", styles={"width": "100%"})
-button5 = pn.widgets.Button(name="Causal Relation Chord Diagrams", button_type="warning", icon="chart-dots-filled", styles={"width": "100%"})
-# Define child buttons
-child_button_1 = pn.widgets.Button(name="Cause", button_type="warning")
-child_button_2 = pn.widgets.Button(name="Enable", button_type="warning")
-child_button_3 = pn.widgets.Button(name="Prevent", button_type="warning")
-child_button_4 = pn.widgets.Button(name="Hinder", button_type="warning")
-child_button_5 = pn.widgets.Button(name="Other", button_type="warning")
-# Layout: dendrogram-style using vertical + indent
-tree_layout = pn.Column(
-    button5,
-    pn.Row(pn.Spacer(width=40),  # indent
-           pn.Column(child_button_1, child_button_2,child_button_3,child_button_4, child_button_5))
-)
-
-entRelsButton = pn.widgets.RadioButtonGroup(name='### Select', options=['Entity','Relation'], value = 'Entity' )
-
-entTypeButton = pn.widgets.RadioButtonGroup(name='### Select Entity Type', options=list(entityTypesFreqMap.keys()), value='Drug')
-
-#relationTypeButton = pn.widgets.RadioButtonGroup(options=list(relationTypesFreqMap.keys()), value='Cause', name='Select Causal Relation')
-
-# Define the callback function to update the HoloMap
-#def update_holomap(event):
-#    initial_holomap.object = filter_triples(event.new)
-
-
-# Create the initial HoloMap
-#initial_holomap = filter_triples(relationTypeButton.value)
-
-# Bind the callback function to the value change event of the RadioButton widget
-#relationTypeButton.param.watch(update_holomap, 'value')
-
-
-def show_page(page_key):
-    main_area.clear()
-    main_area.append(mapping[page_key])
-
-button1.on_click(lambda event: show_page("Page1"))
-button2.on_click(lambda event: show_page("Page2"))
-button3.on_click(lambda event: show_page("Page3"))
-button4.on_click(lambda event: show_page("Page4"))
-button5.on_click(lambda event: show_page("Page5"))
-child_button_1.on_click(lambda event: show_page("Page5a"))
-child_button_2.on_click(lambda event: show_page("Page5b"))
-child_button_3.on_click(lambda event: show_page("Page5c"))
-child_button_4.on_click(lambda event: show_page("Page5d"))
-child_button_5.on_click(lambda event: show_page("Page5e"))
-
-
-### CREATE PAGE LAYOUTS
-
-def CreatePage1():
-    return pn.Column(pn.pane.Markdown("""
-
-This is a dashboard for exploring a causal relation knowledge graph automatically extracted from a collection of drug reviews. The source data consists of around 19200 reviews from the **Drug Reviews (Druglib.com)**  dataset (https://archive.ics.uci.edu/dataset/461/drug+review+dataset+druglib+com) containing patient reviews on specific drugs along with related conditions, crawled from online pharmaceutical review sites.
-The causal relations represented in the KG are defined by the **MIMICause** schema (https://huggingface.co/datasets/pensieves/mimicause). The underlying CausalDrugsKG graph is available in Turtle and RDF serialization format in the European Data portal: https://data.jrc.ec.europa.eu/dataset/acebeb4e-9789-4b5c-97ec-292ce14e75d0.
-
-
----------------------------
-
-## Entities/Relation Types 
-Bar plots of the Entity and Relation type counts.
-
-## Top Key Entities
-Bar plots representing the occurence counts of the top 30 Entities in the KG, where occurrence means the entity is either the Subject or Object of an extracted triple in the KG.
-
-## Causal Relations Chord Diagrams
-Entity Chord Diagrams represent the most frequently connected entity pairs within the KG through chord illustrations, serving as both Subjects and Objects of predicative triples. The size of the chords corresponds to the support of the depicted relations.
-""", width=800), align="center")
-
-def CreatePage2():
-    return pn.Column(
-        pn.pane.Markdown("## Entity/Relation Types "),
-    entRelsButton,
-        pn.bind(create_type_bar_charts, entRelsButton),
-        align="center",
-    )
-
-def CreatePage3():
-    return pn.Column(
-        pn.pane.Markdown("## Top Entities "),
-        entTypeButton,
-        pn.bind(create_ent_bar_charts, entTypeButton),
-        align="center", )
-def CreatePage4():
-    return pn.Column(
-        pn.pane.Markdown("## Bio Ontology Coverage "),
-        entTypeButton,
-        pn.bind(create_ontology_bar_charts, entTypeButton),
-        align="center", )
-def CreatePage5():
-    return pn.Column(
-        pn.pane.Markdown("## Causal Relation Chord Diagrams"),
-        chordify_triples(grouping_filtered),
-        align="center", )
-
-def CreatePage5a():
-    rel_grouping = grouping_filtered[grouping_filtered['causal_relation'] == 'Cause']
-    return pn.Column(
-        pn.pane.Markdown("## Cause Relation Chord Diagrams"),
-        chordify_triples(rel_grouping),
-        align="center", )
-
-def CreatePage5b():
-    rel_grouping = grouping_filtered[grouping_filtered['causal_relation'] == 'Enable']
-    return pn.Column(
-        pn.pane.Markdown("## Enable Relation Chord Diagrams"),
-        chordify_triples(rel_grouping),
-        align="center", )
-
-def CreatePage5c():
-    rel_grouping = grouping_filtered[grouping_filtered['causal_relation'] == 'Prevent']
-    return pn.Column(
-        pn.pane.Markdown("## Prevent Relation Chord Diagrams"),
-        chordify_triples(rel_grouping),
-        align="center", )
-
-def CreatePage5d():
-    rel_grouping = grouping_filtered[grouping_filtered['causal_relation'] == 'Hinder']
-    return pn.Column(
-        pn.pane.Markdown("## Hinder Relation Chord Diagrams"),
-        chordify_triples(rel_grouping),
-        align="center", )
-
-def CreatePage5e():
-    rel_grouping = grouping_filtered[grouping_filtered['causal_relation'] == 'Other']
-    return pn.Column(
-        pn.pane.Markdown("## Causal Relation Chord Diagrams"),
-        chordify_triples(rel_grouping),
-        align="center", )
-mapping = {
-    "Page1": CreatePage1(),
-    "Page2": CreatePage2(),
-    "Page3": CreatePage3(),
-    "Page4": CreatePage4(),
-    "Page5": CreatePage5(),
-    "Page5a": CreatePage5a(),
-    "Page5b": CreatePage5b(),
-    "Page5c": CreatePage5c(),
-    "Page5d": CreatePage5d(),
-    "Page5e": CreatePage5e(),
-}
-
-#################### SIDEBAR LAYOUT ##########################
-sidebar = pn.Column(pn.pane.Markdown("## Panels"), button1,button2,button3,
-                    button4,tree_layout,
-                   styles={"width": "100%", "padding": "15px"})
-
-#################### MAIN AREA LAYOUT ##########################
-main_area = pn.Column(mapping["Page1"], styles={"width":"100%"})
-
-###################### APP LAYOUT ##############################
-template = pn.template.BootstrapTemplate(
-    title=" CausalDrugsKG_Dashboard ",
-    sidebar=[sidebar],
-    main=[main_area],
-    #header_background="black",
-    #site="Charting the Landscape of Digital Health",
-    #theme=pn.template.DarkTheme,
-    sidebar_width=270, ## Default is 330
-    busy_indicator=pn.indicators.BooleanStatus(value=True),
-)
-
-### DEPLOY APP
-
-# Serve the Panel app
-template.servable()
 import csv
 import ast
 from tqdm import tqdm
@@ -385,7 +40,7 @@ data = './data'
 
 def read_freq_map(filename):
     df = pd.read_csv(os.path.join(data,filename), sep='	')
-    print(df)
+    #print(df)
     if 'Unnamed: 0' in df.columns:
         df = df.drop('Unnamed: 0', axis=1)
     column_0 = df.columns[0]
@@ -395,7 +50,7 @@ def read_freq_map(filename):
 
 def read_ont_freq_dataframe(filename):
     df = pd.read_csv(os.path.join(data,filename), sep='	')
-    print(df)
+    #print(df)
     if 'Unnamed: 0' in df.columns:
         df = df.drop('Unnamed: 0', axis=1)
     column_0 = df.columns[0]