import csv
import pickle
with open("./NHIS_OPEN_GJ_2015.csv") as csvfile:
reader = csv.reader(csvfile)
header = next(reader, None)
#header = {header[i]:i for i in range(0, len(header))}
table = list()
for row in reader:
row = {header[i] : row[i] for i in range(len(header))}
if row["신장(5Cm단위)"] == "" or row["체중(5Kg 단위)"] == "" or row["허리둘레"] == "":
continue
bmi = round(1000 * int(row["신장(5Cm단위)"]) / (int(row["체중(5Kg 단위)"]) ** 2), 2)
label = 0
if bmi > 40:label = 3
elif bmi > 35:label = 2
elif bmi > 30:label = 1
nrow = {
"height":int(row["신장(5Cm단위)"]),
"weight":int(row["체중(5Kg 단위)"]),
"waist":int(row["허리둘레"]),
"overweight":label
}
table.append(nrow)
dic = []
for i in range(4):
v = [it for it in table if it["overweight"] == i]
print(len(v))
dic.append(v)
with open("./preprocessing2015.pkl","wb+") as fw:
pickle.dump(table, fw, protocol = pickle.HIGHEST_PROTOCOL)
SVM
import pickle
from matplotlib import pyplot as plt
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
clf= SVC(kernel='poly', probability=True)
x = pickle.load(open('preprocessing2015.pkl', "rb"))
y = pickle.load(open('preprocessing2016.pkl', "rb"))
x = [x[i] for i in range(len(x)) if i % 1000 == 0]
y = [y[i] for i in range(len(y)) if i % 1000 == 0]
data_test = [[row["waist"], row["height"]] for row in y]
labels_test = [row["overweight"] for row in y]
data_train = [[row["waist"], row["height"]] for row in x]
labels_train = [row["overweight"] for row in x]
## 3-1) training
clf.fit(data_train, labels_train)
## 3-2) prediction
prediction_test= clf.predict(data_test)
probability_test= clf.predict_proba(data_test)[:,1]
## 4. Evaluate the model
from sklearn.metrics import confusion_matrix, roc_auc_score
## 4-1) AUC
#auc= roc_auc_score(labels_test, probability_test)
## 4-2) Confusion matrix
#tn, fp, fn, tp= confusion_matrix(labels_test, prediction_test).ravel()
#accuracy = (tp+ tn) / (tn+ fp+ fn+ tp)
#sensitivity = tp/ (tp+ fn)
#specificity = tn/ (fp+ tn)
#precision = tp/ (tp+ fp)
#recall = tp/ (tp+ fn)
#fscore= 2 * precision * recall / (precision + recall)
fig, axs = plt.subplots(1, 2, figsize=(1000, 1000))
axs[0].scatter([row[1] for row in data_test], [row[0] for row in data_test],s = None,c = labels_test)
axs[1].scatter([row[1] for row in data_test], [row[0] for row in data_test],s = None,c = prediction_test)
plt.show()
Deeplearning
import pickle
from matplotlib import pyplot as plt
from sklearn.neural_network import MLPClassifier
clf= MLPClassifier(hidden_layer_sizes=(1024,256,32),
activation='logistic', # sigmoid
solver='adam', # adamgradient optimizer
learning_rate_init=0.01)
x = pickle.load(open('preprocessing2016.pkl', "rb"))
y = pickle.load(open('preprocessing2015.pkl', "rb"))
x = [x[i] for i in range(len(x)) if i % 100 == 0]
y = [y[i] for i in range(len(y)) if i % 100 == 0]
data_test = [[row["weight"], row["height"]] for row in y]
labels_test = [row["overweight"] for row in y]
data_train = [[row["weight"], row["height"]] for row in x]
labels_train = [row["overweight"] for row in x]
## 3-1) training
clf.fit(data_train, labels_train)
## 3-2) prediction
prediction_test= clf.predict(data_test)
probability_test= clf.predict_proba(data_test)[:,1]
## 4. Evaluate the model
from sklearn.metrics import confusion_matrix, roc_auc_score
## 4-1) AUC
#auc= roc_auc_score(labels_test, probability_test)
## 4-2) Confusion matrix
#tn, fp, fn, tp= confusion_matrix(labels_test, prediction_test).ravel()
accuracy = (tp+ tn) / (tn+ fp+ fn+ tp)
sensitivity = tp/ (tp+ fn)
specificity = tn/ (fp+ tn)
precision = tp/ (tp+ fp)
recall = tp/ (tp+ fn)
fscore= 2 * precision * recall / (precision + recall)
fig, axs = plt.subplots(1, 2, figsize=(1000, 1000))
axs[0].scatter([row[1] for row in data_test], [row[0] for row in data_test],s = None,c = labels_test)
axs[1].scatter([row[1] for row in data_test], [row[0] for row in data_test],s = None,c = prediction_test)
plt.show()
keras
# 0. 사용할 패키지 불러오기
import pickle
from matplotlib import pyplot as plt
from keras.utils import np_utils
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Activation
import numpy
fig, axs = plt.subplots(1, 2, figsize=(512, 512))
# 1. 데이터셋 생성하기
#(x_train, y_train), (x_test, y_test) = mnist.load_data()
#x_train = x_train.reshape(60000, 784).astype('float32') / 255.0
#x_test = x_test.reshape(10000, 784).astype('float32') / 255.0
#y_train = np_utils.to_categorical(y_train)
#y_test = np_utils.to_categorical(y_test)
#print(x_train[0])
x = pickle.load(open('preprocessing2016.pkl', "rb"))
y = pickle.load(open('preprocessing2015.pkl', "rb"))
x = [x[i] for i in range(len(x)) ]
y = [y[i] for i in range(len(y)) if i % 10 == 0 ]
#waist = [ row["waist"] for row in x]
#waist_min = numpy.min(waist)
#waist_max = numpy.max(waist)
#waist = [(item - waist_min)/(waist_max - waist_min) for item in waist]
#height = [ row["height"] for row in x]
#height_min = numpy.min(height)
#height_max = numpy.max(height)
#height = [(item - height_min)/(height_max - height_min) for item in height]
test_data= numpy.array([[it["waist"], it["height"]] for it in y])
test_labels =[row["overweight"] for row in y]
train_data = numpy.array( [ [it["waist"], it["height"]] for it in x])
train_labels =np_utils.to_categorical([row["overweight"] for row in x],4)
#print("max: ",numpy.max( [row["weight"] for row in y]),"min: ",numpy.min( [row["weight"] for row in y]))
# 2. 모델 구성하기
model = Sequential()
model.add(Dense(1024, input_dim=2, activation="sigmoid"))
model.add(Dense(512, activation="sigmoid"))
model.add(Dense(128, activation="sigmoid"))
model.add(Dense(units=4, activation='softmax'))
# 3. 모델 학습과정 설정하기
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# 4. 모델 학습시키기
hist = model.fit(train_data, train_labels, epochs=20, batch_size=1024 * 10)
# 5. 학습과정 살펴보기
print('## training loss and acc ##')
print(hist.history['loss'])
print(hist.history['acc'])
# 6. 모델 평가하기
loss_and_metrics = model.evaluate(test_data, np_utils.to_categorical(test_labels,4), batch_size=1024 * 10)
print('## evaluation loss and_metrics ##')
print(loss_and_metrics)
# 7. 모델 사용하기
#xhat = x_test[0:1]
yhat = model.predict(test_data)
model = None
#print('## yhat ##')
#print(yhat)
from matplotlib import pyplot as plt
predict_set = [numpy.argmax(item) for item in yhat]
for i in range(4):
print(sum([1 for row in y if row["overweight"] == i]))
for i in range(4):
print(sum([1 for it in predict_set if it == i]))
axs[0].scatter([row[1] for row in test_data], [row[0] for row in test_data],s = None,c = test_labels)
axs[1].scatter([row[1] for row in test_data], [row[0] for row in test_data],s = None,c = predict_set)
plt.show()