s444386/ium_444386
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

prepare

Browse Source
This commit is contained in:
szymonj98 2022-04-27 19:42:20 +02:00
parent ea5a76edbc
commit 27c2cb7956
9 changed files with 0 additions and 200304 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
Dockerfile
View File

@ -1,12 +0,0 @@
FROM ubuntu:latest
WORKDIR /ium
RUN apt update && apt install -y python3-pip
RUN apt install unzip
RUN pip3 install kaggle
RUN mkdir /.kaggle && chmod o+w /.kaggle
RUN pip3 install pandas
RUN pip3 install numpy
RUN pip3 install sklearn
RUN pip3 install tensorflow
COPY ./steam-200k.csv ./
COPY ./biblioteki_dl.py ./

41
Jenkinsfile vendored
View File

@ -1,41 +0,0 @@
pipeline {
parameters {
string(
defaultValue: 'szymonjadczak',
description: 'Kaggle username',
name: 'KAGGLE_USERNAME',
trim: false
)
password(
defaultValue: '',
description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
name: 'KAGGLE_KEY'
)
string(
defaultValue: '',
description: 'Value for head command',
name: 'CUTOFF'
)
}
environment {
KAGGLE_USERNAME="$params.KAGGLE_USERNAME"
KAGGLE_KEY="$params.KAGGLE_KEY"
CUTOFF="$params.CUTOFF"
}
agent {
dockerfile {
additionalBuildArgs "-t ium"
}
}
stages {
stage('Stage 1') {
steps {
echo 'Hello world!!!'
checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s444386/ium_444386']]])
sh "chmod u+x ./dataset_download.sh"
sh "KAGGLE_USERNAME=${KAGGLE_USERNAME} KAGGLE_KEY=${KAGGLE_KEY} CUTOFF=${CUTOFF} ./dataset_download.sh"
archiveArtifacts 'data.csv'
}
}
}
}

21
Jenkinsfile2
View File

@ -1,21 +0,0 @@
pipeline{
agent {
docker { image 'ium' }
}
parameters {
buildSelector(
defaultSelector: lastSuccessful(),
description: 'Which build to use for copying artifacts',
name: 'BUILD_SELECTOR')
}
stages{
stage('copy artefacts') {
steps {
copyArtifacts filter: 'data.csv', fingerprintArtifacts: true, projectName: 's444386-create-dataset', selector: lastSuccessful()
sh 'chmod u+x ./kagle.py'
sh 'python3 kagle.py'
}
}
}
}

121
biblioteki_dl.py
View File

@ -1,121 +0,0 @@
import tensorflow as tf
import os
import pandas as pd
import numpy as np
import csv
from sklearn.model_selection import train_test_split
os.system("kaggle datasets download -d tamber/steam-video-games")
os.system("unzip -o steam-video-games.zip")
steam=pd.read_csv('steam-200k.csv',usecols=[0,1,2,3],names=['userId','game','behavior','hoursPlayed'])
steam.isnull().values.any()
steam['userId'] = steam.userId.astype(str)
purchaseCount = steam[steam["behavior"] != "play"]["game"].value_counts()
playCount = steam[steam["behavior"] != "purchase"]["game"].value_counts()
playerPurchaseCount = steam[steam["behavior"] != "play"]["userId"].value_counts()
playerPlayCount = steam[steam["behavior"] != "purchase"]["userId"].value_counts()
steam = steam[steam['behavior'] != 'purchase']
steam = steam.groupby("game").filter(lambda x: len(x)>10)
size=int(len(steam)/10)
meanGame = steam[steam["behavior"] != "purchase"].groupby("game").mean()
meanGame = meanGame.to_dict()
meanGame = meanGame['hoursPlayed']
purchaseCount = purchaseCount.to_dict()
playCount = playCount.to_dict()
playerPurchaseCount = playerPurchaseCount.to_dict()
playerPlayCount = playerPlayCount.to_dict()
steam['meanTime'] = 0;
steam['purchaseCount'] = 0;
steam['playCount'] = 0;
steam['playerPurchaseCount'] =0;
steam['playerPlayCount'] =0;
steam['playPercent'] =0;
for i in steam.index:
steam.at[i,'meanTime'] = meanGame[steam.at[i,'game']]
steam.at[i,'purchaseCount'] = purchaseCount[steam.at[i,'game']]
steam.at[i,'playCount'] = playCount[steam.at[i,'game']]
steam.at[i,'playerPurchaseCount'] = playerPurchaseCount[steam.at[i,'userId']]
steam.at[i,'playerPlayCount'] = playerPlayCount[steam.at[i,'userId']]
steam.at[i,'playPercent'] = playerPlayCount[steam.at[i,'userId']]/playerPurchaseCount[steam.at[i,'userId']]
steam_train, steam_test = train_test_split(steam, test_size=size, random_state=1, stratify=steam["game"])
steam_train, steam_dev = train_test_split(steam_train, test_size=size, random_state=1, stratify=steam_train["game"])
print(steam)
games = {}
for i in steam['game']:
games[i] = 0
j=0
for key,game in games.items():
games[key]=j
j=j+1
for i in steam['game']:
i = games[i]
invGames = {v: k for k, v in games.items()}
x_train = steam_train[['hoursPlayed','purchaseCount','playCount','playerPlayCount','playerPurchaseCount']]
y_train = steam_train['game']
x_test = steam_test[['hoursPlayed','purchaseCount','playCount','playerPlayCount','playerPurchaseCount']]
y_test = steam_test['game']
x_train = np.array(x_train)
y_train = np.array(y_train)
x_test = np.array(x_test)
y_test = np.array(y_test)
for i,j in enumerate(y_train):
y_train[i] = games[j]
for i,j in enumerate(y_test):
y_test[i] = games[j]
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(5,1)),
tf.keras.layers.Dense(256, activation='relu'),
tf.keras.layers.Dropout(0.01),
tf.keras.layers.Dense(1000, activation='softmax')
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
y_train = np.array(y_train).astype(np.float32)
y_test = np.array(y_test).astype(np.float32)
model.fit(x_train, y_train, epochs=100)
model.evaluate(x_test, y_test)
prediction = model.predict(x_test)
classes_x=np.argmax(prediction,axis=1)
rows = []
for j,i in enumerate(classes_x):
row = [invGames[i],invGames[y_test[j]]]
rows.append(row)
with open('results.csv','w',encoding='UTF-8',newline='') as f:
writer = csv.writer(f)
writer.writerow(["predicted", "expected"])
for row in rows:
writer.writerow(row)

23
data.txt
View File

@ -1,23 +0,0 @@
151603712,"The Elder Scrolls V Skyrim",purchase,1.0,0
151603712,"The Elder Scrolls V Skyrim",play,273.0,0
151603712,"Fallout 4",purchase,1.0,0
151603712,"Fallout 4",play,87.0,0
151603712,"Spore",purchase,1.0,0
151603712,"Spore",play,14.9,0
151603712,"Fallout New Vegas",purchase,1.0,0
151603712,"Fallout New Vegas",play,12.1,0
151603712,"Left 4 Dead 2",purchase,1.0,0
151603712,"Left 4 Dead 2",play,8.9,0
151603712,"HuniePop",purchase,1.0,0
151603712,"HuniePop",play,8.5,0
151603712,"Path of Exile",purchase,1.0,0
151603712,"Path of Exile",play,8.1,0
151603712,"Poly Bridge",purchase,1.0,0
151603712,"Poly Bridge",play,7.5,0
151603712,"Left 4 Dead",purchase,1.0,0
151603712,"Left 4 Dead",play,3.3,0
151603712,"Team Fortress 2",purchase,1.0,0
151603712,"Team Fortress 2",play,2.8,0
151603712,"Tomb Raider",purchase,1.0,0
151603712,"Tomb Raider",play,2.5,0
151603712,"The Banner Saga",purchase,1.0,0

6
dataset_download.sh
View File

@ -1,6 +0,0 @@
kaggle datasets download -d tamber/steam-video-games
unzip -o steam-video-games.zip
> data.csv
head -n $CUTOFF steam-200k.csv >> data.csv

1
dataset_stats.sh
View File

@ -1 +0,0 @@
wc -l data.csv >> number_of_lines.txt

79
kagle.py
View File

@ -1,79 +0,0 @@
import os
import pandas as pd
from sklearn.model_selection import train_test_split
#os.system("kaggle datasets download -d tamber/steam-video-games")
#os.system("unzip -o steam-video-games.zip")
steam=pd.read_csv('data.csv',usecols=[0,1,2,3],names=['userId','game','behavior','hoursPlayed'])
steam.isnull().values.any()
steam['userId'] = steam.userId.astype(str)
print("Zbior danych:")
print(steam)
print("Describe:")
print(steam.describe(include='all'),"\n\n")
print("Gracze z najwieksza aktywnoscia:")
print(steam["userId"].value_counts(),"\n\n")
print("Gracze z najwieksza liczba kupionych gier:")
print(steam[steam["behavior"] != "play"]["userId"].value_counts())
print("Mediana:")
print(steam[steam["behavior"] != "play"]["userId"].value_counts().median(),"\n\n")
print("Gracze ktorzy zagrali w najwieksza liczbe gier:")
print(steam[steam["behavior"] != "purchase"]["userId"].value_counts())
print("Mediana:")
print(steam[steam["behavior"] != "purchase"]["userId"].value_counts().median(),"\n\n")
print("Gry:")
print(steam["game"].value_counts(),"\n\n")
print("Sredni czas grania w grania w dana gre")
print(steam[steam["behavior"] != "purchase"].groupby("game").mean().sort_values(by="hoursPlayed",ascending=False))
print("Mediana:")
print(steam[steam["behavior"] != "purchase"].groupby("game").mean().sort_values(by="hoursPlayed",ascending=False).median(),"\n\n")
print("Najczesciej kupowana gra")
print(steam[steam["behavior"] != "play"]["game"].value_counts())
print("Mediana:")
print(steam[steam["behavior"] != "play"]["game"].value_counts().median(),"\n\n")
print("Gra w ktora zagralo najwiecej graczy")
print(steam[steam["behavior"] != "purchase"]["game"].value_counts())
print("Mediana:")
print(steam[steam["behavior"] != "purchase"]["game"].value_counts().median(),"\n\n")
print("Liczba kupionych gier i liczba gier w ktore gracze zagrali")
print(steam["behavior"].value_counts(),"\n\n")
print("Gra z najwieksza liczba godzin dla jednego gracza")
print(steam[steam["behavior"] != "purchase"][["userId","hoursPlayed","game"]].sort_values(by="hoursPlayed",ascending=False))
print("Mediana:")
print(steam[steam["behavior"] != "purchase"]["hoursPlayed"].sort_values(ascending=False).median(),"\n\n")
print("Suma rozegranych godzin dla danej gry")
print(steam[steam["behavior"] != "purchase"].groupby("game").sum().sort_values(by="hoursPlayed",ascending=False))
print("Mediana:")
print(steam[steam["behavior"] != "purchase"].groupby("game").sum().sort_values(by="hoursPlayed",ascending=False).median(),"\n\n")
#odrzucenie gier dla których jest mniej niż 10 wierszy
steam = steam.groupby("game").filter(lambda x: len(x)>10)
#rozmiar zbioru testowego i dev proporcje 8:1:1
size=int(len(steam)/10)
steam_train, steam_test = train_test_split(steam, test_size=size, random_state=1, stratify=steam["game"])
steam_train, steam_dev = train_test_split(steam_train, test_size=size, random_state=1, stratify=steam_train["game"])
print("Zbior trenujacy")
print(steam_train["game"].value_counts(),"\n")
print("Zbior testujacy")
print(steam_test["game"].value_counts(),"\n")
print("Zbior dev")
print(steam_dev["game"].value_counts(),"\n")

200000
steam-200k.csv
View File

File diff suppressed because it is too large Load Diff