Prześlij pliki do ''

predict.py

@@ -0,0 +1,34 @@
+import tensorflow as tf
+import pandas as pd
+import numpy as np
+import sklearn
+import sklearn.model_selection
+from tensorflow.keras.models import load_model
+from sklearn.metrics import accuracy_score, precision_score, f1_score
+
+feature_cols = ['year', 'mileage', 'vol_engine']
+
+model = load_model('model.h5')
+test_data = pd.read_csv('test.csv')
+
+predictions = model.predict(test_data[feature_cols])
+predicted_prices = [p[0] for p in predictions]
+
+
+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})
+results.to_csv('predictions.csv', index=False)
+
+y_true = test_data['price']
+y_pred = y_pred = [round(p[0]) for p in predictions]
+
+print(y_pred)
+print(y_true)
+
+accuracy = accuracy_score(y_true, y_pred)
+precision = precision_score(y_true, y_pred, average='micro')
+f1 = f1_score(y_true, y_pred, average='micro')
+
+with open('metrics.txt', 'w') as f:
+    f.write(f"Accuracy: {accuracy:.4f}\n")
+    f.write(f"Micro-average Precision: {precision:.4f}\n")
+    f.write(f"Micro-average F1-score: {f1:.4f}\n")

train.py

@@ -0,0 +1,60 @@
+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_test.rename(columns = {list(cars_test)[0]: 'id'}, inplace = True)
+    cars_train.to_csv('train.csv')
+    cars_test.to_csv('test.csv')
+    
+    feature_cols = ['year', 'mileage', 'vol_engine']
+    inputs = tf.keras.Input(shape=(len(feature_cols),))
+
+    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)
+
+    model = tf.keras.Model(inputs=inputs, outputs=outputs)
+
+    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
+                  loss='mse', metrics=['mae'])
+
+    model.fit(cars_train[feature_cols], cars_train['price'], epochs=100)
+
+    ex.add_resource('train_data.csv')
+    ex.add_resource('test_data.csv')
+
+    ex.add_artifact(__file__)
+
+    model.save('model.h5')
+    ex.add_artifact('model.h5')
+
+    metrics = model.evaluate(cars_train[feature_cols], cars_train['price'])
+    ex.log_scalar('mse', metrics[0])
+    ex.log_scalar('mae', metrics[1])