From 199da04ba69c2da1b7e7d68e6b07098980f34600 Mon Sep 17 00:00:00 2001
From: Maxime Buron <maxime.buron@uca.fr>
Date: Tue, 26 Nov 2024 15:14:56 +0100
Subject: [PATCH] generation of the BID
---
mar.net | 6 ++--
mcc.py | 86 +++++++++++++++++++++++++++++++++++++++++++++++---------
mnar.net | 53 ++++++++++++++++++++++++++++++++++
3 files changed, 129 insertions(+), 16 deletions(-)
create mode 100644 mnar.net
diff --git a/mar.net b/mar.net
index 6ab47c1..e3a978f 100644
--- a/mar.net
+++ b/mar.net
@@ -41,13 +41,13 @@ node Ic {
}
potential (A) {
- data = ( 0.561407 0.438593);
+ data = ( 0.6 0.4);
}
potential ( B | A ) {
data =
- (( 0.515132 0.484868) % A=0
- ( 0.371633 0.628367)); % A=1
+ (( 0.5 0.5) % A=0
+ ( 0.2 0.8)); % A=1
}
potential ( C | B ) {
diff --git a/mcc.py b/mcc.py
index 0bfdd1e..09e3a49 100755
--- a/mcc.py
+++ b/mcc.py
@@ -4,6 +4,13 @@ import psycopg2
import sys
import argparse
+def is_var_indicator(v):
+ return not is_var(v)
+
+def is_var(v):
+ return not v.lower().startswith('i')
+
+
parser = argparse.ArgumentParser()
parser.add_argument("BNFile", help="Bayesian network file")
parser.add_argument("DBSize", help="size of the database")
@@ -38,7 +45,6 @@ cursor.execute(deletion_sql)
# creating the table to store the
col_def = map(lambda name : "{} int NOT NULL".format(name), var_names)
creation_sql = "CREATE TABLE {}({});".format(table_name, ",".join(col_def))
-print(creation_sql)
cursor.execute(creation_sql)
# loading the CSV data to the table
@@ -48,30 +54,84 @@ with open(out_file, "r") as file:
missing_selects = []
for v in var_names:
- if not v.lower().startswith('i') and v[1:] not in var_names:
+ if is_var(v) and v[1:] not in var_names:
missing_selects.append("case when i{}=1 then NULL ELSE {} END".format(v,v))
- elif not v.lower().startswith('i'):
+ elif is_var(v):
missing_selects.append(v)
missing_data_table = "{}_star".format(table_name)
deletion_sql = "DROP TABLE IF EXISTS {};".format(missing_data_table)
cursor.execute(deletion_sql)
-missing_data_sql = "CREATE TABLE {} AS SELECT {} FROM {}".format(missing_data_table, ",".join(missing_selects), table_name)
+missing_selects_text = ",".join(missing_selects)
+missing_data_sql = "CREATE TABLE {} AS SELECT {}, md5(CAST(({}) AS text)) AS superblock FROM {}".format(missing_data_table, missing_selects_text, missing_selects_text, table_name)
print(missing_data_sql)
cursor.execute(missing_data_sql)
+# superblock definitions
+superblock_table = "{}_sb".format(table_name)
+deletion_sql = "DROP TABLE IF EXISTS {};".format(superblock_table)
+cursor.execute(deletion_sql)
+
+vars = list(filter(is_var, var_names))
+col_def = map(lambda name : "{} int NOT NULL".format(name), vars)
+creation_sql = "CREATE TABLE {}(superblock text, {}, prob float NOT NULL);".format(superblock_table, ",".join(col_def))
+cursor.execute(creation_sql)
+cursor.execute("SELECT DISTINCT * FROM {}".format(missing_data_table))
+ie = gum.LazyPropagation(bn)
+
+insert_sql = "INSERT INTO {}({}, superblock, prob) VALUES({},%s,%s)".format(superblock_table, ",".join(vars), ",".join(["%s" for _ in vars]))
+
+def instantiation_to_list(inst, row, vars):
+ l = []
+ i = 0
+ inst_vars = list(map(lambda v : v.name(), inst.variablesSequence()))
+ for v in vars:
+ if v in inst_vars:
+ l.append(inst[v])
+ else:
+ l.append(row[i])
+ i+=1
+ return l
+
+for row in cursor.fetchall():
+ null_vars = []
+ null_pos = []
+ i = 0
+ for v in vars:
+ if row[i] is None:
+ null_vars.append(v)
+ null_pos.append(i)
+ ie.addTarget(v)
+ else:
+ ie.addEvidence(v, row[i])
+ i+=1
+ if len(null_vars) > 0:
+ potentiel = ie.jointPosterior(set(null_vars)) if len(vars) > len(null_vars) else ie.evidenceJointImpact(vars,{})
+ for i in potentiel.loopIn():
+ inserted_row = instantiation_to_list(i, row, vars)
+ inserted_row.append(row[-1])
+ inserted_row.append(potentiel.get(i))
+ cursor.execute(insert_sql, inserted_row)
+ ie.eraseAllTargets()
+ ie.eraseAllEvidence()
+
+
+
+
+
+
###### Imputation
-import numpy as np
-import pandas as pd
-from sklearn.impute import KNNImputer
+# import numpy as np
+# import pandas as pd
+# from sklearn.impute import KNNImputer
-cursor.execute("SELECT * FROM {}".format(missing_data_table))
-tuples_list = cursor.fetchall()
-df = pd.DataFrame(tuples_list)
+# cursor.execute("SELECT * FROM {}".format(missing_data_table))
+# tuples_list = cursor.fetchall()
+# df = pd.DataFrame(tuples_list)
-imputer = KNNImputer(n_neighbors=2)
-impute = imputer.fit_transform(df)
-print(impute)
+# imputer = KNNImputer(n_neighbors=10)
+# impute = imputer.fit_transform(df)
+# print(impute)
diff --git a/mnar.net b/mnar.net
new file mode 100644
index 0000000..a5c22cb
--- /dev/null
+++ b/mnar.net
@@ -0,0 +1,53 @@
+
+net {
+ name = mnar;
+ software = "aGrUM 1.17.1";
+ node_size = (50 50);
+}
+
+node B {
+ states = (0 1 );
+ label = "B";
+ ID = "B";
+}
+
+node A {
+ states = (0 1 );
+ label = "A";
+ ID = "A";
+}
+
+node Ia {
+ states = (0 1 );
+ label = "Ia";
+ ID = "Ia";
+}
+
+node Ib {
+ states = (0 1 );
+ label = "Ib";
+ ID = "Ib";
+}
+
+potential ( B | A ) {
+ data =
+ (( 0.515132 0.484868) % A=0
+ ( 0.371633 0.628367)); % A=1
+}
+
+potential (A) {
+ data = ( 0.561407 0.438593);
+}
+
+potential (Ib) {
+ data = ( 0.8 0.2);
+}
+
+potential ( Ia | B ) {
+ data =
+ (( 0.664707 0.335293) % B=0
+ ( 0.344864 0.655136)); % B=1
+}
+
+
+
--
GitLab