#def get_
from sklearn.tree import DecisionTreeClassifier
train = corpus.load_corpus(all=True)
statistic = analytics.load_analytics(train)
heighest_probabilty = {}
for i in statistic:
heighest_probabilty[i] = max(statistic[i].items(),key=lambda x:x[1])[0]
X_train_raw, Y_train_raw = extract_feature(data=train)
#Global label_encoder to encode X values
global_label_encoder,global_hot_encoder = set_encoder(Y_train_raw)
print("Training Global Classifer ....")
X_train,Y_train = encode_features(X_train_raw,Y_train_raw,global_label_encoder,global_hot_encoder)
global_clf = DecisionTreeClassifier()
global_clf.fit(X_train,Y_train)
print("Completed")
# print(train)
# Identify the ambiguity classes
amb_class = {}
for i in train:
for x,y in enumerate(i):
#If the word only has one tagging, we don't need a classifier
if len(statistic[y[0]]) == 1:
pass
#If there is an ambiguity, we need a decission tree classifier
else:
from features import extract_feature, set_encoder,encode_features from corpus import load_corpus from sklearn.tree import DecisionTreeClassifier X_train_raw, Y_train_raw = extract_feature(data=load_corpus()) label_encoder,hot_encoder = set_encoder(Y_train_raw) X_train,Y_train = encode_features(X_train_raw,Y_train_raw,label_encoder,hot_encoder) clf = DecisionTreeClassifier() clf.fit(X_train,Y_train) X_test_raw,Y_test_raw = extract_feature(load_corpus(last=True)) X_test,Y_test = encode_features(X_test_raw,Y_test_raw,label_encoder,hot_encoder) print(clf.score(X_test,Y_test))