IUM_05

Dockerfile

@@ -0,0 +1,20 @@
+FROM ubuntu:latest
+
+# Instalacja niezbędnych narzędzi
+RUN apt-get update && apt-get install -y python3-pip python3-venv unzip coreutils dos2unix
+
+# Utworzenie i aktywacja wirtualnego środowiska
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Instalacja bibliotek Pythona w wirtualnym środowisku
+RUN pip install numpy tensorflow scikit-learn kaggle pandas
+
+WORKDIR /app
+
+# Kopiowanie plików konfiguracyjnych i skryptów
+COPY kaggle.json /root/.kaggle/kaggle.json
+COPY ./create-dataset.sh ./
+RUN dos2unix ./create-dataset.sh
+COPY ./model.py ./
+COPY ./predict.py ./

create-dataset.sh

@@ -1,21 +1,28 @@
 #!/bin/bash
 
+export PATH=$PATH:/root/.local/bindock
+
 pip install kaggle
 
 kaggle datasets download -d syedanwarafridi/vehicle-sales-data
 
 unzip -o vehicle-sales-data.zip
 
-# Tasowanie
+head -n 1 car_prices.csv > car_prices_header.csv
-shuf car_prices.csv -o car_prices_shuf.csv
+tail -n +2 car_prices.csv | awk -F, '!/,,/' | shuf > car_prices_no_null.csv
 
-# Podział danych na podzbiory
+total_rows=$(wc -l < car_prices_no_null.csv)
-total_rows=$(wc -l < car_prices_shuf.csv)
 test_dev_rows=$(( $1 * 2 ))
 
-head -n $1 car_prices_shuf.csv > car_prices_test.csv
+head -n $1 car_prices_no_null.csv > car_prices_test_temp.csv
-head -n $test_dev_rows car_prices_shuf.csv | tail -n +$(( $1 + 1 )) > car_prices_dev.csv
+head -n $test_dev_rows car_prices_no_null.csv | tail -n +$(( $1 + 1 )) > car_prices_dev_temp.csv
-tail -n +$(( $test_dev_rows + 1 )) car_prices_shuf.csv > car_prices_train.csv
+tail -n +$(( $test_dev_rows + 1 )) car_prices_no_null.csv > car_prices_train_temp.csv
+
+cat car_prices_header.csv car_prices_test_temp.csv > car_prices_test.csv
+cat car_prices_header.csv car_prices_dev_temp.csv > car_prices_dev.csv
+cat car_prices_header.csv car_prices_train_temp.csv > car_prices_train.csv
+
+rm car_prices_test_temp.csv car_prices_dev_temp.csv car_prices_train_temp.csv car_prices_no_null.csv car_prices_header.csv
 
 test_size=$(wc -l < car_prices_test.csv)
 dev_size=$(wc -l < car_prices_dev.csv)
@@ -24,6 +31,5 @@ echo "Rozmiar zbioru testowego: $test_size"
 echo "Rozmiar zbioru deweloperskiego: $dev_size"
 echo "Rozmiar zbioru treningowego: $train_size"
 
-# Zapis artefaktów
 mkdir -p data
-mv car_prices.csv car_prices_shuf.csv car_prices_test.csv car_prices_dev.csv car_prices_train.csv data/
+mv car_prices.csv car_prices_test.csv car_prices_dev.csv car_prices_train.csv data/

model.py

@@ -0,0 +1,33 @@
+import pandas as pd
+import numpy as np
+from tensorflow.keras import Sequential
+from tensorflow.keras.layers import Dense
+from sklearn.preprocessing import MinMaxScaler
+
+train_data = pd.read_csv('./data/car_prices_train.csv')
+
+train_data.dropna(inplace=True)
+
+y_train = train_data['sellingprice'].astype(np.float32)
+
+X_train = train_data[['year', 'condition', 'transmission']]
+
+scaler_x = MinMaxScaler()
+X_train['condition'] = scaler_x.fit_transform(X_train[['condition']])
+
+scaler_y = MinMaxScaler()
+y_train = scaler_y.fit_transform(y_train.values.reshape(-1, 1))
+
+X_train = pd.get_dummies(X_train, columns=['transmission'])
+
+model = Sequential([
+    Dense(64, activation='relu'),
+    Dense(32, activation='relu'),
+    Dense(1)
+])
+
+model.compile(optimizer='adam', loss='mean_squared_error')
+
+model.fit(X_train, y_train, epochs=20, batch_size=32)
+
+model.save('car_prices_predict_model.h5')

predict.py

@@ -0,0 +1,27 @@
+import pandas as pd
+import numpy as np
+from tensorflow.keras import Sequential
+import tensorflow as tf
+from sklearn.preprocessing import MinMaxScaler
+
+test_data = pd.read_csv('./data/car_prices_test.csv')
+test_data.dropna(inplace=True)
+
+y_test = test_data['sellingprice'].astype(np.float32)
+X_test = test_data[['year', 'condition', 'transmission']]
+
+scaler_y = MinMaxScaler()
+scaler_y.fit(y_test.values.reshape(-1, 1))
+
+scaler_X = MinMaxScaler()
+X_test['condition'] = scaler_X.fit_transform(X_test[['condition']])
+X_test = pd.get_dummies(X_test, columns=['transmission'])
+
+model = tf.keras.models.load_model('car_prices_predict_model.h5')
+
+y_pred_scaled = model.predict(X_test)
+
+y_pred = scaler_y.inverse_transform(y_pred_scaled)
+
+y_pred_df = pd.DataFrame(y_pred, columns=['PredictedSellingPrice'])
+y_pred_df.to_csv('predicted_selling_prices.csv', index=False)