import tensorflow as tf

from tensorflow import keras

from tensorflow.keras import layers
import numpy as np

from google.colab import drive

drive.mount('/content/drive')

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).

import pandas as pd
from sklearn.model_selection import train_test_split
df = pd.read_csv('/content/drive/MyDrive/apple_quality.csv')
mapping = {'good': 1, 'bad': 0}

df['Quality'] = df['Quality'].map(mapping)
df.fillna(1, inplace=True)

df = df[:4000]

df = df.astype(np.float32)

tensor = tf.convert_to_tensor(df)
numeric_columns = ['Size', 'Weight', 'Crunchiness', 'Juiciness', 'Ripeness', 'Acidity']
X = df[numeric_columns].values

y=df['Quality'].values

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

len(X_train)

3200

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense
model = Sequential()

model.add(Dense(units=64, activation='relu', input_dim=X_train.shape[1]))

model.add(Dense(units=20, activation='relu'))
model.add(Dense(units=1, activation='sigmoid'))

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

history = model.fit(X_train, y_train, epochs=40, batch_size=32, validation_split=0.2)

Epoch 1/40
80/80 [==============================] - 1s 7ms/step - loss: 0.5541 - accuracy: 0.7266 - val_loss: 0.4837 - val_accuracy: 0.7750
Epoch 2/40
80/80 [==============================] - 0s 4ms/step - loss: 0.4482 - accuracy: 0.7906 - val_loss: 0.4256 - val_accuracy: 0.8047
Epoch 3/40
80/80 [==============================] - 0s 4ms/step - loss: 0.4083 - accuracy: 0.8102 - val_loss: 0.3998 - val_accuracy: 0.8203
Epoch 4/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3867 - accuracy: 0.8246 - val_loss: 0.3871 - val_accuracy: 0.8234
Epoch 5/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3718 - accuracy: 0.8309 - val_loss: 0.3796 - val_accuracy: 0.8281
Epoch 6/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3622 - accuracy: 0.8305 - val_loss: 0.3670 - val_accuracy: 0.8406
Epoch 7/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3527 - accuracy: 0.8383 - val_loss: 0.3713 - val_accuracy: 0.8219
Epoch 8/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3478 - accuracy: 0.8398 - val_loss: 0.3653 - val_accuracy: 0.8297
Epoch 9/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3427 - accuracy: 0.8398 - val_loss: 0.3656 - val_accuracy: 0.8281
Epoch 10/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3376 - accuracy: 0.8402 - val_loss: 0.3546 - val_accuracy: 0.8328
Epoch 11/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3334 - accuracy: 0.8449 - val_loss: 0.3530 - val_accuracy: 0.8203
Epoch 12/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3334 - accuracy: 0.8445 - val_loss: 0.3523 - val_accuracy: 0.8344
Epoch 13/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3260 - accuracy: 0.8496 - val_loss: 0.3507 - val_accuracy: 0.8344
Epoch 14/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3217 - accuracy: 0.8508 - val_loss: 0.3523 - val_accuracy: 0.8266
Epoch 15/40
80/80 [==============================] - 0s 4ms/step - loss: 0.3199 - accuracy: 0.8512 - val_loss: 0.3477 - val_accuracy: 0.8266
Epoch 16/40
80/80 [==============================] - 0s 3ms/step - loss: 0.3156 - accuracy: 0.8578 - val_loss: 0.3512 - val_accuracy: 0.8250
Epoch 17/40
 80/80 [==============================] - 0s 3ms/step - loss: 0.3135 - accuracy: 0.8578 - val_loss: 0.3536 - val_accuracy: 0.8250
Epoch 18/40
80/80 [==============================] - 0s 3ms/step - loss: 0.3114 - accuracy: 0.8605 - val_loss: 0.3482 - val_accuracy: 0.8297
Epoch 19/40
80/80 [==============================] - 0s 3ms/step - loss: 0.3075 - accuracy: 0.8609 - val_loss: 0.3427 - val_accuracy: 0.8313
Epoch 20/40
80/80 [==============================] - 0s 3ms/step - loss: 0.3050 - accuracy: 0.8648 - val_loss: 0.3448 - val_accuracy: 0.8297
Epoch 21/40
80/80 [==============================] - 0s 2ms/step - loss: 0.3050 - accuracy: 0.8668 - val_loss: 0.3414 - val_accuracy: 0.8203
Epoch 22/40
80/80 [==============================] - 0s 2ms/step - loss: 0.2997 - accuracy: 0.8684 - val_loss: 0.3459 - val_accuracy: 0.8219
Epoch 23/40
80/80 [==============================] - 0s 2ms/step - loss: 0.2979 - accuracy: 0.8691 - val_loss: 0.3457 - val_accuracy: 0.8297
Epoch 24/40
80/80 [==============================] - 0s 2ms/step - loss: 0.2983 - accuracy: 0.8687 - val_loss: 0.3515 - val_accuracy: 0.8297
Epoch 25/40
80/80 [==============================] - 0s 3ms/step - loss: 0.2946 - accuracy: 0.8711 - val_loss: 0.3367 - val_accuracy: 0.8297
Epoch 26/40
80/80 [==============================] - 0s 3ms/step - loss: 0.2926 - accuracy: 0.8695 - val_loss: 0.3420 - val_accuracy: 0.8250
Epoch 27/40
80/80 [==============================] - 0s 3ms/step - loss: 0.2890 - accuracy: 0.8664 - val_loss: 0.3311 - val_accuracy: 0.8344
Epoch 28/40
80/80 [==============================] - 0s 3ms/step - loss: 0.2884 - accuracy: 0.8746 - val_loss: 0.3315 - val_accuracy: 0.8313
Epoch 29/40
80/80 [==============================] - 0s 3ms/step - loss: 0.2881 - accuracy: 0.8723 - val_loss: 0.3388 - val_accuracy: 0.8328
E h 30/40

test_loss, test_accuracy = model.evaluate(X_test, y_test)

print(f'Test Accuracy: {test_accuracy}')

25/25 [==============================] - 0s 1ms/step - loss: 0.2708 - accuracy: 0.8850

Test Accuracy: 0.8849999904632568

import matplotlib.pyplot as plt

plt.plot(history.history['accuracy'], label='Training Accuracy')

plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.show()