def upload_file():
if request.method == 'POST':
# 이미지를 현재 시간을 이름으로 저장
now = time.localtime()
imageName = str(now.tm_hour) + str(now.tm_min) + str(
now.tm_sec) + str(".jpg")
f = request.files['file']
f.save("./static/uploader/" + imageName)
print("Saved File : " + "./static/uploader/" + imageName)
# 예측
img = preprocess("./static/uploader/" + imageName) #전처리
prediction = model.predict(img, verbose=1)
max_value = max(prediction[0])
print(max_value)
if max_value < 0.6:
return render_template('cannot_find.html',
name="./uploader/" + imageName)
###
### 여기에 모델이 아직 학습이 안된 경우 제외하는 코드 추가할 예정 ... 20.11.13(신지환)
###
idx = numpy.where(prediction[0] == max_value)[0][0]
s = Place_Name[str(idx)]
print(s) # 결과
return render_template('search_place.html',
name="./uploader/" + imageName,
diease=s)
def predict_data(model_path:str,data_path:str,output_path:str):
with open(model_path,'rb') as f:
model = pickle.load(f)
df = pd.read_csv(data_path)
X,y = preprocess.preprocess(df)
predictions = predict.predict(model,X)
pd.DataFrame(predictions).to_csv(output_path,index=False)
print("Predictions Done")
print("Output file saved in: %s" % output_path)
def train_model(model_path:str,data_path:str,prov:str='Córdoba'):
df=pd.read_csv(data_path)
X,y = preprocess.preprocess(df,prov)
model,X_test,y_test = train.train_randomforest(X,y)
predictions = predict.predict(model,X_test)
mse = mean_squared_error(y_test,predictions)
r2 = r2_score(y_test,predictions)
with open(model_path,'wb') as f:
pickle.dump(model,f)
print("All Done")
print("Metrics - MSE: {} R2: {}".format(mse,r2))
print("Model Saved in: %s" % model_path)
def predictEardiease(self, image_path):
with self.graph.as_default():
set_session(self.sess)
# Preprocess : Resize and CLAHE
img = preprocess(self.directory + "c_" + image_path)
# Predict
prediction = self.classificationModel.predict(img, verbose=1)
# Find Max value's Index
Accuracy = max(prediction[0])
idx = np.where(prediction[0] == Accuracy)[0][0]
return idx, Accuracy
def main(path: str):
raw_files = []
for files in glob.glob(path):
raw_files.append(files)
df = pd.read_csv(raw_files[0])
X,y = preprocess.preprocess(df)
model,X_test,y_test = train.train_randomforest(X,y)
predictions = predict.predict(model,X_test)
mse = mean_squared_error(y_test,predictions)
r2 = r2_score(y_test,predictions)
print("All Done")
print("Metrics - MSE: {} R2: {}".format(mse,r2))
preds = pd.DataFrame(predictions).reset_index().drop(columns='index')
real = pd.DataFrame(y_test).reset_index().drop(columns='index')
output = pd.concat([preds,real],axis=1,ignore_index=True)
output.columns = ['preds','real']
output.to_csv('output.csv',index=False)
from modules import preprocess, train, predict
import glob
import sys
import pandas as pd
if __name__ == '__main__':
raw_files = []
path = '../data/raw/*.csv.gz'
for files in glob.glob(path):
raw_files.append(files)
path = raw_files[0]
df = pd.read_csv(path)
df = preprocess.preprocess(df)
model, X_test, y_test = train.train_randomforest(df)
predictions, mse, r2 = predict.predict(model, X_test, y_test)
print("All Done")
print("Metrics - MSE: {} R2: {}".format(mse, r2))
preds = pd.DataFrame(predictions).reset_index().drop(columns='index')
real = pd.DataFrame(y_test).reset_index().drop(columns='index')
output = pd.concat([preds, real], axis=1, ignore_index=True)
output.columns = ['preds', 'real']
output.to_csv('output.csv', index=False)
import time
from tqdm import tqdm
from pathlib import Path
from modules.preprocess import preprocess
from modules import load_data
raw_dir = Path.cwd() / "data/gutenberg_text"
end_dir = Path.cwd() / "data/gutenberg_processed"
# Preprocess whole book list
book_data = load_data.book_data()
numbers = book_data["Catalogue number"].to_list()
books = [book for book in raw_dir.rglob("*.txt") if int(book.stem) in numbers]
start = time.time()
for b in tqdm(books):
preprocess(b, raw_dir, end_dir, use_id=False)
end = time.time()
print(f"Completed in {round((end - start)/60)} minutes")
import sys
from modules.preprocess import preprocess
from modules.skipgram import skipgram
if __name__ == '__main__':
ARGS = sys.argv
if len(ARGS) == 1 or len(ARGS) > 2:
print('処理の第一内容を引数に記載してください。')
elif ARGS[1] == 'preprocess':
preprocess()
elif ARGS[1] == 'skipgram':
skipgram()
else:
print('処理の内容を第一引数に記載してください。')