Upload all files

BaselineModel.py

@@ -0,0 +1,53 @@
+import numbers
+import numpy as np
+import sklearn
+
+from sklearn.utils import check_X_y, check_array, column_or_1d
+from sklearn.utils.multiclass import check_classification_targets
+
+from sklearn.externals.joblib import Parallel, delayed #For parallel computing TODO: check if we need to be parallel or not
+from sklearn.utils.validation import has_fit_parameter, check_is_fitted
+
+
+class DecisionTreeBaseline():
+    """Base class for ordinal meta-classifier.
+
+    """
+
+    def __init__(self):
+        return self
+
+    def fit(self, X, y, sample_weight=None):
+        return self
+
+    def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
+        return self
+
+    def predict(self, X):
+        X = check_array(X, accept_sparse=['csr', 'csc'])
+
+        # ---------------------------------------------Our CODE
+        n_samples = X.shape[0]
+        prediction = np.zeros((n_samples, 1))
+
+        for i in range(0, n_samples):
+            if X[i,"Scenario"] == "C":
+                if X[i,"VoterType"] == "LB":
+                    prediction[i] = 2 #Q' vote
+                else:
+                    prediction[i] = 1 #Q vote  
+            else:
+                if X[i,"Scenario"] in ["E","F"]:
+                    if X[i,"VoterType"] == "TRT":
+                        prediction[i] = 1 #Q vote   
+                    else:
+                        prediction[i] = 2 #Q' vote
+
+                else:
+                    prediction[i] = 1 #Q vote
+
+
+        return prediction
+
+
+

BayesRuleModel.py

@@ -0,0 +1,53 @@
+import numbers
+import numpy as np
+import sklearn
+
+from sklearn.utils import check_X_y, check_array, column_or_1d
+from sklearn.utils.multiclass import check_classification_targets
+
+from sklearn.externals.joblib import Parallel, \
+    delayed  # For parallel computing TODO: check if we need to be parallel or not
+from sklearn.utils.validation import has_fit_parameter, check_is_fitted
+
+
+class BayesRuleClassifier():
+    """Base class for ordinal meta-classifier.
+
+    """
+
+    def __init__(self):
+        return self
+
+    def fit(self, X, y, sample_weight=None):
+        return self
+
+    def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
+        return self
+
+    def predict(self, X):
+        X = check_array(X, accept_sparse=['csr', 'csc'])
+
+        # ---------------------------------------------Our CODE
+        n_samples = X.shape[0]
+        prediction = np.zeros((n_samples, 1))
+
+        for i in range(0, n_samples):
+            if X[i, "Scenario"] == "C":
+                if X[i, "VoterType"] == "LB":
+                    prediction[i] = 2  # Q' vote
+                else:
+                    prediction[i] = 1  # Q vote
+            else:
+                if X[i, "Scenario"] in ["E", "F"]:
+                    if X[i, "VoterType"] == "TRT":
+                        prediction[i] = 1  # Q vote
+                    else:
+                        prediction[i] = 2  # Q' vote
+
+                else:
+                    prediction[i] = 1  # Q vote
+
+        return prediction
+
+
+

Data/action_table_N3.csv

@@ -0,0 +1,19 @@
+scenario,action,action_name
+1,1,TRT
+1,2,DOM
+1,3,DOM
+2,1,TRT
+2,2,DOM
+2,3,DOM
+3,1,TRT
+3,2,WLB
+3,3,DOM
+4,1,TRT
+4,2,DOM
+4,3,SLB
+5,1,TRT
+5,2,CMP\WLB
+5,3,DOM
+6,1,TRT
+6,2,CMP
+6,3,SLB

Data/action_table_N4.csv

@@ -0,0 +1,97 @@
+scenario,action,action_name
+1,1,TRT
+1,2,DOM
+1,3,DOM
+1,4,DOM
+2,1,TRT
+2,2,DOM
+2,3,DOM
+2,4,DOM
+3,1,TRT
+3,2,DOM
+3,3,DOM
+3,4,DOM
+4,1,TRT
+4,2,DOM
+4,3,DOM
+4,4,DOM
+5,1,TRT
+5,2,DOM
+5,3,DOM
+5,4,DOM
+6,1,TRT
+6,2,DOM
+6,3,DOM
+6,4,DOM
+7,1,TRT
+7,2,WLB
+7,3,DOM
+7,4,DOM
+8,1,TRT
+8,2,WLB
+8,3,DOM
+8,4,DOM
+9,1,TRT
+9,2,CMP\WLB
+9,3,DOM
+9,4,DOM
+10,1,TRT
+10,2,CMP\WLB
+10,3,DOM
+10,4,DOM
+11,1,TRT
+11,2,CMP\WLB
+11,3,DOM
+11,4,DOM
+12,1,TRT
+12,2,CMP\WLB
+12,3,DOM
+12,4,DOM
+13,1,TRT
+13,2,DOM
+13,3,SLB
+13,4,DOM
+14,1,TRT
+14,2,DOM
+14,3,SLB
+14,4,DOM
+15,1,TRT
+15,2,CMP
+15,3,SLB
+15,4,DOM
+16,1,TRT
+16,2,CMP
+16,3,SLB
+16,4,DOM
+17,1,TRT
+17,2,DOM
+17,3,SLB
+17,4,DOM
+18,1,TRT
+18,2,CMP
+18,3,SLB
+18,4,DOM
+19,1,TRT
+19,2,DOM
+19,3,DOM
+19,4,SLB
+20,1,TRT
+20,2,DOM
+20,3,DOM
+20,4,SLB
+21,1,TRT
+21,2,CMP
+21,3,DOM
+21,4,SLB
+22,1,TRT
+22,2,CMP
+22,3,DOM
+22,4,SLB
+23,1,TRT
+23,2,DOM
+23,3,CMP
+23,4,SLB
+24,1,TRT
+24,2,CMP
+24,3,CMP
+24,4,SLB

Data/scenario_table_N3.csv

@@ -0,0 +1,7 @@
+Pref1_pos,Pref2_pos,Pref3_pos,scenario,name
+1,2,3,1,TRT
+1,3,2,2,TRT
+2,1,3,3,WLB
+2,3,1,4,SLB
+3,1,2,5,CMPLB
+3,2,1,6,CMP

Data/scenario_table_N4.csv

@@ -0,0 +1,25 @@
+Pref1_pos,Pref2_pos,Pref3_pos,Pref4_pos,scenario,name
+1,2,3,4,1,TRT
+1,2,4,3,2,TRT
+1,3,2,4,3,TRT
+1,4,2,3,4,TRT
+1,3,4,2,5,TRT
+1,4,3,2,6,TRT
+2,1,3,4,7,LB
+2,1,4,3,8,LB
+3,1,2,4,9,CMPLB
+4,1,2,3,10,CMPLB
+3,1,4,2,11,CMPLB
+4,1,3,2,12,CMPLB
+2,3,1,4,13,LB
+2,4,1,3,14,LB
+3,2,1,4,15,CMP
+4,2,1,3,16,CMP
+3,4,1,2,17,LB
+4,3,1,2,18,CMPLB
+2,3,4,1,19,LB
+2,4,3,1,20,LB
+3,2,4,1,21,CMP
+4,2,3,1,22,CMP
+3,4,2,1,23,CMP
+4,3,2,1,24,CMP

LikelihoodModel.py

@@ -0,0 +1,53 @@
+import numbers
+import numpy as np
+import sklearn
+
+from sklearn.utils import check_X_y, check_array, column_or_1d
+from sklearn.utils.multiclass import check_classification_targets
+
+from sklearn.externals.joblib import Parallel, \
+    delayed  # For parallel computing TODO: check if we need to be parallel or not
+from sklearn.utils.validation import has_fit_parameter, check_is_fitted
+
+
+class LHClassifier():
+    """Base class for ordinal meta-classifier.
+
+    """
+
+    def __init__(self):
+        return self
+
+    def fit(self, X, y, sample_weight=None):
+        return self
+
+    def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
+        return self
+
+    def predict(self, X):
+        X = check_array(X, accept_sparse=['csr', 'csc'])
+
+        # ---------------------------------------------Our CODE
+        n_samples = X.shape[0]
+        prediction = np.zeros((n_samples, 1))
+
+        for i in range(0, n_samples):
+            if X[i, "Scenario"] == "C":
+                if X[i, "VoterType"] == "LB":
+                    prediction[i] = 2  # Q' vote
+                else:
+                    prediction[i] = 1  # Q vote
+            else:
+                if X[i, "Scenario"] in ["E", "F"]:
+                    if X[i, "VoterType"] == "TRT":
+                        prediction[i] = 1  # Q vote
+                    else:
+                        prediction[i] = 2  # Q' vote
+
+                else:
+                    prediction[i] = 1  # Q vote
+
+        return prediction
+
+
+

MaximumLikelihoodModel.py

@@ -0,0 +1,53 @@
+import numbers
+import numpy as np
+import sklearn
+
+from sklearn.utils import check_X_y, check_array, column_or_1d
+from sklearn.utils.multiclass import check_classification_targets
+
+from sklearn.externals.joblib import Parallel, \
+    delayed  # For parallel computing TODO: check if we need to be parallel or not
+from sklearn.utils.validation import has_fit_parameter, check_is_fitted
+
+
+class MLHClassifier():
+    """Base class for ordinal meta-classifier.
+
+    """
+
+    def __init__(self):
+        return self
+
+    def fit(self, X, y, sample_weight=None):
+        return self
+
+    def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
+        return self
+
+    def predict(self, X):
+        X = check_array(X, accept_sparse=['csr', 'csc'])
+
+        # ---------------------------------------------Our CODE
+        n_samples = X.shape[0]
+        prediction = np.zeros((n_samples, 1))
+
+        for i in range(0, n_samples):
+            if X[i, "Scenario"] == "C":
+                if X[i, "VoterType"] == "LB":
+                    prediction[i] = 2  # Q' vote
+                else:
+                    prediction[i] = 1  # Q vote
+            else:
+                if X[i, "Scenario"] in ["E", "F"]:
+                    if X[i, "VoterType"] == "TRT":
+                        prediction[i] = 1  # Q vote
+                    else:
+                        prediction[i] = 2  # Q' vote
+
+                else:
+                    prediction[i] = 1  # Q vote
+
+        return prediction
+
+
+