lab06_01

Jenkinsfile_training

@@ -0,0 +1,27 @@
+pipeline {
+    agent {dockerfile true}
+	parameters {
+		buildSelector(
+					defaultSelector: lastSuccessful(),
+					description: 'Which build to use for copying artifacts',
+					name: 'BUILD_SELECTOR')
+	}
+    stages {
+		stage('copyArtifacts') {
+            steps {
+                copyArtifacts fingerprintArtifacts: true, projectName: 's430705-create-dataset', selector: buildParameter('BUILD_SELECTOR')
+            }
+        }
+		stage('Sh script') {
+			steps {
+                sh 'python3 lab06_training.py ${params.LEARNING_RATE}'
+
+			}
+		}
+		stage('Archive artifacts') {
+			steps{
+				archiveArtifacts artifacts: 'model_movies'
+			}
+		}
+    }
+}

lab06_training.py

@@ -0,0 +1,50 @@
+import string
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn import preprocessing
+import wget
+import numpy as np
+
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+from tensorflow.keras.optimizers import Adam
+from tensorflow.keras.layers import Dropout
+from tensorflow.keras.callbacks import EarlyStopping
+from sklearn.metrics import mean_squared_error, mean_absolute_error
+
+
+movies_data = pd.read_csv('train.csv')
+movies_data.drop(movies_data.columns[0], axis=1, inplace=True)
+movies_data.dropna(inplace=True)
+X = movies_data.drop("rating", axis=1)
+Y = movies_data["rating"]
+
+
+# Split set to train/test 8:2 ratio
+X_train, X_test, Y_train, Y_test = train_test_split(
+    X, Y, test_size=0.2, random_state=42
+)
+
+# Set up model
+model = Sequential()
+model.add(Dense(8, activation="relu"))
+model.add(Dropout(0.5))
+model.add(Dense(3, activation="relu"))
+model.add(Dropout(0.5))
+model.add(Dense(1))
+model.compile(optimizer="adam", loss="mse")
+
+early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
+
+
+model.fit(
+    x=X_train,
+    y=Y_train.values,
+    validation_data=(X_test, Y_test.values),
+    batch_size=128,
+    epochs=400,
+    callbacks=[early_stop],
+)
+
+
+model.save('model_movies')

script2.py

@@ -37,10 +37,22 @@ movies_data["votes_number"] = (movies_data["votes_number"].str.replace(",", ""))
 
 # Normalize number values
 scaler = preprocessing.MinMaxScaler()
-movies_data[["rating", "votes_number", "year", "runtime"]] = scaler.fit_transform(
-    movies_data[["rating", "votes_number", "year", "runtime"]]
+movies_data[["votes_number", "year", "runtime"]] = scaler.fit_transform(
+    movies_data[["votes_number", "year", "runtime"]]
 )
 
+drop_columns = [
+    "original_title",
+    "countries",
+    "genres",
+    "director",
+    "cast",
+    "release_date",
+
+]
+
+movies_data.drop(labels=drop_columns, axis=1, inplace=True)
+
 # Split set to train/dev/test 6:2:2 ratio and save to .csv file
 train, dev = train_test_split(movies_data, train_size=0.6, test_size=0.4, shuffle=True)
 dev, test = train_test_split(dev, train_size=0.5, test_size=0.5, shuffle=True)