biblioteki_dl

Dockerfile

@@ -7,5 +7,6 @@ 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 ./kagle.py ./
+COPY ./biblioteki_dl.py ./

biblioteki_dl.py

@@ -0,0 +1,121 @@
+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)
+
+