IUM_7

sacred/sacred_runs/1/config.json

@@ -0,0 +1,5 @@
+{
+  "batch_size": 32,
+  "epochs": 10,
+  "seed": 373303958
+}

sacred/sacred_runs/1/metrics.json

@@ -0,0 +1 @@
+{}

sacred/sacred_runs/1/run.json

@@ -0,0 +1,100 @@
+{
+  "artifacts": [
+    "beer_review_model.h5"
+  ],
+  "command": "run_experiment",
+  "experiment": {
+    "base_dir": "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred",
+    "dependencies": [
+      "keras==2.12.0",
+      "numpy==1.23.5",
+      "sacred==0.8.5",
+      "scikit-learn==1.2.2"
+    ],
+    "mainfile": "sacred_training_model.py",
+    "name": "464979",
+    "repositories": [
+      {
+        "commit": "e9f53be95453a8da8811653ba3c4a6e75895cd33",
+        "dirty": true,
+        "url": "https://git.wmi.amu.edu.pl/s464979/ium_464979.git"
+      }
+    ],
+    "sources": [
+      [
+        "sacred_training_model.py",
+        "_sources\\sacred_training_model_2a1e89d7c820c7a00319e1e22827c7f9.py"
+      ]
+    ]
+  },
+  "heartbeat": "2024-06-11T17:21:14.840246",
+  "host": {
+    "ENV": {},
+    "cpu": "Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz",
+    "gpus": {
+      "driver_version": "555.85",
+      "gpus": [
+        {
+          "model": "NVIDIA GeForce GTX 1660 Ti",
+          "persistence_mode": false,
+          "total_memory": 6144
+        }
+      ]
+    },
+    "hostname": "DESKTOP-9SEHQM2",
+    "os": [
+      "Windows",
+      "Windows-10-10.0.19045-SP0"
+    ],
+    "python_version": "3.11.7"
+  },
+  "meta": {
+    "command": "run_experiment",
+    "config_updates": {},
+    "named_configs": [],
+    "options": {
+      "--beat-interval": null,
+      "--capture": null,
+      "--comment": null,
+      "--debug": false,
+      "--enforce_clean": false,
+      "--file_storage": null,
+      "--force": false,
+      "--help": false,
+      "--id": null,
+      "--loglevel": null,
+      "--mongo_db": null,
+      "--name": null,
+      "--pdb": false,
+      "--print-config": false,
+      "--priority": null,
+      "--queue": false,
+      "--s3": null,
+      "--sql": null,
+      "--tiny_db": null,
+      "--unobserved": false,
+      "COMMAND": null,
+      "UPDATE": [],
+      "help": false,
+      "with": false
+    }
+  },
+  "resources": [
+    [
+      "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred\\beer_reviews_train.csv",
+      "sacred_runs\\_resources\\beer_reviews_train_e8dab75a0ec202f56510a0e1f9926ad7.csv"
+    ],
+    [
+      "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred\\beer_reviews_test.csv",
+      "sacred_runs\\_resources\\beer_reviews_test_56070f83bef3ee1d17d1a632aa55b798.csv"
+    ]
+  ],
+  "result": {
+    "dtype": "float64",
+    "py/object": "numpy.float64",
+    "value": 0.9237146778770103
+  },
+  "start_time": "2024-06-11T17:21:03.851734",
+  "status": "COMPLETED",
+  "stop_time": "2024-06-11T17:21:14.839247"
+}

sacred/sacred_runs/_sources/sacred_training_model_2a1e89d7c820c7a00319e1e22827c7f9.py

@@ -0,0 +1,85 @@
+import pandas as pd
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, GlobalAveragePooling1D, Dense
+from tensorflow.keras.models import load_model
+from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
+from sacred import Experiment
+from sacred.observers import MongoObserver, FileStorageObserver
+from math import sqrt
+
+ex = Experiment('464979')
+# ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@tzietkiewicz.vm.wmi.amu.edu.pl:27017'))
+ex.observers.append(FileStorageObserver('sacred_runs'))
+
+@ex.config
+def my_config():
+    epochs = 10
+    batch_size = 32
+
+@ex.automain
+def run_experiment(epochs, batch_size, _run):
+    train_data = pd.read_csv('beer_reviews_train.csv')
+    X_train = train_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_train = train_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_train)
+    X_train_seq = tokenizer.texts_to_sequences(X_train)
+
+    X_train_pad = pad_sequences(X_train_seq, maxlen=100)
+
+    model = Sequential([
+        Embedding(input_dim=10000, output_dim=16, input_length=100),
+        GlobalAveragePooling1D(),
+        Dense(16, activation='relu'),
+        Dense(1, activation='sigmoid')
+    ])
+
+    model.compile(optimizer='adam',
+                  loss='binary_crossentropy',
+                  metrics=['accuracy'])
+
+    model.fit(X_train_pad, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1)
+
+    model.save('beer_review_sentiment_model.keras')
+    _run.add_artifact('beer_review_model.h5')
+
+    test_data = pd.read_csv('beer_reviews_test.csv')
+    X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_test = test_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_test)
+
+    X_test_text = X_test.astype(str).agg(' '.join, axis=1)
+    X_test_seq = tokenizer.texts_to_sequences(X_test_text)
+    X_test_pad = pad_sequences(X_test_seq, maxlen=100)
+
+    predictions = model.predict(X_test_pad)
+
+    if len(predictions.shape) > 1:
+        predictions = predictions[:, 0]
+
+    results = pd.DataFrame({'Predictions': predictions, 'Actual': y_test})
+    results.to_csv('beer_review_sentiment_predictions.csv', index=False)
+
+    y_pred = results['Predictions']
+    y_test = results['Actual']
+    y_test_binary = (y_test >= 3).astype(int)
+
+    accuracy = accuracy_score(y_test_binary, y_pred.round())
+    precision, recall, f1, _ = precision_recall_fscore_support(y_test_binary, y_pred.round(), average='micro')
+    rmse = sqrt(mean_squared_error(y_test, y_pred))
+
+    print(f'Accuracy: {accuracy}')
+    print(f'Micro-avg Precision: {precision}')
+    print(f'Micro-avg Recall: {recall}')
+    print(f'F1 Score: {f1}')
+    print(f'RMSE: {rmse}')
+
+    _run.add_resource('./beer_reviews_train.csv')
+    _run.add_resource('./beer_reviews_test.csv')
+
+    return accuracy