reduced classes

lab05_deepLearning.py

@@ -8,6 +8,7 @@ from sklearn.metrics import accuracy_score
 import torch.nn.functional as F
 import pandas as pd
 from sklearn import preprocessing
+import matplotlib.pyplot as plt
 
 
 class Model(nn.Module):
@@ -16,7 +17,7 @@ class Model(nn.Module):
         self.layer1 = nn.Linear(input_dim, 160)
         # self.layer2 = nn.Linear(320, 160)
         self.layer2 = nn.Linear(160, 80)
-        self.layer3 = nn.Linear(80, 23)
+        self.layer3 = nn.Linear(80, 5)
 
     def forward(self, x):
         x = F.relu(self.layer1(x))
@@ -25,44 +26,63 @@ class Model(nn.Module):
         return x
 
 
-def load_dataset():
+def load_dataset_raw():
     """ Load data from .csv file. """
     cars = pd.read_csv('./Car_Prices_Poland_Kaggle.csv', usecols=[1, 4, 5, 6, 10], sep=',')
-    # cars = cars.iloc()
     return cars
 
 
-def prepare_dataset(dataset):
+def remove_rows(dataset):
+    # dataset.drop(dataset[dataset['mark'] == 'alfa-romeo'].index, inplace=True)
+    # dataset.drop(dataset[dataset['mark'] == 'chevrolet'].index, inplace=True)
+    # dataset.drop(dataset[dataset['mark'] == 'mitsubishi'].index, inplace=True)
+    # dataset.drop(dataset[dataset['mark'] == 'mini'].index, inplace=True)
+    # audi bmw ford opel volkswagen
+
+    new_data = dataset.loc[(dataset['mark'] == 'audi') | (dataset['mark'] == 'bmw') | (dataset['mark'] == 'ford') | (dataset['mark'] == 'opel') | (dataset['mark'] == 'volkswagen')]
+    return new_data
+    # dataset = dataset.drop(dataset)
+    # return dataset
+
+
+def prepare_dataset_raw(dataset):
     """ Label make column"""
     le = preprocessing.LabelEncoder()
     mark_column = np.array(dataset[:]['mark'])
     le.fit(mark_column)
 
     print(list(le.classes_))
-    labels = le.transform(mark_column)
-    features = dataset.drop(['mark'], axis=1).to_numpy()
+    lab = le.transform(mark_column)
+    feat = dataset.drop(['mark'], axis=1).to_numpy()
 
     mm_scaler = preprocessing.MinMaxScaler()
-    features = mm_scaler.fit_transform(features)
+    feat = mm_scaler.fit_transform(feat)
 
-    return labels, features
+    return lab, feat
 
 
 # Prepare dataset
-dataset = load_dataset()
-labels, features = prepare_dataset(dataset)
-features_train, features_test, labels_train, labels_test = train_test_split(features, labels, random_state=42, shuffle=True)
-#
-# import matplotlib
-#
-# plt = matplotlib.pyplot.hist(features, 16)
+print("Loading dataset...")
+dataset = load_dataset_raw()
+print("Dataset loaded")
 
+print("Preparing dataset...")
+dataset = remove_rows(dataset)
+labels, features = prepare_dataset_raw(dataset)
+print("Dataset prepared")
+
+plot = plt.hist(labels, bins=[i for i in range(len(set(labels)))], edgecolor="black")
+plt.xticks(np.arange(0, len(set(labels)), 1))
+plt.show()
+features_train, features_test, labels_train, labels_test = train_test_split(features, labels, random_state=42,
+                                                                            shuffle=True)
 # Training
 model = Model(features_train.shape[1])
 optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
 loss_fn = nn.CrossEntropyLoss()
-epochs = 1000
+epochs = 100
 
+print("Starting model training...")
 x_train, y_train = Variable(torch.from_numpy(features_train)).float(), Variable(torch.from_numpy(labels_train)).long()
 for epoch in range(1, epochs + 1):
     print("Epoch #", epoch)
@@ -74,21 +94,23 @@ for epoch in range(1, epochs + 1):
     optimizer.zero_grad()
     loss.backward()  # Gradients
     optimizer.step()  # Update
-
-print(1)
+print("Model training finished")
 
 x_test = Variable(torch.from_numpy(features_test)).float()
 pred = model(x_test)
-
 pred = pred.detach().numpy()
-print(pred)
-
 print("The accuracy is", accuracy_score(labels_test, np.argmax(pred, axis=1)))
 
 # Checking for first value
-print(np.argmax(model(x_test[0]).detach().numpy(), axis=0))
-print(labels_test[0])
-torch.save(model, "iris-pytorch.pkl")
+# print(np.argmax(model(x_test[0]).detach().numpy(), axis=0))
+# print(labels_test[0])
 
-saved_model = torch.load("iris-pytorch.pkl")
+print("Saving model to file...")
+torch.save(model, "CarPrices_pytorch.pkl")
+print("Model saved with name: CarPrices_pytorch.pkl")
+
+saved_model = torch.load("CarPrices_pytorch.pkl")
 print(np.argmax(saved_model(x_test[0]).detach().numpy(), axis=0))
+
+pd_predictions = pd.DataFrame(pred)
+pd_predictions.to_csv("./prediction_results.csv")