Do Task Biblioteki_DL

Dockerfile

@@ -2,7 +2,7 @@ FROM ubuntu:latest
 
 RUN apt-get update && \
     apt-get install -y python3-pip && \
-    pip3 install kaggle pandas scikit-learn
+    pip3 install kaggle pandas scikit-learn tensorflow
 
 RUN useradd -ms /bin/bash jenkins
 
@@ -10,6 +10,4 @@ RUN mkdir -p /.kaggle && chown -R jenkins /.kaggle
 
 USER jenkins
 
-COPY data_processing.sh .
-
 WORKDIR .

create_model.py

@@ -0,0 +1,29 @@
+import pandas as pd
+from keras.models import Sequential
+from keras.layers import Dense
+from keras.optimizers import Adam
+from keras import regularizers
+
+from helper import prepare_tensors
+
+hp_train = pd.read_csv('hp_train.csv')
+hp_dev = pd.read_csv('hp_dev.csv')
+
+X_train, Y_train = prepare_tensors(hp_train)
+X_dev, Y_dev = prepare_tensors(hp_dev)
+
+model = Sequential()
+model.add(Dense(64, input_dim=7, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
+model.add(Dense(32, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
+model.add(Dense(16, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
+model.add(Dense(8, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
+model.add(Dense(1, activation='linear'))
+
+adam = Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-7)
+model.compile(optimizer=adam, loss='mean_squared_error')
+
+model.fit(X_train, Y_train, epochs=20, batch_size=32, validation_data=(X_dev, Y_dev))
+
+model.save('hp_model.h5')
+
+

data_processing.py

@@ -5,13 +5,11 @@ import subprocess
 subprocess.run(["kaggle", "datasets", "download", "muhammadbinimran/housing-price-prediction-data", "--unzip"])
 housing_price_dataset = pd.read_csv('housing_price_dataset.csv')
 
+housing_price_dataset = pd.get_dummies(housing_price_dataset, columns=['Neighborhood'])
+
 hp_train_test, hp_dev = train_test_split(housing_price_dataset, test_size=0.1)
 hp_train, hp_test = train_test_split(hp_train_test, test_size=1000)
 
-hp_train = pd.get_dummies(hp_train, columns=['Neighborhood'])
-hp_dev = pd.get_dummies(hp_dev, columns=['Neighborhood'])
-hp_test = pd.get_dummies(hp_test, columns=['Neighborhood'])
-
 hp_train.to_csv('hp_train.csv', index=False)
 hp_dev.to_csv('hp_dev.csv', index=False)
 hp_test.to_csv('hp_test.csv', index=False)

helper.py

@@ -0,0 +1,8 @@
+import tensorflow as tf
+
+def prepare_tensors(df):
+    Y = df["Price"]
+    X = df.drop("Price", axis=1)
+    X_tensor = tf.convert_to_tensor(X, dtype=tf.float32)
+    Y_tensor = tf.convert_to_tensor(Y, dtype=tf.float32)
+    return X_tensor, Y_tensor

predict_price.py

@@ -0,0 +1,15 @@
+import pandas as pd
+from keras.models import load_model
+
+from helper import prepare_tensors
+
+hp_test = pd.read_csv('hp_test.csv')
+X_test, Y_test = prepare_tensors(hp_test)
+
+model = load_model('hp_model.h5')
+
+test_predictions = model.predict(X_test)
+
+predictions_df = pd.DataFrame(test_predictions, columns=["Predicted_Price"])
+
+predictions_df.to_csv('hp_test_predictions.csv', index=False)