def main(arg=None):
#load npz file.
weights = np.load('./vgg16_weights.npz')
#Weights_Tranined store the data of vgg16_weights.npz that download from internet.
#For example: As a member of Weights_Tranined, 'conv11_w' corresponds with the
# weights of the first conv3-64. 'conv11_b' corresponds with the bias
# of the first conv3-64.
w_trained = Weights_Tranined(weights)
#Build training and validation sets
data_path = os.path.join(os.getcwd(), 'fmnist')
print(data_path)
imgs, labels = pre.processing(data_path, CLASS_NUM)
train_img, train_label, validation_img, validation_label = pre.split(
imgs, labels)
print(train_img.shape)
print(train_label.shape)
train_model(t_x=train_img,
t_y=train_label,
weights=w_trained,
dprate=DROPOUT_RATE,
imgsize=IMG_SIZE,
imgchannel=IMG_CHANNEL,
batchsize=BATCH_SIZE,
train_step=TRAINING_STEP,
learningrate=LEARNING_RATE_BASE,
learningdecay=LEARNING_RATE_DECAY,
regurate=REGULARIZATION_RATE)
def split_sample(file_name):
#splitting datasets into test and train
import preprocess as sp
train_df,test_df = sp.split(file_name)
#(random sampling)bagging train data
dataset_name,file_type = file_name.split('.')
dataset_name_train = dataset_name + "_train.csv"
#(random sampling)bagging test data
dataset_name,file_type = file_name.split('.')
dataset_name_test = dataset_name + "_test.csv"
return dataset_name_train,dataset_name_test,train_df,test_df
def score(filename, disp=True):
cleaned_df = clean('oasis_longitudinal.csv')
_, X_test, _, Y_test = split(cleaned_df)
model = pickle.load(open(filename, 'rb'))
Y_pred = model.predict(X_test)
recall = recall_score(Y_test, Y_pred)
accuracy = accuracy_score(Y_test, Y_pred)
if disp:
print(model)
print(f"Accuracy = {accuracy}")
print(f"Recall= {recall}")
return model
def generate_data(self, seq2seq=False):
import generator as gen
series = gen.complete(self.time, pg.baseline, pg.slope, pg.period,
pg.amplitude, pg.noise_level)
train, valid = pp.split(pg.time, series, pg.split_time)
train_set = pp.window_dataset(train[1],
pm.window_size,
pm.batch_size,
seq2seq=seq2seq)
valid_set = pp.window_dataset(valid[1],
pm.window_size,
pm.batch_size,
seq2seq=seq2seq)
self.main_series = series
self.set_data(train_set, valid_set)
def id3(examples, attributes): root = dt.TreeNode() one_count = sum([int(y) for X, y in examples]) if one_count == len(examples): root.label = 1 return root if one_count == 0: root.label = 0 return root if not attributes: if one_count >= len(examples) / 2.0: root.label = 1 else: root.label = 0 return root best_attribute, best_value, info_gain = pp.split(examples, attributes) if info_gain == 0: if one_count >= len(examples) / 2.0: root.label = 1 else: root.label = 0 return root root.attribute = best_attribute root.split_value = best_value left_exs = [] right_exs = [] for ex in examples: if ex[0][root.attribute] <= root.split_value: left_exs.append(ex) else: right_exs.append(ex) new_attributes = attributes.copy() new_attributes.remove(best_attribute) root.left_child = id3(left_exs, new_attributes) root.right_child = id3(right_exs, new_attributes) return root
def id3(examples, attributes):
root = dt.TreeNode()
one_count = sum([int(y) for X, y in examples])
if one_count == len(examples):
root.label = 1
return root
if one_count == 0:
root.label = 0
return root
if not attributes:
if one_count >= len(examples) / 2.0:
root.label = 1
else:
root.label = 0
return root
best_attribute, best_value, info_gain = pp.split(examples, attributes)
if info_gain == 0:
if one_count >= len(examples) / 2.0:
root.label = 1
else:
root.label = 0
return root
root.attribute = best_attribute
root.split_value = best_value
left_exs = []
right_exs = []
for ex in examples:
if ex[0][root.attribute] <= root.split_value:
left_exs.append(ex)
else:
right_exs.append(ex)
new_attributes = attributes.copy()
new_attributes.remove(best_attribute)
root.left_child = id3(left_exs, new_attributes)
root.right_child = id3(right_exs, new_attributes)
return root
def run():
for gap in xrange(7):
expansion = False
data, comm = preprocess.loadData(gap, expansion)
train_data, test_data = preprocess.split(data, comm)
train = np.array(train_data[0])
test = np.array(test_data[0])
test_com = test_data[1]
train_x = train[:, 1:]
train_y = train[:, 0]
print train_x.shape
reg = gcv(train_x, train_y)
if len(sys.argv) > 1 and sys.argv[1] == 'output':
test_x = test[:, 1:]
pred = reg.predict(test_x)
output_test(pred, test_com, gap)
def id3_depth_limited(examples, attributes, depth): root = dt.TreeNode() if sum([y for X, y in examples]) == len(examples): root.label = 1 return root if sum([y for X, y in examples]) == 0: root.label = 0 return root if not attributes or depth == 0: if sum([y for X, y in examples]) >= len(examples) / 2.0: root.label = 1 else: root.label = 0 return root best_attribute, best_value, info_gain = pp.split(examples, attributes) if info_gain == 0: if sum([y for X, y in examples]) >= len(examples) / 2.0: root.label = 1 else: root.label = 0 return root root.attribute = best_attribute root.split_value = best_value left_exs = [] right_exs = [] for ex in examples: if ex[0][root.attribute] <= root.split_value: left_exs.append(ex) else: right_exs.append(ex) new_attributes = attributes.copy() new_attributes.remove(best_attribute) root.left_child = id3_depth_limited(left_exs, new_attributes, depth-1) root.right_child = id3_depth_limited(right_exs, new_attributes, depth-1) return root
def id3_depth_limited(examples, attributes, depth):
root = dt.TreeNode()
if sum([y for X, y in examples]) == len(examples):
root.label = 1
return root
if sum([y for X, y in examples]) == 0:
root.label = 0
return root
if not attributes or depth == 0:
if sum([y for X, y in examples]) >= len(examples) / 2.0:
root.label = 1
else:
root.label = 0
return root
best_attribute, best_value, info_gain = pp.split(examples, attributes)
if info_gain == 0:
if sum([y for X, y in examples]) >= len(examples) / 2.0:
root.label = 1
else:
root.label = 0
return root
root.attribute = best_attribute
root.split_value = best_value
left_exs = []
right_exs = []
for ex in examples:
if ex[0][root.attribute] <= root.split_value:
left_exs.append(ex)
else:
right_exs.append(ex)
new_attributes = attributes.copy()
new_attributes.remove(best_attribute)
root.left_child = id3_depth_limited(left_exs, new_attributes, depth - 1)
root.right_child = id3_depth_limited(right_exs, new_attributes, depth - 1)
return root
if mode == "train":
print "Training the bayes model"
bayes_model(mode="train")
elif mode == "test":
if os.path.exists(bayes_model_file):
print "Model is already trained! Reading the file ..."
trained_model = pickle.load(open(bayes_model_file, "rb"))
bayes_model(mode="test", trained_model=trained_model)
else:
print "Model file not found :("
elif mode == "score":
bayes_model(mode="score")
elif mode == "join":
pre.join_per_business()
elif mode == "split":
pre.split()
elif sys.argv[1] == 'neural-net':
mode = str(sys.argv[2])
if mode in ["train", "test"]:
neural_net(mode)
# if os.path.exists(bayes_model_file):
# print "Model is already trained! Reading the file ..."
# trained_model = pickle.load(open(bayes_model_file, "rb"))
# bayes_model(mode="test", trained_model=trained_model)
# else:
# print "Model file not found :("
elif mode == "score":
bayes_model(mode="score")
elif mode in ["join", "split"]:
pre.join_and_split(mode=mode)
elif sys.argv[1] == 'scikit-classifier':
mode = sys.argv[1]
input = pd.read_csv(sys.argv[2])
params = json.load(open(sys.argv[3]))
feature = params[FEATURES]
label = params[LABELS]
print('FEATURE: {}\nLABEL: {}'.format(feature, label))
data = pd.DataFrame(columns={label, feature})
data[feature] = filter(input[feature])
if mode == TRAIN:
# preprocess labels
data[label] = filter(input[label])
data[label] = clean(data[label], 'label')
y = data.pop(label)
X_train, y_train, X_test, y_test = split(data, y,
0.3) #train-test ratio 70:30
X_train[label] = y_train
X_test[label] = y_test
X_test.to_csv(PATH + 'test_file.csv', sep=',')
print('Begin training -- TRAIN: {} TEST: {}'.format(
len(X_train), len(X_test)))
# create the datasets for training
test_file, dev_file, train_file = format_data(X_train, label, 0.3)
# train model
model = train(PATH, test_file, dev_file, train_file)
# evaluate
import numpy as np
import pandas as pd
import algo
import preprocess
import recommend
# raw data
movies_raw = pd.read_table('./ml-1m/movies.dat', sep = '::', names = ['MovieID', 'Title', 'Genres'], engine = 'python')
ratings_raw = pd.read_table('./ml-1m/ratings.dat', sep = '::', names = ['UserID', 'MovieID', 'Rating', 'Timestamp'],engine = 'python')
users_raw = pd.read_table('./ml-1m/users.dat', sep = '::', names = ['UserID','Gender','Age','Occupation','Zip-code'], engine = 'python')
##################################### Part - 1 Refining dataset and creating test set
# separting test sets i.e. new users and new movies
ratings_raw, user_test, movie_test = preprocess.split(ratings_raw, fraction = 0.1)
# refining ratings_raw
ratings_nan = ratings_raw.iloc[:,0:3]
ratings_nan = ratings_nan.pivot(index='UserID', columns='MovieID', values='Rating')
# process info of users who have rated
users = preprocess.user_info(users_raw,ratings_raw)
# process info of movie been rated
movies, genres = preprocess.movie_info(movies_raw, ratings_raw)
# genre mapping : helps to convert a new movie vector
lst = []
for i in range(0,len(genres)):
lst.append((genres[i],i))
genre_mapping = dict(lst)
import embedding
import model
import preprocess
from sklearn.model_selection import KFold
input_dataset = './Augmented_Feat.csv'
embedmodel = embedding.train_word2vec('./glove.6B.300d.txt')
question = './questions.csv'
df = preprocess.cleaning_dataset(input_dataset)
df = preprocess.question_demoting(df, question)
X, y = preprocess.scale(df)
X_train, X_test, y_train, y_test = preprocess.split(X, y, 0.2)
split = 5
index = 0
train_model = [None] * split
tokenizer = [None] * split
acc = [None] * split
kfold = KFold(n_splits=split, shuffle=True, random_state=101)
for train, test in kfold.split(X_train, y_train):
train_model[index], tokenizer[index] = model.train(X_train.iloc[train], y_train[train], embedmodel)
test_results = model.predict(X_train.iloc[test], train_model[index], tokenizer[index])
test_results, y_true = model.processresult(test_results, y_train[test])
acc[index], _ = model.evaluate(test_results, y_true)
index += 1
index = 0
def main(args):
# Create output folder
util.mkdir(args['output'], args['clean'])
# Tensorflow logging
tf.logging.set_verbosity(tf.logging.WARN)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '1'
# Logging to DWF server
dwf_logging = None
# Logging
logger = logging.getLogger('DeepBugHunter')
if 'dwf_client_info' in args:
client_info = args['dwf_client_info']
sys.path.insert(0, client_info['util_path'])
dwf_logging = __import__('dwf_logging')
if not logger.handlers:
formatter = logging.Formatter(fmt='%(asctime)s %(levelname)-8s %(message)s',
datefmt='%Y-%m-%d %H:%M:%S')
logger.setLevel(logging.DEBUG)
fh = logging.FileHandler(os.path.join(args['output'], 'dbh.log'), mode='a')
fh.setLevel(logging.DEBUG)
fh.setFormatter(formatter)
logger.addHandler(fh)
if 'dwf_client_info' in args:
http_handler = dwf_logging.LogHandler()
http_handler.setLevel(logging.INFO)
logger.addHandler(http_handler)
else:
ch = logging.StreamHandler()
ch.setLevel(logging.INFO)
ch.setFormatter(formatter)
logger.addHandler(ch)
extra_log_data = {}
if dwf_logging is not None:
extra_log_data = {'progress' : 0, 'hash' : client_info['client_id']}
logger.info(msg='DBH started...', extra=extra_log_data)
logger.info('Input csv is ' + args['csv'])
# Seeding global random states, just in case...
tf.set_random_seed(args['seed'])
# This is used for sklearn algorithms under the hood so we don't have to manually
# set the random seed separately every time
np.random.seed(args['seed'])
# Load the whole input
data = csv2pandas.load_data(args['csv'], args['label'], args['seed'])
# Apply optional preprocessing
for (what, how) in args['preprocess']:
# TODO: use <what> and generalize preprocessors
data = getattr(preprocess, how)(*data)
table = []
strategy_i = 0
strategy_cnt = len(args['strategy'])
for (strategy, sargs) in args['strategy']:
strategy_i += 1
logger.info('(%d/%d) Strategy "%s" started with args: <%s>', strategy_i, strategy_cnt, strategy, sargs)
# Aggregate confusion matrices
cv_train = ConfMatrix()
cv_dev = ConfMatrix()
cv_test = ConfMatrix()
# For each fold
fold_generator = preprocess.split(data, folds=FOLDS, seed=args['seed'])
fold_i = 0
for remainder, test in fold_generator():
fold_i += 1
# A single dev split
# Not fully fair, but fairer...
train, dev = next(preprocess.split(remainder, folds=FOLDS, seed=args['seed'])())
# Resample the training set
if args['resample'] is not 'none':
train = preprocess.resample(*train, mode=args['resample'], amount=args['resample_amount'], seed=args['seed'])
# Evalute according to the current strategy
train_res, dev_res, test_res, cl = getattr(strategies, strategy).learn(train, dev, test, args, sargs)
# Aggregate metrics for cross-validation F-Measure
cv_train.add(train_res)
cv_dev.add(dev_res)
cv_test.add(test_res)
if args['calc_completeness']:
preds = getattr(strategies, strategy).predict(cl, dev, args, sargs)
issues = preprocess.get_orig_labels(dev[1])
cv_dev.calc_completeness(preds, issues)
preds = getattr(strategies, strategy).predict(cl, test, args, sargs)
issues = preprocess.get_orig_labels(test[1])
cv_test.calc_completeness(preds, issues)
if dwf_logging is not None:
extra_log_data = {'progress' : fold_i / FOLDS, 'hash' : client_info['client_id']}
logger.info('Fold %d/10 done', fold_i, extra=extra_log_data)
train_stats = cv_train.stats(False)
dev_stats = cv_dev.stats(args['calc_completeness'])
test_stats = cv_test.stats(args['calc_completeness'])
logger.info('%s[%s] results:', strategy, sargs)
logger.info('train: %s', train_stats)
logger.info('dev: %s', dev_stats)
logger.info('test: %s', test_stats)
if dwf_logging is not None:
result = dwf_logging.pack_results(train_stats, dev_stats, test_stats)
dwf_logging.report_result(result, client_info['client_id'])
table.append([
args['resample'],
args['resample_amount'],
args['preprocess'],
strategy,
sargs,
train_stats['fmes'],
dev_stats['fmes'],
test_stats['fmes'],
train_stats,
dev_stats,
test_stats,
])
with open(os.path.join(args['output'], 'dbh.csv'), 'a') as f:
for line in table:
f.write(';'.join([str(item) for item in line]) + '\n')
def get_data(type, oneyear): #without sequences
data = read_data()
proc_data, y = prepare_data(oneyear, data)
x_train, x_test, y_train, y_test = split(proc_data, y, type)
return x_train, x_test, y_train, y_test
def plot_forecast(self):
series = self.main_series[pg.split_time - pm.window_size:-1]
fc = self.forecast(series)[:, 0]
_, valid = pp.split(pg.time, self.main_series, pg.split_time)
from support import plot_series
plot_series(valid[0], [valid[1], fc], labels=["Real", "Forecast"])
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import AdaBoostClassifier
import pickle
from preprocess import clean, split
cleaned_df = clean('oasis_longitudinal.csv')
X_train, X_test, Y_train, Y_test = split(cleaned_df)
logistic_model = LogisticRegression(C=10).fit(X_train, Y_train)
forest_model = RandomForestClassifier(n_estimators=3,
max_features=4,
n_jobs=4,
max_depth=5,
random_state=0).fit(X_train, Y_train)
tree_model = DecisionTreeClassifier(random_state=0,
max_depth=1,
criterion='gini').fit(X_train, Y_train)
adaboost_model = AdaBoostClassifier(n_estimators=3,
learning_rate=0.0001,
random_state=0).fit(X_train, Y_train)
pickle.dump(logistic_model, open('model_files/logistic.sav', 'wb'))
pickle.dump(forest_model, open('model_files/forest.sav', 'wb'))
pickle.dump(tree_model, open('model_files/tree.sav', 'wb'))
pickle.dump(adaboost_model, open('model_files/adaboost.sav', 'wb'))
def naive(series, split_time):
return series[split_time - 1:-1]
def moving_average(series, window_size):
mov = np.cumsum(series)
mov[window_size:] = mov[window_size:] - mov[:-window_size]
return mov[window_size - 1:-1] / window_size
series = gen.complete(p.time, p.baseline, p.slope, p.period, p.amplitude,
p.noise_level)
time2, series2 = pp.remove_season(time, series)
train, valid = pp.split(time, series, split_time)
train2, valid2 = pp.split(time, series2, split_time - period)
naive_prediction = naive(series, split_time)
plot_series(valid[0], [valid[1], naive_prediction],
labels=["Series", "Naive Forecast"])
print(mae(naive_prediction, valid[1]))
window = 30
moving_avg = moving_average(series, window)[split_time - window:]
plot_series(valid[0], [valid[1], moving_avg],
labels=["Series", "Moving average (30 days)"])
print(mae(moving_avg, valid[1]))
window = 50
diff_moving_avg = moving_average(series2,
def main():
args = sys.argv
ARG_NUM = 5
if(len(sys.argv) < ARG_NUM):
print("Error")
sys.exit(0)
df = pd.read_csv('COVID-19/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv')
df = df[df['Country/Region']=='Japan']
df = df.iloc[:,4:].copy()
data_at_japan = df.iloc[0,:]
data_at_japan.index = pd.to_datetime(data_at_japan.index)
#print(data_at_japan)
plt.figure(figsize=(10,5))
plt.plot(data_at_japan)
plt.title('COVID-19 confilmed at Japan', y = -0.2)
plt.xlabel("Date")
plt.ylabel("Person infected (people)")
plt.grid(True)
#plt.show()
#ファイル保存
fname_1 ='original.png'
plt.savefig(fname_1)
plt.close()
data_at_japan_diff = data_at_japan - data_at_japan.shift(1) # 階差系列データの作成
data_at_japan_diff = data_at_japan_diff.dropna()
data_at_japan_diff = data_at_japan_diff['2020-01-23':'2020-10-28']#10-28
#print(data_at_japan_diff)
plt.figure(figsize=(10,5))
plt.plot(data_at_japan_diff)
plt.title('COVID-19 confilmed at Japan', y=-0.2)
plt.xlabel("Date")
plt.ylabel("Person infected (people)")
plt.grid(True)
#plt.show()
#ファイル保存
fname_2 ='diff.png'
plt.savefig(fname_2)
plt.close()
res = sm.tsa.seasonal_decompose(data_at_japan_diff)#データを分解
original = data_at_japan_diff # オリジナルデータ
trend_original = res.trend # トレンドデータ
seasonal_original = res.seasonal # 季節性データ
residual = res.resid # 残差データ
plt.figure(figsize=(10, 20)) # グラフ描画枠作成、サイズ指定
plt.subplot(411) # グラフ4行1列の1番目の位置（一番上）
plt.plot(original)
plt.title('COVID-19 confilmed(Original) at Japan', y=-0.17)
plt.xlabel("Date")
plt.ylabel("Person infected (people)")
plt.grid(True)
# trend データのプロット
plt.subplot(412) # グラフ4行1列の2番目の位置
plt.plot(trend_original)
plt.title('COVID-19 confilmed(Trend) at Japan', y=-0.17)
plt.xlabel("Date")
plt.ylabel("Person infected (people)")
plt.grid(True)
# seasonalデータ のプロット
plt.subplot(413) # グラフ4行1列の3番目の位置
plt.plot(seasonal_original)
plt.title('COVID-19 confilmed(Seasonality) at Japan', y=-0.17)
plt.xlabel("Date")
plt.ylabel("Person infected (people)")
plt.grid(True)
# residual データのプロット
plt.subplot(414) # グラフ4行1列の4番目の位置（一番下）
plt.plot(residual)
plt.title('COVID-19 confilmed(Residuals) at Japan', y=-0.17)
plt.xlabel("Date")
plt.ylabel("Person infected (people)")
plt.grid(True)
plt.tight_layout() # グラフの間隔を自動調整
fname_3 ='decompose.png'
plt.savefig(fname_3)
y = data_at_japan_diff.values.astype(float)
test_size = 7# test_size
train_original_data, test_original_data = split(y)
train_normalized = normalized(train_original_data)
window = 7# 学習時のウィンドウサイズ
study_data, correct_data = sequence_creator(train_normalized, window)
n_in_out = 1
n_hidden = args[1]
drop_out = args[2]
tf.random.set_seed(0)
# parameters = {
# 'n_hidden': [16, 32, 64, 128, 256, 512, 1024]
# 'dropout': [0, 0.2, 0.4, 0.5, 0.6],
# }
# model = KerasClassifier(build_fn=gru,
# verbose=0)
# gridsearch = GridSearchCV(estimator=model, param_grid=parameters)
# gridsearch.fit(study_data, correct_data)
# print('Best params are: {}'.format(gridsearch.best_params_))
gru = gru(n_in_out, n_hidden, drop_out)
print(gru.summary())
filename = 'gru_'+str(n_hidden)+'_'+str(drop_out)+'.png'
plot_model(gru, show_shapes=True, show_layer_names=True, to_file=filename)
Image(retina=False, filename=filename)
epochs = 1
start_time = time.time()
history = gru.fit(study_data, correct_data, batch_size=1, epochs=epochs, validation_split=0.1, verbose=1, callbacks=[])#lr_decay,
print("学習時間:",time.time() - start_time)
# === 学習推移の可視化 ===
# mse
train_loss = history.history['loss']
val_loss = history.history['val_loss']
plt.plot(np.arange(len(train_loss)), train_loss, label="train_loss")
plt.plot(np.arange(len(val_loss)), val_loss, label="val_loss")
plt.title('Training and Validation loss')
plt.ylim((0, 0.04))#add
plt.legend()
# plt.show()
# === 学習推移の可視化 ===
# mae
train_mae = history.history['mae']
val_mae = history.history['val_mae']
plt.plot(np.arange(len(train_mae)), train_mae, label="train_mae")
plt.plot(np.arange(len(val_mae)), val_mae, label="val_mae")
plt.title('Training and Validation mae')
plt.ylim((0, 0.2))#add
plt.legend()
#plt.show()
train_inverse = past_predict(study_data)
upcoming_future=7
predictions_infected_pepole = test_predict(upcoming_future)
x_all =np.arange('2020-01-23','2020-10-29', dtype='datetime64[D]').astype('datetime64[D]')
x_past_predict = np.arange('2020-01-30','2020-10-22', dtype='datetime64[D]').astype('datetime64[D]')#23-26
x_train = np.arange('2020-01-23','2020-10-22', dtype='datetime64[D]').astype('datetime64[D]')
x_test = np.arange('2020-10-22', '2020-10-29', dtype='datetime64[D]').astype('datetime64[D]')
sns.set()
COVID = plt.figure(figsize=(20,8))
plt.title("COVID-19 in Japan", y=-0.15)
plt.grid(True)
plt.xlabel("Date")
plt.ylabel("Nunber of Person infected with corona virus (people)")
plt.plot(x_all,data_at_japan_diff,'g',lw=3,label='daily_at_japan')
# plt.plot(x_train,train_original_data,label='train_data')
# plt.plot(x_test,test_original_data,label='test_data')
plt.plot(x_past_predict,train_inverse,color='b', ls='-',lw=3,alpha=0.7, label='past_predict')#+8かも
plt.plot(x_test, predictions_infected_pepole, 'r',lw=3,alpha=0.7,label='upcoming_future')
plt.legend(loc='upper left')
#plt.show()
sns.set()
COVID = plt.figure(figsize=(20,8))
plt.title("COVID-19 in Japan", y=-0.15)
plt.grid(True)
plt.xlabel("Date")
plt.ylabel("Nunber of Person infected with corona virus (people)")
plt.plot(x_test,test_original_data,color='b', ls='-',lw=3,alpha=0.7, label='past_predict')
plt.plot(x_test, predictions_infected_pepole, 'r',lw=3,alpha=0.7,label='upcoming_future')
#plt.show()
train_mae, train_mse, train_rmse, train_r2, test_mae, test_mse, test_rmse, test_r2 = eval_func(train_inverse, test_original_data, predictions_infected_pepole)