From a8d388a1c131c341b8659b4eae830950a5233f9f Mon Sep 17 00:00:00 2001
From: Caroline DE POURTALES <cdepourt@montana.irit.fr>
Date: Mon, 25 Apr 2022 15:07:51 +0200
Subject: [PATCH] update
---
Procfile | 1 +
app.py | 25 +-
assets/course_data_format.html | 40 +++
assets/course_decision_tree.html | 14 +
assets/header.css | 2 +
assets/welcome.html | 12 +
callbacks.py | 86 +++---
.../DecisionTree/DecisionTreeComponent.py | 1 +
pages/application/DecisionTree/utils/dtree.py | 66 ++--
pages/application/DecisionTree/utils/dtviz.py | 289 ++++++++----------
pages/application/application.py | 34 +--
requirements.txt | 41 +--
runtime.txt | 1 +
utils.py | 7 +-
14 files changed, 359 insertions(+), 260 deletions(-)
create mode 100644 Procfile
create mode 100644 assets/course_data_format.html
create mode 100644 assets/course_decision_tree.html
create mode 100644 assets/welcome.html
create mode 100644 runtime.txt
diff --git a/Procfile b/Procfile
new file mode 100644
index 0000000..b308fd8
--- /dev/null
+++ b/Procfile
@@ -0,0 +1 @@
+web: gunicorn app:server
\ No newline at end of file
diff --git a/app.py b/app.py
index d4becfd..41087dc 100644
--- a/app.py
+++ b/app.py
@@ -10,7 +10,7 @@ from callbacks import register_callbacks
from pages.application.application import Application, Model, View
from utils import extract_data
-app = dash.Dash(external_stylesheets=[dbc.themes.LUX], suppress_callback_exceptions=True,
+app = dash.Dash(__name__, external_stylesheets=[dbc.themes.LUX], suppress_callback_exceptions=True,
meta_tags=[{'name': 'viewport', 'content': 'width=device-width, initial-scale=1'}])
#################################################################################
@@ -20,15 +20,34 @@ models_data = open('data_retriever.json')
data = json.load(models_data)["data"]
# For home directory
-page_home = dbc.Row([html.H3("Welcome")])
+welcome_message = html.Div(html.Iframe(
+ src=app.get_asset_url("welcome.html"),
+ style={"height": "1067px", "width": "100%"},
+))
+page_home = dbc.Row([welcome_message])
+
# For course directory
-page_course = dbc.Row([])
+course_data_format = html.Div(html.Iframe(
+ src=app.get_asset_url("course_data_format.html"),
+ style={"height": "1067px", "width": "100%"},
+))
+course_decision_tree = html.Iframe(
+ src="assets/course_decision_tree.html",
+ style={"height": "1067px", "width": "100%"},
+)
+main_course = dcc.Tabs(children=[
+ dcc.Tab(label='Data format', children=[course_data_format]),
+ dcc.Tab(label='Course Decision Tree', children=[course_decision_tree])])
+page_course = dbc.Row([main_course])
+
# For the application
names_models, dict_components, dic_solvers, dic_xtypes = extract_data(data)
model_application = Model(names_models, dict_components, dic_solvers, dic_xtypes)
view_application = View(model_application)
page_application = Application(view_application)
+server = app.server
+
app.layout = html.Div([
dcc.Location(id='url', refresh=False),
html.Nav(id='navbar-container',
diff --git a/assets/course_data_format.html b/assets/course_data_format.html
new file mode 100644
index 0000000..59a3085
--- /dev/null
+++ b/assets/course_data_format.html
@@ -0,0 +1,40 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <title>What kinf of model, data, or instance can I upload ?</title>
+</head>
+<body>
+
+<h1> Data format requirements</h1>
+
+<h2> An option to add information on model </h2>
+
+<h3> Why ? </h3>
+<p> There is a switch button, you can use it when you want to attach the csv you trained your model on or a feature mapping. This is useful when the values are categorical.
+</p>
+
+<h3> How ? </h3>
+
+<p> If you decide to upload the dataset, it should be a .csv.
+If you decide to upload the feature mapping, it is a .txt file.
+</p>
+
+<h2> What kind of model can I upload ? </h2>
+
+<p> You can only import .pkl models.</p>
+
+<h2> What should the format of the instance be ? </h2>
+
+<p> You can either upload a .txt file containing hte instance with the format : feature1=value1,feature2=value2,... where feature1, feature2 are the names of the columns.
+
+But you can also upload a json of your instance.</p>
+
+<p> Attention !!!! If you never mention the feature names in your model or additional information, the instance should be of format : f1=...,f2=... precisely</p>
+
+<h1> What are the advanced parameters ? </h1>
+
+<p> These are specific to the kind of model you selected, it would mainly be how the explanation should be computed and the kind of explanation.</p>
+
+</body>
+</html>
\ No newline at end of file
diff --git a/assets/course_decision_tree.html b/assets/course_decision_tree.html
new file mode 100644
index 0000000..b07a373
--- /dev/null
+++ b/assets/course_decision_tree.html
@@ -0,0 +1,14 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <title>What kinf of model, data, or instance can I upload ?</title>
+</head>
+<body>
+
+<h1> What library am I able to use on the platform ?</h1>
+
+<p> Only models from scikit-learn are allowed.</p>
+
+</body>
+</html>
\ No newline at end of file
diff --git a/assets/header.css b/assets/header.css
index 3a882ea..9005062 100644
--- a/assets/header.css
+++ b/assets/header.css
@@ -1,3 +1,5 @@
+
+
/* NAVBAR */
.navbar-dark .navbar-brand {
diff --git a/assets/welcome.html b/assets/welcome.html
new file mode 100644
index 0000000..ff97227
--- /dev/null
+++ b/assets/welcome.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <title>What kinf of model, data, or instance can I upload ?</title>
+</head>
+<body>
+
+<h1> Welcome </h1>
+
+</body>
+</html>
\ No newline at end of file
diff --git a/callbacks.py b/callbacks.py
index 438d511..d832b6e 100644
--- a/callbacks.py
+++ b/callbacks.py
@@ -28,19 +28,40 @@ def register_callbacks(page_home, page_course, page_application, app):
return active_link[0], active_link[1], active_link[2]
@app.callback(Output('solver_sat', 'options'),
+ Output('solver_sat', 'value'),
Output('explanation_type', 'options'),
+ Output('explanation_type', 'value'),
Input('ml_model_choice', 'value'),
prevent_initial_call=True
)
def update_ml_type_options(value_ml_model):
model_application = page_application.model
model_application.update_ml_model(value_ml_model)
- return model_application.solvers, model_application.xtypes
+ return model_application.solvers, model_application.solvers[0], model_application.xtypes, [
+ list(model_application.xtypes.keys())[0]]
+
+ @app.callback(Output('pretrained_model_filename', 'children'),
+ Input('ml_pretrained_model_choice', 'filename'),
+ prevent_initial_call=True
+ )
+ def update_model_prertrained_name(pretrained_model_filename):
+ return pretrained_model_filename
+
+ @app.callback(Output('info_filename', 'children'),
+ Input('model_info_choice', 'filename'),
+ prevent_initial_call=True
+ )
+ def update_model_info_filename(model_info_filename):
+ return model_info_filename
+
+ @app.callback(Output('instance_filename', 'children'),
+ Input('ml_instance_choice', 'filename'),
+ prevent_initial_call=True
+ )
+ def update_instance_filename(instance_filename):
+ return instance_filename
@app.callback(
- Output('pretrained_model_filename', 'children'),
- Output('info_filename', 'children'),
- Output('instance_filename', 'children'),
Output('graph', 'children'),
Output('explanation', 'children'),
Input('ml_model_choice', 'value'),
@@ -68,7 +89,7 @@ def register_callbacks(page_home, page_course, page_application, app):
# Choice of model
if ihm_id == 'ml_model_choice':
model_application.update_ml_model(value_ml_model)
- return None, None, None, None, None
+ return None, None
# Choice of pkl pretrained model
elif ihm_id == 'ml_pretrained_model_choice':
@@ -78,17 +99,22 @@ def register_callbacks(page_home, page_course, page_application, app):
model_application.update_pretrained_model(graph)
if not model_application.add_info:
model_application.update_pretrained_model_layout()
- return pretrained_model_filename, None, None, model_application.component.network, None
+ return model_application.component.network, None
else:
- return pretrained_model_filename, None, None, None, None
+ if model_application.model_info is None:
+ raise PreventUpdate
+ model_application.update_pretrained_model_layout_with_info(model_application.model_info,
+ model_info_filename)
+ return model_application.component.network, None
# Choice of information for the model
elif ihm_id == 'model_info_choice':
- if model_application.ml_model is None:
- raise PreventUpdate
model_info = parse_contents_data(model_info, model_info_filename)
+ model_application.model_info = model_info
+ if model_application.ml_model is None or model_application.pretrained_model is None:
+ raise PreventUpdate
model_application.update_pretrained_model_layout_with_info(model_info, model_info_filename)
- return pretrained_model_filename, model_info_filename, None, model_application.component.network, None
+ return model_application.component.network, None
# Choice of instance to explain
elif ihm_id == 'ml_instance_choice':
@@ -96,50 +122,42 @@ def register_callbacks(page_home, page_course, page_application, app):
raise PreventUpdate
instance = parse_contents_instance(instance_contents, instance_filename)
model_application.update_instance(instance)
- return pretrained_model_filename, model_info_filename, instance_filename, model_application.component.network, model_application.component.explanation
+ return model_application.component.network, model_application.component.explanation
- # Choice of number of expls
+ # Choice of number of expls
elif ihm_id == 'number_explanations':
- if model_application.ml_model is None or model_application.pretrained_model is None or len(
- model_application.instance) == 0 or model_application.xtype is None:
+ if model_application.ml_model is None or model_application.pretrained_model is None or model_application.instance is None or model_application.solver is None or model_application.xtype is None:
raise PreventUpdate
model_application.update_enum(enum)
- return pretrained_model_filename, model_info_filename, instance_filename, model_application.component.network, model_application.component.explanation
+ return model_application.component.network, model_application.component.explanation
- # Choice of AxP or CxP
+ # Choice of AxP or CxP
elif ihm_id == 'explanation_type':
- if model_application.ml_model is None or model_application.pretrained_model is None or len(
- model_application.instance) == 0 or model_application.enum <= 0:
+ if model_application.ml_model is None or model_application.pretrained_model is None or model_application.instance is None or model_application.enum <= 0 or model_application.solver is None:
raise PreventUpdate
model_application.update_xtype(xtype)
- return pretrained_model_filename, model_info_filename, instance_filename, model_application.component.network, model_application.component.explanation
+ return model_application.component.network, model_application.component.explanation
- # Choice of solver
+ # Choice of solver
elif ihm_id == 'solver_sat':
- if model_application.ml_model is None or model_application.pretrained_model is None or len(
- model_application.instance) == 0 or model_application.enum <= 0 or len(
- model_application.xtype) == 0:
+ if model_application.ml_model is None or model_application.pretrained_model is None or model_application.instance is None or model_application.enum <= 0 or model_application.xtype is None:
raise PreventUpdate
model_application.update_solver(solver)
- return pretrained_model_filename, model_info_filename, instance_filename, model_application.component.network, model_application.component.explanation
+ return model_application.component.network, model_application.component.explanation
- # Choice of AxP to draw
+ # Choice of AxP to draw
elif ihm_id == 'expl_choice':
- if model_application.ml_model is None or model_application.pretrained_model is None or len(
- model_application.instance) == 0 or model_application.enum <= 0 or len(
- model_application.xtype) == 0:
+ if model_application.ml_model is None or model_application.pretrained_model is None or model_application.instance is None or model_application.enum <= 0 or model_application.xtype is None:
raise PreventUpdate
model_application.update_expl(expl_choice)
- return pretrained_model_filename, model_info_filename, instance_filename, model_application.component.network, model_application.component.explanation
+ return model_application.component.network, model_application.component.explanation
- # Choice of CxP to draw
+ # Choice of CxP to draw
elif ihm_id == 'cont_expl_choice':
- if model_application.ml_model is None or model_application.pretrained_model is None or len(
- model_application.instance) == 0 or model_application.enum <= 0 or len(
- model_application.xtype) == 0:
+ if model_application.ml_model is None or model_application.pretrained_model is None or model_application.instance is None or model_application.enum <= 0 or model_application.xtype is None:
raise PreventUpdate
model_application.update_cont_expl(cont_expl_choice)
- return pretrained_model_filename, model_info_filename, instance_filename, model_application.component.network, model_application.component.explanation
+ return model_application.component.network, model_application.component.explanation
@app.callback(
Output('explanation', 'hidden'),
diff --git a/pages/application/DecisionTree/DecisionTreeComponent.py b/pages/application/DecisionTree/DecisionTreeComponent.py
index c177652..edb89a4 100644
--- a/pages/application/DecisionTree/DecisionTreeComponent.py
+++ b/pages/application/DecisionTree/DecisionTreeComponent.py
@@ -119,6 +119,7 @@ class DecisionTreeComponent():
instance_translated = self.translate_instance(instance)
self.explanation = []
list_explanations_path = []
+ list_contrastive_explanations_path = []
explanation = self.dt.explain(instance_translated, enum=enum, xtype=xtype, solver=solver)
dot_source = visualize_instance(self.dt, instance_translated)
diff --git a/pages/application/DecisionTree/utils/dtree.py b/pages/application/DecisionTree/utils/dtree.py
index c2775df..b67d26d 100644
--- a/pages/application/DecisionTree/utils/dtree.py
+++ b/pages/application/DecisionTree/utils/dtree.py
@@ -1,5 +1,5 @@
#!/usr/bin/env python
-#-*- coding:utf-8 -*-
+# -*- coding:utf-8 -*-
##
## dtree.py
##
@@ -9,7 +9,7 @@
##
#
-#==============================================================================
+# ==============================================================================
from __future__ import print_function
import collections
from functools import reduce
@@ -25,6 +25,7 @@ except ImportError: # for Python3
from sklearn.tree import _tree
import numpy as np
+
class Node():
"""
Node class.
@@ -38,8 +39,9 @@ class Node():
self.feat = feat
self.vals = vals
+
#
-#==============================================================================
+# ==============================================================================
class DecisionTree():
"""
Simple decision tree class.
@@ -62,14 +64,14 @@ class DecisionTree():
self.feids = {}
self.fdoms = {}
self.fvmap = {}
- self.feature_names = {f'f{i}' : feature_names[i] for i, f in enumerate(feature_names)}
+ self.feature_names = {f'f{i}': feature_names[i] for i, f in enumerate(feature_names)}
# OHE mapping
OHEMap = collections.namedtuple('OHEMap', ['dir', 'opp'])
self.ohmap = OHEMap(dir={}, opp={})
if from_dt:
- self.from_dt(from_dt)
+ self.from_dt(from_dt)
if mapfile:
self.parse_mapping(mapfile)
@@ -103,7 +105,7 @@ class DecisionTree():
self.terms = {}
for i in range(self.nof_terms):
nd, _, t = lines[i + 4].strip().split()
- self.terms[int(nd)] = t #int(t)
+ self.terms[int(nd)] = t # int(t)
# finally, reading the nodes
self.nodes = collections.defaultdict(lambda: Node(feat='', vals={}))
@@ -132,7 +134,7 @@ class DecisionTree():
# simplifying the features and their domains
self.feats = sorted(self.feats)
- #self.feids = {f: i for i, f in enumerate(self.feats)}
+ # self.feids = {f: i for i, f in enumerate(self.feats)}
self.fdoms = {f: sorted(self.fdoms[f]) for f in self.fdoms}
# here we assume all features are present in the tree
@@ -175,10 +177,10 @@ class DecisionTree():
for line in lines[1:]:
feat, val, real = line.split()
self.fvmap[tuple([feat, int(val)])] = '{0}{1}'.format(self.feature_names[feat], real)
- #if feat not in self.feids:
+ # if feat not in self.feids:
# self.feids[feat] = len(self.feids)
- #assert len(self.feids) == self.nof_feats
+ # assert len(self.feids) == self.nof_feats
def convert_to_multiedges(self):
"""
@@ -324,34 +326,38 @@ class DecisionTree():
# returning the set of sets with no duplicates
return list(dict.fromkeys(sets))
- def explain(self, inst, enum=1, pathlits=False, xtype = ["AXp"], solver='g3', htype='sorted'):
+ def explain(self, inst, enum=1, pathlits=False, xtype=["AXp"], solver='g3', htype='sorted'):
"""
Compute a given number of explanations.
"""
- #contaiins all the elements for explanation
+ # contaiins all the elements for explanation
explanation_dic = {}
self.feids = {f'f{i}': i for i, f in enumerate(inst)}
- inst = [(f'f{i}', int(inst[i][1])) for i,f in enumerate(inst)]
+ inst = [(f'f{i}', int(inst[i][1])) for i, f in enumerate(inst)]
path, term, depth = self.execute(inst, pathlits)
- #decision path
- decision_path_str = 'IF {0} THEN class={1}'.format(' AND '.join([self.fvmap[inst[self.feids[self.nodes[n].feat]]] for n in path]), term)
+ # decision path
+ decision_path_str = 'IF {0} THEN class={1}'.format(
+ ' AND '.join([self.fvmap[inst[self.feids[self.nodes[n].feat]]] for n in path]), term)
explanation_dic["Decision path of instance : "] = decision_path_str
- explanation_dic["Decision path length : "] = 'Path length is :'+ str(depth)
+ explanation_dic["Decision path length : "] = 'Path length is :' + str(depth)
if self.ohmap.dir:
f2v = {fv[0]: fv[1] for fv in inst}
# updating fvmap for printing ohe features
for fo, fis in self.ohmap.dir.items():
- self.fvmap[tuple([fo, None])] = '(' + ' AND '.join([self.fvmap[tuple([fi, f2v[fi]])] for fi in fis]) + ')'
+ self.fvmap[tuple([fo, None])] = '(' + ' AND '.join(
+ [self.fvmap[tuple([fi, f2v[fi]])] for fi in fis]) + ')'
# computing the sets to hit
to_hit = self.prepare_sets(inst, term)
- for type in xtype :
+ explanation_dic["List of path explanation(s)"] = []
+ explanation_dic["List of path contrastive explanation(s)"] = []
+ for type in xtype:
if type == "AXp":
explanation_dic.update(self.enumerate_abductive(to_hit, enum, solver, htype, term))
- else :
+ else:
explanation_dic.update(self.enumerate_contrastive(to_hit, term))
return explanation_dic
@@ -367,7 +373,8 @@ class DecisionTree():
expls = []
for i, expl in enumerate(hitman.enumerate(), 1):
list_expls.append([self.fvmap[p] for p in sorted(expl, key=lambda p: p[0])])
- list_expls_str.append('Explanation: IF {0} THEN class={1}'.format(' AND '.join([self.fvmap[p] for p in sorted(expl, key=lambda p: p[0])]), term))
+ list_expls_str.append('Explanation: IF {0} THEN class={1}'.format(
+ ' AND '.join([self.fvmap[p] for p in sorted(expl, key=lambda p: p[0])]), term))
expls.append(expl)
if i == enum:
@@ -375,9 +382,10 @@ class DecisionTree():
explanation["List of path explanation(s)"] = list_expls
explanation["List of abductive explanation(s)"] = list_expls_str
explanation["Number of abductive explanation(s) : "] = str(i)
- explanation["Minimal abductive explanation : "] = str( min([len(e) for e in expls]))
- explanation["Maximal abductive explanation : "] = str( max([len(e) for e in expls]))
- explanation["Average abductive explanation : "] = '{0:.2f}'.format(sum([len(e) for e in expls]) / len(expls))
+ explanation["Minimal abductive explanation : "] = str(min([len(e) for e in expls]))
+ explanation["Maximal abductive explanation : "] = str(max([len(e) for e in expls]))
+ explanation["Average abductive explanation : "] = '{0:.2f}'.format(
+ sum([len(e) for e in expls]) / len(expls))
return explanation
@@ -385,6 +393,7 @@ class DecisionTree():
"""
Enumerate contrastive explanations.
"""
+
def process_set(done, target):
for s in done:
if s <= target:
@@ -401,14 +410,15 @@ class DecisionTree():
list_expls_str = []
explanation = {}
for expl in expls:
- list_contrastive_expls.append([self.fvmap[(p[0],1-p[1])] for p in sorted(expl, key=lambda p: p[0])])
- list_expls_str.append('Contrastive: IF {0} THEN class!={1}'.format(' OR '.join(['!{0}'.format(self.fvmap[p]) for p in sorted(expl, key=lambda p: p[0])]), term))
+ list_contrastive_expls.append([self.fvmap[(p[0], 1 - p[1])] for p in sorted(expl, key=lambda p: p[0])])
+ list_expls_str.append('Contrastive: IF {0} THEN class!={1}'.format(
+ ' OR '.join(['!{0}'.format(self.fvmap[p]) for p in sorted(expl, key=lambda p: p[0])]), term))
explanation["List of path contrastive explanation(s)"] = list_contrastive_expls
explanation["List of contrastive explanation(s)"] = list_expls_str
- explanation["Number of contrastive explanation(s) : "]=str(len(expls))
- explanation["Minimal contrastive explanation : "]= str( min([len(e) for e in expls]))
- explanation["Maximal contrastive explanation : "]= str( max([len(e) for e in expls]))
- explanation["Average contrastive explanation : "]='{0:.2f}'.format(sum([len(e) for e in expls]) / len(expls))
+ explanation["Number of contrastive explanation(s) : "] = str(len(expls))
+ explanation["Minimal contrastive explanation : "] = str(min([len(e) for e in expls]))
+ explanation["Maximal contrastive explanation : "] = str(max([len(e) for e in expls]))
+ explanation["Average contrastive explanation : "] = '{0:.2f}'.format(sum([len(e) for e in expls]) / len(expls))
return explanation
diff --git a/pages/application/DecisionTree/utils/dtviz.py b/pages/application/DecisionTree/utils/dtviz.py
index cf71d2b..02aa847 100755
--- a/pages/application/DecisionTree/utils/dtviz.py
+++ b/pages/application/DecisionTree/utils/dtviz.py
@@ -1,5 +1,5 @@
#!/usr/bin/env python
-#-*- coding:utf-8 -*-
+# -*- coding:utf-8 -*-
##
## dtviz.py
##
@@ -9,255 +9,234 @@
##
#
-#==============================================================================
+# ==============================================================================
import getopt
-import pygraphviz
+import pydot
import ast
import re
+
+
#
-#==============================================================================
-def create_legend(g):
- legend = g.subgraphs()[-1]
- legend.graph_attr.update(size="2,2")
- legend.add_node("a", style = "invis")
- legend.add_node("b", style = "invis")
- legend.add_node("c", style = "invis")
- legend.add_node("d", style = "invis")
- legend.add_node("e", style = "invis")
- legend.add_node("f", style = "invis")
-
- legend.add_edge("a","b")
- edge = legend.get_edge("a","b")
- edge.attr["label"] = "instance"
- edge.attr["style"] = "dashed"
-
- legend.add_edge("c","d")
- edge = legend.get_edge("c","d")
- edge.attr["label"] = "instance with explanation"
- edge.attr["color"] = "blue"
- edge.attr["style"] = "dashed"
-
- legend.add_edge("e","f")
- edge = legend.get_edge("e","f")
- edge.attr["label"] = "contrastive explanation"
- edge.attr["color"] = "red"
+# ==============================================================================
+def create_legend(G):
+ legend = pydot.Cluster('legend', rankdir="TB")
+
+ # non-terminal nodes
+ for n in ["a", "b", "c", "d", "e", "f"]:
+ node = pydot.Node(n, label=n)
+ legend.add_node(node)
+
+ edge = pydot.Edge("a", "b")
+ edge.obj_dict['attributes']["label"] = "instance"
+ edge.obj_dict['attributes']["style"] = "dashed"
+ legend.add_edge(edge)
+
+ edge = pydot.Edge("e", "f")
+ edge.obj_dict['attributes']["label"] = "contrastive explanation"
+ edge.obj_dict['attributes']["color"] = "red"
+ edge.obj_dict['attributes']["style"] = "dashed"
+ legend.add_edge(edge)
+
+ edge = pydot.Edge("c", "d")
+ edge.obj_dict['attributes']["label"] = "instance with explanation"
+ edge.obj_dict['attributes']["color"] = "blue"
+ edge.obj_dict['attributes']["style"] = "dashed"
+ legend.add_edge(edge)
+
+ G.add_subgraph(legend)
+
+
#
-#==============================================================================
+# ==============================================================================
def visualize(dt):
"""
Visualize a DT with graphviz.
"""
- g = pygraphviz.AGraph(directed=True, strict=True)
- g.edge_attr['dir'] = 'forward'
- g.graph_attr['rankdir'] = 'TB'
+ G = pydot.Dot('tree_total', graph_type='graph')
+
+ g = pydot.Cluster('tree', graph_type='graph')
# non-terminal nodes
for n in dt.nodes:
- g.add_node(n, label=dt.feature_names[dt.nodes[n].feat])
- node = g.get_node(n)
- node.attr['shape'] = 'circle'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.feature_names[dt.nodes[n].feat], shape="circle")
+ g.add_node(node)
# terminal nodes
for n in dt.terms:
- g.add_node(n, label=dt.terms[n])
- node = g.get_node(n)
- node.attr['shape'] = 'square'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.terms[n], shape="square")
+ g.add_node(node)
# transitions
for n1 in dt.nodes:
for v in dt.nodes[n1].vals:
n2 = dt.nodes[n1].vals[v]
- g.add_edge(n1, n2)
- edge = g.get_edge(n1, n2)
+ edge = pydot.Edge(n1, n2)
if len(v) == 1:
- edge.attr['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
+ edge.obj_dict['attributes']['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
else:
- edge.attr['label'] = '{0}'.format('\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
- edge.attr['fontsize'] = 10
- edge.attr['arrowsize'] = 0.8
+ edge.obj_dict['attributes']['label'] = '{0}'.format(
+ '\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
+ edge.obj_dict['attributes']['fontsize'] = 10
+ edge.obj_dict['attributes']['arrowsize'] = 0.8
+
+ g.add_edge(edge)
+
+ G.add_subgraph(g)
+
+ return G.to_string()
- # saving file
- g.layout(prog='dot')
- return(g.to_string())
#
-#==============================================================================
+# ==============================================================================
def visualize_instance(dt, instance):
"""
Visualize a DT with graphviz and plot the running instance.
"""
- #path that follows the instance - colored in blue
+ # path that follows the instance - colored in blue
path, term, depth = dt.execute(instance)
edges_instance = []
- for i in range (len(path)-1) :
- edges_instance.append((path[i], path[i+1]))
- edges_instance.append((path[-1],"term:"+term))
+ for i in range(len(path) - 1):
+ edges_instance.append((path[i], path[i + 1]))
+ edges_instance.append((path[-1], "term:" + term))
+
+ G = pydot.Dot('tree_total', graph_type='graph')
- g = pygraphviz.AGraph(directed=True, strict=True)
- g.edge_attr['dir'] = 'forward'
- g.graph_attr['rankdir'] = 'TB'
+ g = pydot.Cluster('tree', graph_type='graph')
# non-terminal nodes
for n in dt.nodes:
- g.add_node(n, label=dt.feature_names[dt.nodes[n].feat])
- node = g.get_node(n)
- node.attr['shape'] = 'circle'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.feature_names[dt.nodes[n].feat], shape="circle")
+ g.add_node(node)
# terminal nodes
for n in dt.terms:
- g.add_node(n, label=dt.terms[n])
- node = g.get_node(n)
- node.attr['shape'] = 'square'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.terms[n], shape="square")
+ g.add_node(node)
# transitions
for n1 in dt.nodes:
for v in dt.nodes[n1].vals:
n2 = dt.nodes[n1].vals[v]
- n2_type = g.get_node(n2).attr['shape']
-
- g.add_edge(n1, n2)
- edge = g.get_edge(n1, n2)
+ n2_type = g.get_node(str(n2))[0].obj_dict['attributes']['shape']
+ edge = pydot.Edge(n1, n2)
if len(v) == 1:
- edge.attr['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
+ edge.obj_dict['attributes']['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
else:
- edge.attr['label'] = '{0}'.format('\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
-
- #instance path in dashed
- if ((n1,n2) in edges_instance) or (n2_type=='square' and (n1, "term:"+ dt.terms[n2]) in edges_instance):
- edge.attr['style'] = 'dashed'
+ edge.obj_dict['attributes']['label'] = '{0}'.format(
+ '\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
+ edge.obj_dict['attributes']['fontsize'] = 10
+ edge.obj_dict['attributes']['arrowsize'] = 0.8
- edge.attr['fontsize'] = 10
- edge.attr['arrowsize'] = 0.8
+ # instance path in dashed
+ if ((n1, n2) in edges_instance) or (n2_type == 'square' and (n1, "term:" + dt.terms[n2]) in edges_instance):
+ edge.obj_dict['attributes']['style'] = 'dashed'
- g.add_subgraph(name='legend')
- create_legend(g)
+ g.add_edge(edge)
- # saving file
- g.layout(prog='dot')
- return(g.to_string())
+ create_legend(G)
+ G.add_subgraph(g)
-#==============================================================================
+ return G.to_string()
+
+
+# ==============================================================================
def visualize_expl(dt, instance, expl):
"""
Visualize a DT with graphviz and plot the running instance.
"""
- #path that follows the instance - colored in blue
+ # path that follows the instance - colored in blue
path, term, depth = dt.execute(instance)
edges_instance = []
- for i in range (len(path)-1) :
- edges_instance.append((path[i], path[i+1]))
- edges_instance.append((path[-1],"term:"+term))
-
- g = pygraphviz.AGraph(directed=True, strict=True)
- g.edge_attr['dir'] = 'forward'
+ for i in range(len(path) - 1):
+ edges_instance.append((path[i], path[i + 1]))
+ edges_instance.append((path[-1], "term:" + term))
- g.graph_attr['rankdir'] = 'TB'
+ g = pydot.Dot('my_graph', graph_type='graph')
# non-terminal nodes
for n in dt.nodes:
- g.add_node(n, label=dt.feature_names[dt.nodes[n].feat])
- node = g.get_node(n)
- node.attr['shape'] = 'circle'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.feature_names[dt.nodes[n].feat], shape="circle")
+ g.add_node(node)
# terminal nodes
for n in dt.terms:
- g.add_node(n, label=dt.terms[n])
- node = g.get_node(n)
- node.attr['shape'] = 'square'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.terms[n], shape="square")
+ g.add_node(node)
# transitions
for n1 in dt.nodes:
for v in dt.nodes[n1].vals:
n2 = dt.nodes[n1].vals[v]
- n2_type = g.get_node(n2).attr['shape']
- g.add_edge(n1, n2)
- edge = g.get_edge(n1, n2)
+ n2_type = g.get_node(str(n2))[0].obj_dict['attributes']['shape']
+ edge = pydot.Edge(n1, n2)
if len(v) == 1:
- edge.attr['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
+ edge.obj_dict['attributes']['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
else:
- edge.attr['label'] = '{0}'.format('\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
-
- #instance path in dashed
- if ((n1,n2) in edges_instance) or (n2_type=='square' and (n1, "term:"+ dt.terms[n2]) in edges_instance):
- edge.attr['style'] = 'dashed'
- for label in edge.attr['label'].split('\n'):
+ edge.obj_dict['attributes']['label'] = '{0}'.format(
+ '\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
+ edge.obj_dict['attributes']['fontsize'] = 10
+ edge.obj_dict['attributes']['arrowsize'] = 0.8
+
+ # instance path in dashed
+ if ((n1, n2) in edges_instance) or (n2_type == 'square' and (n1, "term:" + dt.terms[n2]) in edges_instance):
+ edge.obj_dict['attributes']['style'] = 'dashed'
+
+ for label in edge.obj_dict['attributes']['label'].split('\n'):
if label in expl:
- edge.attr['color'] = 'blue'
+ edge.obj_dict['attributes']['color'] = 'blue'
- edge.attr['fontsize'] = 10
- edge.attr['arrowsize'] = 0.8
+ g.add_edge(edge)
- g.add_subgraph(name='legend')
- create_legend(g)
+ return g.to_string()
- # saving file
- g.layout(prog='dot')
- return(g.to_string())
-#==============================================================================
+# ==============================================================================
def visualize_contrastive_expl(dt, instance, cont_expl):
"""
Visualize a DT with graphviz and plot the running instance.
"""
- #path that follows the instance - colored in blue
+ # path that follows the instance - colored in blue
path, term, depth = dt.execute(instance)
edges_instance = []
- for i in range (len(path)-1) :
- edges_instance.append((path[i], path[i+1]))
- edges_instance.append((path[-1],"term:"+term))
-
- g = pygraphviz.AGraph(directed=True, strict=True)
- g.edge_attr['dir'] = 'forward'
+ for i in range(len(path) - 1):
+ edges_instance.append((path[i], path[i + 1]))
+ edges_instance.append((path[-1], "term:" + term))
- g.graph_attr['rankdir'] = 'TB'
+ g = pydot.Dot('my_graph', graph_type='graph')
# non-terminal nodes
for n in dt.nodes:
- g.add_node(n, label=dt.feature_names[dt.nodes[n].feat])
- node = g.get_node(n)
- node.attr['shape'] = 'circle'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.feature_names[dt.nodes[n].feat], shape="circle")
+ g.add_node(node)
# terminal nodes
for n in dt.terms:
- g.add_node(n, label=dt.terms[n])
- node = g.get_node(n)
- node.attr['shape'] = 'square'
- node.attr['fontsize'] = 13
+ node = pydot.Node(n, label=dt.terms[n], shape="square")
+ g.add_node(node)
# transitions
for n1 in dt.nodes:
for v in dt.nodes[n1].vals:
n2 = dt.nodes[n1].vals[v]
- n2_type = g.get_node(n2).attr['shape']
- g.add_edge(n1, n2)
- edge = g.get_edge(n1, n2)
+ n2_type = g.get_node(str(n2))[0].obj_dict['attributes']['shape']
+ edge = pydot.Edge(n1, n2)
if len(v) == 1:
- edge.attr['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
+ edge.obj_dict['attributes']['label'] = dt.fvmap[tuple([dt.nodes[n1].feat, tuple(v)[0]])]
else:
- edge.attr['label'] = '{0}'.format('\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
-
- #instance path in dashed
- if ((n1,n2) in edges_instance) or (n2_type=='square' and (n1, "term:"+ dt.terms[n2]) in edges_instance):
- edge.attr['style'] = 'dashed'
-
- for label in edge.attr['label'].split('\n'):
- if label in cont_expl:
- edge.attr['color'] = 'red'
+ edge.obj_dict['attributes']['label'] = '{0}'.format(
+ '\n'.join([dt.fvmap[tuple([dt.nodes[n1].feat, val])] for val in tuple(v)]))
+ edge.obj_dict['attributes']['fontsize'] = 10
+ edge.obj_dict['attributes']['arrowsize'] = 0.8
+
+ # instance path in dashed
+ if ((n1, n2) in edges_instance) or (n2_type == 'square' and (n1, "term:" + dt.terms[n2]) in edges_instance):
+ edge.obj_dict['attributes']['style'] = 'dashed'
- edge.attr['fontsize'] = 10
- edge.attr['arrowsize'] = 0.8
+ for label in edge.obj_dict['attributes']['label'].split('\n'):
+ if label in cont_expl:
+ edge.obj_dict['attributes']['color'] = 'red'
- g.add_subgraph(name='legend')
- create_legend(g)
+ g.add_edge(edge)
- # saving file
- g.layout(prog='dot')
- return(g.to_string())
+ return g.to_string()
diff --git a/pages/application/application.py b/pages/application/application.py
index 65475b9..6d33030 100644
--- a/pages/application/application.py
+++ b/pages/application/application.py
@@ -6,16 +6,14 @@ from pages.application.DecisionTree.DecisionTreeComponent import DecisionTreeCom
from pages.application.NaiveBayes.NaiveBayesComponent import NaiveBayesComponent
from pages.application.RandomForest.RandomForestComponent import RandomForestComponent
-import subprocess
-
-class Application():
+class Application:
def __init__(self, view):
self.view = view
self.model = view.model
-class Model():
+class Model:
def __init__(self, names_models, dict_components, dic_solvers, dic_xtypes):
self.dict_components = dict_components
@@ -23,38 +21,40 @@ class Model():
self.dic_xtypes = dic_xtypes
self.ml_models = names_models
- self.ml_model = ''
+ self.ml_model = None
- self.pretrained_model = ''
+ self.pretrained_model = None
self.add_info = False
- self.model_info = ''
+ self.model_info = None
self.enum = 1
self.xtypes = []
- self.xtype = ""
+ self.xtype = None
self.solvers = []
- self.solver = ""
+ self.solver = None
- self.instance = ''
+ self.instance = None
self.list_expls = []
self.list_cont_expls = []
- self.expl = ''
- self.cont_expl = ''
+ self.expl = None
+ self.cont_expl = None
- self.component_class = ''
- self.component = ''
+ self.component_class = None
+ self.component = None
def update_ml_model(self, ml_model_update):
self.ml_model = ml_model_update
self.component_class = self.dict_components[self.ml_model]
self.component_class = globals()[self.component_class]
self.solvers = self.dic_solvers[self.ml_model]
+ self.solver = self.solvers[0]
self.xtypes = self.dic_xtypes[self.ml_model]
+ self.xtype = [list(self.xtypes.keys())[0]]
def update_pretrained_model(self, pretrained_model_update):
self.pretrained_model = pretrained_model_update
@@ -99,7 +99,7 @@ class Model():
self.component.draw_contrastive_explanation(self.instance, cont_expl)
-class View():
+class View:
def __init__(self, model):
self.model = model
@@ -128,7 +128,7 @@ class View():
self.add_model_info_choice = html.Div([
html.Hr(),
- html.Label("Do you wish to upload more info for your model ? : "),
+ html.Label("Upload more data model (only for model with categorical variables) ?"),
html.Br(),
daq.BooleanSwitch(id='add_info_model_choice', on=False, color="#000000", )])
@@ -192,9 +192,9 @@ class View():
self.sidebar = dcc.Tabs(children=[
dcc.Tab(label='Basic Parameters', children=[
self.ml_menu_models,
- self.pretrained_model_upload,
self.add_model_info_choice,
self.model_info,
+ self.pretrained_model_upload,
self.instance_upload], className="sidebar"),
dcc.Tab(label='Advanced Parameters', children=[
html.Br(),
diff --git a/requirements.txt b/requirements.txt
index 8f12a33..0731570 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,24 +1,27 @@
-# Core
-gunicorn>=19.8.1
-dash>=1.0.0
-
-# Additional
colorlover>=0.2.1
-numpy>=1.16.2
-pandas>=0.24.2
-scikit-learn>=0.20.3
scipy>=1.2.1
-dash_bootstrap_components
-dash_interactive_graphviz
python-sat[pblib,aiger]
-pygraphviz
+matplotlib==3.5.1
+xgboost==1.6.0
+lime==0.2.0.1
+shap==0.40.0
+anchor-exp==0.0.2.0
+pysmt==0.9.0
anytree==2.8.0
+dash==2.1.0
+dash_bootstrap_components==1.0.3
dash_daq==0.5.0
-matplotlib
-six
-xgboost
-lime
-shap
-anchor-exp
-pysmt
-anytree
+dash_interactive_graphviz==0.3.0
+Jinja2==3.0.3
+joblib==1.1.0
+json2html==1.3.0
+numpy==1.21
+pandas==1.4.1
+pysat==3.0.1
+pytest==7.0.1
+python_sat==0.1.7.dev15
+scikit_learn==1.0.2
+six==1.16.0
+gunicorn==20.1.0
+Werkzeug==2.0.1
+pydot==1.4.2
\ No newline at end of file
diff --git a/runtime.txt b/runtime.txt
new file mode 100644
index 0000000..f96c0fa
--- /dev/null
+++ b/runtime.txt
@@ -0,0 +1 @@
+python-3.8.10
\ No newline at end of file
diff --git a/utils.py b/utils.py
index 9fd8a54..87f4fa3 100644
--- a/utils.py
+++ b/utils.py
@@ -8,20 +8,19 @@ from dash import html
from pages.application.RandomForest.utils import xrf
from pages.application.RandomForest.utils.xrf import *
+
sys.modules['xrf'] = xrf
from pages.application.RandomForest.utils import options
from pages.application.RandomForest.utils.options import *
+
sys.modules['options'] = options
-def parse_contents_graph(contents, filename):
+def parse_contents_graph(contents, filename):
content_type, content_string = contents.split(',')
decoded = base64.b64decode(content_string)
try:
if 'mod.pkl' in filename:
- print("in")
- print(io.BytesIO(decoded))
- print(pickle.load(io.BytesIO(decoded)))
data = pickle.load(io.BytesIO(decoded))
elif '.pkl' in filename:
data = joblib.load(io.BytesIO(decoded))
--
GitLab