s434686/ium_z434686
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update 'create-dataset.py'

Browse Source
This commit is contained in:
Patryk Gałka 2023-05-10 19:13:25 +02:00
parent 55ff7334b4
commit 6a313cc874
1 changed files with 36 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
create-dataset.py
View File

@ -1,6 +1,10 @@
import pandas import pandas
import os import os
from keras.applications.densenet import layers
from sklearn.model_selection import train_test_split from sklearn.model_selection import train_test_split
import tensorflow
CUTOFF = int(os.environ['CUTOFF']) CUTOFF = int(os.environ['CUTOFF'])
@ -10,13 +14,16 @@ video_games = pandas.read_csv('./ium_z434686/Video_Games_Sales_as_at_22_Dec_2016
engine='python', engine='python',
encoding='ISO-8859-1', encoding='ISO-8859-1',
sep=',') sep=',')
# DROP NA FIELDS # DROP NA FIELDS
video_games = video_games.dropna() video_games = video_games.dropna()
video_games = video_games.drop(video_games.columns[[0, 1, 3, 4, 13, 14, 15]], axis=1)
# CUT OFF DATASET TO X LINES # CUT OFF DATASET TO X LINES
video_games = video_games.sample(CUTOFF) video_games = video_games.sample(CUTOFF)
X, Y = video_games, video_games X = video_games.copy()
Y = pandas.DataFrame(video_games.pop('User_Score'))
# SPLIT BETWEEN DEV, TRAINS, AND TEST # SPLIT BETWEEN DEV, TRAINS, AND TEST
X_train, X_temp, Y_train, Y_temp = train_test_split(X, Y, test_size=0.3, random_state=1) X_train, X_temp, Y_train, Y_temp = train_test_split(X, Y, test_size=0.3, random_state=1)
@ -25,3 +32,31 @@ X_dev, X_test, Y_dev, Y_test = train_test_split(X_temp, Y_temp, test_size=0.3, r
X_train.to_csv('X_train.csv', index=False) X_train.to_csv('X_train.csv', index=False)
X_dev.to_csv('X_dev.csv', index=False) X_dev.to_csv('X_dev.csv', index=False)
X_test.to_csv('X_test.csv', index=False) X_test.to_csv('X_test.csv', index=False)
Y_test.to_csv('Y_test.csv', index=False)
Y_train.to_csv('Y_train.csv', index=False)
Y_dev.to_csv('Y_dev.csv', index=False)
train_data_x = pandas.read_csv('./X_train.csv')
train_data_x = pandas.read_csv('./X_train.csv')
games_all = train_data_x.copy()
games_predict = train_data_x.pop('User_Score')
normalize = layers.Normalization()
normalize.adapt(games_all)
norm_games_model = tensorflow.keras.Sequential([
normalize,
layers.Dense(64),
layers.Dense(1)
])
norm_games_model.compile(
loss=tensorflow.keras.losses.MeanSquaredError(),
optimizer=tensorflow.keras.optimizers.Adam())
norm_games_model.fit(games_all, games_predict, epochs=500)
norm_games_model.save('test')