def recognize_symbol(features, img, fsize): # Get the feature feat = extract_feature(img, fsize) retval = None min = 1 # For every feature for val, f in features: # Compare the feature to our own d = compare_feature(f, feat) if d < min: # We got a match! retval = val min = d return retval
import time
import pandas as pd
# ------------------------------------------------------------------
# -------------- Import Images and Create DataFrame ----------------
# ------------------------------------------------------------------
name = "gfrp"
# Import original image
# ------------------------------------------------------------------
img = cv2.imread(name +'.tif')
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Feature Extraction
# ------------------------------------------------------------------
df=extract_feature(img)
# Import labeled image and add to dataframe
# ------------------------------------------------------------------
labeled = cv2.imread('labeled_'+ name +'.tif')
labeled = cv2.cvtColor(labeled, cv2.COLOR_BGR2GRAY)
labeled_array = labeled.reshape(-1)
df['Label']= labeled_array
# ------------------------------------------------------------------
# ---------------------- Training and Validation -------------------
# ------------------------------------------------------------------
# Dependent variables
# ------------------------------------------------------------------
Y= df['Label'].values
except ValueError:
print("Enter 0,1,2 to specify testing document")
exit()
except IndexError:
TEST = 2
#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
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))
'''
if ((feature_no<14) & (preprocess=='preclean_Tweet')):
continue
'''
train_save_path = '..//features//train_feature_' + str(
feature_no) + "_" + preprocess + ".pkl"
test_save_path = '..//features//test_feature_' + str(
feature_no) + "_" + preprocess + ".pkl"
if (os.path.isfile(train_save_path) & os.path.isfile(test_save_path)):
print('read feature')
X = pickle.load(open(train_save_path, 'rb'))
X_test = pickle.load(open(test_save_path, 'rb'))
else:
print('extract feature')
X, X_test = extract_feature(preprocess, preprocessed_train_tweets,
preprocessed_test_tweets, feature_no,
train_save_path, test_save_path)
print(X.shape)
print(X_test.shape)
'''
X1, X_test1=extract_feature(preprocessed_train_tweets,preprocessed_test_tweets,0,'','')
X2, X_test2=extract_feature(preprocessed_train_tweets,preprocessed_test_tweets,2,'','')
X=np.concatenate((X1.toarray(), X2), axis=1)
X_test=np.concatenate((X_test1.toarray(),X_test2),axis=1)
'''
# Model Training
# Single Stage
# Combine
if (
not os.path.isfile(result_path + 'svm_OneStage_combine_' +
str(feature_no) + "_" + preprocess + ".txt")
