Upload files to ''

pred.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import tensorflow as tf
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+import numpy as np
+
+categorical_cols = ['bacteria', 'viruses']
+encoder = OneHotEncoder(sparse=False, handle_unknown='ignore')
+
+data_test = pd.read_csv('dane/water_test.csv')
+
+X_test = data_test.drop('is_safe', axis=1)
+y_test = data_test['is_safe']
+X_test_encoded = pd.DataFrame(encoder.fit_transform(X_test[categorical_cols]))
+X_test_processed = pd.concat([X_test.drop(categorical_cols, axis=1), X_test_encoded], axis=1)
+X_test_processed.columns = X_test_processed.columns.astype(str)
+
+scaler = StandardScaler()
+X_test_scaled = scaler.fit_transform(X_test_processed)
+
+model = tf.keras.models.load_model('savedmodel')
+
+predictions = model.predict(X_test_scaled)
+print(predictions)
+prediction_classes = [1 if prob > 0.5 else 0 for prob in np.ravel(predictions)]
+print(prediction_classes[:30])
+
+with open("predictionsResults.txt", mode='w', newline='') as f:
+    for pred in predictions:
+        f.write(str(f'{pred[0]}'))
+        f.write("\n")
+
+loss, accuracy, precision, recall = model.evaluate(X_test_scaled, y_test)
+
+from sklearn.metrics import accuracy_score, precision_score, recall_score
+
+print(f'Accuracy:  {accuracy_score(y_test, prediction_classes):.2f}')
+print(f'Precision: {precision_score(y_test, prediction_classes):.2f}')
+print(f'Recall:    {recall_score(y_test, prediction_classes):.2f}')

train.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import tensorflow as tf
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+
+data_train = pd.read_csv('dane/water_train.csv')
+
+X_train = data_train.drop('is_safe', axis=1)
+y_train = data_train['is_safe']
+
+categorical_cols = ['bacteria', 'viruses']
+encoder = OneHotEncoder(sparse=False, handle_unknown='ignore')
+X_train_encoded = pd.DataFrame(encoder.fit_transform(X_train[categorical_cols]))
+X_train_processed = pd.concat([X_train.drop(categorical_cols, axis=1), X_train_encoded], axis=1)
+X_train_processed.columns = X_train_processed.columns.astype(str)
+
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train_processed)
+
+model = tf.keras.Sequential([
+    tf.keras.layers.Dense(128, activation='relu'),
+    tf.keras.layers.Dense(256, activation='relu'),
+    tf.keras.layers.Dense(256, activation='relu'),
+    tf.keras.layers.Dense(1, activation='sigmoid')
+])
+
+model.compile(
+    loss=tf.keras.losses.binary_crossentropy,
+    optimizer=tf.keras.optimizers.Adam(lr=0.03),
+    metrics=[
+        tf.keras.metrics.BinaryAccuracy(name='accuracy'),
+        tf.keras.metrics.Precision(name='precision'),
+        tf.keras.metrics.Recall(name='recall')
+    ]
+)
+
+model.fit(X_train_scaled, y_train, batch_size=32, epochs=5, verbose=2)
+model.save("savedmodel")
+