49 lines
1.8 KiB
Python
49 lines
1.8 KiB
Python
import sys
|
|
import pandas as pd
|
|
import numpy as np
|
|
from sklearn import preprocessing
|
|
from sklearn.linear_model import LinearRegression
|
|
from sklearn.metrics import mean_squared_error
|
|
import tensorflow as tf
|
|
from tensorflow import keras
|
|
from tensorflow.keras.layers import Input, Dense, Activation,Dropout
|
|
from tensorflow.keras.models import Model
|
|
from tensorflow.keras.callbacks import EarlyStopping
|
|
from tensorflow.keras.models import Sequential
|
|
|
|
# odczytanie danych z plików
|
|
vgsales_train = pd.read_csv('train.csv')
|
|
vgsales_test = pd.read_csv('test.csv')
|
|
vgsales_dev = pd.read_csv('dev.csv')
|
|
|
|
vgsales_train['Nintendo'] = vgsales_train['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
|
|
vgsales_test['Nintendo'] = vgsales_test['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
|
|
vgsales_dev['Nintendo'] = vgsales_dev['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
|
|
|
|
# podzial na X i y
|
|
X_train = vgsales_train.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
|
|
y_train = vgsales_train[['Nintendo']]
|
|
X_test = vgsales_test.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
|
|
y_test = vgsales_test[['Nintendo']]
|
|
|
|
print(X_train.shape[1])
|
|
# keras model
|
|
model = Sequential()
|
|
model.add(Dense(9, input_dim = X_train.shape[1], kernel_initializer='normal', activation='relu'))
|
|
model.add(Dense(1,kernel_initializer='normal', activation='sigmoid'))
|
|
|
|
early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
|
|
|
|
# kompilacja
|
|
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
|
|
|
|
# model fit
|
|
epochs = int(sys.argv[1])
|
|
batch_size = int(sys.argv[2])
|
|
|
|
# trenowanie modelu
|
|
model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
|
|
|
|
# zapisanie modelu
|
|
model.save('vgsales_model.h5')
|