def daun():
# fixed-sizes for image
fixed_size = tuple((1000,1000)) #Resize pixel menjadi px x px
filename = open('data.csv', 'r')
dataframe = pandas.read_csv(filename)
kelas = dataframe.drop(dataframe.columns[:-1], axis=1)
data = dataframe.drop(dataframe.columns[-1:], axis=1)
# print(data)
# print(kelas)
# empty lists to hold feature vectors and labels
global_features = []
labels = []
i, j = 0, 0
k = 0
# create all the machine learning models
models = []
models.append(('Random Forest',RandomForestClassifier(max_depth=None, random_state=0)))
# variables to hold the results and names
results = []
names = []
scoring = "accuracy"
# filter all the warnings
import warnings
warnings.filterwarnings('ignore')
# 10-fold cross validation
for name, model in models:
kfold = KFold(n_splits=10, random_state=7)
cv_results = cross_val_score(model, data, kelas, cv=kfold, scoring=scoring)
results.append(cv_results)
names.append(name)
msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
print(msg)
import matplotlib.pyplot as plt
# create the model - Random Forests
clf = RandomForestClassifier(max_depth=None, random_state=0)
# fit the training data to the model
clf.fit(data,kelas)
image = cv2.imread('daona2_2.jpg')
image = cv2.resize(image, fixed_size)
humoments = mp.hu_moments(image)
cannywhite = mp.canny(image)
morphsum = mp.morph(image)
H,S,V = mp.rataHSV(image)
diamA, diamB = mp.diameterDetect(image)
red,green,blue = mp.rataRGB(image)
global_feature = np.hstack([humoments, cannywhite, morphsum, H, S, V, diamA, diamB])
prediction = clf.predict(global_feature.reshape(1,-1))[0]
return render_template('result.html', prediksi = prediction)
# Membuat model - Random Forests
clf = RandomForestClassifier(max_depth=None, random_state=5)
# Memasukan data training kedalam model
clf.fit(data, kelas)
# Path dari data test
test_path = "./data_test/"
for file in glob.glob(
test_path + "/*.jpg"
): #Melakukan loop ke semua file di dalam folder dan menambahkan nama filenya yang berekstensi .jpg
image = cv2.imread(file) #Membaca image
wpercent = (mywidth / float(image.size[0]))
hsize = int((float(image.size[1]) * float(wpercent)))
image = image.resize((mywidth, hsize), PIL.Image.ANTIALIAS)
#Ekstrasi informasi dari gambar
humoments = mp.hu_moments(image)
cannywhite = mp.canny(image)
morphsum = mp.morph(image)
H, S, V = mp.rataHSV(image)
diamA, diamB = mp.diameterDetect(image)
#Menggabungkan informasi atribut
global_feature = np.hstack(
[humoments, cannywhite, morphsum, H, S, V, diamA, diamB])
# Melakukan prediksi gambar
prediction = clf.predict(global_feature.reshape(1, -1))[0]
print(prediction)
# Jika ingin melihat hasil output gambar, hapus # pada kode dibawah
#cv2.putText(image,prediction, (20,30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,255), 3)
#plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
#plt.show()
tanya = input("Apakah klasifikasi benar? Y/N")