ium_434704/training.py

import sys

import pandas as pd
import numpy as np
import tensorflow as tf
import os.path

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.layers.experimental import preprocessing

arguments = sys.argv[1:]

verbose = [command.split('=')[1] for command in arguments if command.split('=')[0] == 'verbose']
epochs = [command.split('=')[1] for command in arguments if command.split('=')[0] == 'epochs']


pd.set_option("display.max_columns", None)

# Wczytanie danych
train_data = pd.read_csv("./MoviesOnStreamingPlatforms_updated.train")

# Stworzenie modelu 
columns_to_use = ['Year', 'Runtime', 'Netflix']
train_X = tf.convert_to_tensor(train_data[columns_to_use])
train_Y = tf.convert_to_tensor(train_data[["IMDb"]])

normalizer = preprocessing.Normalization(input_shape=[3,])
normalizer.adapt(train_X)

if os.path.isdir('linear_regression'):
    model = keras.models.load_model('linear_regression')
else:
    model = keras.Sequential([
        keras.Input(shape=(len(columns_to_use),)),
        normalizer,
        layers.Dense(30, activation='relu'),
        layers.Dense(10, activation='relu'),
        layers.Dense(25, activation='relu'),
        layers.Dense(1)
    ])

    model.compile(loss='mean_absolute_error',
                    optimizer=tf.keras.optimizers.Adam(0.001),
                    metrics=[tf.keras.metrics.RootMeanSquaredError()])

    verbose = 0 if len(verbose) == 0 else int(verbose[0])
    epochs = 100 if len(epochs) == 0 else int(epochs[0])
    model.fit(train_X, train_Y, verbose=verbose, epochs=epochs)

    model.save('linear_regression.h5')