s434788/ium_434788
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

mongo?

Browse Source
This commit is contained in:
Dominik Strzako 2021-05-15 20:26:44 +02:00
parent 1425365d68
commit 61f3ba7549
1 changed files with 47 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
Zadanie_06_training.py
View File

@ -7,50 +7,69 @@ import numpy as np
import sys import sys
from sklearn.preprocessing import StandardScaler, LabelEncoder from sklearn.preprocessing import StandardScaler, LabelEncoder
from tensorflow.keras.optimizers import Adam from tensorflow.keras.optimizers import Adam
from sacred.observers import FileStorageObserver from sacred.observers import FileStorageObserver, MongoObserver
from sacred import Experiment from sacred import Experiment
from datetime import datetime from datetime import datetime
import os import os
import pymongo import pymongo
ex = Experiment("434788-mongo", interactive=False, save_git_info=False)
ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017', db_name='sacred'))
wine=pd.read_csv('train.csv') @ex.config
def my_config():
batch_param = int(sys.argv[1])
epoch_param = int(sys.argv[2])
y = wine['quality'] @ex.capture
x = wine.drop('quality', axis=1) def prepare_model(epoch_param, batch_param, _run):
_run.info["prepare_model_ts"] = str(datetime.now())
citricacid = x['fixed acidity'] * x['citric acid'] wine=pd.read_csv('train.csv')
citric_acidity = pd.DataFrame(citricacid, columns=['citric_accidity'])
density_acidity = x['fixed acidity'] * x['density'] y = wine['quality']
density_acidity = pd.DataFrame(density_acidity, columns=['density_acidity']) x = wine.drop('quality', axis=1)
citricacid = x['fixed acidity'] * x['citric acid']
citric_acidity = pd.DataFrame(citricacid, columns=['citric_accidity'])
density_acidity = x['fixed acidity'] * x['density']
density_acidity = pd.DataFrame(density_acidity, columns=['density_acidity'])
x = wine.join(citric_acidity).join(density_acidity) x = wine.join(citric_acidity).join(density_acidity)
bins = (2, 5, 8) bins = (2, 5, 8)
gnames = ['bad', 'nice'] gnames = ['bad', 'nice']
y = pd.cut(y, bins = bins, labels = gnames) y = pd.cut(y, bins = bins, labels = gnames)
enc = LabelEncoder() enc = LabelEncoder()
yenc = enc.fit_transform(y) yenc = enc.fit_transform(y)
scale = StandardScaler() scale = StandardScaler()
scaled_x = scale.fit_transform(x) scaled_x = scale.fit_transform(x)
NeuralModel = Sequential([ NeuralModel = Sequential([
Dense(128, activation='relu', input_shape=(14,)), Dense(128, activation='relu', input_shape=(14,)),
Dense(32, activation='relu'), Dense(32, activation='relu'),
Dense(64, activation='relu'), Dense(64, activation='relu'),
Dense(64, activation='relu'), Dense(64, activation='relu'),
Dense(64, activation='relu'), Dense(64, activation='relu'),
Dense(1, activation='sigmoid') Dense(1, activation='sigmoid')
]) ])
rms = Adam(lr=0.0003) rms = Adam(lr=0.0003)
NeuralModel.compile(optimizer=rms, loss='binary_crossentropy', metrics=['accuracy']) NeuralModel.compile(optimizer=rms, loss='binary_crossentropy', metrics=['accuracy'])
NeuralModel.fit(scaled_x, yenc, batch_size=int(sys.argv[1]), epochs = int(sys.argv[2])) #verbose = 1 NeuralModel.fit(scaled_x, yenc, batch_size= batch_param, epochs = epoch_param) #verbose = 1
NeuralModel.save('wine_model.h5') NeuralModel.save('wine_model.h5')
@ex.main
def my_main(train_size_param, test_size_param):
print(prepare_model())
r = ex.run()
ex.add_artifact("saved_model/saved_model.pb")