2021-05-13 22:20:25 +02:00
|
|
|
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
|
|
|
|
|
|
|
|
|
|
pd.set_option("display.max_columns", None)
|
|
|
|
|
|
2021-05-14 00:20:04 +02:00
|
|
|
cols = ['0','ID','Title','Year','Age','IMDb','Rotten Tomatoes','Netflix','Hulu','Prime Video','Disney+','Type','Directors','Genres','Country','Language','Runtime']
|
|
|
|
|
|
2021-05-13 22:20:25 +02:00
|
|
|
# Wczytanie danych
|
2021-05-14 00:20:04 +02:00
|
|
|
train_data = pd.read_csv("./MoviesOnStreamingPlatforms_updated.train", header=None, usecols=cols)
|
2021-05-13 22:20:25 +02:00
|
|
|
|
|
|
|
|
# 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"]])
|
|
|
|
|
test_X = tf.convert_to_tensor(test_data[columns_to_use])
|
|
|
|
|
test_Y = tf.convert_to_tensor(test_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))
|
|
|
|
|
|
|
|
|
|
model.fit(train_X, train_Y, verbose=0, epochs=100)
|
|
|
|
|
|
|
|
|
|
model.save('linear_regression')
|
