added logic to feature_modeling & fold cls

logic/feature_modeling.py

@@ -191,4 +191,3 @@ def count_grams(headline, body):
 
 
 
-

logic/n_kfold.py

@@ -16,4 +16,41 @@ def generate_features(stances, dataset, name ):
  for stance in stances:
  y.append(LABELS.index(stance['Stance']))
  h.append(stance['Headline'])
- b.append(dataset.articles[stance['Body id']])
+ b.append(dataset.articles[stance['Body id']])
+
+
+
+#Generate folds
+if __name__ == "__main__":
+ versioning()
+ #load the traing dataset
+ parameter_parser()
+ my_dataset = Datasets()
+ folds,hold_out = kfold_split(my_dataset,n_folds=10)
+ fold_stances, hold_out_stances = get_stances_4_folds(my_dataset,folds,hold_out)
+
+ demo_dateset = Datasets("Demo /test")
+ X_demo, Y_demo = generate_features(demo_dateset.stances, demo_dateset, "demo")
+
+ Xs = dict()
+ Ys = dict()
+
+ #populat all features
+ X_holdout,y_holdout = generate_features(hold_out_stances, my_dataset,"holder")
+ for fold in fold_stances:
+ Xs[fold],Ys[fold] = generate_features(fold_stances[fold] , demo_dateset ,str(fold))
+
+ best_score = 0
+ best_fold = None
+
+ for fold in fold_stances:
+ ids = list(range(len(folds)))
+ del ids[fold]
+
+ X_train = np.vstack(tuple([Xs[i] for i in ids]))
+ Y_train = np.stack(tuple(Ys[i] for i in ids))
+
+ x_demo = Xs[fold]
+ Y_demo = Ys[fold]
+
+