Prześlij pliki do ''

predict.ipynb

@@ -0,0 +1,70 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "47153112-da26-4dbd-a32a-1abdd8bda4fa",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2949/2949 [==============================] - 1s 462us/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "import tensorflow as tf\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import sklearn\n",
+    "import sklearn.model_selection\n",
+    "from tensorflow.keras.models import load_model\n",
+    "\n",
+    "feature_cols = ['year', 'mileage', 'vol_engine']\n",
+    "\n",
+    "model = load_model('model.h5')\n",
+    "test_data = pd.read_csv('test.csv')\n",
+    "\n",
+    "predictions = model.predict(test_data[feature_cols])\n",
+    "predicted_prices = [p[0] for p in predictions]\n",
+    "\n",
+    "\n",
+    "results = pd.DataFrame({'id': test_data['id'], 'year': test_data['year'], 'mileage': test_data['mileage'], 'vol_engine': test_data['vol_engine'], 'predicted_price': predicted_prices})\n",
+    "results.to_csv('predictions.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bca76252-c90d-4343-8ff8-a665cd32cf26",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

sacred.py

@@ -0,0 +1,66 @@
+import tensorflow as tf
+from sacred import Experiment
+from sacred.observers import FileStorageObserver
+import pandas as pd
+import sklearn
+import sklearn.model_selection
+import numpy as np
+
+ex = Experiment('452662')
+ex.observers.append(FileStorageObserver.create('my_runs'))
+#ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@172.17.0.1:27017', db_name='sacred'))
+
+def normalize(df,feature_name):
+    result = df.copy()
+    max_value = df[feature_name].max()
+    min_value = df[feature_name].min()
+    result[feature_name] = (df[feature_name] - min_value) / (max_value - min_value)
+    return result
+
+
+@ex.automain
+def run_experiment():
+    cars = pd.read_csv('zbior_ium/Car_Prices_Poland_Kaggle.csv')
+
+    cars = cars.drop(73436) #wiersz z błednymi danymi
+    
+    cars_normalized = normalize(cars,'vol_engine')
+    
+    cars_train, cars_test = sklearn.model_selection.train_test_split(cars_normalized, test_size=23586, random_state=1)
+    cars_dev, cars_test = sklearn.model_selection.train_test_split(cars_test, test_size=11793, random_state=1)
+    cars_train.rename(columns = {list(cars_train)[0]: 'id'}, inplace = True)
+    cars_train.to_csv('test.csv')
+    
+    feature_cols = ['year', 'mileage', 'vol_engine']
+    inputs = tf.keras.Input(shape=(len(feature_cols),))
+
+    # Warstwy sieci neuronowej
+    x = tf.keras.layers.Dense(10, activation='relu')(inputs)
+    x = tf.keras.layers.Dense(10, activation='relu')(x)
+    outputs = tf.keras.layers.Dense(1, activation='linear')(x)
+
+    # Utworzenie modelu
+    model = tf.keras.Model(inputs=inputs, outputs=outputs)
+
+    # Kompilacja modelu
+    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
+                  loss='mse', metrics=['mae'])
+
+    # Trenowanie modelu
+    model.fit(cars_train[feature_cols], cars_train['price'], epochs=100)
+
+    # Zapis plików wejściowych
+    ex.add_resource('train_data.csv')
+    ex.add_resource('test_data.csv')
+
+    # Zapis kodu źródłowego
+    ex.add_artifact(__file__)
+
+    # Zapis modelu do pliku
+    model.save('model.h5')
+    ex.add_artifact('model.h5')
+
+    # Zapisanie metryk
+    metrics = model.evaluate(cars_train[feature_cols], cars_train['price'])
+    ex.log_scalar('mse', metrics[0])
+    ex.log_scalar('mae', metrics[1])