training changes

Jenkinsfile

@@ -29,7 +29,7 @@ pipeline {
         }
       stage('archiveArtifacts') {
 			steps{
-				archiveArtifacts 'model1.h5'
+				archiveArtifacts 'vgsales_model.h5'
 			}
 		}
     }

train.py

@@ -1,42 +1,48 @@
-#! /usr/bin/python3
-from tensorflow.keras.models import Sequential, load_model
-from tensorflow.keras.layers import Dense
-from sklearn.metrics import accuracy_score, classification_report
+import sys
 import pandas as pd
-from sklearn.model_selection import train_test_split
 import numpy as np
-import requests
-url = 'https://git.wmi.amu.edu.pl/s434695/ium_434695/raw/commit/2301fb86e434734376f73503307a8f3255a75cc6/vgsales.csv'
-r = requests.get(url, allow_redirects=True)
+from sklearn import preprocessing
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras.layers import Input, Dense, Activation,Dropout
+from tensorflow.keras.models import Model
+from tensorflow.keras.callbacks import EarlyStopping
+from tensorflow.keras.models import Sequential
 
-open('vgsales.csv', 'wb').write(r.content)
-df = pd.read_csv('vgsales.csv')
+# odczytanie danych z plików
+vgsales_train = pd.read_csv('train.csv')
+vgsales_test = pd.read_csv('test.csv')
+vgsales_dev = pd.read_csv('dev.csv')
 
+vgsales_train['Nintendo'] = vgsales_train['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+vgsales_test['Nintendo'] = vgsales_test['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+vgsales_dev['Nintendo'] = vgsales_dev['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
 
+# podzial na X i y
+X_train = vgsales_train.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+y_train = vgsales_train[['Nintendo']]
+X_test = vgsales_test.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+y_test = vgsales_test[['Nintendo']]
 
-def regression_model():
-    model = Sequential()
-    model.add(Dense(16,activation = "relu", input_shape = (x_train.shape[1],)))
-    model.add(Dense(32,activation = "relu"))
-    model.add(Dense(1,activation = "relu"))
-    
-    model.compile(optimizer = "adam", loss = "mean_squared_error")
-    return model
+print(X_train.shape[1])
+# keras model
+model = Sequential()
+model.add(Dense(9, input_dim = X_train.shape[1], kernel_initializer='normal', activation='relu'))
+model.add(Dense(1,kernel_initializer='normal', activation='sigmoid'))
 
-df['Nintendo'] = df['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
-df = df.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
-df
+early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
 
-y = df.Nintendo
+# kompilacja
+model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
 
-df=((df-df.min())/(df.max()-df.min()))
+# model fit
+epochs = int(sys.argv[1])
+batch_size = int(sys.argv[2])
 
-x = df.drop(['Nintendo'],axis = 1)
+# trenowanie modelu
+model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
 
-x_train, x_test, y_train, y_test = train_test_split(x,y , test_size=0.2,train_size=0.8, random_state=21)
-
-model = regression_model()
-model.fit(x_train, y_train, epochs = 600, verbose = 1)
-
-y_pred = model.predict(x_test)
-model.save('model1.h5')
+# zapisanie modelu
+model.save('vgsales_model.h5')

train2.py

@@ -0,0 +1,48 @@
+import sys
+import pandas as pd
+import numpy as np
+from sklearn import preprocessing
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras.layers import Input, Dense, Activation,Dropout
+from tensorflow.keras.models import Model
+from tensorflow.keras.callbacks import EarlyStopping
+from tensorflow.keras.models import Sequential
+
+# odczytanie danych z plików
+vgsales_train = pd.read_csv('train.csv')
+vgsales_test = pd.read_csv('test.csv')
+vgsales_dev = pd.read_csv('dev.csv')
+
+vgsales_train['Nintendo'] = vgsales_train['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+vgsales_test['Nintendo'] = vgsales_test['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+vgsales_dev['Nintendo'] = vgsales_dev['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+
+# podzial na X i y
+X_train = vgsales_train.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+y_train = vgsales_train[['Nintendo']]
+X_test = vgsales_test.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+y_test = vgsales_test[['Nintendo']]
+
+print(X_train.shape[1])
+# keras model
+model = Sequential()
+model.add(Dense(9, input_dim = X_train.shape[1], kernel_initializer='normal', activation='relu'))
+model.add(Dense(1,kernel_initializer='normal', activation='sigmoid'))
+
+early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
+
+# kompilacja
+model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+
+# model fit
+epochs = int(sys.argv[1])
+batch_size = int(sys.argv[2])
+
+# trenowanie modelu
+model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
+
+# zapisanie modelu
+model.save('vgsales_model.h5')